Measurement Sensors最新文献

{"title":"State-of-the-art review on fall prediction among older Adults: Exploring edge devices as a promising approach for the future","authors":"Md Maruf,&nbsp;Md Mahbubul Haque,&nbsp;Md Mehedi Hasan,&nbsp;Muqit Farhan,&nbsp;Ariful Islam","doi":"10.1016/j.measen.2025.101878","DOIUrl":"10.1016/j.measen.2025.101878","url":null,"abstract":"<div><div>Falling is one of the most serious threats to the health and well-being of older people, resulting in their daily activities and standard of living. In addition, the cost of treating fall-related injuries is substantial, and some patients face incomplete recovery. Current fall prediction methods focus mainly on biological factors such as locomotion, vision, and cognition, often overlooking the multifaceted nature of falls. This paper comprehensively reviewed state-of-the-art fall prediction systems and listed different factors directly associated with falls. We analyzed the current trends and extracted that machine learning, deep learning, sensors, and gait-based fall prediction methods are some of the most prevalent technologies. This paper also identifies the challenges of current fall prediction and prevention systems. It visualizes a road map for future systems that can be integrated into daily life and greatly improve telehealth monitoring and assessment. TinyML-based intelligent wearable technologies have significant potential to predict complex physiological phenomena such as falls. This study highlights the importance of leveraging TinyML-powered smart wearables to aid fall prevention in the geriatric population. By advancing the understanding of existing systems, this research aims to enhance the quality of life for older adults and guide future innovations in the field.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101878"},"PeriodicalIF":0.0,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143858725","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":"Enhancing acute leukemia classification through hybrid fuzzy C means and random forest methods","authors":"K. Lakshmi Narayanan ,&nbsp;R. Santhana Krishnan ,&nbsp;Y. Harold Robinson ,&nbsp;S. Vimal ,&nbsp;Tarik A. Rashid ,&nbsp;Chetna Kausha ,&nbsp;Md. Mehedi Hassan","doi":"10.1016/j.measen.2025.101876","DOIUrl":"10.1016/j.measen.2025.101876","url":null,"abstract":"<div><div>Leukemia is a category of cancer that is normally found in blood and bone marrow, and which causes rapid abnormal development in the making of white blood cells than the required amount. The produced white blood cells could be ineffective to fight against harmful infections and can even prejudice or restrict the capability of the bone marrow to generate red blood cells and blood platelets. If this is not diagnosed in the earlier stage, it may start to affect the function of the internal organs and cause death. Normally, entire blood counts image analysis and diagnosis are done manually which is an inaccurate and time-intensive process. In this proposed method the classification is tested with two Machine Learning algorithms which are Hybrid Fuzzy C Means (FCM) and Random Forest algorithm (RF) and Support Vector Machine for the detection and classification of Acute Leukemia disease and their performance was evaluated. The dataset comprised of 8637 images which included infected images, normal images and augmented images from different dataset providers and RGB to CMYK conversion with histogram equalization is applied for pre-processing, K means for Image Segmentation. Experimental results convey that Hybrid FCM and RF Algorithm attained an accuracy of 99.06 %, a sensitivity of 99.4 %, and a specificity of 97.8 % respectively, and the ROC (Receiver Operating Characteristic) curve shows that the result produced by the Hybrid FCM &amp; RF based Classifier is best suitable in diagnosing the classification of the Acute Leukemia disease. The tool used for developing the proposed method was Matlab R2018 software.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101876"},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799514","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}

{"title":"Quantitation of total soil carbon (TSC) using an electrochemical impedance probe","authors":"Anirban Paul ,&nbsp;Mohammed A. Eldeeb ,&nbsp;Vikram N. Dhamu ,&nbsp;Aniruddh Sharma ,&nbsp;Shabbir Mufazzal Bohri ,&nbsp;Sriram Muthukumar ,&nbsp;Shalini Prasad","doi":"10.1016/j.measen.2025.101875","DOIUrl":"10.1016/j.measen.2025.101875","url":null,"abstract":"<div><div>Soil is an essential element of Earth's ecosystem that helps regulate the nitrogen and carbon cycles while providing an adequate environment to promote plant growth. Soil carbon is one of the key elements present in soil which provides valuable information on soil health. Total soil carbon (TSC) is a combined constituent of organic and inorganic sources of carbon, and it is important to further enhance our understanding of carbon sequestration in soil. An electrochemical sensor, using a three-electrode platform, modified by EMIM[TF₂N]-calixarene-chitosan composite was used to develop a proof of concept to track total soil carbon in-situ without sample pretreatment. Computational chemistry and FTIR spectroscopy were utilized to understand the interaction chemistry between TSC and transducing elements. Based on the interaction results obtained, the sensor was calibrated in three different soil textures; sandy loam, loamy clay, and clay loam. Electrochemical impedance spectroscopy (EIS) technique was used to measure TSC across the range of 0.01 %–4 %. The dose dependent response showed excellent repeatability for all three soil types. This is a novel proof of concept for building a consolidated total soil carbon in-situ sensor, which was further field tested using standard validation principle, to obtain its real field capability.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101875"},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785788","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}

{"title":"Comparative analysis of inertial measurement units and markerless video motion capture systems for assessing rotational parameters in snowboard freestyle","authors":"Tom Gorges ,&nbsp;Christian Merz ,&nbsp;Felix Friedl ,&nbsp;Ingo Sandau","doi":"10.1016/j.measen.2025.101872","DOIUrl":"10.1016/j.measen.2025.101872","url":null,"abstract":"<div><div>In snowboard freestyle, the measured amount of rotation (mAR) is a key judging criteria. Rotational parameters like angular velocity (AV) support athletes and coaches in performance enhancements. This study evaluates the validity of on-snow available inertial measurement unit (IMU) data with a markerless optical tracking system. Eight elite snowboard riders performed 88 tricks with a bounce board on a trampoline that were concurrently measured using a board-mounted IMU and a video motion capture system (criterion). The validity of the IMU was determined for discrete (mAR) and time-series (AV) data via t-test, effect size (d), concordance correlation coefficient (CCC), standard deviation of differences (SDD), and bias ±limits of agreement (LoA). For discrete data, results indicated excellent absolute and relative concurrent validity of mAR (SDD = ±8.18°; SDD% = ±1.42%; CCC = 0.998; bias ± LoA = 1.80° ± 16.02°) despite significant mean differences (p <span><math><mo>&lt;</mo></math></span> 0.05; d <span><math><mrow><mo>&lt;</mo><mrow><mo>|</mo><mn>0</mn><mo>.</mo><mn>2</mn><mo>|</mo></mrow></mrow></math></span>) between both systems. For time-series data, acceptable absolute and relative concurrent validity exist for AV (mean SDD <span><math><mo>&lt;</mo></math></span> 45°; mean SDD% <span><math><mo>&lt;</mo></math></span> 10%; mean CCC <span><math><mo>&gt;</mo></math></span> 0.9; bias ± LoA = −0.19°/s ± 87.48°/s) showing significant mean differences only in the first 1% of the time-series (p <span><math><mo>&lt;</mo></math></span> 0.05; d <span><math><mrow><mo>&gt;</mo><mspace></mspace><mrow><mo>|</mo><mn>0</mn><mo>.</mo><mn>2</mn><mo>|</mo></mrow></mrow></math></span>). In conclusion, using a board-mounted IMU is a valid approach to measure rotational parameters in snowboard freestyle, highlighting IMUs’ potential for on-field performance analysis. Nonetheless, caution is advised when interpreting AV at individual time points due to the observed variability, especially in close temporal proximity to take-off and landing events.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101872"},"PeriodicalIF":0.0,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739109","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}

{"title":"Selected channel based multiclass emotion classification from wearable human brain EEG signal","authors":"Khushboo Singh,&nbsp;Mitul Kumar Ahirwal,&nbsp;Manish Pandey","doi":"10.1016/j.measen.2025.101874","DOIUrl":"10.1016/j.measen.2025.101874","url":null,"abstract":"<div><div>Emotion recognition is a crucial issue in human-computer interaction, and EEG (electroencephalography) plays a significant role in deciphering human emotions based on physiological data. However, the complex and non-stationary nature of EEG signals, coupled with redundant information from multi-channel recordings, poses challenges in accurate emotion classification. To address this, we propose a hybrid 1DCNN-Bi-LSTM model that integrates spatial feature extraction (1DCNN) with temporal dependency learning (Bi-LSTM), enhancing the robustness of emotion classification. Furthermore, we present a channel selection mechanism to find the most pertinent EEG channels for emotion recognition, hence lowering computing complexity without compromising accuracy. With the chosen-channel model (8 channels) attaining 85.16 % accuracy, a notable improvement over standard full-channel approaches, experimental results on the DEAP dataset show that the suggested methodology provides significant performance gains. This work fits wearable devices and real-time affective computing systems since it offers a scalable and effective method for EEG-based emotion recognition.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101874"},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739892","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}

{"title":"Entropy based earlier detection and mitigation of DDOS attack using stochastic method in SDN_IOT","authors":"I. Varalakshmi,&nbsp;M. Thenmozhi","doi":"10.1016/j.measen.2025.101873","DOIUrl":"10.1016/j.measen.2025.101873","url":null,"abstract":"<div><div>Software-defined networking (SDN) is characterized by the separation of control plane as well as data plane in the network. Data packets are forwarded by the data plane, while routing decisions are made by the control plane. This separation of concerns allows for greater flexibility and programmability in the network. It is a promising technology that can allow IoT networks to perform better, be more secure, and be more manageable. However, there are some challenges that need to be addressed before SDN can be widely adopted in IoT environments. The requests can be made from a variety of sources, including compromised computers, botnets, and even legitimate users who have been tricked into visiting a malicious website. Detecting and mitigating DDoS attacks at an early stage is the goal of a stochastic method based on Entropy that prevents failure of SDN controller. The proposed algorithm Entropy based DDoS Detection algorithm (EDDA) detects the attack by analyzing entropy fluctuations in incoming data packets, thereby preserving the integrity of sensor-generated data and dynamically configure rate-limiting mechanisms on network devices to restrict the rate at which packets can be transmitted. With our proposed method, DDoS attacks like TCP, UDP, and ICMP SYN Flood can be detected with high accuracy, using less computing power. As a result of the proposed solution, DDoS attacks are detected and mitigated using SDN-based techniques under 70 hosts connected within 9 switches with a high degree of detection accuracy and significantly low detection time. By integrating entropy as a measurement parameter, the proposed system effectively distinguishes between legitimate and malicious network flows, ensuring stable and secure data transmission in sensor-driven IoT networks.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101873"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808803","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":"IOT based wearable sensor system architecture for classifying human activity","authors":"V. Mahalakshmi ,&nbsp;Pramod Kumar ,&nbsp;Manisha Bhende ,&nbsp;Ismail Keshta ,&nbsp;Swatiben Yashvantbhai Rathod ,&nbsp;Janjhyam Venkata Naga Ramesh","doi":"10.1016/j.measen.2025.101871","DOIUrl":"10.1016/j.measen.2025.101871","url":null,"abstract":"<div><div>Human Activity Recognition (HAR) has applications in diverse fields, including sports management and behavior classification. Existing HAR methods can be categorized into three main approaches: camera-based, wearable sensor-based, and Wi-Fi sensing-based. Camera-based methods suffer from privacy concerns, while wearable sensor-based methods face limitations in battery longevity and continuous monitoring. Wi-Fi sensing methods mitigate privacy and battery issues but rely on costly Intel 5300 network cards or software-defined radio (SDR) platforms, limiting scalability. This paper presents a cost-effective IoT-based human activity recognition system using ESP32, leveraging its Wi-Fi sensing capabilities. The proposed system follows a structured workflow: (i) channel state information (CSI) is extracted from ESP32 modules, (ii) data preprocessing is performed using Hampel and Gaussian filters for noise and outlier removal, (iii) dimensionality reduction is achieved through Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT), and (iv) activity classification is conducted using Dynamic Time Warping (DTW) and the K-Nearest Neighbors (KNN) algorithm. Experimental evaluations demonstrate that the proposed system achieves an average recognition accuracy of 98.6 % across six human activities, comparable to high-end Intel 5300-based HAR systems, while significantly reducing hardware costs and improving ease of deployment.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101871"},"PeriodicalIF":0.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716031","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}

{"title":"Wearable sensor-based fall detection for elderly care using ensemble machine learning techniques","authors":"Ch Gangadhar ,&nbsp;P Pavithra Roy ,&nbsp;R. Dinesh Kumar ,&nbsp;Janjhyam Venkata Naga Ramesh ,&nbsp;S. Ravikanth ,&nbsp;N. Akhila","doi":"10.1016/j.measen.2025.101870","DOIUrl":"10.1016/j.measen.2025.101870","url":null,"abstract":"<div><div>Older people face serious issues with unintentional collisions that result in healthcare admissions and fatalities. Since numerous accidents happen quickly, it might be difficult to identify crashes in context. Enhancing the quality of services for older people requires the development of a computerized surveillance network that can anticipate accidents before occur, offer protection throughout the incident, and send out remote warnings following an accident. This research suggested a wearing surveillance system that seeks to detect accidents at the onset and lineage, triggering an alarm to reduce damages caused by accidents and sending out an external alert when the human body hits the hard surface. Meanwhile, the research's offsite evaluation of a combined structure utilizing the Random Forest technique (RF), Supporting Vectors Machines (SVM), and available information were used to illustrate this idea. The suggested method employed RF to reliably retrieve features from speedometer and inertial facts, while SVM provides an estimator and classification-capable method. Each module in the unique category-based composite structure is recognized at a certain level. The suggested strategy outperformed modern fall identification techniques when tested using the labeled KFall database, achieving average precision of 95 percent, 96 percent, as well as 98 percent for Non-Falls, Pre-Falls, as well as detectable fall incidents, correspondingly. The whole assessment proved the algorithmic learning structure's efficacy. Older people's standard of existence will increase, and accidents will be avoided because of such smart tracking devices.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101870"},"PeriodicalIF":0.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747686","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}

{"title":"High-fidelity EEG feature-engineered taxonomy for bruxism and PLMS prognostication through pioneering and avant-garde ML frameworks","authors":"Shivam Tiwari ,&nbsp;Deepak Arora ,&nbsp;Barkha Bhardwaj","doi":"10.1016/j.measen.2025.101868","DOIUrl":"10.1016/j.measen.2025.101868","url":null,"abstract":"<div><div>Periodic Leg Movement during Sleep (PLMS) and Bruxism are linked with changes in EEG signal characteristics. This work applies machine learning and data mining approaches to examine these changes. Patients with PLMS and bruxism had nighttime EEG recordings to examine changes in brain activity. The findings revealed constant variations in brain hemodynamics even in the absence of clearly observable arousals in the EEG. Wavelet decomposition was used to improve classification precision. Using the N3 sleep stage, accuracy varied from 92 % to 96 %, with an AUC of 0.85–0.89, in diagnosing binary sleep disorders. Still, adding wavelet-based elements greatly enhanced performance, obtaining an AUC of 0.99 with classification accuracy ranging from 94 % to 98 %. This emphasizes how strongly discriminative power wavelet-extracted EEG characteristics possess. Using K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), and Support Vector Machines (SVM) with Radial Basis Function (RBF), Bruxism categorization was accomplished. These models attained respectively 82 %, 90 %, and 93 % percent classification accuracy. This work is the first to show a direct connection among differences in brain activity based on PLMS, Bruxism, and EEG-based technologies. The results show how well machine learning methods and EEG feature extraction might diagnose sleep problems. Although the therapeutic relevance of these findings is yet unknown, the results imply that enhanced EEG-based classification techniques could produce more reliable and automated diagnostic instruments for Bruxism and PLMS.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101868"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682455","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}

{"title":"Wearable sensor-based intent recognition for adaptive control of intelligent ankle-foot prosthetics","authors":"Vidyapati Kumar,&nbsp;Dilip Kumar Pratihar","doi":"10.1016/j.measen.2025.101865","DOIUrl":"10.1016/j.measen.2025.101865","url":null,"abstract":"<div><div>Prosthetic motor control requires improvement to better adapt to varying gait speeds and terrain inclinations in real time. Traditional methods often fail to meet these demands, prompting research into advanced sensor data and machine learning algorithms. This research study tackles the challenge by using wearable sensors and comparing various machine learning approaches, namely Sparse Bidirectional Long Short-Term Memory (SBLSTM), Adaptive Neuro-Fuzzy Inference System (ANFIS), convolutional neural network (CNN), logistic regression, and K-nearest neighbors (KNN) for effective classification of gait speed and terrain inclination. Various wearable sensor data, such as FSR and accelerometers, were employed to develop robust models for prosthetic control. The SBLSTM model, which utilizes time-series data through Bi-Directional LSTM layers, demonstrated impressive performance with an accuracy of 96.3 %, precision of 96.4 %, recall of 96.5 %, and an F1-score of 96.4 %. In contrast, the ANFIS model, combining gradient-based learning and least squares estimation, showed reasonable predictive capabilities with root mean square error (RMSE) values of 0.12 for speed and 0.14 for inclination. The accuracy of CNN, logistic regression, and KNN was reported to be 60 %, 31 %, and 93 %, respectively. Comparing the other models in terms of computation, the mean inference time for SBLSTM was found to be 25 ms, which proved to balance speed and accuracy better than other models. Furthermore, the SBLSTM model is particularly suited for time-dependent data, making it more appropriate for real-time prosthetic control. The results highlight that using advanced machine learning algorithms and wearable sensor data has great potential to increase the responsiveness and adaptability of lower-limb prosthetic systems. Ultimately, the goal of this work is for prosthetic users to benefit in terms of quality of life-related to improved mobility and adaptability across a range of environmental conditions.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101865"},"PeriodicalIF":0.0,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628498","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}