<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns="http://purl.org/rss/1.0/"
 xmlns:dc="http://purl.org/dc/elements/1.1/"
 xmlns:dcterms="http://purl.org/dc/terms/"
 xmlns:cc="http://web.resource.org/cc/"
 xmlns:prism="http://prismstandard.org/namespaces/basic/2.0/"
 xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
 xmlns:admin="http://webns.net/mvcb/"
 xmlns:content="http://purl.org/rss/1.0/modules/content/">
    <channel rdf:about="https://www.mdpi.com/rss/journal/aisens">
		<title>AI Sensors</title>
		<description>Latest open access articles published in AI Sens. at https://www.mdpi.com/journal/aisens</description>
		<link>https://www.mdpi.com/journal/aisens</link>
		<admin:generatorAgent rdf:resource="https://www.mdpi.com/journal/aisens"/>
		<admin:errorReportsTo rdf:resource="mailto:support@mdpi.com"/>
		<dc:publisher>MDPI</dc:publisher>
		<dc:language>en</dc:language>
		<dc:rights>Creative Commons Attribution (CC-BY)</dc:rights>
						<prism:copyright>MDPI</prism:copyright>
		<prism:rightsAgent>support@mdpi.com</prism:rightsAgent>
		<image rdf:resource="https://pub.mdpi-res.com/img/design/mdpi-pub-logo.png?13cf3b5bd783e021?1789118799"/>
				<items>
			<rdf:Seq>
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/3/12" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/3/11" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/3/10" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/3/9" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/3/8" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/2/7" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/2/6" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/2/5" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/2/4" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/1/3" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/1/2" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/2/1/1" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/2/9" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/2/8" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/2/7" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/6" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/5" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/4" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/3" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/2" />
            				<rdf:li rdf:resource="https://www.mdpi.com/3042-5999/1/1/1" />
                    	</rdf:Seq>
		</items>
				<cc:license rdf:resource="https://creativecommons.org/licenses/by/4.0/" />
	</channel>

        <item rdf:about="https://www.mdpi.com/3042-5999/2/3/12">

	<title>AI Sensors, Vol. 2, Pages 12: AI-Assisted MOS Gas Sensors: Sensing Materials, MEMS Platforms, Dynamic Operation, and Intelligent Applications</title>
	<link>https://www.mdpi.com/3042-5999/2/3/12</link>
	<description>Metal oxide semiconductor (MOS) gas sensors are widely used for low-cost chemical detection, but their practical performance is still limited by high operating temperature, insufficient selectivity, signal drift, and device-to-device variation. Recent advances in microelectromechanical systems (MEMS), dynamic sensing protocols, and artificial intelligence (AI) provide new opportunities to improve MOS gas sensing from both hardware and data-processing perspectives. MEMS micro-hotplates enable miniaturized devices, low-power heating, rapid thermal control, temperature-modulated operation, and compatibility with integrated readout and interface circuits, while AI methods extract multivariate, nonlinear, and temporal information from cross-sensitive sensor responses. This review summarizes the fundamentals of MOS sensing materials, MEMS micro-hotplate platforms, material&amp;amp;ndash;device integration strategies, and AI-assisted data-processing methods ranging from classical statistical analysis to deep learning. Representative strategies are discussed, including single-sensor feature extraction, sensor-array recognition, temperature-modulated sensing, drift compensation, and AI-guided material design. Application studies in food quality assessment, agriculture, medical diagnostics, environmental monitoring, and public safety are further reviewed to show how sensing tasks evolve from odor-fingerprint discrimination to nonlinear feature interpretation, dynamic response analysis, domain adaptation, and deployable intelligent monitoring. Particular attention is given to the role of high-consistency integration of MOS sensing layers on MEMS platforms, since reproducible material loading, morphology, electrode coverage, and thermal coupling are essential for reliable datasets and transferable AI models. Finally, key challenges are discussed, including dataset heterogeneity, long-term drift, edge deployment, and material&amp;amp;ndash;device reproducibility. This review highlights that future AI-assisted MOS/MEMS gas sensors require coordinated design of sensing materials, device platforms, fabrication processes, operating protocols, and data-driven models.</description>
	<pubDate>2026-09-05</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 12: AI-Assisted MOS Gas Sensors: Sensing Materials, MEMS Platforms, Dynamic Operation, and Intelligent Applications</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/3/12">doi: 10.3390/aisens2030012</a></p>
	<p>Authors:
		Jin Li
		Tongheng Cheng
		Haoqing Li
		Junwen Wei
		Yukun Wu
		Yuhua Hu
		Ziqi Luo
		Bo Tang
		Fei Wang
		</p>
	<p>Metal oxide semiconductor (MOS) gas sensors are widely used for low-cost chemical detection, but their practical performance is still limited by high operating temperature, insufficient selectivity, signal drift, and device-to-device variation. Recent advances in microelectromechanical systems (MEMS), dynamic sensing protocols, and artificial intelligence (AI) provide new opportunities to improve MOS gas sensing from both hardware and data-processing perspectives. MEMS micro-hotplates enable miniaturized devices, low-power heating, rapid thermal control, temperature-modulated operation, and compatibility with integrated readout and interface circuits, while AI methods extract multivariate, nonlinear, and temporal information from cross-sensitive sensor responses. This review summarizes the fundamentals of MOS sensing materials, MEMS micro-hotplate platforms, material&amp;amp;ndash;device integration strategies, and AI-assisted data-processing methods ranging from classical statistical analysis to deep learning. Representative strategies are discussed, including single-sensor feature extraction, sensor-array recognition, temperature-modulated sensing, drift compensation, and AI-guided material design. Application studies in food quality assessment, agriculture, medical diagnostics, environmental monitoring, and public safety are further reviewed to show how sensing tasks evolve from odor-fingerprint discrimination to nonlinear feature interpretation, dynamic response analysis, domain adaptation, and deployable intelligent monitoring. Particular attention is given to the role of high-consistency integration of MOS sensing layers on MEMS platforms, since reproducible material loading, morphology, electrode coverage, and thermal coupling are essential for reliable datasets and transferable AI models. Finally, key challenges are discussed, including dataset heterogeneity, long-term drift, edge deployment, and material&amp;amp;ndash;device reproducibility. This review highlights that future AI-assisted MOS/MEMS gas sensors require coordinated design of sensing materials, device platforms, fabrication processes, operating protocols, and data-driven models.</p>
	]]></content:encoded>

	<dc:title>AI-Assisted MOS Gas Sensors: Sensing Materials, MEMS Platforms, Dynamic Operation, and Intelligent Applications</dc:title>
			<dc:creator>Jin Li</dc:creator>
			<dc:creator>Tongheng Cheng</dc:creator>
			<dc:creator>Haoqing Li</dc:creator>
			<dc:creator>Junwen Wei</dc:creator>
			<dc:creator>Yukun Wu</dc:creator>
			<dc:creator>Yuhua Hu</dc:creator>
			<dc:creator>Ziqi Luo</dc:creator>
			<dc:creator>Bo Tang</dc:creator>
			<dc:creator>Fei Wang</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2030012</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-09-05</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-09-05</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>3</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>12</prism:startingPage>
		<prism:doi>10.3390/aisens2030012</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/3/12</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/3/11">

	<title>AI Sensors, Vol. 2, Pages 11: AI-Driven Innovations in Micromachined Ultrasonic Transducers: From Smart Design to Intelligent Systems</title>
	<link>https://www.mdpi.com/3042-5999/2/3/11</link>
	<description>Micromachined ultrasonic transducers (MUTs) represent a notable advance in miniaturized sensing, enabling compact, low-power, and complementary metal-oxide-semiconductor (CMOS)-integrated platforms that extend ultrasonic capabilities into wearable, implantable, and edge-computing domains. The integration of artificial intelligence (AI) has introduced new approaches for signal interpretation, adaptive control, and data-driven optimization, enhancing performance in specific areas such as compressed sensing, neural beamforming, and learned image enhancement that complement conventional signal processing. Meanwhile, sensor fusion strategies that combine ultrasonic data with complementary modalities have improved robustness, contextual awareness, and diagnostic accuracy across applications ranging from industrial monitoring to clinical diagnostics. This review provides a comprehensive analysis of this active research area, systematically covering transducer hardware platforms, design methodologies, and intelligent signal processing frameworks. While traditional bulk piezoelectric transducers remain the benchmark for high-power applications, capacitive and piezoelectric micromachined variants offer superior acoustic impedance matching and monolithic CMOS compatibility essential for portable systems. We examine the evolution from deterministic analytical and numerical modeling toward AI-powered inverse design, which enables the discovery of non-intuitive, high-performance geometries beyond human intuition. Furthermore, the integration of machine learning (ML) for signal recovery, image enhancement, and multi-modal sensor fusion is discussed as a pathway to compensate for hardware constraints such as limited aperture, sparse sampling, and low signal-to-noise ratio (SNR), while pointing out that AI technology cannot overcome fundamental physical limits including acoustic attenuation, thermal noise floors, and transduction efficiency boundaries. By synthesizing recent advancements, this review demonstrates how the convergence of classical acoustic physics and data-driven intelligence is guiding the development of of intelligent ultrasonic systems.</description>
	<pubDate>2026-08-18</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 11: AI-Driven Innovations in Micromachined Ultrasonic Transducers: From Smart Design to Intelligent Systems</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/3/11">doi: 10.3390/aisens2030011</a></p>
	<p>Authors:
		Yiwei Wang
		Tao Wu
		</p>
	<p>Micromachined ultrasonic transducers (MUTs) represent a notable advance in miniaturized sensing, enabling compact, low-power, and complementary metal-oxide-semiconductor (CMOS)-integrated platforms that extend ultrasonic capabilities into wearable, implantable, and edge-computing domains. The integration of artificial intelligence (AI) has introduced new approaches for signal interpretation, adaptive control, and data-driven optimization, enhancing performance in specific areas such as compressed sensing, neural beamforming, and learned image enhancement that complement conventional signal processing. Meanwhile, sensor fusion strategies that combine ultrasonic data with complementary modalities have improved robustness, contextual awareness, and diagnostic accuracy across applications ranging from industrial monitoring to clinical diagnostics. This review provides a comprehensive analysis of this active research area, systematically covering transducer hardware platforms, design methodologies, and intelligent signal processing frameworks. While traditional bulk piezoelectric transducers remain the benchmark for high-power applications, capacitive and piezoelectric micromachined variants offer superior acoustic impedance matching and monolithic CMOS compatibility essential for portable systems. We examine the evolution from deterministic analytical and numerical modeling toward AI-powered inverse design, which enables the discovery of non-intuitive, high-performance geometries beyond human intuition. Furthermore, the integration of machine learning (ML) for signal recovery, image enhancement, and multi-modal sensor fusion is discussed as a pathway to compensate for hardware constraints such as limited aperture, sparse sampling, and low signal-to-noise ratio (SNR), while pointing out that AI technology cannot overcome fundamental physical limits including acoustic attenuation, thermal noise floors, and transduction efficiency boundaries. By synthesizing recent advancements, this review demonstrates how the convergence of classical acoustic physics and data-driven intelligence is guiding the development of of intelligent ultrasonic systems.</p>
	]]></content:encoded>

	<dc:title>AI-Driven Innovations in Micromachined Ultrasonic Transducers: From Smart Design to Intelligent Systems</dc:title>
			<dc:creator>Yiwei Wang</dc:creator>
			<dc:creator>Tao Wu</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2030011</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-08-18</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-08-18</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>3</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>11</prism:startingPage>
		<prism:doi>10.3390/aisens2030011</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/3/11</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/3/10">

	<title>AI Sensors, Vol. 2, Pages 10: Deep Learning for Space Debris Tracking: One-Step Tracklet Filtering with a Hybrid GRU-CNN Architecture</title>
	<link>https://www.mdpi.com/3042-5999/2/3/10</link>
	<description>The proliferation of space debris in Low Earth Orbit (LEO) poses a growing threat to operational satellites, requiring robust surveillance and tracking systems. Radar is a primary technology for monitoring these objects; however, standard tracking algorithms often degrade when measurements are sparse, corrupted by non-Gaussian noise, or available only as short tracklets. Traditional methods, such as the Unscented Kalman Filter (UKF), rely on explicit physical and statistical models that may struggle to converge under highly nonlinear dynamics, uncertain initialization, and non-ideal sensor perturbations. In this study, we propose a hybrid deep learning framework for learned one-step tracklet filtering of radar measurements. The architecture consists of a stateful Gated Recurrent Unit (GRU) layer followed by one-dimensional Convolutional Neural Network (1D-CNN) layers, complemented by variable-specific preprocessing strategies, including residual learning for range and relative pivoting for azimuth, to handle the scale disparities and heterogeneous behavior of radar observables. This design combines the ability of GRUs to model temporal dependencies with the effectiveness of CNNs in extracting local features for signal denoising. The method is validated on synthetically generated LEO trajectories with realistic orbital perturbations and tunable radar noise profiles, including Gaussian noise, impulsive spikes, transient degradation, and state-dependent perturbations. Compared with EKF- and UKF-based analytical baselines, the proposed model achieves lower filtering error and improved robustness under severe non-Gaussian disturbances. Stress testing further shows that the network can reject non-physical sensor anomalies without requiring long initialization warm-up phases, making it suitable for sparse short-tracklet processing in synthetic SST benchmark scenarios.</description>
	<pubDate>2026-07-28</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 10: Deep Learning for Space Debris Tracking: One-Step Tracklet Filtering with a Hybrid GRU-CNN Architecture</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/3/10">doi: 10.3390/aisens2030010</a></p>
	<p>Authors:
		Alessandro Cabras
		Niccolò Pilloni
		Victor Mustieles-Perez
		Jan Siminski
		Marco Alessandrini
		Davide Bacciu
		</p>
	<p>The proliferation of space debris in Low Earth Orbit (LEO) poses a growing threat to operational satellites, requiring robust surveillance and tracking systems. Radar is a primary technology for monitoring these objects; however, standard tracking algorithms often degrade when measurements are sparse, corrupted by non-Gaussian noise, or available only as short tracklets. Traditional methods, such as the Unscented Kalman Filter (UKF), rely on explicit physical and statistical models that may struggle to converge under highly nonlinear dynamics, uncertain initialization, and non-ideal sensor perturbations. In this study, we propose a hybrid deep learning framework for learned one-step tracklet filtering of radar measurements. The architecture consists of a stateful Gated Recurrent Unit (GRU) layer followed by one-dimensional Convolutional Neural Network (1D-CNN) layers, complemented by variable-specific preprocessing strategies, including residual learning for range and relative pivoting for azimuth, to handle the scale disparities and heterogeneous behavior of radar observables. This design combines the ability of GRUs to model temporal dependencies with the effectiveness of CNNs in extracting local features for signal denoising. The method is validated on synthetically generated LEO trajectories with realistic orbital perturbations and tunable radar noise profiles, including Gaussian noise, impulsive spikes, transient degradation, and state-dependent perturbations. Compared with EKF- and UKF-based analytical baselines, the proposed model achieves lower filtering error and improved robustness under severe non-Gaussian disturbances. Stress testing further shows that the network can reject non-physical sensor anomalies without requiring long initialization warm-up phases, making it suitable for sparse short-tracklet processing in synthetic SST benchmark scenarios.</p>
	]]></content:encoded>

	<dc:title>Deep Learning for Space Debris Tracking: One-Step Tracklet Filtering with a Hybrid GRU-CNN Architecture</dc:title>
			<dc:creator>Alessandro Cabras</dc:creator>
			<dc:creator>Niccolò Pilloni</dc:creator>
			<dc:creator>Victor Mustieles-Perez</dc:creator>
			<dc:creator>Jan Siminski</dc:creator>
			<dc:creator>Marco Alessandrini</dc:creator>
			<dc:creator>Davide Bacciu</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2030010</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-07-28</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-07-28</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>3</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>10</prism:startingPage>
		<prism:doi>10.3390/aisens2030010</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/3/10</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/3/9">

	<title>AI Sensors, Vol. 2, Pages 9: Recent Advances in Two-Dimensional Materials for In-Sensor Computing</title>
	<link>https://www.mdpi.com/3042-5999/2/3/9</link>
	<description>Edge sensing systems seamlessly integrate multimodal signals for capturing visual, spectral, pressure, acoustic, and chemical data through robots, wearables, and distributed nodes at the sensing front end [...]</description>
	<pubDate>2026-07-17</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 9: Recent Advances in Two-Dimensional Materials for In-Sensor Computing</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/3/9">doi: 10.3390/aisens2030009</a></p>
	<p>Authors:
		Zhen Wan
		Zixuan Zhang
		Chengkuo Lee
		</p>
	<p>Edge sensing systems seamlessly integrate multimodal signals for capturing visual, spectral, pressure, acoustic, and chemical data through robots, wearables, and distributed nodes at the sensing front end [...]</p>
	]]></content:encoded>

	<dc:title>Recent Advances in Two-Dimensional Materials for In-Sensor Computing</dc:title>
			<dc:creator>Zhen Wan</dc:creator>
			<dc:creator>Zixuan Zhang</dc:creator>
			<dc:creator>Chengkuo Lee</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2030009</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-07-17</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-07-17</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>3</prism:number>
	<prism:section>Editorial</prism:section>
	<prism:startingPage>9</prism:startingPage>
		<prism:doi>10.3390/aisens2030009</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/3/9</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/3/8">

	<title>AI Sensors, Vol. 2, Pages 8: Atmospheric Exposures and Cardiovascular Mortality in United States Counties: Formaldehyde and Wet-Bulb Temperature as Leading Predictors</title>
	<link>https://www.mdpi.com/3042-5999/2/3/8</link>
	<description>Cardiovascular disease (CVD) is the leading cause of mortality in the United States, yet the role of atmospheric exposures as independent predictors of county-level CVD mortality remains poorly characterized. We integrated satellite-derived atmospheric data alongside socioeconomic, demographic, and livestock predictors across 24,487 county-year observations in the contiguous United States (2012&amp;amp;ndash;2019) and applied an XGBoost model with SHAP-based interpretability to identify the leading predictors of county-level CVD mortality (Test R2 = 0.706, RMSE = 29.55 per 100,000 persons). Four of the top ten predictors came from CAMS/ERA5. Ambient formaldehyde exposure frequency ranked second among all 43 predictors, exceeded only by educational attainment and surpassing poverty rate. Wet-bulb temperature ranked third, Leaf Area Index for High Vegetation ranked seventh, and sulphate aerosol mixing ratio ranked eighth. These variables added county-level prediction information beyond socioeconomic covariates. Integrating atmospheric exposure monitoring into county-level CVD surveillance alongside socioeconomic indicators may improve the identification of high-risk geographies.</description>
	<pubDate>2026-07-07</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 8: Atmospheric Exposures and Cardiovascular Mortality in United States Counties: Formaldehyde and Wet-Bulb Temperature as Leading Predictors</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/3/8">doi: 10.3390/aisens2030008</a></p>
	<p>Authors:
		Samyak Shrestha
		David J. Lary
		Shisir Ruwali
		Faiz Ahmad
		</p>
	<p>Cardiovascular disease (CVD) is the leading cause of mortality in the United States, yet the role of atmospheric exposures as independent predictors of county-level CVD mortality remains poorly characterized. We integrated satellite-derived atmospheric data alongside socioeconomic, demographic, and livestock predictors across 24,487 county-year observations in the contiguous United States (2012&amp;amp;ndash;2019) and applied an XGBoost model with SHAP-based interpretability to identify the leading predictors of county-level CVD mortality (Test R2 = 0.706, RMSE = 29.55 per 100,000 persons). Four of the top ten predictors came from CAMS/ERA5. Ambient formaldehyde exposure frequency ranked second among all 43 predictors, exceeded only by educational attainment and surpassing poverty rate. Wet-bulb temperature ranked third, Leaf Area Index for High Vegetation ranked seventh, and sulphate aerosol mixing ratio ranked eighth. These variables added county-level prediction information beyond socioeconomic covariates. Integrating atmospheric exposure monitoring into county-level CVD surveillance alongside socioeconomic indicators may improve the identification of high-risk geographies.</p>
	]]></content:encoded>

	<dc:title>Atmospheric Exposures and Cardiovascular Mortality in United States Counties: Formaldehyde and Wet-Bulb Temperature as Leading Predictors</dc:title>
			<dc:creator>Samyak Shrestha</dc:creator>
			<dc:creator>David J. Lary</dc:creator>
			<dc:creator>Shisir Ruwali</dc:creator>
			<dc:creator>Faiz Ahmad</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2030008</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-07-07</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-07-07</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>3</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>8</prism:startingPage>
		<prism:doi>10.3390/aisens2030008</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/3/8</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/2/7">

	<title>AI Sensors, Vol. 2, Pages 7: Making Sense of Sensors: Improving LLM Interpretation of Time-Series Data</title>
	<link>https://www.mdpi.com/3042-5999/2/2/7</link>
	<description>The increasing expansion of ubiquitous sensing systems has created large streams of time-series data that are difficult for non-technical users to interpret. Large Language Models (LLMs) offer a promising interface for transforming sensor data into natural language insights, particularly in distributed environments where users may lack familiarity with data analysis. However, models optimized for text generation often struggle to interpret raw time-series signals, producing responses that are generic, inaccurate, or poorly grounded in the data. This study evaluates a prompt structure based on the Retrieval-Augmented Generation (RAG) framework for interpreting sensor-derived time-series data from water-consumption monitoring systems installed in household storage tanks. The prompt integrates statistical summaries, sensor metadata, and contextual information about household water-use practices. Performance is evaluated using synthetic datasets representing a year of tank water-consumption measurements and a rubric-based evaluation framework applied by three independent language-model evaluators. Results show that augmenting prompts with structured contextual information improves the clarity and grounding of language model responses to sensor time-series data, increasing evaluation scores and reducing failure modes such as hallucination, contradiction with the data, and misuse of contextual information, as assessed by independent evaluator models. These findings highlight the potential of structured contextual prompting to support locally deployed language models that produce reliable and actionable interpretations of sensor time-series data.</description>
	<pubDate>2026-06-03</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 7: Making Sense of Sensors: Improving LLM Interpretation of Time-Series Data</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/2/7">doi: 10.3390/aisens2020007</a></p>
	<p>Authors:
		Andres Rico
		Kent Larson
		</p>
	<p>The increasing expansion of ubiquitous sensing systems has created large streams of time-series data that are difficult for non-technical users to interpret. Large Language Models (LLMs) offer a promising interface for transforming sensor data into natural language insights, particularly in distributed environments where users may lack familiarity with data analysis. However, models optimized for text generation often struggle to interpret raw time-series signals, producing responses that are generic, inaccurate, or poorly grounded in the data. This study evaluates a prompt structure based on the Retrieval-Augmented Generation (RAG) framework for interpreting sensor-derived time-series data from water-consumption monitoring systems installed in household storage tanks. The prompt integrates statistical summaries, sensor metadata, and contextual information about household water-use practices. Performance is evaluated using synthetic datasets representing a year of tank water-consumption measurements and a rubric-based evaluation framework applied by three independent language-model evaluators. Results show that augmenting prompts with structured contextual information improves the clarity and grounding of language model responses to sensor time-series data, increasing evaluation scores and reducing failure modes such as hallucination, contradiction with the data, and misuse of contextual information, as assessed by independent evaluator models. These findings highlight the potential of structured contextual prompting to support locally deployed language models that produce reliable and actionable interpretations of sensor time-series data.</p>
	]]></content:encoded>

	<dc:title>Making Sense of Sensors: Improving LLM Interpretation of Time-Series Data</dc:title>
			<dc:creator>Andres Rico</dc:creator>
			<dc:creator>Kent Larson</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2020007</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-06-03</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-06-03</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>7</prism:startingPage>
		<prism:doi>10.3390/aisens2020007</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/2/7</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/2/6">

	<title>AI Sensors, Vol. 2, Pages 6: AI Framework Integrated with InN Gas Sensing to Distinguish Sedentary Metabolic Fingerprints from Chronic Liver Disease</title>
	<link>https://www.mdpi.com/3042-5999/2/2/6</link>
	<description>Clinical monitoring of chronic liver disease (CLD) is currently hindered by the invasiveness of conventional biopsies. While breath-borne volatile organic compound (VOC) analysis offers a promising non-invasive alternative, the metabolic profiles of sedentary populations often overlap significantly with those of healthy individuals, making latent pathologies difficult to identify. To overcome this high-resolution diagnostic challenge, this study developed an integrated framework that couples high-performance semiconductor sensing technology with a machine learning-based analytical baseline. During the biomarker screening phase, GC-MS was utilized to analyze over 2000 VOCs, identifying 20 markers associated with CLD. These were further optimized into a robust feature panel including ammonia, isoprene, dimethyl sulfide (DMS), and limonene. For several critical metabolic features exhibiting high diagnostic potential, preliminary identifications were conducted by referencing NIST database matches and relevant literature. To maintain analytical rigor and account for the inherent complexity of trace volatile metabolites in biological samples, these signals are treated as putative metabolic features and characterized by their retention times. Regarding hardware, an InN-based sensor with Pt-AlN surface modification was fabricated, achieving a limit of detection (LOD) for ammonia below 0.2 ppm. Crucially, while the InN sensor was validated for specific core markers such as ammonia, the current AI classification model is trained on a refined 7-VOC panel derived from the comprehensive GC-MS data. To resolve diagnostic overlaps, a three-state dynamic sampling protocol (resting, exercise, and recovery) was implemented to isolate biomarkers that remain physiologically stable. By integrating multi-dimensional VOC features (e.g., isoprene and DMS) with sensor-validated data through DBSCAN and Random Forest algorithms, the framework successfully captured non-linear metabolic fingerprints. Machine learning results confirm that the framework effectively distinguished sedentary controls from CLD patients, achieving a macro-average AUC of 0.96. This integration provides a high-precision technical pathway for early-stage liver disease screening.</description>
	<pubDate>2026-05-21</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 6: AI Framework Integrated with InN Gas Sensing to Distinguish Sedentary Metabolic Fingerprints from Chronic Liver Disease</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/2/6">doi: 10.3390/aisens2020006</a></p>
	<p>Authors:
		Tsung Ming Chao
		Rakesh Kumar Patnaik
		Yu Chen Lin
		Ming-Chih Ho
		J. Andrew Yeh
		</p>
	<p>Clinical monitoring of chronic liver disease (CLD) is currently hindered by the invasiveness of conventional biopsies. While breath-borne volatile organic compound (VOC) analysis offers a promising non-invasive alternative, the metabolic profiles of sedentary populations often overlap significantly with those of healthy individuals, making latent pathologies difficult to identify. To overcome this high-resolution diagnostic challenge, this study developed an integrated framework that couples high-performance semiconductor sensing technology with a machine learning-based analytical baseline. During the biomarker screening phase, GC-MS was utilized to analyze over 2000 VOCs, identifying 20 markers associated with CLD. These were further optimized into a robust feature panel including ammonia, isoprene, dimethyl sulfide (DMS), and limonene. For several critical metabolic features exhibiting high diagnostic potential, preliminary identifications were conducted by referencing NIST database matches and relevant literature. To maintain analytical rigor and account for the inherent complexity of trace volatile metabolites in biological samples, these signals are treated as putative metabolic features and characterized by their retention times. Regarding hardware, an InN-based sensor with Pt-AlN surface modification was fabricated, achieving a limit of detection (LOD) for ammonia below 0.2 ppm. Crucially, while the InN sensor was validated for specific core markers such as ammonia, the current AI classification model is trained on a refined 7-VOC panel derived from the comprehensive GC-MS data. To resolve diagnostic overlaps, a three-state dynamic sampling protocol (resting, exercise, and recovery) was implemented to isolate biomarkers that remain physiologically stable. By integrating multi-dimensional VOC features (e.g., isoprene and DMS) with sensor-validated data through DBSCAN and Random Forest algorithms, the framework successfully captured non-linear metabolic fingerprints. Machine learning results confirm that the framework effectively distinguished sedentary controls from CLD patients, achieving a macro-average AUC of 0.96. This integration provides a high-precision technical pathway for early-stage liver disease screening.</p>
	]]></content:encoded>

	<dc:title>AI Framework Integrated with InN Gas Sensing to Distinguish Sedentary Metabolic Fingerprints from Chronic Liver Disease</dc:title>
			<dc:creator>Tsung Ming Chao</dc:creator>
			<dc:creator>Rakesh Kumar Patnaik</dc:creator>
			<dc:creator>Yu Chen Lin</dc:creator>
			<dc:creator>Ming-Chih Ho</dc:creator>
			<dc:creator>J. Andrew Yeh</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2020006</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-05-21</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-05-21</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>6</prism:startingPage>
		<prism:doi>10.3390/aisens2020006</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/2/6</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/2/5">

	<title>AI Sensors, Vol. 2, Pages 5: Correction: Fonseca et al. Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence. AI Sens. 2025, 1, 3</title>
	<link>https://www.mdpi.com/3042-5999/2/2/5</link>
	<description>In the original publication [...]</description>
	<pubDate>2026-05-20</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 5: Correction: Fonseca et al. Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence. AI Sens. 2025, 1, 3</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/2/5">doi: 10.3390/aisens2020005</a></p>
	<p>Authors:
		Flávio Secco Fonseca
		Adrielly Sayonara de Oliveira Silva
		Maria Vitória Soares Muniz
		Catarina Victória Nascimento de Oliveira
		Arthur Moreira Nogueira de Melo
		Maria Luísa Mendes de Siqueira Passos
		Ana Beatriz de Souza Sampaio
		Thailson Caetano Valdeci da Silva
		Alana Elza Fontes da Gama
		Ana Cristina de Albuquerque Montenegro
		Bianca Arruda Manchester de Queiroga
		Marilú Gomes Netto Monte da Silva
		Rafaella Asfora Siqueira Campos Lima
		Sadi da Silva Seabra Filho
		Shirley da Silva Jacinto de Oliveira Cruz
		Cecília Cordeiro da Silva
		Clarisse Lins de Lima
		Giselle Machado Magalhães Moreno
		Maíra Araújo de Santana
		Juliana Carneiro Gomes
		Wellington Pinheiro dos Santos
		</p>
	<p>In the original publication [...]</p>
	]]></content:encoded>

	<dc:title>Correction: Fonseca et al. Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence. AI Sens. 2025, 1, 3</dc:title>
			<dc:creator>Flávio Secco Fonseca</dc:creator>
			<dc:creator>Adrielly Sayonara de Oliveira Silva</dc:creator>
			<dc:creator>Maria Vitória Soares Muniz</dc:creator>
			<dc:creator>Catarina Victória Nascimento de Oliveira</dc:creator>
			<dc:creator>Arthur Moreira Nogueira de Melo</dc:creator>
			<dc:creator>Maria Luísa Mendes de Siqueira Passos</dc:creator>
			<dc:creator>Ana Beatriz de Souza Sampaio</dc:creator>
			<dc:creator>Thailson Caetano Valdeci da Silva</dc:creator>
			<dc:creator>Alana Elza Fontes da Gama</dc:creator>
			<dc:creator>Ana Cristina de Albuquerque Montenegro</dc:creator>
			<dc:creator>Bianca Arruda Manchester de Queiroga</dc:creator>
			<dc:creator>Marilú Gomes Netto Monte da Silva</dc:creator>
			<dc:creator>Rafaella Asfora Siqueira Campos Lima</dc:creator>
			<dc:creator>Sadi da Silva Seabra Filho</dc:creator>
			<dc:creator>Shirley da Silva Jacinto de Oliveira Cruz</dc:creator>
			<dc:creator>Cecília Cordeiro da Silva</dc:creator>
			<dc:creator>Clarisse Lins de Lima</dc:creator>
			<dc:creator>Giselle Machado Magalhães Moreno</dc:creator>
			<dc:creator>Maíra Araújo de Santana</dc:creator>
			<dc:creator>Juliana Carneiro Gomes</dc:creator>
			<dc:creator>Wellington Pinheiro dos Santos</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2020005</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-05-20</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-05-20</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Correction</prism:section>
	<prism:startingPage>5</prism:startingPage>
		<prism:doi>10.3390/aisens2020005</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/2/5</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/2/4">

	<title>AI Sensors, Vol. 2, Pages 4: AI-Enabled RF Sensing: A Pipeline-Centric Review from Design to Recognition</title>
	<link>https://www.mdpi.com/3042-5999/2/2/4</link>
	<description>For electromagnetic (EM)-driven design, we summarize surrogate modeling and inverse design based on full-wave simulations and, when available, measurements, use adjacent-domain EM exemplars only as methodological templates where direct closed-loop RF design-to-recognition evidence remains limited, and explain why reported speedups depend on the sampled design domain, sample density near feasibility boundaries, and how constraint-boundary checks and final verification are implemented. For RF sensing and recognition, we discuss how the learned &amp;amp;ldquo;signature&amp;amp;rdquo; is shaped by the measurement chain (hardware, placement, synchronization, calibration, and preprocessing). We then outline an author-synthesized set of checkable evaluation and reporting items, including explicit domains/constraints, complete sensing metadata, cross-condition tests, and edge deployment evidence, where deployability is defined at the full-pipeline level and requires measured latency, throughput, peak memory, energy per inference, preprocessing overhead, runtime, numerical precision, and an explicit statement of whether communication or offloading is included.</description>
	<pubDate>2026-04-16</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 4: AI-Enabled RF Sensing: A Pipeline-Centric Review from Design to Recognition</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/2/4">doi: 10.3390/aisens2020004</a></p>
	<p>Authors:
		Zirui Zhang
		Xianyue Liao
		Zhirun Hu
		</p>
	<p>For electromagnetic (EM)-driven design, we summarize surrogate modeling and inverse design based on full-wave simulations and, when available, measurements, use adjacent-domain EM exemplars only as methodological templates where direct closed-loop RF design-to-recognition evidence remains limited, and explain why reported speedups depend on the sampled design domain, sample density near feasibility boundaries, and how constraint-boundary checks and final verification are implemented. For RF sensing and recognition, we discuss how the learned &amp;amp;ldquo;signature&amp;amp;rdquo; is shaped by the measurement chain (hardware, placement, synchronization, calibration, and preprocessing). We then outline an author-synthesized set of checkable evaluation and reporting items, including explicit domains/constraints, complete sensing metadata, cross-condition tests, and edge deployment evidence, where deployability is defined at the full-pipeline level and requires measured latency, throughput, peak memory, energy per inference, preprocessing overhead, runtime, numerical precision, and an explicit statement of whether communication or offloading is included.</p>
	]]></content:encoded>

	<dc:title>AI-Enabled RF Sensing: A Pipeline-Centric Review from Design to Recognition</dc:title>
			<dc:creator>Zirui Zhang</dc:creator>
			<dc:creator>Xianyue Liao</dc:creator>
			<dc:creator>Zhirun Hu</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2020004</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-04-16</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-04-16</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>4</prism:startingPage>
		<prism:doi>10.3390/aisens2020004</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/2/4</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/1/3">

	<title>AI Sensors, Vol. 2, Pages 3: Recent Advances in Neuromorphic Tactile Perception for Robotic Applications</title>
	<link>https://www.mdpi.com/3042-5999/2/1/3</link>
	<description>Skin plays an important role in biological organisms perceiving and mediating our interactions with the world [...]</description>
	<pubDate>2026-02-26</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 3: Recent Advances in Neuromorphic Tactile Perception for Robotic Applications</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/1/3">doi: 10.3390/aisens2010003</a></p>
	<p>Authors:
		Zixuan Zhang
		Chengkuo Lee
		</p>
	<p>Skin plays an important role in biological organisms perceiving and mediating our interactions with the world [...]</p>
	]]></content:encoded>

	<dc:title>Recent Advances in Neuromorphic Tactile Perception for Robotic Applications</dc:title>
			<dc:creator>Zixuan Zhang</dc:creator>
			<dc:creator>Chengkuo Lee</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2010003</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-02-26</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-02-26</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Editorial</prism:section>
	<prism:startingPage>3</prism:startingPage>
		<prism:doi>10.3390/aisens2010003</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/1/3</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/1/2">

	<title>AI Sensors, Vol. 2, Pages 2: A Novel SRAM In-Memory Computing Accelerator Design Approach with R2R-Ladder for AI Sensors and Eddy Current Testing</title>
	<link>https://www.mdpi.com/3042-5999/2/1/2</link>
	<description>This work presents a 6T-SRAM-based in-memory computing (IMC) system fabricated in a 180 nm CMOS technology. A total of 128 integrated polysilicon R2R-DACs for fully analog wordline control and performance analysis are integrated into the system. The proposed architecture enables analog computation directly inside the memory array and introduces a compact 1-bit per-column comparator scheme for energy-efficient classification without requiring ADCs. A dedicated pull-down-dominant SRAM sizing and an analog activation scheme ensure stable analog discharge behavior and precise control of the computation through time-dependent bitline dynamics. The system integrates a complete sensor front-end, which allows real eddy current data to be classified directly on-chip. Measurements demonstrate a performance density of 3.2 TOPS/mm2, a simulated energy efficiency of 45 TOPS/W at 50 MHz, and a measured efficiency of 3.4 TOPS/W at 5 MHz on silicon. The implemented online training mechanism further improves classification accuracy by adapting the SRAM cell states during operation. These results highlight the suitability of the presented IMC architecture for compact, low-power edge intelligence and sensor-driven machine learning applications.</description>
	<pubDate>2026-01-15</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 2: A Novel SRAM In-Memory Computing Accelerator Design Approach with R2R-Ladder for AI Sensors and Eddy Current Testing</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/1/2">doi: 10.3390/aisens2010002</a></p>
	<p>Authors:
		Kevin Becker
		Martin Zimmerling
		Matthias Landwehr
		Dirk Koster
		Hans-Georg Herrmann
		Wolf-Joachim Fischer
		</p>
	<p>This work presents a 6T-SRAM-based in-memory computing (IMC) system fabricated in a 180 nm CMOS technology. A total of 128 integrated polysilicon R2R-DACs for fully analog wordline control and performance analysis are integrated into the system. The proposed architecture enables analog computation directly inside the memory array and introduces a compact 1-bit per-column comparator scheme for energy-efficient classification without requiring ADCs. A dedicated pull-down-dominant SRAM sizing and an analog activation scheme ensure stable analog discharge behavior and precise control of the computation through time-dependent bitline dynamics. The system integrates a complete sensor front-end, which allows real eddy current data to be classified directly on-chip. Measurements demonstrate a performance density of 3.2 TOPS/mm2, a simulated energy efficiency of 45 TOPS/W at 50 MHz, and a measured efficiency of 3.4 TOPS/W at 5 MHz on silicon. The implemented online training mechanism further improves classification accuracy by adapting the SRAM cell states during operation. These results highlight the suitability of the presented IMC architecture for compact, low-power edge intelligence and sensor-driven machine learning applications.</p>
	]]></content:encoded>

	<dc:title>A Novel SRAM In-Memory Computing Accelerator Design Approach with R2R-Ladder for AI Sensors and Eddy Current Testing</dc:title>
			<dc:creator>Kevin Becker</dc:creator>
			<dc:creator>Martin Zimmerling</dc:creator>
			<dc:creator>Matthias Landwehr</dc:creator>
			<dc:creator>Dirk Koster</dc:creator>
			<dc:creator>Hans-Georg Herrmann</dc:creator>
			<dc:creator>Wolf-Joachim Fischer</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2010002</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2026-01-15</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2026-01-15</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>2</prism:startingPage>
		<prism:doi>10.3390/aisens2010002</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/1/2</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/2/1/1">

	<title>AI Sensors, Vol. 2, Pages 1: A Review of Intelligent Self-Powered Sensing Systems Enabling Autonomous AIoT</title>
	<link>https://www.mdpi.com/3042-5999/2/1/1</link>
	<description>The rapid development of the Artificial Intelligence of Things (AIoT) has created unprecedented demands for distributed, long-term, and maintenance-free sensing systems. Conventional battery-powered sensors suffer from inherent drawbacks such as limited lifetime, high maintenance costs, and environmental concerns, which hinder large-scale deployment. Self-powered sensing technologies provide a transformative pathway by integrating energy harvesting and sensing into a single platform, thereby eliminating the reliance on external power supplies. This review systematically summarizes the key components of self-powered wireless sensing systems, with a particular focus on different energy harvesting technologies, self-powered sensing technologies, and the latest advances in low-power intelligent computation for diverse application scenarios. The integration of energy harvesting, self-sensing, and intelligent computation will make self-powered wireless sensing systems an inevitable direction for the evolution of AIoT, enabling sustainable, scalable, and intelligent monitoring networks.</description>
	<pubDate>2025-12-22</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 2, Pages 1: A Review of Intelligent Self-Powered Sensing Systems Enabling Autonomous AIoT</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/2/1/1">doi: 10.3390/aisens2010001</a></p>
	<p>Authors:
		Hangrui Cui
		Tianyi Tang
		Huicong Liu
		</p>
	<p>The rapid development of the Artificial Intelligence of Things (AIoT) has created unprecedented demands for distributed, long-term, and maintenance-free sensing systems. Conventional battery-powered sensors suffer from inherent drawbacks such as limited lifetime, high maintenance costs, and environmental concerns, which hinder large-scale deployment. Self-powered sensing technologies provide a transformative pathway by integrating energy harvesting and sensing into a single platform, thereby eliminating the reliance on external power supplies. This review systematically summarizes the key components of self-powered wireless sensing systems, with a particular focus on different energy harvesting technologies, self-powered sensing technologies, and the latest advances in low-power intelligent computation for diverse application scenarios. The integration of energy harvesting, self-sensing, and intelligent computation will make self-powered wireless sensing systems an inevitable direction for the evolution of AIoT, enabling sustainable, scalable, and intelligent monitoring networks.</p>
	]]></content:encoded>

	<dc:title>A Review of Intelligent Self-Powered Sensing Systems Enabling Autonomous AIoT</dc:title>
			<dc:creator>Hangrui Cui</dc:creator>
			<dc:creator>Tianyi Tang</dc:creator>
			<dc:creator>Huicong Liu</dc:creator>
		<dc:identifier>doi: 10.3390/aisens2010001</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-12-22</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-12-22</prism:publicationDate>
	<prism:volume>2</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>1</prism:startingPage>
		<prism:doi>10.3390/aisens2010001</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/2/1/1</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/2/9">

	<title>AI Sensors, Vol. 1, Pages 9: Wearable Intelligent Human&amp;ndash;Machine Interfaces Ready for Sustainable Edge Computing Systems</title>
	<link>https://www.mdpi.com/3042-5999/1/2/9</link>
	<description>To better serve human life with smart and harmonic communication between the real and digital worlds, wearable human&amp;amp;ndash;machine interfaces (HMIs) with edge computing capabilities indicate the path to the next revolution of information technology. In this review, we focus on wearable HMIs and highlight several key aspects which are worth investigating. Firstly, we review wearable HMIs powered by commercial-ready technologies, highlighting some limitations. Next, to establish a dual-way interaction for exchanging comprehensive information, sensing and feedback functions on the human body need to be customized based on specific scenarios. Power consumption is another primary issue that is critical to wearable applications due to limited space, one that is possible to be solved by energy harvesting techniques and self-powered data transmission approaches. To further improve the data interpretation with higher intelligence, machine learning (ML)-assisted analysis is preferred for multi-dimensional data. Eventually, with the presence of edge computing systems, those data can be pre-processed locally for downstream applications. Generally, this review offers an overview of the development of intelligent wearable HMIs with edge computing capabilities and self-sustainability, which can greatly enhance the user experience in healthcare, industrial productivity, education, etc.</description>
	<pubDate>2025-12-10</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 9: Wearable Intelligent Human&amp;ndash;Machine Interfaces Ready for Sustainable Edge Computing Systems</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/2/9">doi: 10.3390/aisens1020009</a></p>
	<p>Authors:
		Minglu Zhu
		Shuhan He
		Tao Chen
		Chengkuo Lee
		</p>
	<p>To better serve human life with smart and harmonic communication between the real and digital worlds, wearable human&amp;amp;ndash;machine interfaces (HMIs) with edge computing capabilities indicate the path to the next revolution of information technology. In this review, we focus on wearable HMIs and highlight several key aspects which are worth investigating. Firstly, we review wearable HMIs powered by commercial-ready technologies, highlighting some limitations. Next, to establish a dual-way interaction for exchanging comprehensive information, sensing and feedback functions on the human body need to be customized based on specific scenarios. Power consumption is another primary issue that is critical to wearable applications due to limited space, one that is possible to be solved by energy harvesting techniques and self-powered data transmission approaches. To further improve the data interpretation with higher intelligence, machine learning (ML)-assisted analysis is preferred for multi-dimensional data. Eventually, with the presence of edge computing systems, those data can be pre-processed locally for downstream applications. Generally, this review offers an overview of the development of intelligent wearable HMIs with edge computing capabilities and self-sustainability, which can greatly enhance the user experience in healthcare, industrial productivity, education, etc.</p>
	]]></content:encoded>

	<dc:title>Wearable Intelligent Human&amp;amp;ndash;Machine Interfaces Ready for Sustainable Edge Computing Systems</dc:title>
			<dc:creator>Minglu Zhu</dc:creator>
			<dc:creator>Shuhan He</dc:creator>
			<dc:creator>Tao Chen</dc:creator>
			<dc:creator>Chengkuo Lee</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1020009</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-12-10</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-12-10</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>9</prism:startingPage>
		<prism:doi>10.3390/aisens1020009</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/2/9</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/2/8">

	<title>AI Sensors, Vol. 1, Pages 8: A Review of Non-Invasive Continuous Blood Pressure Measurement: From Flexible Sensing to Intelligent Modeling</title>
	<link>https://www.mdpi.com/3042-5999/1/2/8</link>
	<description>Accurate and continuous, non-invasive blood pressure (BP) monitoring plays a vital role in the long-term management of cardiovascular diseases. Advances in wearable and flexible sensing technologies have facilitated the transition of non-invasive BP monitoring from clinical settings to ambulatory home environments. However, the measurement consistency and algorithm adaptability of existing devices have not yet reached the level required for routine clinical practice. To address these limitations, comprehensive innovations have been made in material development, sensor design, and algorithm optimization. This review examines the evolution of non-invasive continuous BP measurement, highlighting cutting-edge advances in flexible electronic devices and BP estimation algorithms. First, we introduce measurement principles, sensing devices and limitations of traditional non-invasive BP measurement, including arterial tonometry, arterial volume clamp, and ultrasound-based methods. Subsequently, we review the pulse wave analysis-based BP estimation methods from two perspectives: flexible sensors based on optical, mechanical, and electrical principles, and estimation models that use physiological features or raw waveforms as input. Finally, we conclude the existing challenges and future development directions of flexible electronic technology and intelligent estimation algorithms for non-invasive continuous BP measurement.</description>
	<pubDate>2025-11-07</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 8: A Review of Non-Invasive Continuous Blood Pressure Measurement: From Flexible Sensing to Intelligent Modeling</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/2/8">doi: 10.3390/aisens1020008</a></p>
	<p>Authors:
		Zhan Shen
		Jian Li
		Hao Hu
		Chentao Du
		Xiaorong Ding
		Tingrui Pan
		Xinge Yu
		</p>
	<p>Accurate and continuous, non-invasive blood pressure (BP) monitoring plays a vital role in the long-term management of cardiovascular diseases. Advances in wearable and flexible sensing technologies have facilitated the transition of non-invasive BP monitoring from clinical settings to ambulatory home environments. However, the measurement consistency and algorithm adaptability of existing devices have not yet reached the level required for routine clinical practice. To address these limitations, comprehensive innovations have been made in material development, sensor design, and algorithm optimization. This review examines the evolution of non-invasive continuous BP measurement, highlighting cutting-edge advances in flexible electronic devices and BP estimation algorithms. First, we introduce measurement principles, sensing devices and limitations of traditional non-invasive BP measurement, including arterial tonometry, arterial volume clamp, and ultrasound-based methods. Subsequently, we review the pulse wave analysis-based BP estimation methods from two perspectives: flexible sensors based on optical, mechanical, and electrical principles, and estimation models that use physiological features or raw waveforms as input. Finally, we conclude the existing challenges and future development directions of flexible electronic technology and intelligent estimation algorithms for non-invasive continuous BP measurement.</p>
	]]></content:encoded>

	<dc:title>A Review of Non-Invasive Continuous Blood Pressure Measurement: From Flexible Sensing to Intelligent Modeling</dc:title>
			<dc:creator>Zhan Shen</dc:creator>
			<dc:creator>Jian Li</dc:creator>
			<dc:creator>Hao Hu</dc:creator>
			<dc:creator>Chentao Du</dc:creator>
			<dc:creator>Xiaorong Ding</dc:creator>
			<dc:creator>Tingrui Pan</dc:creator>
			<dc:creator>Xinge Yu</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1020008</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-11-07</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-11-07</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>8</prism:startingPage>
		<prism:doi>10.3390/aisens1020008</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/2/8</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/2/7">

	<title>AI Sensors, Vol. 1, Pages 7: Innovations in Multidimensional Force Sensors for Accurate Tactile Perception and Embodied Intelligence</title>
	<link>https://www.mdpi.com/3042-5999/1/2/7</link>
	<description>Multidimensional force sensors are key devices capable of simultaneously perceiving and analyzing force in multiple directions (normally triaxial forces). They are designed to provide intelligent systems with skin-like precision in environmental interaction, offering high sensitivity, spatial resolution, decoupling capability, and environmental adaptability. However, the inherent complexity of tactile information coupling, combined with stringent demands for miniaturization, robustness, and low cost in practical applications, makes high-performance and reliable multidimensional sensing and decoupling a major challenge. This drives ongoing innovation in sensor structural design and sensing mechanisms. Various structural strategies have demonstrated significant advantages in improving sensor performance, simplifying decoupling algorithms, and enhancing adaptability&amp;amp;mdash;attributes that are essential in scenarios requiring fine physical interactions. From this perspective, this article reviews recent advances in multidimensional force sensing technology, with a focus on the operating principles and performance characteristics of sensors with different structural designs. It also highlights emerging trends toward multimodal sensing and the growing integration with system architectures and artificial intelligence, which together enable higher-level intelligence. These developments support a wide range of applications, including intelligent robotic manipulation, natural human&amp;amp;ndash;computer interaction, wearable health monitoring, and precision automation in agriculture and industry. Finally, the article discusses remaining challenges and future opportunities in the development of multidimensional force sensors.</description>
	<pubDate>2025-09-29</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 7: Innovations in Multidimensional Force Sensors for Accurate Tactile Perception and Embodied Intelligence</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/2/7">doi: 10.3390/aisens1020007</a></p>
	<p>Authors:
		Jiyuan Chen
		Meili Xia
		Pinzhen Chen
		Binbin Cai
		Huasong Chen
		Xinkai Xie
		Jun Wu
		Qiongfeng Shi
		</p>
	<p>Multidimensional force sensors are key devices capable of simultaneously perceiving and analyzing force in multiple directions (normally triaxial forces). They are designed to provide intelligent systems with skin-like precision in environmental interaction, offering high sensitivity, spatial resolution, decoupling capability, and environmental adaptability. However, the inherent complexity of tactile information coupling, combined with stringent demands for miniaturization, robustness, and low cost in practical applications, makes high-performance and reliable multidimensional sensing and decoupling a major challenge. This drives ongoing innovation in sensor structural design and sensing mechanisms. Various structural strategies have demonstrated significant advantages in improving sensor performance, simplifying decoupling algorithms, and enhancing adaptability&amp;amp;mdash;attributes that are essential in scenarios requiring fine physical interactions. From this perspective, this article reviews recent advances in multidimensional force sensing technology, with a focus on the operating principles and performance characteristics of sensors with different structural designs. It also highlights emerging trends toward multimodal sensing and the growing integration with system architectures and artificial intelligence, which together enable higher-level intelligence. These developments support a wide range of applications, including intelligent robotic manipulation, natural human&amp;amp;ndash;computer interaction, wearable health monitoring, and precision automation in agriculture and industry. Finally, the article discusses remaining challenges and future opportunities in the development of multidimensional force sensors.</p>
	]]></content:encoded>

	<dc:title>Innovations in Multidimensional Force Sensors for Accurate Tactile Perception and Embodied Intelligence</dc:title>
			<dc:creator>Jiyuan Chen</dc:creator>
			<dc:creator>Meili Xia</dc:creator>
			<dc:creator>Pinzhen Chen</dc:creator>
			<dc:creator>Binbin Cai</dc:creator>
			<dc:creator>Huasong Chen</dc:creator>
			<dc:creator>Xinkai Xie</dc:creator>
			<dc:creator>Jun Wu</dc:creator>
			<dc:creator>Qiongfeng Shi</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1020007</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-09-29</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-09-29</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>2</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>7</prism:startingPage>
		<prism:doi>10.3390/aisens1020007</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/2/7</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/6">

	<title>AI Sensors, Vol. 1, Pages 6: TV-LSTM: Multimodal Deep Learning for Predicting the Progression of Late Age-Related Macular Degeneration Using Longitudinal Fundus Images and Genetic Data</title>
	<link>https://www.mdpi.com/3042-5999/1/1/6</link>
	<description>Age-related macular degeneration (AMD) is the leading cause of blindness in developed countries. Predicting its progression is crucial for preventing late-stage AMD, as it is an irreversible retinal disease. Both genetic factors and retinal images are instrumental in diagnosing and predicting AMD progression. Previous studies have explored automated diagnosis using single fundus images and genetic variants, but they often fail to utilize the valuable longitudinal data from multiple visits. Longitudinal retinal images offer a dynamic view of disease progression, yet standard Long Short-Term Memory (LSTM) models assume consistent time intervals between training and testing, limiting their effectiveness in real-world settings. To address this limitation, we propose time-varied Long Short-Term Memory (TV-LSTM), which accommodates irregular time intervals in longitudinal data. Our innovative approach enables the integration of both longitudinal fundus images and AMD-associated genetic variants for more precise progression prediction. Our TV-LSTM model achieved an AUC-ROC of 0.9479 and an AUC-PR of 0.8591 for predicting late AMD within two years, using data from four visits with varying time intervals.</description>
	<pubDate>2025-08-04</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 6: TV-LSTM: Multimodal Deep Learning for Predicting the Progression of Late Age-Related Macular Degeneration Using Longitudinal Fundus Images and Genetic Data</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/6">doi: 10.3390/aisens1010006</a></p>
	<p>Authors:
		Jipeng Zhang
		Chongyue Zhao
		Lang Zeng
		Heng Huang
		Ying Ding
		Wei Chen
		</p>
	<p>Age-related macular degeneration (AMD) is the leading cause of blindness in developed countries. Predicting its progression is crucial for preventing late-stage AMD, as it is an irreversible retinal disease. Both genetic factors and retinal images are instrumental in diagnosing and predicting AMD progression. Previous studies have explored automated diagnosis using single fundus images and genetic variants, but they often fail to utilize the valuable longitudinal data from multiple visits. Longitudinal retinal images offer a dynamic view of disease progression, yet standard Long Short-Term Memory (LSTM) models assume consistent time intervals between training and testing, limiting their effectiveness in real-world settings. To address this limitation, we propose time-varied Long Short-Term Memory (TV-LSTM), which accommodates irregular time intervals in longitudinal data. Our innovative approach enables the integration of both longitudinal fundus images and AMD-associated genetic variants for more precise progression prediction. Our TV-LSTM model achieved an AUC-ROC of 0.9479 and an AUC-PR of 0.8591 for predicting late AMD within two years, using data from four visits with varying time intervals.</p>
	]]></content:encoded>

	<dc:title>TV-LSTM: Multimodal Deep Learning for Predicting the Progression of Late Age-Related Macular Degeneration Using Longitudinal Fundus Images and Genetic Data</dc:title>
			<dc:creator>Jipeng Zhang</dc:creator>
			<dc:creator>Chongyue Zhao</dc:creator>
			<dc:creator>Lang Zeng</dc:creator>
			<dc:creator>Heng Huang</dc:creator>
			<dc:creator>Ying Ding</dc:creator>
			<dc:creator>Wei Chen</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010006</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-08-04</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-08-04</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>6</prism:startingPage>
		<prism:doi>10.3390/aisens1010006</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/6</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/5">

	<title>AI Sensors, Vol. 1, Pages 5: Technology Landscape Review of In-Sensor Photonic Intelligence: From Optical Sensors to Smart Devices</title>
	<link>https://www.mdpi.com/3042-5999/1/1/5</link>
	<description>Optical sensors have undergone significant evolution, transitioning from discrete optical microsystems toward sophisticated photonic integrated circuits (PICs) that leverage artificial intelligence (AI) for enhanced functionality. This review systematically explores the integration of optical sensing technologies with AI, charting the advancement from conventional optical microsystems to AI-driven smart devices. First, we examine classical optical sensing methodologies, including refractive index sensing, surface-enhanced infrared absorption (SEIRA), surface-enhanced Raman spectroscopy (SERS), surface plasmon-enhanced chiral spectroscopy, and surface-enhanced fluorescence (SEF) spectroscopy, highlighting their principles, capabilities, and limitations. Subsequently, we analyze the architecture of PIC-based sensing platforms, emphasizing their miniaturization, scalability, and real-time detection performance. This review then introduces the emerging paradigm of in-sensor computing, where AI algorithms are integrated directly within photonic devices, enabling real-time data processing, decision making, and enhanced system autonomy. Finally, we offer a comprehensive outlook on current technological challenges and future research directions, addressing integration complexity, material compatibility, and data processing bottlenecks. This review provides timely insights into the transformative potential of AI-enhanced PIC sensors, setting the stage for future innovations in autonomous, intelligent sensing applications.</description>
	<pubDate>2025-07-14</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 5: Technology Landscape Review of In-Sensor Photonic Intelligence: From Optical Sensors to Smart Devices</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/5">doi: 10.3390/aisens1010005</a></p>
	<p>Authors:
		Hong Zhou
		Dongxiao Li
		Chengkuo Lee
		</p>
	<p>Optical sensors have undergone significant evolution, transitioning from discrete optical microsystems toward sophisticated photonic integrated circuits (PICs) that leverage artificial intelligence (AI) for enhanced functionality. This review systematically explores the integration of optical sensing technologies with AI, charting the advancement from conventional optical microsystems to AI-driven smart devices. First, we examine classical optical sensing methodologies, including refractive index sensing, surface-enhanced infrared absorption (SEIRA), surface-enhanced Raman spectroscopy (SERS), surface plasmon-enhanced chiral spectroscopy, and surface-enhanced fluorescence (SEF) spectroscopy, highlighting their principles, capabilities, and limitations. Subsequently, we analyze the architecture of PIC-based sensing platforms, emphasizing their miniaturization, scalability, and real-time detection performance. This review then introduces the emerging paradigm of in-sensor computing, where AI algorithms are integrated directly within photonic devices, enabling real-time data processing, decision making, and enhanced system autonomy. Finally, we offer a comprehensive outlook on current technological challenges and future research directions, addressing integration complexity, material compatibility, and data processing bottlenecks. This review provides timely insights into the transformative potential of AI-enhanced PIC sensors, setting the stage for future innovations in autonomous, intelligent sensing applications.</p>
	]]></content:encoded>

	<dc:title>Technology Landscape Review of In-Sensor Photonic Intelligence: From Optical Sensors to Smart Devices</dc:title>
			<dc:creator>Hong Zhou</dc:creator>
			<dc:creator>Dongxiao Li</dc:creator>
			<dc:creator>Chengkuo Lee</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010005</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-07-14</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-07-14</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Review</prism:section>
	<prism:startingPage>5</prism:startingPage>
		<prism:doi>10.3390/aisens1010005</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/5</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/4">

	<title>AI Sensors, Vol. 1, Pages 4: CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion</title>
	<link>https://www.mdpi.com/3042-5999/1/1/4</link>
	<description>This study presents CORE-ReID V2, an enhanced framework built upon CORE-ReID V1. The new framework extends its predecessor by addressing unsupervised domain adaptation (UDA) challenges in person ReID and vehicle ReID, with further applicability to object ReID. During pre-training, CycleGAN is employed to synthesize diverse data, bridging image characteristic gaps across different domains. In the fine-tuning, an advanced ensemble fusion mechanism, consisting of the Efficient Channel Attention Block (ECAB) and the Simplified Efficient Channel Attention Block (SECAB), enhances both local and global feature representations while reducing ambiguity in pseudo-labels for target samples. Experimental results on widely used UDA person ReID and vehicle ReID datasets demonstrate that the proposed framework outperforms state-of-the-art methods, achieving top performance in mean average precision (mAP) and Rank-k Accuracy (Top-1, Top-5, Top-10). Moreover, the framework supports lightweight backbones such as ResNet18 and ResNet34, ensuring both scalability and efficiency. Our work not only pushes the boundaries of UDA-based object ReID but also provides a solid foundation for further research and advancements in this domain.</description>
	<pubDate>2025-07-04</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 4: CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/4">doi: 10.3390/aisens1010004</a></p>
	<p>Authors:
		Trinh Quoc Nguyen
		Oky Dicky Ardiansyah Prima
		Syahid Al Irfan
		Hindriyanto Dwi Purnomo
		Radius Tanone
		</p>
	<p>This study presents CORE-ReID V2, an enhanced framework built upon CORE-ReID V1. The new framework extends its predecessor by addressing unsupervised domain adaptation (UDA) challenges in person ReID and vehicle ReID, with further applicability to object ReID. During pre-training, CycleGAN is employed to synthesize diverse data, bridging image characteristic gaps across different domains. In the fine-tuning, an advanced ensemble fusion mechanism, consisting of the Efficient Channel Attention Block (ECAB) and the Simplified Efficient Channel Attention Block (SECAB), enhances both local and global feature representations while reducing ambiguity in pseudo-labels for target samples. Experimental results on widely used UDA person ReID and vehicle ReID datasets demonstrate that the proposed framework outperforms state-of-the-art methods, achieving top performance in mean average precision (mAP) and Rank-k Accuracy (Top-1, Top-5, Top-10). Moreover, the framework supports lightweight backbones such as ResNet18 and ResNet34, ensuring both scalability and efficiency. Our work not only pushes the boundaries of UDA-based object ReID but also provides a solid foundation for further research and advancements in this domain.</p>
	]]></content:encoded>

	<dc:title>CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion</dc:title>
			<dc:creator>Trinh Quoc Nguyen</dc:creator>
			<dc:creator>Oky Dicky Ardiansyah Prima</dc:creator>
			<dc:creator>Syahid Al Irfan</dc:creator>
			<dc:creator>Hindriyanto Dwi Purnomo</dc:creator>
			<dc:creator>Radius Tanone</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010004</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-07-04</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-07-04</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>4</prism:startingPage>
		<prism:doi>10.3390/aisens1010004</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/4</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/3">

	<title>AI Sensors, Vol. 1, Pages 3: Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence</title>
	<link>https://www.mdpi.com/3042-5999/1/1/3</link>
	<description>Deficits in social interaction and communication characterize Autism Spectrum Disorder (ASD). Although widely recognized by its symptoms, diagnosing ASD remains challenging due to its wide range of clinical presentations. Methods: In this study, we propose a method to assist in the early diagnosis of autism, which is currently primarily based on clinical assessments. Our approach aims to develop an early differential diagnosis based on electroencephalogram (EEG) signals, seeking to identify patterns associated with ASD. In this study, we used EEG data from 56 participants obtained from the Sheffield dataset, including 28 individuals diagnosed with Autism Spectrum Conditions (ASC) and 28 neurotypical controls, applying numerical techniques to handle missing data. Subsequently, after a detailed analysis of the signals, we applied three different starting approaches: one with the original database and the other two with selection of the most significant attributes using the PSO and evolutionary search methods. In each of these approaches, we applied a series of machine learning models, where relatively high performances for classification were observed. Results: We achieved accuracies of 99.13% ± 0.44 for the dataset with original signals, 99.23% ± 0.38 for the dataset after applying PSO, and 93.91% ± 1.10 for the dataset after the evolutionary search methodology. These results were obtained using classical classifiers, with SVM being the most effective among the first two approaches, while Random Forest with 500 trees proved more efficient in the third approach. Conclusions: Even with all the limitations of the base, the results of the experiments demonstrated promising findings in identifying patterns associated with Autism Spectrum Disorder through the analysis of EEG signals. Finally, we emphasize that this work is the starting point for a larger project with the objective of supporting and democratizing the diagnosis of ASD both in children early and later in adults.</description>
	<pubDate>2025-06-24</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 3: Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/3">doi: 10.3390/aisens1010003</a></p>
	<p>Authors:
		Flávio Fonseca
		Adrielly Silva
		Maria Muniz
		Catarina de Oliveira
		Arthur de Melo
		Maria Passos
		Ana Sampaio
		Thailson da Silva
		Alana da Gama
		Ana Montenegro
		Bianca de Queiroga
		Marilú da Silva
		Rafaella Lima
		Sadi Seabra Filho
		Shirley Cruz
		Cecília da Silva
		Clarisse de Lima
		Giselle Moreno
		Maíra de Santana
		Juliana Gomes
		Wellington dos Santos
		</p>
	<p>Deficits in social interaction and communication characterize Autism Spectrum Disorder (ASD). Although widely recognized by its symptoms, diagnosing ASD remains challenging due to its wide range of clinical presentations. Methods: In this study, we propose a method to assist in the early diagnosis of autism, which is currently primarily based on clinical assessments. Our approach aims to develop an early differential diagnosis based on electroencephalogram (EEG) signals, seeking to identify patterns associated with ASD. In this study, we used EEG data from 56 participants obtained from the Sheffield dataset, including 28 individuals diagnosed with Autism Spectrum Conditions (ASC) and 28 neurotypical controls, applying numerical techniques to handle missing data. Subsequently, after a detailed analysis of the signals, we applied three different starting approaches: one with the original database and the other two with selection of the most significant attributes using the PSO and evolutionary search methods. In each of these approaches, we applied a series of machine learning models, where relatively high performances for classification were observed. Results: We achieved accuracies of 99.13% ± 0.44 for the dataset with original signals, 99.23% ± 0.38 for the dataset after applying PSO, and 93.91% ± 1.10 for the dataset after the evolutionary search methodology. These results were obtained using classical classifiers, with SVM being the most effective among the first two approaches, while Random Forest with 500 trees proved more efficient in the third approach. Conclusions: Even with all the limitations of the base, the results of the experiments demonstrated promising findings in identifying patterns associated with Autism Spectrum Disorder through the analysis of EEG signals. Finally, we emphasize that this work is the starting point for a larger project with the objective of supporting and democratizing the diagnosis of ASD both in children early and later in adults.</p>
	]]></content:encoded>

	<dc:title>Supporting ASD Diagnosis with EEG, ML and Swarm Intelligence: Early Detection of Autism Spectrum Disorder Based on Electroencephalography Analysis by Machine Learning and Swarm Intelligence</dc:title>
			<dc:creator>Flávio Fonseca</dc:creator>
			<dc:creator>Adrielly Silva</dc:creator>
			<dc:creator>Maria Muniz</dc:creator>
			<dc:creator>Catarina de Oliveira</dc:creator>
			<dc:creator>Arthur de Melo</dc:creator>
			<dc:creator>Maria Passos</dc:creator>
			<dc:creator>Ana Sampaio</dc:creator>
			<dc:creator>Thailson da Silva</dc:creator>
			<dc:creator>Alana da Gama</dc:creator>
			<dc:creator>Ana Montenegro</dc:creator>
			<dc:creator>Bianca de Queiroga</dc:creator>
			<dc:creator>Marilú da Silva</dc:creator>
			<dc:creator>Rafaella Lima</dc:creator>
			<dc:creator>Sadi Seabra Filho</dc:creator>
			<dc:creator>Shirley Cruz</dc:creator>
			<dc:creator>Cecília da Silva</dc:creator>
			<dc:creator>Clarisse de Lima</dc:creator>
			<dc:creator>Giselle Moreno</dc:creator>
			<dc:creator>Maíra de Santana</dc:creator>
			<dc:creator>Juliana Gomes</dc:creator>
			<dc:creator>Wellington dos Santos</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010003</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-06-24</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-06-24</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Article</prism:section>
	<prism:startingPage>3</prism:startingPage>
		<prism:doi>10.3390/aisens1010003</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/3</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/2">

	<title>AI Sensors, Vol. 1, Pages 2: Students&amp;rsquo; Burnout Symptoms Detection Using Smartwatch Wearable Devices: A Systematic Literature Review</title>
	<link>https://www.mdpi.com/3042-5999/1/1/2</link>
	<description>(1) Background: The current uses of smartwatch wearable devices have expanded, not only being a part of everyday routine life but also playing a dynamic role in the early detection of many behavioral patterns of users. Furthermore, in the modern era, there is an increasing trend of mental disturbances even in early adolescence, a phenomenon that continues into academic life. Taking into account the current situation, the objective of this systematic literature review emphasizes the role of AI wearable devices in the early symptom detection of burnout in the student population. (2) Methods: A systematic literature review was designed based on the PRISMA guidelines. The general extracted aspect was to exploit all the current related research evidence about the effectiveness of wearable devices in the student population. (3) Results: The reviewed studies document the importance of physiological monitoring and AI-driven predictive models, with the collaboration of self-reported scales in assessing mental well-being. It is reported that stress is the most frequently studied burnout-related symptom. Meanwhile, heart rate (HR) and heart rate variability (HRV) are the most commonly used biomarkers that can be used to monitor and evaluate early burnout detection. (4) Conclusions: Despite the promising potential of these technologies, several challenges and limitations must be addressed to enhance their effectiveness and reliability.</description>
	<pubDate>2025-05-08</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 2: Students&amp;rsquo; Burnout Symptoms Detection Using Smartwatch Wearable Devices: A Systematic Literature Review</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/2">doi: 10.3390/aisens1010002</a></p>
	<p>Authors:
		Paschalina Lialiou
		Ilias Maglogiannis
		</p>
	<p>(1) Background: The current uses of smartwatch wearable devices have expanded, not only being a part of everyday routine life but also playing a dynamic role in the early detection of many behavioral patterns of users. Furthermore, in the modern era, there is an increasing trend of mental disturbances even in early adolescence, a phenomenon that continues into academic life. Taking into account the current situation, the objective of this systematic literature review emphasizes the role of AI wearable devices in the early symptom detection of burnout in the student population. (2) Methods: A systematic literature review was designed based on the PRISMA guidelines. The general extracted aspect was to exploit all the current related research evidence about the effectiveness of wearable devices in the student population. (3) Results: The reviewed studies document the importance of physiological monitoring and AI-driven predictive models, with the collaboration of self-reported scales in assessing mental well-being. It is reported that stress is the most frequently studied burnout-related symptom. Meanwhile, heart rate (HR) and heart rate variability (HRV) are the most commonly used biomarkers that can be used to monitor and evaluate early burnout detection. (4) Conclusions: Despite the promising potential of these technologies, several challenges and limitations must be addressed to enhance their effectiveness and reliability.</p>
	]]></content:encoded>

	<dc:title>Students&amp;amp;rsquo; Burnout Symptoms Detection Using Smartwatch Wearable Devices: A Systematic Literature Review</dc:title>
			<dc:creator>Paschalina Lialiou</dc:creator>
			<dc:creator>Ilias Maglogiannis</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010002</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-05-08</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-05-08</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Systematic Review</prism:section>
	<prism:startingPage>2</prism:startingPage>
		<prism:doi>10.3390/aisens1010002</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/2</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
        <item rdf:about="https://www.mdpi.com/3042-5999/1/1/1">

	<title>AI Sensors, Vol. 1, Pages 1: Journal Editorial: Welcome to the New Era of AI-Enabled Sensing</title>
	<link>https://www.mdpi.com/3042-5999/1/1/1</link>
	<description>Artificial intelligence (AI) has been under the spotlight for scientific research in recent years [...]</description>
	<pubDate>2025-02-11</pubDate>

	<content:encoded><![CDATA[
	<p><b>AI Sensors, Vol. 1, Pages 1: Journal Editorial: Welcome to the New Era of AI-Enabled Sensing</b></p>
	<p>AI Sensors <a href="https://www.mdpi.com/3042-5999/1/1/1">doi: 10.3390/aisens1010001</a></p>
	<p>Authors:
		Ting Leng
		Lin Li
		Chengkuo Lee
		</p>
	<p>Artificial intelligence (AI) has been under the spotlight for scientific research in recent years [...]</p>
	]]></content:encoded>

	<dc:title>Journal Editorial: Welcome to the New Era of AI-Enabled Sensing</dc:title>
			<dc:creator>Ting Leng</dc:creator>
			<dc:creator>Lin Li</dc:creator>
			<dc:creator>Chengkuo Lee</dc:creator>
		<dc:identifier>doi: 10.3390/aisens1010001</dc:identifier>
	<dc:source>AI Sensors</dc:source>
	<dc:date>2025-02-11</dc:date>

	<prism:publicationName>AI Sensors</prism:publicationName>
	<prism:publicationDate>2025-02-11</prism:publicationDate>
	<prism:volume>1</prism:volume>
	<prism:number>1</prism:number>
	<prism:section>Editorial</prism:section>
	<prism:startingPage>1</prism:startingPage>
		<prism:doi>10.3390/aisens1010001</prism:doi>
	<prism:url>https://www.mdpi.com/3042-5999/1/1/1</prism:url>
	
	<cc:license rdf:resource="CC BY 4.0"/>
</item>
    
<cc:License rdf:about="https://creativecommons.org/licenses/by/4.0/">
	<cc:permits rdf:resource="https://creativecommons.org/ns#Reproduction" />
	<cc:permits rdf:resource="https://creativecommons.org/ns#Distribution" />
	<cc:permits rdf:resource="https://creativecommons.org/ns#DerivativeWorks" />
</cc:License>

</rdf:RDF>
