Search Results (44)

Wearable technologies are increasingly integrated into digital health systems to support continuous remote monitoring in oncology; however, the lack of standardized and reproducible criteria for device selection limits their scalable and regulation-compliant adoption in clinically oriented infrastructures. This study proposes a preclinical benchmarking framework for the systematic evaluation of commercially available wearable devices for oncology applications. Devices were assessed across six predefined dimensions: biometric data acquisition, application programming interface-based interoperability, regulatory compliance, battery autonomy, cost, and absence of mandatory subscription fees. From an initial pool of 23 devices, a stepwise screening process identified 6 eligible wearables, which were compared using a semi-quantitative weighted scoring system. The benchmarking analysis identified the Withings ScanWatch 2 as the highest-ranked device, achieving a score of 37/40 and representing the only solution combining medical-grade certification for selected functions, extended battery life (up to 30 days), declared General Data Protection Regulation-compliant data governance, and fully accessible application programming interfaces. The remaining devices scored between 17 and 23 due to limitations in certification, battery autonomy, or data accessibility. This work introduces a reproducible preclinical benchmarking methodology that supports transparent wearable device selection in oncology and provides a foundation for future scalable digital health integration under appropriate regulatory and interoperability governance. Full article

Wearable devices provide reliable biometric measurements in different contexts, and AI algorithms are increasingly being used to analyze this data. The objective of this review is to examine the use of wearable devices to collect biometric data combined with AI algorithms in an educational setting. A systematic review was conducted through the PRISMA methodology, by searching the Scopus database for works that included wearables, biometrics, and AI algorithms. A total of 43 studies were included and examined. The objectives, the type of collected data, and the methodologies of the included studies were investigated. Most articles utilized machine learning and deep learning algorithms for classification tasks, such as detecting stress or attention. Other applications included human activity recognition (HAR) for classroom orchestration and emotional or cognitive state detection. Many of the studies applied knowledge from previous works to the educational context, resembling exploratory research. Conversely, some authors developed tasks and methodologies tailored to the educational context. The strengths and weaknesses of the presented studies were discussed to propose future research directions. The main findings of this review highlight the advantages of the combination of multimodal sensing and predictive modeling in education with the eventual prospect of personalization. The absence of standardized acquisition and reporting remains the main barrier to replication, benchmarking, and synthesis across studies. Full article

Unmanned aerial vehicles (UAVs) are transforming agriculture through enhanced data acquisition, improved monitoring efficiency, and support for data-driven decision-making. Complementing this, AI-driven platforms provide intuitive and reliable tools for advanced UAV analytics. However, their integration remains underexplored, particularly in specialty crops. Therefore, in this study, we evaluated the performance of an AI-driven web platform (Solvi) for automated plant counting and biometric trait estimation in two contrasting systems: pecan, a perennial nut crop, and onion, an annual vegetable. Ground-truth measurements included pecan tree number, tree height, and canopy area, as well as onion bulb number and diameter, the latter used for market class classification. Counting performance was assessed using precision, recall, and F1 score, while trait estimation was evaluated with linear regression analysis. UAV-based counts showed strong agreement with ground-truth data, achieving precision, recall, and F1 scores above 97% for both crops. For pecans, UAV-derived estimates of tree height (R² = 0.98, error = 11.48%) and canopy area (R² = 0.99, error = 23.16%) demonstrated high accuracy, while errors were larger in young trees compared with mature trees. For onions, UAV-derived bulb diameters achieved an R² of 0.78 with a 6.29% error, and market class classification (medium, jumbo, colossal) was predicted with <10% error. These findings demonstrate that UAV imagery integrated with a user-friendly AI platform can deliver accurate, scalable solutions for biometric monitoring in both perennial and annual specialty crops, supporting applications in harvest planning, orchard management, and market supply forecasting. Full article

A smart device unlocking scheme based on ultrasonic gesture recognition is proposed, allowing users to unlock their devices by customizing the unlock code through gesture movements. This method utilizes ultrasound to detect multiple consecutive gestures, identifying micro-features within these gestures for authentication. To enhance recognition accuracy, an unsupervised segmentation algorithm is employed to accurately segment the gesture feature region and extract the time-frequency domain data of the gestures. Additionally, two-stage data enhancement techniques are applied to generate user-specific data based on a small sample size. Finally, the user-specific model is deployed to mobile devices via transfer learning for on-device, real-time inference. Experimental validation on a commercial smartphone (Redmi K50) demonstrates that the entire authentication pipeline, from signal acquisition to decision, processes 8 types of gestures in a sequence in sequence in approximately 1.2 s, with the core model inference taking less than 50 milliseconds. This ensures that the raw biometric data (ultrasonic echoes) and the recognition results never leave the user’s device during authentication, thereby safeguarding privacy. It is important to note that while model training is performed offline on a server to leverage greater computational resources for personalization, the deployed system operates fully in real time on the edge device. Experimental results demonstrate that our system achieves accurate and robust identity verification, with an average five-fold cross-validation accuracy rate of up to $93.56\%$, and it shows robustness across different environments. Full article

Background: There is an emerging need for new scalable behavioral assays, i.e., assays that are feasible to administer from the comfort of the person’s home, with ease and at higher frequency than clinical visits or visits to laboratory settings can afford us today. This need poses several challenges which we address in this work along with scalable solutions for behavioral data acquisition and analyses aimed at diversifying various populations under study here and to encourage citizen-driven participatory models of research and clinical practices. Methods: Our methods are centered on the biophysical fluctuations unique to the person and on the characterization of behavioral states using standardized biorhythmic time series data (from kinematic, electrocardiographic, voice, and video-based tools) in naturalistic settings, outside a laboratory environment. The methods are illustrated with three representative studies (58 participants, 8–70 years old, 34 males, 24 females). Data is presented across the nervous systems under a proposed functional taxonomy that permits data organization according to nervous systems’ maturation and decline levels. These methods can be applied to various research programs ranging from clinical trials at home, to remote pedagogical settings. They are aimed at creating new standardized biometric scales to screen and diagnose neurological disorders across the human lifespan. Results: Using this remote data collection system under our new unifying statistical platform for individualized behavioral analysis, we characterize the digital ranges of biophysical signals of neurotypical participants and report departure from normative ranges in neurodevelopmental and neurodegenerative disorders. Each study provides parameter spaces with self-emerging clusters whereby data points corresponding to a cluster are probability distribution parameters automatically classifying participants into different continuous Gamma probability distribution families. Non-parametric analysis reveals significant differences in distributions’ shape and scale (p < 0.01). Data reduction is realizable from full probability distribution families to a single parameter, the Gamma scale, amenable to represent each participant within each subclass, and each cluster of similar participants within each cohort. We report on data integration from stochastic analyses that serve to differentiate participants and propose new ways to highly scale our research, education, and clinical practices. Conclusions: This work highlights important methodological and analytical techniques for developing personalized and scalable biometrics across various populations outside a laboratory setting. Full article

This submission is focused on the implementation of a system that acquires data from various types of sensors and securely stores them after encryption on a chip with a reconfigurable architecture. The system has the unique capability of encrypting the input data with a single secret cryptographic key, which is stored only inside the hardware of the system itself, so the key remains unrecognizable upon completion of the system synthesis for any unauthorized user. Being stored as a part of the whole system architecture, the cryptographic key cannot be attained. It is not stored separately on the system RAM or any other supported memory, making the collected data fully protected. The reported work shows a data acquisition system which measures temperature with a high level of precision, transforms it to degrees Celsius, stores the collected data, and transfers them via serial interface when requested. Before storage, the data are encrypted with a 256-bit key, applying the AES algorithm. The data which are stored in the system memory and sent as UART packets towards the main computer do not include the cryptographic key in the data stream, so it is impossible for it to be retrieved from them. We show the flexibility of such kinds of data acquisition systems for sensing different types of signals, emphasizing secure storage and transferring, including data from meteorological sensors or highly confidential or biometrical data. Full article

Current finger-vein or palm-vein recognition systems usually require direct contact of the subject with the apparatus. This can be problematic in environments where hygiene is of primary importance. In this work we present a contactless vascular biometrics sensor platform named sweet which can be used for hand vascular biometrics studies (wrist, palm, and finger-vein) and surface features such as palmprint. It supports several acquisition modalities such as multi-spectral Near-Infrared (NIR), RGB-color, Stereo Vision (SV) and Photometric Stereo (PS). Using this platform we collected a dataset consisting of the fingers, palm and wrist vascular data of 120 subjects. We present biometric experimental results, focusing on Finger-Vein Recognition (FVR). Finally, we discuss fusion of multiple modalities. The acquisition software, parts of the hardware design, the new FV dataset, as well as source-code for our experiments are publicly available for research purposes. Full article

Especially in real-world circumstances with uneven road surfaces and impulsive shocks, nonlinear dynamic effects in vehicle systems can greatly skew biometric data utilized to track passenger and driver physiological states. By creating a thorough multibody human–seat–chassis model, this work tackles the effect of vehicle-induced vibrations on the accuracy and dependability of biometric measures. The model includes external excitation from road-induced inputs, nonlinear damping between structural linkages, and vertical and angular degrees of freedom in the head–neck system. Motion equations are derived using a second-order Lagrangian method; simulations are run using representative values of a typical car and human body segments. Results show that higher vehicle speed generates more vibrational energy input, which especially in the head and torso enhances vertical and angular accelerations. Modal studies, on the other hand, show that while resonant frequencies stay constant, speed causes a considerable rise in amplitude and frequency dispersion. At speeds ≥ 50 km/h, RMS and VDV values exceed ISO 2631 comfort standards in the body and head. The results highlight the need to include vibration-optimized suspension systems and ergonomic design approaches to safeguard sensitive body areas and preserve biometric data integrity. This study helps to increase comfort and safety in both traditional and autonomous car uses. Full article

The acquisition of depth information sensorial data is critically important in medical applications, such as the monitoring of the elderly or the extraction of human biometrics. In such applications, compressing the stream of depth video data plays an important role due to bandwidth constraints on transmission channels. This paper introduces a novel lightweight compression system that encodes the semantics of the input depth video and can operate in both lossless and L-infinite near-lossless compression modes. A quantization technique that targets the L-infinite norm for sparse distributions and a new L-infinite compression method that sets bounds on the quantization error is proposed. The proposed codec enables the control of the coding error on every pixel in the input video data, which is crucial in medical applications. Experimental results show an average improvement of 45% and 17% in lossless mode compared to standalone JPEG-LS and CALIC codecs, respectively. Furthermore, in near-lossless mode, the proposed codec achieves superior rate-distortion performance and reduced maximum error per frame compared to HEVC. Additionally, the proposed lightweight codec is designed to perform efficiently in real time when deployed on an embedded depth-camera platform. Full article

Computer vision-based gait recognition (CVGR) is a technology that has gained considerable attention in recent years due to its non-invasive, unobtrusive, and difficult-to-conceal nature. Beyond its applications in biometrics, CVGR holds significant potential for healthcare and human–computer interaction. Current CVGR systems often transmit collected data to a cloud server for machine learning-based gait pattern recognition. While effective, this cloud-centric approach can result in increased system response times. Alternatively, the emerging paradigm of edge computing, which involves moving computational processes to local devices, offers the potential to reduce latency, enable real-time surveillance, and eliminate reliance on internet connectivity. Furthermore, recent advancements in low-cost, compact microcomputers capable of handling complex inference tasks (e.g., Jetson Nano Orin, Jetson Xavier NX, and Khadas VIM4) have created exciting opportunities for deploying CVGR systems at the edge. This paper reports the state of the art in gait data acquisition modalities, feature representations, models, and architectures for CVGR systems suitable for edge computing. Additionally, this paper addresses the general limitations and highlights new avenues for future research in the promising intersection of CVGR and edge computing. Full article

Using biometric data for user authentication is a frequently addressed subject within the context of computer security. Despite significant advancements in technology, handwriting analysis continues to be the most common method of identifying individuals. There are two distinct types of handwriting recognition: offline and online. The first type involves the identification and interpretation of handwritten content obtained from an image, such as digitized human handwriting. The latter pertains to the identification of handwriting derived from digital writing performed on a touchpad or touchscreen. This research paper provides a comprehensive overview of the proposed apparatus specifically developed for collecting handwritten data. The acquisition of biometric information is conducted using a touchscreen device equipped with a variety of integrated and external sensors. In addition to acquiring signatures, the sensor-fusion-based configuration accumulates handwritten phrases, words, and individual letters to facilitate online user authentication. The proposed system can collect an extensive array of data. Specifically, it is possible to capture data related to stylus pressure, magnetometer readings, images, videos, and audio signals associated with handwriting executed on a tablet device. The study incorporates instances of gathered records, providing a graphical representation of the variation in handwriting among distinct users. The data obtained were additionally analyzed with regard to inter-person variability, intra-person variability, and classification potential. Initial findings from a limited sample of users demonstrate favorable results, intending to gather data from a more extensive user base. Full article

The vitreous humor (VH) is a transparent gelatin-like substance that occupies two-thirds of the eyeball and undergoes the most significant changes during eye elongation. Quantitative proteomics on the normal growth period in the VH could provide new insights into understanding its progression mechanism in the early stages of myopia. In this study, a data-independent acquisition (SWATH-MS) was combined with targeted LC-ESI-MS/MS to identify and quantify the relative protein changes in the vitreous during the normal growth period (4, 7, 14, 21 and 28 days old) in the chick model. Chicks were raised under normal growing conditions (12/12 h Dark/light cycle) for 28 days, where ocular measurements, including refractive and biometric measurements, were performed on days 4 (baseline), 7, 14, 21 and 28 (n = 6 chicks at each time point). Extracted vitreous proteins from individual animals were digested and pooled into a left eye pool and a right pool at each time point for protein analysis. The vitreous proteome for chicks was generated using an information-dependent acquisition (IDA) method by combining injections from individual time points. Using individual pool samples, SWATH-MS was employed to quantify proteins between each time point. DEPs were subsequently confirmed in separate batches of animals individually on random eyes (n = 4) using MRMHR between day 7 and day 14. Refraction and vitreous chamber depth (VCD) were found to be significantly changed (p < 0.05, n = 6 at each time point) during the period. A comprehensive vitreous protein ion library was built with 1576 non-redundant proteins (22987 distinct peptides) identified at a 1% false discovery rate (FDR). A total of 12 up-regulated and 26 down-regulated proteins were found across all time points compared to day 7 using SWATH-MS. Several DEPs, such as alpha-fetoprotein, the cadherin family group, neurocan, and reelin, involved in structural and growth-related pathways, were validated for the first time using MRMHR under this experimental condition. This study provided the first comprehensive spectral library of the vitreous for chicks during normal growth as well as a list of potential growth-related protein biomarker candidates using SWATH-MS and MRMHR during the emmetropization period. Full article

Electrocardiogram (ECG) signals are a measure minute electrical signals generated during the cardiac cycle, a biometric signal that occurs during vital human activity. ECG signals are susceptible to various types of noise depending on the data acquisition conditions, with factors such as sensor placement and the physiological and mental states of the subject contributing to the diverse shapes of these signals. When the data are acquired in a single session, the environmental variables are relatively similar, resulting in similar ECG signals; however, in subsequent sessions, even for the same person, changes in the environmental variables can alter the signal shape. This phenomenon poses challenges for person identification using ECG signals acquired on different days. To improve the performance of individual identification, even when ECG data is acquired on different days, this paper proposes an ensemble deep neural network for person identification by comparing and analyzing the ECG recognition performance under various conditions. The proposed ensemble deep neural network comprises three streams that incorporate two well-known pretrained models. Each network receives the time-frequency representation of ECG signals as input, and a stream reuses the same network structure under different learning conditions with or without data augmentation. The proposed ensemble deep neural network was validated on the Physikalisch-Technische Bundesanstalt dataset, and the results confirmed a 3.39% improvement in accuracy compared to existing methods. Full article

The advancement of technology and its developments have provided the forensic sciences with many cutting-edge tools, devices, and applications, allowing forensics a better and more accurate understanding of the crime scene, a better and optimal acquisition of data and information, and faster processing, allowing more reliable conclusions to be obtained and substantially improving the scientific investigation of crime. This article describes the technological advances, their impacts, and the challenges faced by forensic specialists in using and implementing these technologies as tools to strengthen their field and laboratory investigations. The systematic review of the scientific literature used the PRISMA^® methodology, analyzing documents from databases such as SCOPUS, Web of Science, Taylor & Francis, PubMed, and ProQuest. Studies were selected using a Cohen Kappa coefficient of 0.463. In total, 63 reference articles were selected. The impact of technology on investigations by forensic science experts presents great benefits, such as a greater possibility of digitizing the crime scene, allowing remote analysis through extended reality technologies, improvements in the accuracy and identification of biometric characteristics, portable equipment for on-site analysis, and Internet of things devices that use artificial intelligence and machine learning techniques. These alternatives improve forensic investigations without diminishing the investigator’s prominence and responsibility in the resolution of cases. Full article

Recent studies have focused on user authentication methods that use biometric signals such as electrocardiogram (ECG) and photo-plethysmography (PPG). These authentication technologies have advantages such as ease of acquisition, strong security, and the capability for non-aware authentication. This study addresses user authentication using electromyogram (EMG) signals, which are particularly easy to acquire, can be fabricated in a wearable form such as a wristwatch, and are readily expandable with technologies such as human–machine interface. However, despite their potential, they often exhibit lower accuracy (approximately 90%) than traditional methods such as fingerprint recognition. Accuracy can be improved using complex algorithms and multiple biometric authentication technologies; however, complex algorithms use substantial hardware resources, making their application to wearable devices difficult. In this study, a simple Siamese model with long short-term memory (LSTM) (SSiamese-LSTM) is proposed to achieve a high accuracy of over 99% with limited resources suitable for wearable devices. The hardware implementation was accomplished using field-programmable gate arrays (FPGAs). In terms of accuracy, EMG measurement results from Chosun University were used, and data from 100 individuals were employed for verification. The proposed digital logic will be integrated with an EMG sensor in the form of a watch that can be used for user authentication. Full article