Pub Date : 2024-10-21DOI: 10.1109/LSENS.2024.3483990
Nibedita Kalita;Samir Kumar Borgohain
Glaucoma, an incurable eye disease, is a significant global health concern recognized by the World Health Organization. It progresses by increasing eye pressure, damaging the optic nerve, and leading to blindness. Regular eye exams are crucial for early detection and preventing vision loss, as early stages are often asymptomatic. Advanced feature engineering and machine learning are key to uncovering new glaucoma biomarkers, aiding early diagnosis and improving automated systems for ophthalmologists. The glaucoma biomarkers in the realm of machine learning are the features that act as a metaphor of biological biomarkers. Most research has concentrated on either structural or nonstructural feature selection strategies, with limited analysis on combined feature sets. In this letter, a new reduced feature set is investigated by combining both handcrafted structural and nonstructural features that act as a novel glaucoma biomarker for efficient and robust glaucoma diagnosis system. The proposed biomarker is a combination of structural and nonstructural (statistical, spectral, and geometric) features, which has been rigorously evaluated on the publicly available, large, and diverse standardized multi-channel dataset (SMDG)-19 glaucoma dataset. The classification accuracy achieved from Extra Tree Classifier is 85.42 % using tenfold cross-validation approach. In light of this, the suggested method's outcome set it apart from other State-of-the-Art models in biomarker determination and makes it a unique choice for ophthalmologists seeking a glaucoma biomarker for diagnosis systems.
{"title":"An Ocular Feature-Based Novel Biomarker Determination for Glaucoma Diagnosis Using Supervised Machine Learning and Fundus Imaging","authors":"Nibedita Kalita;Samir Kumar Borgohain","doi":"10.1109/LSENS.2024.3483990","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3483990","url":null,"abstract":"Glaucoma, an incurable eye disease, is a significant global health concern recognized by the World Health Organization. It progresses by increasing eye pressure, damaging the optic nerve, and leading to blindness. Regular eye exams are crucial for early detection and preventing vision loss, as early stages are often asymptomatic. Advanced feature engineering and machine learning are key to uncovering new glaucoma biomarkers, aiding early diagnosis and improving automated systems for ophthalmologists. The glaucoma biomarkers in the realm of machine learning are the features that act as a metaphor of biological biomarkers. Most research has concentrated on either structural or nonstructural feature selection strategies, with limited analysis on combined feature sets. In this letter, a new reduced feature set is investigated by combining both handcrafted structural and nonstructural features that act as a novel glaucoma biomarker for efficient and robust glaucoma diagnosis system. The proposed biomarker is a combination of structural and nonstructural (statistical, spectral, and geometric) features, which has been rigorously evaluated on the publicly available, large, and diverse standardized multi-channel dataset (SMDG)-19 glaucoma dataset. The classification accuracy achieved from Extra Tree Classifier is 85.42 % using tenfold cross-validation approach. In light of this, the suggested method's outcome set it apart from other State-of-the-Art models in biomarker determination and makes it a unique choice for ophthalmologists seeking a glaucoma biomarker for diagnosis systems.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565506","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}
The selection of the sensor array represents a pivotal aspect of the system design for the electronic nose (E-nose). In practical applications, achieving an optimal balance between array size and system performance is often challenging. Therefore, realizing a high-performance E-nose with a minimum number of sensors is necessary, particularly for portable E-noses with limited size and power. This letter proposes a cost-effectiveness ratio (CER) as an array optimization criterion to address these issues. The CER is defined for quantifying costs and benefits as a basis for array optimization. Applying the designed array optimization criterion to the portable E-nose system, which comprises eight MEMS sensors, achieves an 80% prediction accuracy while reducing the number of sensors by nearly 40%. In addition, the concept of extreme sensor number is proposed to illustrate the existence of limit values for the number of sensors in the process of array optimization. This study offers a foundation for quantitative metrics for sensor array optimization, which serves as a crucial reference for the design of size- and power-sensitive portable E-nose systems.
{"title":"A Quantitative Array Optimization Method for the Electronic Nose System Based on Edge Computing and MEMS Sensors","authors":"Lechen Chen;Tao Wang;Wangze Ni;Jiaqing Zhu;Weiwei Cheng;Haixia Mei;Bowei Zhang;Fuzhen Xuan;Jianhua Yang;Min Zeng;Nantao Hu;Zhi Yang","doi":"10.1109/LSENS.2024.3483576","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3483576","url":null,"abstract":"The selection of the sensor array represents a pivotal aspect of the system design for the electronic nose (E-nose). In practical applications, achieving an optimal balance between array size and system performance is often challenging. Therefore, realizing a high-performance E-nose with a minimum number of sensors is necessary, particularly for portable E-noses with limited size and power. This letter proposes a cost-effectiveness ratio (CER) as an array optimization criterion to address these issues. The CER is defined for quantifying costs and benefits as a basis for array optimization. Applying the designed array optimization criterion to the portable E-nose system, which comprises eight MEMS sensors, achieves an 80% prediction accuracy while reducing the number of sensors by nearly 40%. In addition, the concept of extreme sensor number is proposed to illustrate the existence of limit values for the number of sensors in the process of array optimization. This study offers a foundation for quantitative metrics for sensor array optimization, which serves as a crucial reference for the design of size- and power-sensitive portable E-nose systems.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565499","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}
This letter introduces an efficient linearizing digital interface designed for remote thermistors. The proposed approach utilizes an enhanced relaxation-oscillator topology to render a direct-digital output that is directly proportional to the sensed temperature. Furthermore, the system compensates for cable resistance and maintains constant-current excitation for the sensor. The digitizer design is both simple and innovative, avoiding the need for matched references and minimizing the impact of various circuit nonidealities. The working principle of the interfacing system is established in this letter, followed by simulation studies. A thorough hardware evaluation of the developed digitizer reveals promising results, including low nonlinearity (0.41%), a high signal-to-noise ratio ( $>$ 67 dB), and a measurement span of 120 $^{circ }$ C, all while remaining unaffected by cable resistance. This system is well-suited for aerospace applications and other scenarios, requiring accurate thermistor-based temperature measurements.
{"title":"Efficient Electronic Digitizer for Linearizing Remotely Located Thermistors","authors":"Sajeev Ramachandran;Anoop Chandrika Sreekantan;Roy Thankachan","doi":"10.1109/LSENS.2024.3482367","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3482367","url":null,"abstract":"This letter introduces an efficient linearizing digital interface designed for remote thermistors. The proposed approach utilizes an enhanced relaxation-oscillator topology to render a direct-digital output that is directly proportional to the sensed temperature. Furthermore, the system compensates for cable resistance and maintains constant-current excitation for the sensor. The digitizer design is both simple and innovative, avoiding the need for matched references and minimizing the impact of various circuit nonidealities. The working principle of the interfacing system is established in this letter, followed by simulation studies. A thorough hardware evaluation of the developed digitizer reveals promising results, including low nonlinearity (0.41%), a high signal-to-noise ratio (\u0000<inline-formula><tex-math>$>$</tex-math></inline-formula>\u000067 dB), and a measurement span of 120 \u0000<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>\u0000C, all while remaining unaffected by cable resistance. This system is well-suited for aerospace applications and other scenarios, requiring accurate thermistor-based temperature measurements.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565556","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}
Pub Date : 2024-10-17DOI: 10.1109/LSENS.2024.3482990
Debabrata Paul;Sunil K. Khijwania
Etched fiber Bragg grating (FBG)-based temperature-insensitive, simple, all-optical tilt sensor design, employing effective refractive index (RI) induced intensity modulation (instead of traditional strain modulation), is proposed and theoretically demonstrated. The etched FBG splits into two distinct gratings when partially immersed in a liquid. Applied tilt modulates the length of etched FBG immersed into a liquid, which, in turn, modulates the characteristic reflection spectrum of both the sections (exposed to liquid and to the air). The theoretical maximum sensitivity of the proposed sensor comes out to be 1.20 dB/°. Further, the sensor exhibits the ability to quantify both the magnitude and direction of inclination relative to the horizontal plane across the designated dynamic range of ±10°.
{"title":"Etched Fiber Bragg Grating-Based Novel Tilt Sensor Employing Effective Refractive Index Induced Intensity Modulation Mechanism","authors":"Debabrata Paul;Sunil K. Khijwania","doi":"10.1109/LSENS.2024.3482990","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3482990","url":null,"abstract":"Etched fiber Bragg grating (FBG)-based temperature-insensitive, simple, all-optical tilt sensor design, employing effective refractive index (RI) induced intensity modulation (instead of traditional strain modulation), is proposed and theoretically demonstrated. The etched FBG splits into two distinct gratings when partially immersed in a liquid. Applied tilt modulates the length of etched FBG immersed into a liquid, which, in turn, modulates the characteristic reflection spectrum of both the sections (exposed to liquid and to the air). The theoretical maximum sensitivity of the proposed sensor comes out to be 1.20 dB/°. Further, the sensor exhibits the ability to quantify both the magnitude and direction of inclination relative to the horizontal plane across the designated dynamic range of ±10°.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565507","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}
The proliferation of voice-activated devices, such as virtual assistants and voice-controlled systems, has changed how people interact with technology and the environment. These devices collect data that can be sent to servers to process sound, returning responses or suggestions to the user. However, the widespread use of these devices has led to intensive data collection, exposing sensitive information, such as conversations and intimate audio. In this context, we developed PRISM-guardian, a technique for sharing and tracking sound data without revealing its origin, thus preserving privacy. Transparently, audio generators, such as residential users, can track who accessed their information and why. We collected 1000 audio samples, each lasting 10 s, to recognize short-duration cough and sneeze sounds. We achieved average sound recognition processing times of 3.78 s, 6.78 ms to encapsulate the data in the API, and an average of 48 ms to save the data on the blockchain. Besides, we present a mathematical formalization of PRISM and conduct tests to identify the origin of the sound. The results showed that the identity of the sound source is preserved while this source can view and track the data.
{"title":"PRISM-Guardian: Enhancing Data Privacy in Devices With Sound Collection, Recognition, and Sharing Through Blockchain Technology","authors":"Edilson Filho;Matheus Ferreira;Gabriel Palitot;César Marcon;Laurent Vercouter;Jarbas Silveira","doi":"10.1109/LSENS.2024.3482177","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3482177","url":null,"abstract":"The proliferation of voice-activated devices, such as virtual assistants and voice-controlled systems, has changed how people interact with technology and the environment. These devices collect data that can be sent to servers to process sound, returning responses or suggestions to the user. However, the widespread use of these devices has led to intensive data collection, exposing sensitive information, such as conversations and intimate audio. In this context, we developed PRISM-guardian, a technique for sharing and tracking sound data without revealing its origin, thus preserving privacy. Transparently, audio generators, such as residential users, can track who accessed their information and why. We collected 1000 audio samples, each lasting 10 s, to recognize short-duration cough and sneeze sounds. We achieved average sound recognition processing times of 3.78 s, 6.78 ms to encapsulate the data in the API, and an average of 48 ms to save the data on the blockchain. Besides, we present a mathematical formalization of PRISM and conduct tests to identify the origin of the sound. The results showed that the identity of the sound source is preserved while this source can view and track the data.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142540373","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}
Pub Date : 2024-10-16DOI: 10.1109/LSENS.2024.3482120
Pedro D. R. Araujo;Rita Macedo;Marta Pereira;Tiago P. Fernandes;Susana Cardoso
Tunneling magnetoresistive (TMR) sensors with enhanced thermal resilience are being pursued for harsh environment applications. In this letter, we explore MnNi as a possible candidate for exchange bias in TMR sensor multilayers. We use ion beam assisted deposition for MnNi layer growth. A significant emergence of exchange bias field of $mu _{0}H_{text{ex}} =$ 110 mT was obtained in MnNi/CoFe bilayers against the ion beam deposited counterpart. In addition, we demonstrate for the first time in literature the compatibility with state-of-the-art sensor multilayers comprising synthetic antiferromagnets and MgO tunnel barriers. The optimized device shows a tunneling magnetoresistance ratio of 130 $%$ at RT and a 30 $%$ at 300 $^circ$ C corresponding to sensitivities of 17.0 and 9.5 $%$ /mT with well-defined parallel/antiparallel plateaus in the full-temperature operation window.
{"title":"Combining High Thermal Stability of MnNi Antiferromagnets With High-Performance MgO-TMR Sensors Through Texture Engineering With Ion Beam Assisted Deposition","authors":"Pedro D. R. Araujo;Rita Macedo;Marta Pereira;Tiago P. Fernandes;Susana Cardoso","doi":"10.1109/LSENS.2024.3482120","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3482120","url":null,"abstract":"Tunneling magnetoresistive (TMR) sensors with enhanced thermal resilience are being pursued for harsh environment applications. In this letter, we explore MnNi as a possible candidate for exchange bias in TMR sensor multilayers. We use ion beam assisted deposition for MnNi layer growth. A significant emergence of exchange bias field of \u0000<inline-formula><tex-math>$mu _{0}H_{text{ex}} =$</tex-math></inline-formula>\u0000 110 mT was obtained in MnNi/CoFe bilayers against the ion beam deposited counterpart. In addition, we demonstrate for the first time in literature the compatibility with state-of-the-art sensor multilayers comprising synthetic antiferromagnets and MgO tunnel barriers. The optimized device shows a tunneling magnetoresistance ratio of 130\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 at RT and a 30\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 at 300 \u0000<inline-formula><tex-math>$^circ$</tex-math></inline-formula>\u0000C corresponding to sensitivities of 17.0 and 9.5\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000/mT with well-defined parallel/antiparallel plateaus in the full-temperature operation window.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142540445","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}
Pub Date : 2024-10-15DOI: 10.1109/LSENS.2024.3481308
Bidesh Mahata;Pallab Banerji;Prasanta Kumar Guha
Fish freshness monitoring is now paramount for maintaining a healthy lifestyle. This letter represents the development of a marigold flower-like NiO nanostructure-based chemiresistor that can sense ppb-level ammonia for monitoring freshwater fish freshness. A simple low-temperature hydrothermal method was utilized to synthesize the sensing material. Using X-ray diffraction and a field emission scanning electron microscope, the synthesized material was examined in terms of structure and morphology. The sensor was fabricated using the drop casting method over gold interdigitated electrodes on alumina substrate. According to the gas sensing study, the sensor was more responsive to ammonia at 250 °C. The sensor device gained a response of 10% in the presence of 1 parts per million (ppm) ammonia. The response and recovery times were about 150 and 180 s, respectively, for 1 ppm ammonia. The experimental limit of detection of the sensor was 100 ppb. The proposed sensor is suitable for monitoring freshwater fish freshness.
鱼类新鲜度监测对于保持健康的生活方式至关重要。这封信介绍了一种基于万寿菊花状氧化镍纳米结构的化学电阻器的开发情况，该电阻器可感应ppb级氨气，用于监测淡水鱼的新鲜度。该传感材料的合成采用了一种简单的低温水热法。利用 X 射线衍射和场发射扫描电子显微镜对合成材料的结构和形态进行了检测。传感器是在氧化铝基底上的金穿插电极上用滴铸法制造的。根据气体传感研究，该传感器在 250 °C 时对氨气的反应更灵敏。在百万分之 1（ppm）的氨气存在下，传感器装置的响应为 10%。对于百万分之 1 的氨气，响应时间和恢复时间分别约为 150 秒和 180 秒。传感器的实验检测限为 100 ppb。拟议的传感器适用于监测淡水鱼的新鲜度。
{"title":"Ppb-Level Ammonia Sensing of Marigold Flower-Like NiO Nanostructure for Freshwater Fish Freshness","authors":"Bidesh Mahata;Pallab Banerji;Prasanta Kumar Guha","doi":"10.1109/LSENS.2024.3481308","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3481308","url":null,"abstract":"Fish freshness monitoring is now paramount for maintaining a healthy lifestyle. This letter represents the development of a marigold flower-like NiO nanostructure-based chemiresistor that can sense ppb-level ammonia for monitoring freshwater fish freshness. A simple low-temperature hydrothermal method was utilized to synthesize the sensing material. Using X-ray diffraction and a field emission scanning electron microscope, the synthesized material was examined in terms of structure and morphology. The sensor was fabricated using the drop casting method over gold interdigitated electrodes on alumina substrate. According to the gas sensing study, the sensor was more responsive to ammonia at 250 °C. The sensor device gained a response of 10% in the presence of 1 parts per million (ppm) ammonia. The response and recovery times were about 150 and 180 s, respectively, for 1 ppm ammonia. The experimental limit of detection of the sensor was 100 ppb. The proposed sensor is suitable for monitoring freshwater fish freshness.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565542","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}
Human activity recognition (HAR) has become a popular stream in computing and wearable technologies, opening doors to multiple applications including healthcare and sports analysis. The primary challenge in HAR is developing models that generalize effectively across multiple domains due to variations in sensor qualities and individual differences. In addition, labeling the voluminous sensed data is a major challenge for classifying the activities. Therefore, domain adaptation approaches are being extensively investigated to help address these issues, transferring knowledge from a labeled source domain to a target domain. In this letter, a novel Kolmogorov–Arnold representation-based generative adversarial network (GAN), abbreviated as KGAN is designed for recognizing activities in a semi-supervised domain-adapted environment with enhanced robustness. The proposed KGAN-based HAR framework creates synthetic data for solving the scarcity of labeled data in the target domain and enables better handling of multidimensional data through structured function approximation. In addition, the combined use of kernel mean matching (KMM) and maximum mean and covariance discrepancy (MMCD) methods boosts the domain adapted framework by negating the weaknesses of each other. HAR experiments carried out on two publicly available datasets, namely, UCI-HAR and HHAR, exhibit enhanced performance of the proposed KGAN-based framework in target domain over few state-of-the-art models. The proposed framework significantly improves the overall accuracy of HAR across various domains by utilizing the strengths of GAN, KMM, and MMCD.
人类活动识别（HAR）已成为计算和可穿戴技术领域的一个流行趋势，为包括医疗保健和运动分析在内的多种应用打开了大门。由于传感器质量和个体差异的不同，人类活动识别的主要挑战是开发能在多个领域有效通用的模型。此外，对大量传感数据进行标注也是对活动进行分类的一大挑战。因此，人们正在广泛研究领域适应方法，以帮助解决这些问题，将知识从标记源领域转移到目标领域。在这封信中，我们设计了一种新颖的基于柯尔莫哥洛夫-阿诺德表示的生成对抗网络（GAN），简称 KGAN，用于在半监督的领域适应环境中识别活动，并增强鲁棒性。所提出的基于 KGAN 的 HAR 框架可创建合成数据，以解决目标领域中标记数据稀缺的问题，并通过结构化函数近似更好地处理多维数据。此外，核均值匹配（KMM）和最大均值与协方差（MMCD）方法的结合使用，通过相互抵消对方的弱点，增强了领域适应框架。在两个公开数据集（即 UCI-HAR 和 HHAR）上进行的 HAR 实验表明，与少数最先进的模型相比，基于 KGAN 的拟议框架在目标领域的性能有所提高。通过利用 GAN、KMM 和 MMCD 的优势，所提出的框架大大提高了 HAR 在不同领域的整体准确性。
{"title":"KGAN-Based Semisupervised Domain Adapted Human Activity Recognition","authors":"Pritam Khan;Soham Chaudhuri;Dhruv Santosh Singh;Faisal Amaan","doi":"10.1109/LSENS.2024.3481149","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3481149","url":null,"abstract":"Human activity recognition (HAR) has become a popular stream in computing and wearable technologies, opening doors to multiple applications including healthcare and sports analysis. The primary challenge in HAR is developing models that generalize effectively across multiple domains due to variations in sensor qualities and individual differences. In addition, labeling the voluminous sensed data is a major challenge for classifying the activities. Therefore, domain adaptation approaches are being extensively investigated to help address these issues, transferring knowledge from a labeled source domain to a target domain. In this letter, a novel Kolmogorov–Arnold representation-based generative adversarial network (GAN), abbreviated as KGAN is designed for recognizing activities in a semi-supervised domain-adapted environment with enhanced robustness. The proposed KGAN-based HAR framework creates synthetic data for solving the scarcity of labeled data in the target domain and enables better handling of multidimensional data through structured function approximation. In addition, the combined use of kernel mean matching (KMM) and maximum mean and covariance discrepancy (MMCD) methods boosts the domain adapted framework by negating the weaknesses of each other. HAR experiments carried out on two publicly available datasets, namely, UCI-HAR and HHAR, exhibit enhanced performance of the proposed KGAN-based framework in target domain over few state-of-the-art models. The proposed framework significantly improves the overall accuracy of HAR across various domains by utilizing the strengths of GAN, KMM, and MMCD.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555143","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}
The development of a conformal frequency selective surface (FSS) loaded on a conformal cylindrical dielectric resonator antenna (CDRA) for the improvement of radiation characteristics for C band applications is presented in this letter. Sinusoidal slot aperture feeding is used for the excitation of the proposed structure. Perturbation on the CDRA is used to improve the impedance bandwidth of an antenna. For obtaining the circular polarization, CDRA is loaded with a conformal FSS at a distance of (2n ± 1) λ/4. To minimize radiation exposure to nearby human bodies, specific absorption rate (SAR) value is calculated, which is less than the 1.6 W/Kg, and the SAR value decreases as the distance between DRA and human head increases. The proposed structure is fabricated, and the measured results are in close agreement with simulated results.
本信介绍了在共形圆柱介质谐振器天线（CDRA）上加载共形频率选择表面（FSS）的开发情况，以改善 C 波段应用的辐射特性。正弦槽孔馈电用于激励所提议的结构。CDRA 上的扰动用于改善天线的阻抗带宽。为了获得圆极化，CDRA 在 (2n ± 1) λ/4 的距离上装载了共形 FSS。为了尽量减少对附近人体的辐射，计算出的比吸收率（SAR）值小于 1.6 W/Kg，且 SAR 值随着 DRA 与人体头部距离的增加而降低。对所提出的结构进行了制作，测量结果与模拟结果非常吻合。
{"title":"CDRA on Concave Conformal GP Loaded With Conformal FSS for Biomedical Applications","authors":"Manshree Mishra;Garima Tiwari;Pramod Kumar Gupta;Atul Kumar;Biswajeet Mukherjee","doi":"10.1109/LSENS.2024.3481258","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3481258","url":null,"abstract":"The development of a conformal frequency selective surface (FSS) loaded on a conformal cylindrical dielectric resonator antenna (CDRA) for the improvement of radiation characteristics for \u0000<italic>C</i>\u0000 band applications is presented in this letter. Sinusoidal slot aperture feeding is used for the excitation of the proposed structure. Perturbation on the CDRA is used to improve the impedance bandwidth of an antenna. For obtaining the circular polarization, CDRA is loaded with a conformal FSS at a distance of (2n ± 1) λ/4. To minimize radiation exposure to nearby human bodies, specific absorption rate (SAR) value is calculated, which is less than the 1.6 W/Kg, and the SAR value decreases as the distance between DRA and human head increases. The proposed structure is fabricated, and the measured results are in close agreement with simulated results.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587606","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}
Pub Date : 2024-10-15DOI: 10.1109/LSENS.2024.3480970
Rahul Gond;Prajjwal Shukla;Brajesh Rawat
Continuous and real-time monitoring of carbon dioxide (CO $_{2}$ ) has become an urgent demand due to its significant impact on climate change, asphyxiation risks, agricultural productivity, and human health. Electrochemical sensors for CO $_{2}$ monitoring face challenges, such as slow response time, high operating temperature, and lack of selectivity. To overcome these challenges, we propose a highly selective room-temperature (RT) CO $_{2}$ detection sensor based on TiO $_{2}$ -MoS $_{2}$ nanocomposite (NC), which is manufactured using a screen printing methodology. The fabricated sensor achieved a response of approximately 2.11% and response/recovery times of nearly 102/37s at 1000 ppm. The sensitivity is observed to be approximately 0.0032%/ppm with an excellent response for the CO $_{2}$ concentration range of 500–5000 ppm. Despite the typically low selectivity of unreactive CO $_{2}$ gas, the fabricated sensor exhibits high selectivity, with a response of around 2.21× higher than that of the CO gas with the next highest response. The scalable fabrication methodology and RT operation make TiO $_{2}$ -MoS $_{2}$ sensor a highly viable candidate for production through a cost-effective and high performance CO $_{2}$ sensing.
{"title":"TiO$_{2}$-Decorated MoS$_{2}$ Nanocomposite for CO$_{2}$ Sensing At Room Temperature","authors":"Rahul Gond;Prajjwal Shukla;Brajesh Rawat","doi":"10.1109/LSENS.2024.3480970","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3480970","url":null,"abstract":"Continuous and real-time monitoring of carbon dioxide (CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000) has become an urgent demand due to its significant impact on climate change, asphyxiation risks, agricultural productivity, and human health. Electrochemical sensors for CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 monitoring face challenges, such as slow response time, high operating temperature, and lack of selectivity. To overcome these challenges, we propose a highly selective room-temperature (RT) CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 detection sensor based on TiO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000-MoS\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 nanocomposite (NC), which is manufactured using a screen printing methodology. The fabricated sensor achieved a response of approximately 2.11% and response/recovery times of nearly 102/37s at 1000 ppm. The sensitivity is observed to be approximately 0.0032%/ppm with an excellent response for the CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 concentration range of 500–5000 ppm. Despite the typically low selectivity of unreactive CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 gas, the fabricated sensor exhibits high selectivity, with a response of around 2.21× higher than that of the CO gas with the next highest response. The scalable fabrication methodology and RT operation make TiO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000-MoS\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 sensor a highly viable candidate for production through a cost-effective and high performance CO\u0000<inline-formula><tex-math>$_{2}$</tex-math></inline-formula>\u0000 sensing.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"8 11","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579205","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：