IEEE Sensors Letters最新文献_第4页

How Many Sensors are Necessary?—Sensor Reduction in HVAC Control Modeling Using Feature Attribution and Rule Extraction 需要多少个传感器？-基于特征属性和规则提取的暖通空调控制建模中的传感器缩减

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-26 DOI: 10.1109/LSENS.2025.3602850

Alexander Stieger;Christian Stippel;Aleksey Bratukhin;Ralph Hoch;Thilo Sauter

{"title":"How Many Sensors are Necessary?—Sensor Reduction in HVAC Control Modeling Using Feature Attribution and Rule Extraction","authors":"Alexander Stieger;Christian Stippel;Aleksey Bratukhin;Ralph Hoch;Thilo Sauter","doi":"10.1109/LSENS.2025.3602850","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3602850","url":null,"abstract":"Reinforcement learning (RL) has become a popular approach for process control design, especially for systems that are complex and not fully understood. The opaquenature of neural networks makes it tempting to use a variety of sensor data as input variables. In case of doubt, additional sensors are often introduced under the assumption that more sensors will also increase the accuracy of the model and, therefore, the control performance. However, this is not necessarily true, and the lack of interpretabilitycomplicates the identification of which sensors influence decision-making and are thus essential for the control function, and which are less important. Gaining insight into the significance of particular sensors allows for dimensionality reduction by fully removing less relevant sensors without compromising the system's performance. Investigating the example of heating, ventilation, and air conditioning (HVAC) systems, we suggest two approaches: rule extraction and feature attribution to identify key sensor inputs that are most relevant for optimizing control performance. In addition, when using rule extraction, we translate RL models into rule-based systems compatible with existing HVAC setups. This approach adds explainability and, in the given example, was able to reduce the required number of sensors by more than 70%.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 10","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11141763","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021256","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}

引用次数: 0

Quadratic-Baseline Partitioning of Indoor PM$_{2.5}$ Using a Low-Cost Optical Sensor During a Facade Retrofit Case Study 在立面改造过程中使用低成本光学传感器对室内PM$_{2.5}$进行二次基线划分

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-26 DOI: 10.1109/LSENS.2025.3603121

Rostyslav Sipakov;Olena Voloshkina

{"title":"Quadratic-Baseline Partitioning of Indoor PM$_{2.5}$ Using a Low-Cost Optical Sensor During a Facade Retrofit Case Study","authors":"Rostyslav Sipakov;Olena Voloshkina","doi":"10.1109/LSENS.2025.3603121","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3603121","url":null,"abstract":"A quadratic-baseline algorithm was developed to partition indoor particulate matter (PM<inline-formula><tex-math>$_{2.5}$</tex-math></inline-formula>) sources using data from a single low-cost sensor without outdoor reference. A Temtop LKC–1000S+ (2nd generation) optical particle counter (<inline-formula><tex-math>$R^{2} > 0.90$</tex-math></inline-formula> versus <italic>Federal Equivalent Method (FEM) (U.S. EPA designation) GRIMM Aerosol Technik) was deployed for 48 days during a facade retrofit. The algorithm reproduced background periods with a mean absolute error of 2.3 µg m<inline-formula><tex-math>$^{-3}$</tex-math></inline-formula> and resolved daily PM<inline-formula><tex-math>$_{2.5}$</tex-math></inline-formula> dose shares for facade work, cooking, and passive accumulation (31%, 24%, and 45%). During the plastic barrier stage, the PM<inline-formula><tex-math>$_{2.5}$</tex-math></inline-formula> baseline doubled, highlighting the tradeoff between dust shielding and background elevation. This framework enables affordable, real-time indoor air quality diagnostics in occupied retrofits. Robust baseline fitting made it possible to account for sensor limitations at low concentrations. However, the generalizability of the findings is limited by the study design (single subject, only internal measurements), which necessitates further validation with external monitoring.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 10","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036721","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}

引用次数: 0

Experimental Study on the Thermal Response of Electric Submersible Pump Motors to Load Variation Using Raman Distributed Temperature Sensing 基于拉曼分布温度传感的潜水泵电机对负载变化的热响应实验研究

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-25 DOI: 10.1109/LSENS.2025.3602583

Gabriel de A. Torelli;Jhoan M. C. Cubas;Jessé de Pelegrin;Rafael Piazentin;Gabriel A. Romero;Francisco R. R. Bacellar;Luiz C. T. da Silva;Jurandir A. G. da Silva;Henrique Stel;Uilian J. Dreyer;Rigoberto E. M. Morales;Jean Carlos Cardozo da Silva

{"title":"Experimental Study on the Thermal Response of Electric Submersible Pump Motors to Load Variation Using Raman Distributed Temperature Sensing","authors":"Gabriel de A. Torelli;Jhoan M. C. Cubas;Jessé de Pelegrin;Rafael Piazentin;Gabriel A. Romero;Francisco R. R. Bacellar;Luiz C. T. da Silva;Jurandir A. G. da Silva;Henrique Stel;Uilian J. Dreyer;Rigoberto E. M. Morales;Jean Carlos Cardozo da Silva","doi":"10.1109/LSENS.2025.3602583","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3602583","url":null,"abstract":"This letter proposes a fiber-optic-based method for monitoring the temperature of stator windings and housing regions in electric submersible pump (ESP) motors using Raman distributed temperature sensing (RDTS). The experimental setup replicates conditions of downhole installations or subsea skids by enclosing the ESP within an unplasticized polyvinyl chloride pipe, with annular flow established between the motor housing and the inner wall of the pipe. Flow rate and electric parameters are continuously monitored to evaluate their relationship with motor temperature. The results indicate that RDTS can be an intrinsically safe solution for temperature monitoring in ESP-lifted wells for oil and gas production, where conventional electric-based sensors are often unsuitable due to limited installation space, harsh environment, high electromagnetic interference, and long distance between the ESP motor and platform.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 10","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021255","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}

引用次数: 0

Multigas Differentiation With Individual Electrochemical Gas Sensors 多气体区分与单独的电化学气体传感器

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-25 DOI: 10.1109/LSENS.2025.3602710

Radislav A. Potyrailo;Baokai Cheng;Shiyao Shan;Janell Crowder

{"title":"Multigas Differentiation With Individual Electrochemical Gas Sensors","authors":"Radislav A. Potyrailo;Baokai Cheng;Shiyao Shan;Janell Crowder","doi":"10.1109/LSENS.2025.3602710","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3602710","url":null,"abstract":"Existing gas sensors are low cost and operate at low power. However, their high gas cross sensitivity reduces their acceptance for reliable monitoring of ambient environmental pollutants, indoor air quality, breath biomarkers, and many other applications. Thus, at present, traditional analytical instruments are used for accurate gas detection and multigas differentiation. These popular instruments unfortunately require periodic maintenance and demand a lot of electrical power even in their fieldable formats. A competing technology is individual multiresponse (a.k.a. multivariable) sensors to meet contemporary gas monitoring needs. In this letter, we present results on two methodologies to achieve multigas differentiation with individual amperometric electrochemical sensors. In one methodology, a sensor was operated at two modulated bias levels. In the second methodology, a sensor was operated with impedance and direct current readouts at one or two bias levels. For multigas differentiation, a standard unsupervised multivariate data analysis was sufficient. This direction in multigas detection with individual multiresponse (multivariable) sensors will compete with traditional instruments and will improve the “3S” sensor system characteristics—sensitivity, selectivity, and stability, facilitating green analytical chemistry implementations and leading to positive societal impact.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 9","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145005477","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}

引用次数: 0

Estimating Movement Direction From Body Orientation Using Dual Ultra-Wideband Sensors 利用双超宽带传感器从身体方向估计运动方向

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-25 DOI: 10.1109/LSENS.2025.3602011

Amir Shahbazi Ojghaz;Sayeh Bayat;Farnaz Sadeghpour

{"title":"Estimating Movement Direction From Body Orientation Using Dual Ultra-Wideband Sensors","authors":"Amir Shahbazi Ojghaz;Sayeh Bayat;Farnaz Sadeghpour","doi":"10.1109/LSENS.2025.3602011","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3602011","url":null,"abstract":"Accurate short-term prediction of human movement is vital for safety-critical and context-aware applications in dynamic environments. While conventional trajectory prediction methods depend on historical motion data, they often fall short in anticipating sudden directional changes. This study investigates whether body orientation, estimated using a dual ultra-wideband (UWB) sensor configuration, can serve as a reliable predictor of near-future movement direction. A wearable device with two shoulder-mounted UWB tags was used to collect position and orientation data during controlled walking experiments. Eight participants walked freely within a controlled lab environment while data were recorded. Circular cross-correlation was applied to analyze the temporal relationship between body orientation and subsequent movement direction. Results revealed a strong and statistically significant correlation across all participants (mean correlation = 0.7688, p < 0.001), with an average optimal lead time of 200 ms. The relationship remained robust using a standardized 200 ms lag (mean correlation = 0.7453). These findings demonstrate that UWB-derived body orientation can effectively predict short-term movement direction, supporting the use of UWB sensing not only for localization but also as a foundation for predictive on-body systems that enhance real-time safety and mobility monitoring.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 10","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061946","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}

引用次数: 0

Speckle Noise Reduction in FMCW LiDAR Using Intensity-Weighted Signal Acquisition With a Quadrant Photodiode Receiver 基于四象限光电二极管接收机强度加权信号采集的FMCW激光雷达散斑噪声抑制

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-21 DOI: 10.1109/LSENS.2025.3601566

Jubong Lee;Kyungwon Kim;Kyihwan Park

引用次数: 0

A New Approach for Real-Time Center-of-Pressure Correction in Pressure Sensitive Mats Using Feedforward Neural Networks 基于前馈神经网络的压敏垫压力中心实时校正新方法

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-20 DOI: 10.1109/LSENS.2025.3601010

Sergio Domínguez Gimeno;Raul Igual Catalán;Carlos Medrano Sánchez;Inmaculada Plaza García;Javier Martínez Cesteros;Marco Pasetti

引用次数: 0

Implicit Graph-Based Cardiovascular Disease Detection Using Cardiac Axis Deviation in Reduced-Lead ECG 基于隐式图的心轴偏差降导心电图心血管疾病检测

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-20 DOI: 10.1109/LSENS.2025.3600990

Akriti Jaiswal;Samarendra Dandapat;Prabin Kumar Bora

{"title":"Implicit Graph-Based Cardiovascular Disease Detection Using Cardiac Axis Deviation in Reduced-Lead ECG","authors":"Akriti Jaiswal;Samarendra Dandapat;Prabin Kumar Bora","doi":"10.1109/LSENS.2025.3600990","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3600990","url":null,"abstract":"Accurate and effective cardiovascular disease (CVD) diagnosis is particularly difficult in telemedicine and resource-constrained environments due to traditional multilead electrocardiogram (ECG) devices' high computational and operational expenses. We propose a computationally effective graph-based approach to the automated detection of CVD from reduced-lead {I, II} ECG. The approach formulates lead relationships as a dynamic graph <inline-formula><tex-math>$G=(V, E)$</tex-math></inline-formula> whose nodes <inline-formula><tex-math>$V=lbrace text{I}, text{II}rbrace$</tex-math></inline-formula> correspond to leads and whose edge weights <inline-formula><tex-math>$w_{ij}(t) in E$</tex-math></inline-formula> capture time-varying cardiac axis deviation angles <inline-formula><tex-math>$theta (t)$</tex-math></inline-formula> in the frontal plane. Three statistical features are obtained: mean angle <inline-formula><tex-math>$mu _theta$</tex-math></inline-formula>, angular variance <inline-formula><tex-math>$sigma _theta ^{2}$</tex-math></inline-formula>, and lead correlation coefficient <inline-formula><tex-math>$rho _{text{I, II}}$</tex-math></inline-formula>. Experimental testing on PTB-XL and PTB datasets establishes state-of-the-art performance at 89.2% and 84.1% accuracy, respectively, without redundant computations native to multilead ECG. The approach ensures clinical-grade accuracy with <inline-formula><tex-math>$O(1)$</tex-math></inline-formula> feature extraction complexity, providing an optimal tradeoff between accuracy and computational efficiency for resource-constrained wearable ECG sensors and tele-ECG applications.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 9","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144934562","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}

引用次数: 0

RAFT: Regularized Adversarial Fine-Tuning to Enhance Deep Reinforcement Learning for Self-Parking RAFT：正则化对抗性微调以增强自动停车的深度强化学习

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-20 DOI: 10.1109/LSENS.2025.3600982

Alessandro Pighetti;Francesco Bellotti;Riccardo Berta;Andrea Cavallaro;Luca Lazzaroni;Changjae Oh

引用次数: 0

Highly Sensitive Capacitive Tilt Sensor Using Liquid Metal Movable Electrode 采用液态金属可移动电极的高灵敏度电容式倾斜传感器

IF 2.2

IEEE Sensors Letters Pub Date : 2025-08-19 DOI: 10.1109/LSENS.2025.3600167

Jinwon Jeong;Muhammad Luqman Haider;Tanzila Noushin;Yun Ting Hsia;Jeong Bong Lee

{"title":"Highly Sensitive Capacitive Tilt Sensor Using Liquid Metal Movable Electrode","authors":"Jinwon Jeong;Muhammad Luqman Haider;Tanzila Noushin;Yun Ting Hsia;Jeong Bong Lee","doi":"10.1109/LSENS.2025.3600167","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3600167","url":null,"abstract":"Capacitive liquid-based tilt sensors offer advantages, such as environmental stability, mechanical robustness, and linear output characteristics. However, achieving high sensitivity remains challenging due to the low permittivity of dielectric liquids and the inevitable air gaps between the electrodes. We report on a new design using a liquid metal movable electrode to improve the sensitivity of capacitive tilt sensors. The tilt sensor was fabricated using Galinstan liquid metal as a movable electrode, a Cr/Au (20/200 nm) fixed electrode, and a CF4/O2 plasma-etched polyimide as a fixed dielectric layer. To make the liquid metal electrode movable, optimization of the CF4/O2 plasma was performed to achieve a nonwetting surface against the liquid metal. To assess the durability of the CF4/O2 plasma-etched polyimide, repeated tilting of the sensor over 100 cycles between −45° and 45° was performed, and there was no sign of the liquid metal wetting on the plasma-etched polyimide. By using a liquid metal movable electrode, the proposed tilt sensor showed a high sensitivity of 3.67 pF/°, i.e., several orders of magnitude higher than the previous works.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 9","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990110","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}

引用次数: 0