Goran M. Stojanović;Saima Qureshi;Hima Zafar;Dušica Dimitrijević;Ivana Tomić
{"title":"Tampon-Based Sensors for Monitoring Intravaginal pH Levels","authors":"Goran M. Stojanović;Saima Qureshi;Hima Zafar;Dušica Dimitrijević;Ivana Tomić","doi":"10.1109/LSENS.2025.3549185","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3549185","url":null,"abstract":"The proposed work is a proof-of-concept study aimed at developing a sensor capable of measuring and monitoring vaginal pH. The objective of this research is to examine the design concepts and operational principles of a vaginal sensor that utilizes soft, biodegradable textile materials. Traditional methods of assessing vaginal pH levels, such as evaluating vaginal fluids or discharge from the vaginal walls, are difficult to perform consistently over long periods and are often prone to errors. Our sensor demonstrates a simple fabrication technique of pH value monitoring based on the capacitive principle by embroidering the sensors onto a tampon, which is comfortable and biocompatible. Silver conductive threads, known for their antibacterial properties, are used. Two different geometries of embroidered electrodes are proposed for the pH sensors, enabling the monitoring of vaginal pH. A device that tracks changes in pH value aids in early detection, notifies users of potential health changes, supports women's self-management of wellness, and helps prevent conditions, such as vaginitis or sexually transmitted infections associated with pH levels above 4.7.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10916920","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vinayak Bairagi;Vaishali H. Kamble;Sharad T Jadhav;Mrinal R Bachute
{"title":"A Novel Machine Learning and Sensor-Driven System for Nondestructive Detection of Jaggery Adulteration","authors":"Vinayak Bairagi;Vaishali H. Kamble;Sharad T Jadhav;Mrinal R Bachute","doi":"10.1109/LSENS.2025.3548887","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3548887","url":null,"abstract":"Food adulteration is a major challenge on a global scale impacting 10% of the food supply and leading to financial losses up to $30–40 billion annually. A developing country, such as India, is also not an exception to this widespread concerning issue and has significant adulteration cases reported across various categories, including Jaggery, which is its major product sharing 55% of the total world Jaggery production. While the literature reports a few methods for detecting various food adulterations, jaggery—the most popular food in India—has received meagre attention. Moreover, the reported methods have limited success and need further experimentation on a variety of diverse datasets before they are practically deployable. This research presents a classical, novel color-based method for detecting the adulteration in the jaggery. A color sensor is used to detect the color of melted jaggery samples, and an Arduino Uno is used to further analyze the color for reliable detection of adulteration. This research exploits the direct relationship between the captured pixel intensities of the jaggery and its purity to develop a linear regression model. The developed product is validated using samples having varying percentages of adulterations (10%–70%) caused due to single and multiple adulterants (sugar and food color) in jaggery. The machine learning-based novel approach developed in this research gives promising results with an accuracy of 94.67% and a precision as 92.6%. The developed method for identifying tampered jaggery is user-friendly, affordable, portable, and nondestructive and the experimental results confirm its superiority.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Wearable Multisensory Glove for Shape, Size, and Stiffness Recognition Based on Off-the-Shelf Components","authors":"Mohamad Yaacoub;Ali Ibrahim;Fatima Khansa;Leila Hammadi;Christian Gianoglio","doi":"10.1109/LSENS.2025.3548264","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3548264","url":null,"abstract":"This letter presents a wearable multisensory glove that integrates commercial sensors, off-the-shelf components, and an embedded machine learning (ML) approach for object recognition. Sixteen printed objects, categorized by shape, size, and stiffness, were examined using the developed system. Time-domain features and raw data fed ML algorithms including single-layer feed-forward neural network, multilayer perceptron (MLP), and 1-D convolution neural network (1D-CNN). The algorithms were deployed on a low-cost Arduino Nano 33 BLE sense edge device for real-time recognition. Results demonstrate that 1D-CNN achieved the highest classification accuracy of 99.2%, with an inference time of 167 ms while consuming only 2.8 mJ of energy per inference. This study demonstrates the effectiveness of the proposed system in recognizing objects opening up interesting perspectives for various biomedical applications, such as poststroke rehabilitation.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FPGA-Based Real-Time Road Object Detection System Using mmWave Radar","authors":"Anand Mohan;Hemant Kumar Meena;Mohd Wajid;Abhishek Srivastava","doi":"10.1109/LSENS.2025.3547008","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3547008","url":null,"abstract":"This letter presents the development of a real-time object detection system using frequency modulated continuous wave millimeter-wave (mmWave) radar signals and the python productivity for zynq ultrascale + mpsocs (PYNQ-ZU) field-programmable gate array (FPGA) board, which is widely used in advanced driving assistance system and robotic applications. A hardware FPGA platform serves as a valid embedded architecture for the purpose of validating object detection and recognition applications. We used our experiment's point cloud images to apply different machine learning models to detect these objects. Using a top-view (TV) filter to convert 3-D point cloud images into 2-D representations made object detection more accurate. Following the use of filtration techniques, we extracted features from the filtered 2-D image using the visual geometry group (VGG) 16 model. We then assessed four machine learning models for object detection and found that the support vector machine (SVM) model and logistic regression (LR) had better results, obtaining an accuracy of 97%. Our proposed work uses mmWave radar, TV filter, VGG 16 Model, and LR to highly increase object detection accuracy over existing methods.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harshit Shukla;Alka Verma;Anuj K. Sharma;Yogendra Kumar Prajapati
{"title":"Thin-Film Magneto-Optic Plasmonic Sensor With the Photonic Spin Hall Effect","authors":"Harshit Shukla;Alka Verma;Anuj K. Sharma;Yogendra Kumar Prajapati","doi":"10.1109/LSENS.2025.3547745","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3547745","url":null,"abstract":"This letter explores advanced thin-film magneto-optic plasmonic (TF-MOP) sensors that integrate the photonic spin Hall effect (PSHE) into sensing applications. The proposed structure, consisting of a BK7 prism, gold, graphene, cobalt, and air, enables ultraprecise measurement of the refractive index and magnetic field at an excitation wavelength of 633 nm in air. Our study demonstrates an exceptionally large transverse spin-dependent shift of approximately 9.15 µm, which is 11.58 times greater than that observed in a purely plasmonic structure. This significant transverse shift allows the TF-MOP sensor to function as a highly sensitive PSHE-based refractometer, achieving a remarkable sensitivity of 25 861.25 µm/RIU across a minute change in refractive index range, including air and helium.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IDMatchHAR: Semi-Supervised Learning for Sensor-Based Human Activity Recognition Using Pretraining","authors":"Koki Takenaka;Shunsuke Sakai;Tatsuhito Hasegawa","doi":"10.1109/LSENS.2025.3546985","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3546985","url":null,"abstract":"In sensor-based human activity recognition (HAR), the annotation cost for sensor data is higher compared to data, such as images. One can use semisupervised learning (semi-SL) to reduce annotation costs. This method lever-ages unlabeled datasets by assigning pseudolabels. How- ever, these methods have the issue of confirmation bias, where performance degrades due to incorrect pseudolabels. Some approaches have attempted to solve this problem by performing multistage pretraining with labeled and unlabeled data, but these methods require significant computational resources. We propose a framework called IDMatchHAR, which performs semi-SL with a single-stage pretraining process on small-scale datasets. We use instance discrimination (ID) during pretraining to learn robust feature representations applied to the subsequent semi-SL task. We verify the effectiveness of the proposed framework using various convolutional neural networks (CNNs), such as VGG and residual network (ResNet), as well as Transformers, on HASC, WISDM, and Pamap2. Our proposed framework significantly reduces the computational cost of pretraining while demonstrating performance comparable to or exceeding that of existing semi-SL methods.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Longbin Zhu;Wenjie Wang;Risheng Su;Zhijun Zhou;Keping Wang
{"title":"A Charge Balanced Stimulators With a Twin Compensation Loop for Evoked Neural Potential Sensing","authors":"Longbin Zhu;Wenjie Wang;Risheng Su;Zhijun Zhou;Keping Wang","doi":"10.1109/LSENS.2025.3546239","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3546239","url":null,"abstract":"Neurological functional electrical stimulation (NFES) provides a well-controlled and high degree of reconfigurability amount for producing the desired stimulation effect. For evaluating the effect of stimulation, the evoked potentials can be sensed. However, in practice, the unbalanced charge accumulation leads to residual charges and toxic electrochemical reactions at the electrode-tissue sensing interface, which causes electrode corrosion and tissue damage. This letter presents a twin compensation loop (TCL) charge-balancing (CB) topology for the NFES. The TCL-CB consists of two compensation loops, including a positive compensation loop (PCL) and a negative compensation loop (NCL). The PCL and NCL continuously detect and compensate for the accumulated negative and positive charges at the output of the Wilson current mirror (WSC), respectively. The circuits are targeted at integrated circuit (IC) realization, designed and fabricated in a 0.18-<italic>μ</i>m complementary metal oxide semiconductor (CMOS) technology. The power consumption of the WSC with TCL-CB is circa 79.2 μW and occupies a die area of 0.047 mm<sup>2</sup> (0.265 μm × 0.18 μm). Benefiting from TCL-CB, the charge mismatch at the output of WSC is reduced to less than 1%.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimal Load Type for Passive Magnetic Energy Harvesters","authors":"Alon Kuperman","doi":"10.1109/LSENS.2025.3546246","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3546246","url":null,"abstract":"Due to the practical current source characteristics of a passive magnetic energy harvester, it may be conveniently interfaced by either voltage-type or resistance-type load. The load type preferable for interfacing an energy source is the one possessing the narrowest range of values belonging to the maximum power line (a curve linking all possible maximum power point coordinates of power source output characteristics). The brief adopts a set of recently developed equations to compare output characteristics (power–voltage and power–resistance) of a passive magnetic energy harvester and corresponding maximum power lines under a wide range of primary currents. It is clearly shown that voltage-type load should be preferred over resistance-type load for passive magnetic energy harvester interfacing. The findings are supported by experimental results of a passive magnetic energy harvester operating under primary currents of 50–350 A.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Localization of RFID Tags Through Real-Time Angle-of-Arrival Estimation","authors":"Antonello Florio;Gianfranco Avitabile;Giuseppe Coviello","doi":"10.1109/LSENS.2025.3546092","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3546092","url":null,"abstract":"Radio frequency identification (RFID) is an enabling technology for many applications of the Internet-of-Things. The most interesting one is its use for localization and tracking purposes. Among all the possible localization techniques, angle-of-arrival (AoA) estimation performed through phase interferometry proved to be accurate and lightweight in terms of complexity, allowing operation in real-time. In this letter, we propose an approach to UHF RFID tag localization by real-time AoA estimation through a dedicated digital architecture. After introducing the idea and its underlying principles, we discuss a preliminary validation campaign using a software-defined radio and a custom RF front-end aiming to demonstrate the accuracy consistency varying the path loss and the signal power levels.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 3","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harsh Mishra;Mahendra K. Shukla;Priyanshu;Som Dengre;Yashveer Singh;Om Jee Pandey
{"title":"A Lightweight Causal Sound Separation Model for Real-Time Hearing Aid Applications","authors":"Harsh Mishra;Mahendra K. Shukla;Priyanshu;Som Dengre;Yashveer Singh;Om Jee Pandey","doi":"10.1109/LSENS.2025.3546132","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3546132","url":null,"abstract":"Real-time audio processing is crucial for hearing aid IoT applications, where low latency and efficiency are paramount. State-of-the-art models like Demucs achieve high signal-to-distortion ratio (SDR) but are unsuitable for real-time use due to their noncausal nature and high latency. This letter introduces a lightweight causal model tailored for real-time hearing aid applications, designed to minimize latency while maintaining acceptable SDR. The model was trained and evaluated on the MUSDB-18 dataset using established protocols. Performance metrics, including SDR and latency, were used to compare it against Demucs. Results show that while Demucs achieves higher SDR, the proposed model significantly reduces latency (9.42 ms compared to 52.25 ms), making it suitable for real-time IoT systems. This research demonstrates the potential of causal architectures in addressing the challenges of real-time audio processing for hearing aids and sets the stage for future improvements in SDR without compromising latency.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}