Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (34)

Search Parameters:
Keywords = relevant fingerprinting feature

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
11 pages, 7608 KiB  
Article
A Theoretical Raman Spectra Analysis of the Effect of the Li2S and Li3PS4 Content on the Interface Formation Between (110)Li2S and (100)β-Li3PS4
by Naiara Leticia Marana, Eleonora Ascrizzi, Fabrizio Silveri, Mauro Francesco Sgroi, Lorenzo Maschio and Anna Maria Ferrari
Materials 2025, 18(15), 3515; https://doi.org/10.3390/ma18153515 - 26 Jul 2025
Viewed by 336
Abstract
In this study, we perform density functional theory (DFT) simulations to investigate the Raman spectra of the bulk and surface phases of β-Li3PS4 (LPS) and Li2S, as well as their interfaces at varying compositional ratios. This analysis is [...] Read more.
In this study, we perform density functional theory (DFT) simulations to investigate the Raman spectra of the bulk and surface phases of β-Li3PS4 (LPS) and Li2S, as well as their interfaces at varying compositional ratios. This analysis is relevant given the widespread application of these materials in Li–S solid-state batteries, where Li2S functions not only as a cathode material but also as a protective layer for the lithium anode. Understanding the interfacial structure and how compositional variations influence its chemical and mechanical stability is therefore crucial. Our results demonstrate that the LPS/Li2S interface remains stable regardless of the compositional ratio. However, when the content of both materials is low, the Raman-active vibrational mode associated with the [PS4]3− tetrahedral cluster dominates the interface spectrum, effectively obscuring the characteristic peaks of Li2S and other interfacial features. Only when sufficient amounts of both LPS and Li2S are present does the coupling between their vibrational modes become sufficiently pronounced to alter the Raman profile and reveal distinct interfacial fingerprints. Full article
(This article belongs to the Section Advanced Materials Characterization)
Show Figures

Graphical abstract

19 pages, 3234 KiB  
Article
siRNA Features—Automated Machine Learning of 3D Molecular Fingerprints and Structures for Therapeutic Off-Target Data
by Michael Richter and Alem Admasu
Int. J. Mol. Sci. 2025, 26(14), 6795; https://doi.org/10.3390/ijms26146795 - 16 Jul 2025
Viewed by 443
Abstract
Chemical modifications are the standard for small interfering RNAs (siRNAs) in therapeutic applications, but predicting their off-target effects remains a significant challenge. Current approaches often rely on sequence-based encodings, which fail to fully capture the structural and protein–RNA interaction details critical for off-target [...] Read more.
Chemical modifications are the standard for small interfering RNAs (siRNAs) in therapeutic applications, but predicting their off-target effects remains a significant challenge. Current approaches often rely on sequence-based encodings, which fail to fully capture the structural and protein–RNA interaction details critical for off-target prediction. In this study, we developed a framework to generate reproducible structure-based chemical features, incorporating both molecular fingerprints and computationally derived siRNA–hAgo2 complex structures. Using an RNA-Seq off-target study, we generated over 30,000 siRNA–gene data points and systematically compared nine distinct types of feature representation strategies. Among the datasets, the highest predictive performance was achieved by Dataset 3, which used extended connectivity fingerprints (ECFPs) to encode siRNA and mRNA features. An energy-minimized dataset (7R), representing siRNA–hAgo2 structural alignments, was the second-best performer, underscoring the value of incorporating reproducible structural information into feature engineering. Our findings demonstrate that combining detailed structural representations with sequence-based features enables the generation of robust, reproducible chemical features for machine learning models, offering a promising path forward for off-target prediction and siRNA therapeutic design that can be seamlessly extended to include any modification, such as clinically relevant 2′-F or 2′-OMe. Full article
(This article belongs to the Section Biochemistry)
Show Figures

Figure 1

12 pages, 740 KiB  
Article
Deep Learning-Based Molecular Fingerprint Prediction for Metabolite Annotation
by Hoi Yan Katharine Chau, Xinran Zhang and Habtom W. Ressom
Metabolites 2025, 15(2), 132; https://doi.org/10.3390/metabo15020132 - 14 Feb 2025
Viewed by 1335
Abstract
Background/Objectives: Liquid chromatography coupled with mass spectrometry (LC-MS) is a commonly used platform for many metabolomics studies. However, metabolite annotation has been a major bottleneck in these studies in part due to the limited publicly available spectral libraries, which consist of tandem mass [...] Read more.
Background/Objectives: Liquid chromatography coupled with mass spectrometry (LC-MS) is a commonly used platform for many metabolomics studies. However, metabolite annotation has been a major bottleneck in these studies in part due to the limited publicly available spectral libraries, which consist of tandem mass spectrometry (MS/MS) data acquired from just a fraction of known compounds. Application of deep learning methods is increasingly reported as an alternative to spectral matching due to their ability to map complex relationships between molecular fingerprints and mass spectrometric measurements. The objectives of this study are to investigate deep learning methods for molecular fingerprint based on MS/MS spectra and to rank putative metabolite IDs according to similarity of their known and predicted molecular fingerprints. Methods: We trained three types of deep learning methods to model the relationships between molecular fingerprints and MS/MS spectra. Prior to training, various data processing steps, including scaling, binning, and filtering, were performed on MS/MS spectra obtained from National Institute of Standards and Technology (NIST), MassBank of North America (MoNA), and Human Metabolome Database (HMDB). Furthermore, selection of the most relevant m/z bins and molecular fingerprints was conducted. The trained deep learning models were evaluated on ranking putative metabolite IDs obtained from a compound database for the challenges in Critical Assessment of Small Molecule Identification (CASMI) 2016, CASMI 2017, and CASMI 2022 benchmark datasets. Results: Feature selection methods effectively reduced redundant molecular and spectral features prior to model training. Deep learning methods trained with the truncated features have shown comparable performances against CSI:FingerID on ranking putative metabolite IDs. Conclusion: The results demonstrate a promising potential of deep learning methods for metabolite annotation. Full article
Show Figures

Figure 1

11 pages, 1432 KiB  
Article
Volatile Fingerprints of Synthetic Wines Fermented by Different Oenological Yeast Strains
by Sandra Pati, Ilaria Benucci, Giuseppe Rosiello and Marco Esti
Beverages 2024, 10(4), 122; https://doi.org/10.3390/beverages10040122 - 12 Dec 2024
Viewed by 964
Abstract
Background: The role of the S. cerevisiae strain in defining the volatile fingerprint is expressed throughout alcoholic fermentation and post-fermentation sur lie aging and is crucial for customizing the wine style. Methods: In this study, the alcoholic fermentation was carried out in a [...] Read more.
Background: The role of the S. cerevisiae strain in defining the volatile fingerprint is expressed throughout alcoholic fermentation and post-fermentation sur lie aging and is crucial for customizing the wine style. Methods: In this study, the alcoholic fermentation was carried out in a synthetic must to exclusively bring out the performance of the yeast in terms of volatile compound production, excluding the effect of the grape. Results: Among the 33 volatile organic compounds identified in the synthetic wines by GC-MS, esters, alcohols, and acids, represented the major groups for the nine different commercial oenological strains tested. All the relevant differences in the volatile fingerprint of the synthetic wines, which were lab-scale fermented, were quantitative rather than qualitative. The clustergram representation of the volatiles revealed an outstanding fingerprint for two strains (VIN13 and VIN7) among those tested, featuring hexanoic acid, octanoic acid, the corresponding esters (ethyl hexanoate, ethyl octanoate), and the acetates (2-phenylethyl acetate, isoamyl acetate), all at the highest levels. No relationship was appreciated between the fermentation rate and the volatile fingerprints. Conclusions: The outcomes of this study address the wine industry’s needs, supplying a full characterization of a broad range of commercial yeasts’ ability in fermentative volatile production. Full article
(This article belongs to the Section Beverage Technology Fermentation and Microbiology)
Show Figures

Figure 1

15 pages, 3259 KiB  
Article
Towards Sustainable Material Design: A Comparative Analysis of Latent Space Representations in AI Models
by Ulises Martin Casado, Facundo Ignacio Altuna and Luis Alejandro Miccio
Sustainability 2024, 16(23), 10681; https://doi.org/10.3390/su162310681 - 5 Dec 2024
Cited by 3 | Viewed by 1676
Abstract
In this study, we employed machine learning techniques to improve sustainable materials design by examining how various latent space representations affect the AI performance in property predictions. We compared three fingerprinting methodologies: (a) neural networks trained on specific properties, (b) encoder–decoder architectures, and [...] Read more.
In this study, we employed machine learning techniques to improve sustainable materials design by examining how various latent space representations affect the AI performance in property predictions. We compared three fingerprinting methodologies: (a) neural networks trained on specific properties, (b) encoder–decoder architectures, and c) traditional Morgan fingerprints. Their encoding quality was quantitatively compared by using these fingerprints as inputs for a simple regression model (Random Forest) to predict glass transition temperatures (Tg), a critical parameter in determining material performance. We found that the task-specific neural networks achieved the highest accuracy, with a mean absolute percentage error (MAPE) of 10% and an R2 of 0.9, significantly outperforming encoder–decoder models (MAPE: 19%, R2: 0.76) and Morgan fingerprints (MAPE: 24%, R2: 0.6). In addition, we used dimensionality reduction techniques, such as principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE), to gain insights on the models’ abilities to learn relevant molecular features to Tg. By offering a more profound understanding of how chemical structures influence AI-based property predictions, this approach enables the efficient identification of high-performing materials in applications that range from water decontamination to polymer recyclability with minimum experimental effort, promoting a circular economy in materials science. Full article
Show Figures

Figure 1

19 pages, 2872 KiB  
Article
Channel and Spatial Attention in Chest X-Ray Radiographs: Advancing Person Identification and Verification with Self-Residual Attention Network
by Hazem Farah, Akram Bennour, Neesrin Ali Kurdi, Samir Hammami and Mohammed Al-Sarem
Diagnostics 2024, 14(23), 2655; https://doi.org/10.3390/diagnostics14232655 - 25 Nov 2024
Cited by 1 | Viewed by 975
Abstract
Background/Objectives: In contrast to traditional biometric modalities, such as facial recognition, fingerprints, and iris scans or even DNA, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual’s skeletal structure, [...] Read more.
Background/Objectives: In contrast to traditional biometric modalities, such as facial recognition, fingerprints, and iris scans or even DNA, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual’s skeletal structure, the ribcage of the chest, lungs, and heart, chest X-rays have emerged as a focal point for identification and verification, especially in the forensic field, even in scenarios where the human body damaged or disfigured. Discriminative feature embedding is essential for large-scale image verification, especially in applying chest X-ray radiographs for identity identification and verification. This study introduced a self-residual attention-based convolutional neural network (SRAN) aimed at effective feature embedding, capturing long-range dependencies and emphasizing critical spatial features in chest X-rays. This method offers a novel approach to person identification and verification through chest X-ray categorization, relevant for biometric applications and patient care, particularly when traditional biometric modalities are ineffective. Method: The SRAN architecture integrated a self-channel and self-spatial attention module to minimize channel redundancy and enhance significant spatial elements. The attention modules worked by dynamically aggregating feature maps across channel and spatial dimensions to enhance feature differentiation. For the network backbone, a self-residual attention block (SRAB) was implemented within a ResNet50 framework, forming a Siamese network trained with triplet loss to improve feature embedding for identity identification and verification. Results: By leveraging the NIH ChestX-ray14 and CheXpert datasets, our method demonstrated notable improvements in accuracy for identity verification and identification based on chest X-ray images. This approach effectively captured the detailed anatomical characteristics of individuals, including skeletal structure, ribcage, lungs, and heart, highlighting chest X-rays as a viable biometric tool even in cases of body damage or disfigurement. Conclusions: The proposed SRAN with self-residual attention provided a promising solution for biometric identification through chest X-ray imaging, showcasing its potential for accurate and reliable identity verification where traditional biometric approaches may fall short, especially in postmortem cases or forensic investigations. This methodology could play a transformative role in both biometric security and healthcare applications, offering a robust alternative modality for identity verification. Full article
Show Figures

Figure 1

34 pages, 6053 KiB  
Article
Insights into the Identification of iPSC- and Monocyte-Derived Macrophage-Polarizing Compounds by AI-Fueled Cell Painting Analysis Tools
by Johanna B. Brüggenthies, Jakob Dittmer, Eva Martin, Igor Zingman, Ibrahim Tabet, Helga Bronner, Sarah Groetzner, Julia Sauer, Mozhgan Dehghan Harati, Rebekka Scharnowski, Julia Bakker, Katharina Riegger, Caroline Heinzelmann, Birgit Ast, Robert Ries, Sophie A. Fillon, Anna Bachmayr-Heyda, Kerstin Kitt, Marc A. Grundl, Ralf Heilker, Lina Humbeck, Michael Schuler and Bernd Weigleadd Show full author list remove Hide full author list
Int. J. Mol. Sci. 2024, 25(22), 12330; https://doi.org/10.3390/ijms252212330 - 17 Nov 2024
Viewed by 2771
Abstract
Macrophage polarization critically contributes to a multitude of human pathologies. Hence, modulating macrophage polarization is a promising approach with enormous therapeutic potential. Macrophages are characterized by a remarkable functional and phenotypic plasticity, with pro-inflammatory (M1) and anti-inflammatory (M2) states at the extremes of [...] Read more.
Macrophage polarization critically contributes to a multitude of human pathologies. Hence, modulating macrophage polarization is a promising approach with enormous therapeutic potential. Macrophages are characterized by a remarkable functional and phenotypic plasticity, with pro-inflammatory (M1) and anti-inflammatory (M2) states at the extremes of a multidimensional polarization spectrum. Cell morphology is a major indicator for macrophage activation, describing M1(-like) (rounded) and M2(-like) (elongated) states by different cell shapes. Here, we introduced cell painting of macrophages to better reflect their multifaceted plasticity and associated phenotypes beyond the rigid dichotomous M1/M2 classification. Using high-content imaging, we established deep learning- and feature-based cell painting image analysis tools to elucidate cellular fingerprints that inform about subtle phenotypes of human blood monocyte-derived and iPSC-derived macrophages that are characterized as screening surrogate. Moreover, we show that cell painting feature profiling is suitable for identifying inter-donor variance to describe the relevance of the morphology feature ‘cell roundness’ and dissect distinct macrophage polarization signatures after stimulation with known biological or small-molecule modulators of macrophage (re-)polarization. Our novel established AI-fueled cell painting analysis tools provide a resource for high-content-based drug screening and candidate profiling, which set the stage for identifying novel modulators for macrophage (re-)polarization in health and disease. Full article
(This article belongs to the Special Issue Advanced Research on Macrophages in Human Health and Disease)
Show Figures

Graphical abstract

20 pages, 5792 KiB  
Review
A Review of the Sediment Production and Transport Processes of Forest Road Erosion
by Jinhai Yu, Qinghe Zhao, Zaihui Yu, Yi Liu and Shengyan Ding
Forests 2024, 15(3), 454; https://doi.org/10.3390/f15030454 - 28 Feb 2024
Cited by 9 | Viewed by 2567
Abstract
Forest roads are a common land use feature with a significant impact on sediment yield and the water sediment transport processes within a watershed, seriously disrupting the safety and stability of the watershed. Previous studies have focused on the sediment production processes within [...] Read more.
Forest roads are a common land use feature with a significant impact on sediment yield and the water sediment transport processes within a watershed, seriously disrupting the safety and stability of the watershed. Previous studies have focused on the sediment production processes within the road prism. However, there has been limited attention given to the transport processes of road-eroded sediment at various scales, which is crucial for understanding the off-site effects of road erosion. This paper reviews research conducted on forest road erosion over the past two decades. It summarizes the mechanisms of sediment production from road erosion and provides a detailed analysis of the transport mechanisms of eroded sediments from roads to streams at the watershed scale. The paper also examines the ecological and hydrological effects, research methods, and control measures related to sediment transport caused by forest road erosion. It identifies current research limitations and outlines future research directions. The findings of this review highlight several key points: (1) Most research on forest road erosion tends to be specific and unilateral, often neglecting the broader interaction between roads and the watershed in terms of water–sediment dynamics. (2) Various research methods are employed in the study of forest road erosion, including field monitoring, artificial simulation experiments, and road erosion prediction models. Each method has its advantages and disadvantages, but the integration of emerging technologies like laser scanning and fingerprint recognition remains underutilized, hindering the simultaneous achievement of convenience and accuracy. (3) The transport processes of forest road-eroded sediment, particularly on road–stream slopes, are influenced by numerous factors, including terrain, soil, and vegetation. These processes exhibit significant spatial and temporal variability, and the precise quantification of sediment transport efficiency to the stream remains challenging due to a lack of long-term and stable investigation and monitoring methods. The establishment and operation of runoff plots and sedimentation basins may help offer a solution to this challenge. (4) Both biological and engineering measures have proven effective in reducing and limiting sediment erosion and transport. However, the costs and economic benefits associated with these regulation measures require further investigation. This review provides a comprehensive summary of relevant research on sediment erosion and transport processes on unpaved forest roads, enhancing our understanding of sediment yield in watersheds and offering valuable insights for reducing sediment production and transport to streams. Full article
(This article belongs to the Special Issue Recent Advances in Forests Roads Research)
Show Figures

Figure 1

18 pages, 3295 KiB  
Article
Kinematic Analysis of Human Gait in Healthy Young Adults Using IMU Sensors: Exploring Relevant Machine Learning Features for Clinical Applications
by Xavier Marimon, Itziar Mengual, Carlos López-de-Celis, Alejandro Portela, Jacobo Rodríguez-Sanz, Iria Andrea Herráez and Albert Pérez-Bellmunt
Bioengineering 2024, 11(2), 105; https://doi.org/10.3390/bioengineering11020105 - 23 Jan 2024
Cited by 10 | Viewed by 5676
Abstract
Background: Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the [...] Read more.
Background: Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the treatment or prevention of gait disorders. The aim of the present study was to identify the key features of normal human gait using inertial unit (IMU) recordings in a walking test. Methods: Gait analysis was conducted on 32 healthy participants (age range 19–29 years) at speeds of 2 km/h and 4 km/h using a treadmill. Dynamic data were obtained using a microcontroller (Arduino Nano 33 BLE Sense Rev2) with IMU sensors (BMI270). The collected data were processed and analyzed using a custom script (MATLAB 2022b), including the labeling of the four relevant gait phases and events (Stance, Toe-Off, Swing, and Heel Strike), computation of statistical features (64 features), and application of machine learning techniques for classification (8 classifiers). Results: Spider plot analysis revealed significant differences in the four events created by the most relevant statistical features. Among the different classifiers tested, the Support Vector Machine (SVM) model using a Cubic kernel achieved an accuracy rate of 92.4% when differentiating between gait events using the computed statistical features. Conclusions: This study identifies the optimal features of acceleration and gyroscope data during normal gait. The findings suggest potential applications for injury prevention and performance optimization in individuals engaged in activities involving normal gait. The creation of spider plots is proposed to obtain a personalised fingerprint of each patient’s gait fingerprint that could be used as a diagnostic tool. A deviation from a normal gait pattern can be used to identify human gait disorders. Moving forward, this information has potential for use in clinical applications in the diagnosis of gait-related disorders and developing novel orthoses and prosthetics to prevent falls and ankle sprains. Full article
(This article belongs to the Special Issue Biomechanics of Human Movement and Its Clinical Applications)
Show Figures

Figure 1

23 pages, 979 KiB  
Review
Authentication of Cocoa Products Based on Profiling and Fingerprinting Approaches: Assessment of Geographical, Varietal, Agricultural and Processing Features
by Sonia Sentellas and Javier Saurina
Foods 2023, 12(16), 3120; https://doi.org/10.3390/foods12163120 - 20 Aug 2023
Cited by 9 | Viewed by 3661
Abstract
Cocoa and its derivative products, especially chocolate, are highly appreciated by consumers for their exceptional organoleptic qualities, thus being often considered delicacies. They are also regarded as superfoods due to their nutritional and health properties. Cocoa is susceptible to adulteration to obtain illicit [...] Read more.
Cocoa and its derivative products, especially chocolate, are highly appreciated by consumers for their exceptional organoleptic qualities, thus being often considered delicacies. They are also regarded as superfoods due to their nutritional and health properties. Cocoa is susceptible to adulteration to obtain illicit economic benefits, so strategies capable of authenticating its attributes are needed. Features such as cocoa variety, origin, fair trade, and organic production are increasingly important in our society, so they need to be guaranteed. Most of the methods dealing with food authentication rely on profiling and fingerprinting approaches. The compositional profiles of natural components –such as polyphenols, biogenic amines, amino acids, volatile organic compounds, and fatty acids– are the source of information to address these issues. As for fingerprinting, analytical techniques, such as chromatography, infrared, Raman, and mass spectrometry, generate rich fingerprints containing dozens of features to be used for discrimination purposes. In the two cases, the data generated are complex, so chemometric methods are usually applied to extract the underlying information. In this review, we present the state of the art of cocoa and chocolate authentication, highlighting the pros and cons of the different approaches. Besides, the relevance of the proposed methods in quality control and the novel trends for sample analysis are also discussed. Full article
(This article belongs to the Special Issue Food Fraud and Food Authenticity across the Food Supply Chain)
Show Figures

Figure 1

22 pages, 5162 KiB  
Article
Intrusion Detection System for IoT: Analysis of PSD Robustness
by Lamoussa Sanogo, Eric Alata, Alexandru Takacs and Daniela Dragomirescu
Sensors 2023, 23(4), 2353; https://doi.org/10.3390/s23042353 - 20 Feb 2023
Cited by 5 | Viewed by 1897
Abstract
The security of internet of things (IoT) devices remains a major concern. These devices are very vulnerable because of some of their particularities (limited in both their memory and computing power, and available energy) that make it impossible to implement traditional security mechanisms. [...] Read more.
The security of internet of things (IoT) devices remains a major concern. These devices are very vulnerable because of some of their particularities (limited in both their memory and computing power, and available energy) that make it impossible to implement traditional security mechanisms. Consequently, researchers are looking for new security mechanisms adapted to these devices and the networks of which they are part. One of the most promising new approaches is fingerprinting, which aims to identify a given device by associating it with a unique signature built from its unique intrinsic characteristics, i.e., inherent imperfections, introduced by the manufacturing processes of its hardware. However, according to state-of-the-art studies, the main challenge that fingerprinting faces is the nonrelevance of the fingerprinting features extracted from hardware imperfections. Since these hardware imperfections can reflect on the RF signal for a wireless communicating device, in this study, we aim to investigate whether or not the power spectral density (PSD) of a device’s RF signal could be a relevant feature for its fingerprinting, knowing that a relevant fingerprinting feature should remain stable regardless of the environmental conditions, over time and under influence of any other parameters. Through experiments, we were able to identify limits and possibilities of power spectral density (PSD) as a fingerprinting feature. Full article
(This article belongs to the Special Issue Cybersecurity in the Internet of Things)
Show Figures

Figure 1

31 pages, 3349 KiB  
Article
Robustness of Deep Learning-Based Specific Emitter Identification under Adversarial Attacks
by Liting Sun, Da Ke, Xiang Wang, Zhitao Huang and Kaizhu Huang
Remote Sens. 2022, 14(19), 4996; https://doi.org/10.3390/rs14194996 - 7 Oct 2022
Cited by 16 | Viewed by 3653
Abstract
Deep learning (DL)-based specific emitter identification (SEI) technique can automatically extract radio frequency (RF) fingerprint features in RF signals to distinguish between legal and illegal devices and enhance the security of wireless network. However, deep neural network (DNN) can easily be fooled by [...] Read more.
Deep learning (DL)-based specific emitter identification (SEI) technique can automatically extract radio frequency (RF) fingerprint features in RF signals to distinguish between legal and illegal devices and enhance the security of wireless network. However, deep neural network (DNN) can easily be fooled by adversarial examples or perturbations of the input data. If a malicious device emits signals containing a specially designed adversarial samples, will the DL-based SEI still work stably to correctly identify the malicious device? To the best of our knowledge, this research is still blank, let alone the corresponding defense methods. Therefore, this paper designs two scenarios of attack and defense and proposes the corresponding implementation methods to specializes in the robustness of DL-based SEI under adversarial attacks. On this basis, detailed experiments are carried out based on the real-world data and simulation data. The attack scenario is that the malicious device adds an adversarial perturbation signal specially designed to the original signal, misleading the original system to make a misjudgment. Experiments based on three different attack generation methods show that DL-based SEI is very vulnerability. Even if the intensity is very low, without affecting the probability density distribution of the original signal, the performance can be reduced to about 50%, and at −22 dB it is completely invalid. In the defense scenario, the adversarial training (AT) of DL-based SEI is added, which can significantly improve the system’s performance under adversarial attacks, with ≥60% improvement in the recognition rate compared to the network without AT. Further, AT has a more robust effect on white noise. This study fills the relevant gaps and provides guidance for future research. In the future research, the impact of adversarial attacks must be considered, and it is necessary to add adversarial training in the training process. Full article
(This article belongs to the Special Issue Internet of Things (IoT) Remote Sensing)
Show Figures

Figure 1

17 pages, 1916 KiB  
Review
Electrochemical Profiling of Plants
by Mansi Gandhi and Khairunnisa Amreen
Electrochem 2022, 3(3), 434-450; https://doi.org/10.3390/electrochem3030030 - 4 Aug 2022
Cited by 12 | Viewed by 4168
Abstract
The profiling, or fingerprinting, of distinct varieties of the Plantae kingdom is based on the bioactive ingredients, which are systematically segregated to perform their detailed analysis. The secondary products portray a pivotal role in defining the ecophysiology of distinct plant species. There is [...] Read more.
The profiling, or fingerprinting, of distinct varieties of the Plantae kingdom is based on the bioactive ingredients, which are systematically segregated to perform their detailed analysis. The secondary products portray a pivotal role in defining the ecophysiology of distinct plant species. There is a crucial role of the profiling domain in understanding the various features, characteristics, and conditions related to plants. Advancements in variable technologies have contributed to the development of highly specific sensors for the non-invasive detection of molecules. Furthermore, many hyphenated techniques have led to the development of highly specific integrated systems that allow multiplexed detection, such as high-performance liquid chromatography, gas chromatography, etc., which are quite cumbersome and un-economical. In contrast, electrochemical sensors are a promising alternative which are capable of performing the precise recognition of compounds due to efficient signal transduction. However, due to a few bottlenecks in understanding the principles and non-redox features of minimal metabolites, the area has not been explored. This review article provides an insight to the electrochemical basis of plants in comparison with other traditional approaches and with necessary positive and negative outlooks. Studies consisting of the idea of merging the fields are limited; hence, relevant non-phytochemical reports are included for a better comparison of reports to broaden the scope of this work. Full article
(This article belongs to the Special Issue Feature Papers in Electrochemistry)
Show Figures

Figure 1

16 pages, 3356 KiB  
Article
WLAN RSS-Based Fingerprinting for Indoor Localization: A Machine Learning Inspired Bag-of-Features Approach
by Sohaib Bin Altaf Khattak, Fawad, Moustafa M. Nasralla, Maged Abdullah Esmail, Hala Mostafa and Min Jia
Sensors 2022, 22(14), 5236; https://doi.org/10.3390/s22145236 - 13 Jul 2022
Cited by 34 | Viewed by 5150
Abstract
Location-based services have permeated Smart academic institutions, enhancing the quality of higher education. Position information of people and objects can predict different potential requirements and provide relevant services to meet those needs. Indoor positioning system (IPS) research has attained robust location-based services in [...] Read more.
Location-based services have permeated Smart academic institutions, enhancing the quality of higher education. Position information of people and objects can predict different potential requirements and provide relevant services to meet those needs. Indoor positioning system (IPS) research has attained robust location-based services in complex indoor structures. Unforeseeable propagation loss in complex indoor environments results in poor localization accuracy of the system. Various IPSs have been developed based on fingerprinting to precisely locate an object even in the presence of indoor artifacts such as multipath and unpredictable radio propagation losses. However, such methods are deleteriously affected by the vulnerability of fingerprint matching frameworks. In this paper, we propose a novel machine learning framework consisting of Bag-of-Features and followed by a k-nearest neighbor classifier to categorize the final features into their respective geographical coordinate data. BoF calculates the vocabulary set using k-mean clustering, where the frequency of the vocabulary in the raw fingerprint data represents the robust final features that improve localization accuracy. Experimental results from simulation-based indoor scenarios and real-time experiments demonstrate that the proposed framework outperforms previously developed models. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Machine-Learning-Based Localization)
Show Figures

Figure 1

14 pages, 3998 KiB  
Article
Predicting Active Sites in Photocatalytic Degradation Process Using an Interpretable Molecular-Image Combined Convolutional Neural Network
by Zhuoying Jiang, Jiajie Hu, Anna Samia and Xiong (Bill) Yu
Catalysts 2022, 12(7), 746; https://doi.org/10.3390/catal12070746 - 7 Jul 2022
Cited by 9 | Viewed by 2900
Abstract
Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are “black-box” models due to lack of interpretability. This paper describes the [...] Read more.
Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are “black-box” models due to lack of interpretability. This paper describes the development of an interpretable neural-network model on the performance of photocatalytic degradation of organic contaminants by TiO2. The molecular structures of the organic contaminants are represented by molecular images, which are subsequently encoded by feeding into a special convolutional neural network (CNN), EfficientNet, to extract the critical structural features. The extracted features in addition to five other experimental variables were input to a neural network that was subsequently trained to predict the photodegradation reaction rates of the organic contaminants by TiO2. The results show that this machine-learning (ML) model attains a higher accuracy to predict the photocatalytic degradation rate of organic contaminants than a previously developed machine-learning model that used molecular fingerprint encoding. In addition, the most relevant regions in the molecular image affecting the photocatalytic rates can be extracted with gradient-weighted class activation mapping (Grad-CAM). This interpretable machine-learning model, leveraging the graphic interpretability of CNN model, allows us to highlight regions of the molecular structure serving as the active sites of water contaminants during the photocatalytic degradation process. This provides an important piece of information to understand the influence of molecular structures on the photocatalytic degradation process. Full article
(This article belongs to the Special Issue 10th Anniversary of Catalysts—Feature Papers in Photocatalysis)
Show Figures

Figure 1

Back to TopTop