Pub Date : 2024-11-09DOI: 10.1016/j.measen.2024.101402
Shraddha R. Modi , Hetalben Kanubhai Gevariya , Reshma Dayma , Adesh V. Panchal , Harshad L. Chaudhary
Pose graph optimization is a crucial method that helps reduce cumulative errors while estimating visual trajectories for wearable cameras. However, when the posture graph's size increases with each additional camera movement, the optimization's efficiency diminishes. In terms of ongoing sensitive applications, such as extended reality and computer-generated reality, direction assessment is a major test. This research proposes an incremental pose graph segmentation technique that accounts for camera orientation variations as a solution to this challenge. The computation only improves the cameras that have seen large direction changes by breaking the posture chart during these instances. As a result, pose graph optimization is essentially slowed down and optimized more quickly. For every camera that hasn't been optimized using a pose graph, the algorithm employs the wearable cameras at the start and end of each camera's trajectory segment. The final camera in attendance is then determined by weighted average the various postures evaluated with these wearable cameras; this eliminates the need for lengthy nonlinear enhancement computations, reduces disturbance, and achieves excellent accuracy. Experiments on the EuRoC, TUM, and KITTI datasets demonstrate that pose graph optimization scope is reduced while maintaining camera trajectories accuracy.
{"title":"Augmented and virtual reality based segmentation algorithm for human pose detection in wearable cameras","authors":"Shraddha R. Modi , Hetalben Kanubhai Gevariya , Reshma Dayma , Adesh V. Panchal , Harshad L. Chaudhary","doi":"10.1016/j.measen.2024.101402","DOIUrl":"10.1016/j.measen.2024.101402","url":null,"abstract":"<div><div>Pose graph optimization is a crucial method that helps reduce cumulative errors while estimating visual trajectories for wearable cameras. However, when the posture graph's size increases with each additional camera movement, the optimization's efficiency diminishes. In terms of ongoing sensitive applications, such as extended reality and computer-generated reality, direction assessment is a major test. This research proposes an incremental pose graph segmentation technique that accounts for camera orientation variations as a solution to this challenge. The computation only improves the cameras that have seen large direction changes by breaking the posture chart during these instances. As a result, pose graph optimization is essentially slowed down and optimized more quickly. For every camera that hasn't been optimized using a pose graph, the algorithm employs the wearable cameras at the start and end of each camera's trajectory segment. The final camera in attendance is then determined by weighted average the various postures evaluated with these wearable cameras; this eliminates the need for lengthy nonlinear enhancement computations, reduces disturbance, and achieves excellent accuracy. Experiments on the EuRoC, TUM, and KITTI datasets demonstrate that pose graph optimization scope is reduced while maintaining camera trajectories accuracy.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101402"},"PeriodicalIF":0.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655472","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}
Pub Date : 2024-11-07DOI: 10.1016/j.measen.2024.101403
Hemlata Sandip Ohal, Shamla Mantri
This paper presents a comprehensive investigation into Electroencephalogram (EEG) signal processing and analysis techniques aimed at enhancing early diagnosis methods for Alzheimer's Disease (AD). Leveraging a dataset that has EEG data of individuals diagnosed with Mild Cognitive Impairment (MCI), AD, Healthy Controls, and the study explores Preprocessing Methods and Feature Extraction Techniques, with machine learning model notably Support Vector Machines (SVM).
In the preprocessing phase, a combination of high pass, lowpass, Savitzky–Golay, and median filters are applied, informed by a comprehensive review of filter comparison literature. Feature extraction encompasses three primary categories: ‘Statistical, ‘Frequency Domain’ and ‘Time Domain’. The scope of this work is to explore features in all these three domains and build SVM based model for efficient classification. In our investigation, we achieved a categorization accuracy of 92 % through the utilization of statistical features. Employing time domain features resulted in an accuracy of 87 %, while frequency domain features also yielded an 87 % accuracy rate in our study. The primary objective of this study is that it aims to enhance early AD diagnosis through advanced EEG signal processing and machine learning techniques, focusing on preprocessing methods, feature extraction, and classification accuracy.
{"title":"Exploring EEG-Based biomarkers for improved early Alzheimer's disease detection: A feature-based approach utilizing machine learning","authors":"Hemlata Sandip Ohal, Shamla Mantri","doi":"10.1016/j.measen.2024.101403","DOIUrl":"10.1016/j.measen.2024.101403","url":null,"abstract":"<div><div>This paper presents a comprehensive investigation into Electroencephalogram (EEG) signal processing and analysis techniques aimed at enhancing early diagnosis methods for Alzheimer's Disease (AD). Leveraging a dataset that has EEG data of individuals diagnosed with Mild Cognitive Impairment (MCI), AD, Healthy Controls, and the study explores Preprocessing Methods and Feature Extraction Techniques, with machine learning model notably Support Vector Machines (SVM).</div><div>In the preprocessing phase, a combination of high pass, lowpass, Savitzky–Golay, and median filters are applied, informed by a comprehensive review of filter comparison literature. Feature extraction encompasses three primary categories: ‘Statistical, ‘Frequency Domain’ and ‘Time Domain’. The scope of this work is to explore features in all these three domains and build SVM based model for efficient classification. In our investigation, we achieved a categorization accuracy of 92 % through the utilization of statistical features. Employing time domain features resulted in an accuracy of 87 %, while frequency domain features also yielded an 87 % accuracy rate in our study. The primary objective of this study is that it aims to enhance early AD diagnosis through advanced EEG signal processing and machine learning techniques, focusing on preprocessing methods, feature extraction, and classification accuracy.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101403"},"PeriodicalIF":0.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655471","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}
With the proliferation of smart wearables, motion wristbands provide a wealth of data essential for comprehending the dynamic nature of health. However, outlier detection is typically necessary due to the presence of unknown outliers in their multidimensional activity data. Conventional approaches frequently result in incorrect object identification due to the curse of dimensionality. Using the Gaussian Mixture Generative Model (GMGM), we provide a method to identify outliers and address this problem. Training on raw data is done using a VariationalAutoencoder (VAE). While avoiding rebuilding mistakes, we want to achieve as many brief features as possible. To predict the likelihood that examples contain many types of data, a DBN will utilise feature extractions and latent distributions in the future. The model's robustness is enhanced by enhancing the VAE, deep learning components, and the GMM overall. When densities surpass the training level, the Gaussian Mixture Model identifies outliers. To achieve this, it makes educated guesses about the densities of each data point. Compared to the deep learning Autoencoding Gaussian Mixture Model (DAGMM), GMGM achieves a 5.5 % higher area under the curve (AUC) on the ODDS standard dataset. Experiments conducted on real datasets further demonstrate the efficacy of this strategy.
{"title":"Deep learning model for smart wearables device to detect human health conduction","authors":"Rathod Hiral Yashwantbhai , Haresh Dhanji Chande , Sachinkumar Harshadbhai Makwana , Payal Prajapati , Archana Gondalia , Pinesh Arvindbhai Darji","doi":"10.1016/j.measen.2024.101401","DOIUrl":"10.1016/j.measen.2024.101401","url":null,"abstract":"<div><div>With the proliferation of smart wearables, motion wristbands provide a wealth of data essential for comprehending the dynamic nature of health. However, outlier detection is typically necessary due to the presence of unknown outliers in their multidimensional activity data. Conventional approaches frequently result in incorrect object identification due to the curse of dimensionality. Using the Gaussian Mixture Generative Model (GMGM), we provide a method to identify outliers and address this problem. Training on raw data is done using a VariationalAutoencoder (VAE). While avoiding rebuilding mistakes, we want to achieve as many brief features as possible. To predict the likelihood that examples contain many types of data, a DBN will utilise feature extractions and latent distributions in the future. The model's robustness is enhanced by enhancing the VAE, deep learning components, and the GMM overall. When densities surpass the training level, the Gaussian Mixture Model identifies outliers. To achieve this, it makes educated guesses about the densities of each data point. Compared to the deep learning Autoencoding Gaussian Mixture Model (DAGMM), GMGM achieves a 5.5 % higher area under the curve (AUC) on the ODDS standard dataset. Experiments conducted on real datasets further demonstrate the efficacy of this strategy.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101401"},"PeriodicalIF":0.0,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655470","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}
Pub Date : 2024-11-01DOI: 10.1016/j.measen.2024.101391
Kadiyam Anusha, A.D.D. Dwivedi
Recent years have seen an increase in the use of Organic Thin Film Transistors (OTFTs), with applications ranging from flexible, low-cost displays to organic memory, RFID tag components, low-cost electronic appliances, and polymer circuits and sensors. Thin-film transistors (TFTs) have developed into a critical business on the grounds levels to their wide scope of utilizations in display; Radio-Frequency ID labels (RFID SENSOR), intelligent computation, and different areas. Reduced models are basic in the turn of events and execution of TFTs on the grounds that they overcome any barrier between the manufacture cycle and circuit plan. The motivation behind this exploration is to assemble a hypothetical structure for nanoscale TFT models made of polysilicon, indistinct silicon, natural, and In-Ga-Zn-O (IGZO) semiconductors. Extraordinary consideration is paid to surface-expected based smaller models of silicon-based TFTs. Surface-potential-based compact models and parameter extraction approaches were presented based on our knowledge of charge transport characteristics and TFT needs in organic and IGZO TFTs.
{"title":"Review and analysis on numerical simulation and compact modeling of InGaZno thin-film transistor for display SENSOR applications","authors":"Kadiyam Anusha, A.D.D. Dwivedi","doi":"10.1016/j.measen.2024.101391","DOIUrl":"10.1016/j.measen.2024.101391","url":null,"abstract":"<div><div>Recent years have seen an increase in the use of Organic Thin Film Transistors (OTFTs), with applications ranging from flexible, low-cost displays to organic memory, RFID tag components, low-cost electronic appliances, and polymer circuits and sensors. Thin-film transistors (TFTs) have developed into a critical business on the grounds levels to their wide scope of utilizations in display; Radio-Frequency ID labels (RFID SENSOR), intelligent computation, and different areas. Reduced models are basic in the turn of events and execution of TFTs on the grounds that they overcome any barrier between the manufacture cycle and circuit plan. The motivation behind this exploration is to assemble a hypothetical structure for nanoscale TFT models made of polysilicon, indistinct silicon, natural, and In-Ga-Zn-O (IGZO) semiconductors. Extraordinary consideration is paid to surface-expected based smaller models of silicon-based TFTs. Surface-potential-based compact models and parameter extraction approaches were presented based on our knowledge of charge transport characteristics and TFT needs in organic and IGZO TFTs.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101391"},"PeriodicalIF":0.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655469","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}
Numerous devices, including sensors, RF ID, and other types of smart devices, have been developed as a result of the Artificial Intelligence (AI), and Internet of Things (IoT) revolution. Urban areas can become smart by monitoring and collecting data about their surroundings through the deployment of technologies with powerful computational capabilities and those that are converted into intelligent things. Waste management is among the most significant issues in smart cities, a rise in metropolitan regions and faster increases in population are the main reasons. When it comes to gathering data about waste management, intelligent services can serve as the front line. Waste management with IoT support is a common example of a service offered by smart cities. Various duties, like gathering, processing, and use of waste in appropriate facilities, are included in waste management. The present study proposed an updated waste management system architecture design after reviewing existing artificial intelligence and IoT-based waste management systems and automation in smart cities. The proposed system architecture deals with the automation of municipality trash in smarter urban areas, using IoT technology and sending notification messages based on sensor data relating to the dustbin state, such as full or empty. The notifications are sent simultaneously to the municipality office and the waste carrier vehicle driver, so that waste can be emptied on time. The proposed system architecture represents a scalable and adaptable model for municipalities that aim to transform their waste collection processes and play a key step in minimizing municipality waste in smart cities. By deploying this proposed system architecture with smart sensors and IoT devices, municipalities can monitor waste levels to ensure that bins are emptied when it is necessary. This reduces the frequency of waste collection, lowers fuel consumption, and minimizes operational costs. The Route optimization algorithms further enhance efficiency by determining the most efficient paths for waste collection trucks, so they can reduce travel time and fuel emissions.
{"title":"Artificial intelligence and IoT driven system architecture for municipality waste management in smart cities: A review","authors":"Khalil Ahmed , Mithilesh Kumar Dubey , Ajay Kumar , Sudha Dubey","doi":"10.1016/j.measen.2024.101395","DOIUrl":"10.1016/j.measen.2024.101395","url":null,"abstract":"<div><div>Numerous devices, including sensors, RF ID, and other types of smart devices, have been developed as a result of the Artificial Intelligence (AI), and Internet of Things (IoT) revolution. Urban areas can become smart by monitoring and collecting data about their surroundings through the deployment of technologies with powerful computational capabilities and those that are converted into intelligent things. Waste management is among the most significant issues in smart cities, a rise in metropolitan regions and faster increases in population are the main reasons. When it comes to gathering data about waste management, intelligent services can serve as the front line. Waste management with IoT support is a common example of a service offered by smart cities. Various duties, like gathering, processing, and use of waste in appropriate facilities, are included in waste management. The present study proposed an updated waste management system architecture design after reviewing existing artificial intelligence and IoT-based waste management systems and automation in smart cities. The proposed system architecture deals with the automation of municipality trash in smarter urban areas, using IoT technology and sending notification messages based on sensor data relating to the dustbin state, such as full or empty. The notifications are sent simultaneously to the municipality office and the waste carrier vehicle driver, so that waste can be emptied on time. The proposed system architecture represents a scalable and adaptable model for municipalities that aim to transform their waste collection processes and play a key step in minimizing municipality waste in smart cities. By deploying this proposed system architecture with smart sensors and IoT devices, municipalities can monitor waste levels to ensure that bins are emptied when it is necessary. This reduces the frequency of waste collection, lowers fuel consumption, and minimizes operational costs. The Route optimization algorithms further enhance efficiency by determining the most efficient paths for waste collection trucks, so they can reduce travel time and fuel emissions.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101395"},"PeriodicalIF":0.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571526","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}
Pub Date : 2024-10-30DOI: 10.1016/j.measen.2024.101390
V. Rama Krishna , Vuppala Sukanya , Mohd Abdul Hameed
Efficient utilization of energy is a crucial concern in Wireless Sensor Networks (WSNs) to increase the network's longevity. However, it is impossible to investigate routing without considering the effective formation of chains or clustering methods to optimize the problem in WSNs. The proposed routing technique aims to extend the lifespan of sensors using various network partitioning techniques. The approach utilized in the strategy is PEGASIS (Power EfficientGathering in Sensor Information Systems) protocol, it uses Prim's Algorithm to modify the chain structure and is based on hierarchical chain-based routing. In order to transmit information from the working nodes to the base station (BS), we employ and vertical network partitioning techniques named EEPEG-PA-V. According to this approach, the transition is carried out when the node's residual energy is about to run out. The suggested method has the potential to enhance the average network longevity substantially when compared to existing routing techniques. For instance, EEPEG-PA improves it by 21.7092 % and EEPEG-PA-V by 29.9056 % compared to PEGASIS. Similarly, EEPEG-PA-V by 6.1708 % compared to EEPEG-PAacross various network sizes.
{"title":"Optimizing Wireless Sensor Network longevity with hierarchical chain-based routing and vertical network partitioning techniques","authors":"V. Rama Krishna , Vuppala Sukanya , Mohd Abdul Hameed","doi":"10.1016/j.measen.2024.101390","DOIUrl":"10.1016/j.measen.2024.101390","url":null,"abstract":"<div><div>Efficient utilization of energy is a crucial concern in Wireless Sensor Networks (WSNs) to increase the network's longevity. However, it is impossible to investigate routing without considering the effective formation of chains or clustering methods to optimize the problem in WSNs. The proposed routing technique aims to extend the lifespan of sensors using various network partitioning techniques. The approach utilized in the strategy is PEGASIS (<strong>P</strong>ower <strong>E</strong>fficient<strong>Ga</strong>thering in <strong>S</strong>ensor <strong>I</strong>nformation <strong>S</strong>ystems) protocol, it uses Prim's Algorithm to modify the chain structure and is based on hierarchical chain-based routing. In order to transmit information from the working nodes to the base station (BS), we employ and vertical network partitioning techniques named EEPEG-PA-V. According to this approach, the transition is carried out when the node's residual energy is about to run out. The suggested method has the potential to enhance the average network longevity substantially when compared to existing routing techniques. For instance, EEPEG-PA improves it by 21.7092 % and EEPEG-PA-V by 29.9056 % compared to PEGASIS. Similarly, EEPEG-PA-V by 6.1708 % compared to EEPEG-PAacross various network sizes.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101390"},"PeriodicalIF":0.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571527","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}
Pub Date : 2024-10-29DOI: 10.1016/j.measen.2024.101399
R. Dhanush Babu, S. Siva Adithya, M. Dhanalakshmi
Electromyography (EMG) signals are biomedical signals that measure electrical currents generated by the activity of muscles when they contract. EMG is essential for optimizing the control of various prosthetic devices, particularly for transfemoral amputees, where the complexity of muscle signal integration presents significant challenges. The proposed study aims to develop a prosthetic knee that actuates in real-time using the EMG signals from the amputee’s residual limb. Pre-processing techniques are employed to obtain EMG signals from the femoris and vastus muscle targets in the transfemoral region. Moving average filters and Butterworth bandpass filters are implemented to process the raw signals. Sliding windows of various widths were applied for feature extraction. The window size of 200 ms is determined for our study based on the outcomes of the t-SNE plots and the corresponding silhouette scores. After the extraction of the pertinent features, several supervised classifier algorithms are put into practice to classify the knee flexion and extension motion. The k-nearest Neighbor (KNN) algorithm, with an accuracy rating of 80 %, proved to be suitable for motor control. Real-time control is implemented using the Raspberry Pi board to power the prosthesis allowing above-the-knee amputees to voluntarily move the leg back and forth. The EMG signals are then extracted and used to drive the DC motor. The prosthesis would therefore be able to move more precisely since the EMG readings are being gathered in real-time. Thus, this work can enhance the patient’s comfort with the ease of carrying out knee movements.
{"title":"Design and development of an EMG controlled transfemoral prosthesis","authors":"R. Dhanush Babu, S. Siva Adithya, M. Dhanalakshmi","doi":"10.1016/j.measen.2024.101399","DOIUrl":"10.1016/j.measen.2024.101399","url":null,"abstract":"<div><div>Electromyography (EMG) signals are biomedical signals that measure electrical currents generated by the activity of muscles when they contract. EMG is essential for optimizing the control of various prosthetic devices, particularly for transfemoral amputees, where the complexity of muscle signal integration presents significant challenges. The proposed study aims to develop a prosthetic knee that actuates in real-time using the EMG signals from the amputee’s residual limb. Pre-processing techniques are employed to obtain EMG signals from the femoris and vastus muscle targets in the transfemoral region. Moving average filters and Butterworth bandpass filters are implemented to process the raw signals. Sliding windows of various widths were applied for feature extraction. The window size of 200 ms is determined for our study based on the outcomes of the t-SNE plots and the corresponding silhouette scores. After the extraction of the pertinent features, several supervised classifier algorithms are put into practice to classify the knee flexion and extension motion. The k-nearest Neighbor (KNN) algorithm, with an accuracy rating of 80 %, proved to be suitable for motor control. Real-time control is implemented using the Raspberry Pi board to power the prosthesis allowing above-the-knee amputees to voluntarily move the leg back and forth. The EMG signals are then extracted and used to drive the DC motor. The prosthesis would therefore be able to move more precisely since the EMG readings are being gathered in real-time. Thus, this work can enhance the patient’s comfort with the ease of carrying out knee movements.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101399"},"PeriodicalIF":0.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571528","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}
Pub Date : 2024-10-28DOI: 10.1016/j.measen.2024.101400
Sravanthi Pagidipala, Vuddanti Sandeep
This paper proposes an optimal planning technique for placing the multiple renewable energy (RE) based distributed generators (DGs), Distribution Static Compensators (DSTATCOMs), and electric vehicle charging stations (EVCSs) in the radial distribution network (RDN) considering the related uncertainties. This approach gives optimal placement and sizes for DGs and DSTATCOMs as well as a number of electric vehicles (EVs) that can be charged at the EVCSs by considering the network reconfiguration (NR). The optimal allocation of EVCSs fulfills the power demand from EVs at various locations and minimizes the negative impact on the power network. The RE-based DGs considered for this work are solar photovoltaic (PV) and wind. The uncertainties related to RE-based DGs and EVCSs have been modeled by using the probabilistic-based two-point estimate method (2PEM). The best locations and sizes are identified by optimizing the individual objectives that is active power losses and voltage stability index (VSI) using the teaching learning based optimization (TLBO) algorithm. Then both objectives are optimized by using the non-dominated sorting-based TLBO algorithm. Furthermore, the optimal planning approach is implemented on IEEE 33 and 69 bus test systems to demonstrate the suitability, practicality, and efficiency of the proposed optimal planning strategy. The obtained results reveal that the proposed technique is beneficial for determining the optimal locations for DGs, DSTATCOMs, and EVCSs without affecting the grid stability. The proposed planning approach can search better network structure with reduced power losses and voltage deviation, enhanced voltage profile, and improved voltage stability.
{"title":"Optimal planning of electric vehicle charging stations and distributed generators with network reconfiguration in smart distribution networks considering uncertainties","authors":"Sravanthi Pagidipala, Vuddanti Sandeep","doi":"10.1016/j.measen.2024.101400","DOIUrl":"10.1016/j.measen.2024.101400","url":null,"abstract":"<div><div>This paper proposes an optimal planning technique for placing the multiple renewable energy (RE) based distributed generators (DGs), Distribution Static Compensators (DSTATCOMs), and electric vehicle charging stations (EVCSs) in the radial distribution network (RDN) considering the related uncertainties. This approach gives optimal placement and sizes for DGs and DSTATCOMs as well as a number of electric vehicles (EVs) that can be charged at the EVCSs by considering the network reconfiguration (NR). The optimal allocation of EVCSs fulfills the power demand from EVs at various locations and minimizes the negative impact on the power network. The RE-based DGs considered for this work are solar photovoltaic (PV) and wind. The uncertainties related to RE-based DGs and EVCSs have been modeled by using the probabilistic-based two-point estimate method (2PEM). The best locations and sizes are identified by optimizing the individual objectives that is active power losses and voltage stability index (VSI) using the teaching learning based optimization (TLBO) algorithm. Then both objectives are optimized by using the non-dominated sorting-based TLBO algorithm. Furthermore, the optimal planning approach is implemented on IEEE 33 and 69 bus test systems to demonstrate the suitability, practicality, and efficiency of the proposed optimal planning strategy. The obtained results reveal that the proposed technique is beneficial for determining the optimal locations for DGs, DSTATCOMs, and EVCSs without affecting the grid stability. The proposed planning approach can search better network structure with reduced power losses and voltage deviation, enhanced voltage profile, and improved voltage stability.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101400"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552184","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}
Pub Date : 2024-10-24DOI: 10.1016/j.measen.2024.101397
Hernan Paz Penagos, Esteban Morales Mahecha, Adriana Melo Camargo, Edison Sanchez Jimenez, Diego Arturo Coy Sarmiento, Sara Valentina Hernández Salazar
This study focuses on the monitoring, transmission, recognition and detection of snoring signals and their relationship with obstructive sleep apnea. To achieve this purpose, the ESP32 microcontroller and a MEMS technology microphone were used to capture and measure characteristic parameters of snoring signals, such as their intensity, frequency and duration. In addition, the WiFi radio interface was used to send the signals to a server where the information was processed, the snoring was detected, linked to a chatbot in Nodred to show the user in a graphical interface his diagnosis of the snoring level. This comprehensive approach allows real-time, wireless monitoring of snoring, leading to a less invasive diagnosis of obstructive sleep apnea.
{"title":"Detection, recognition and transmission of snoring signals by ESP32","authors":"Hernan Paz Penagos, Esteban Morales Mahecha, Adriana Melo Camargo, Edison Sanchez Jimenez, Diego Arturo Coy Sarmiento, Sara Valentina Hernández Salazar","doi":"10.1016/j.measen.2024.101397","DOIUrl":"10.1016/j.measen.2024.101397","url":null,"abstract":"<div><div>This study focuses on the monitoring, transmission, recognition and detection of snoring signals and their relationship with obstructive sleep apnea. To achieve this purpose, the ESP32 microcontroller and a MEMS technology microphone were used to capture and measure characteristic parameters of snoring signals, such as their intensity, frequency and duration. In addition, the WiFi radio interface was used to send the signals to a server where the information was processed, the snoring was detected, linked to a chatbot in Nodred to show the user in a graphical interface his diagnosis of the snoring level. This comprehensive approach allows real-time, wireless monitoring of snoring, leading to a less invasive diagnosis of obstructive sleep apnea.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101397"},"PeriodicalIF":0.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528531","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}
Pub Date : 2024-10-24DOI: 10.1016/j.measen.2024.101398
S.M. Mohidul Islam, Kamrul Hasan Talukder
Recognizing human activity plays a crucial role in many applications such as medical care services in smart healthcare environments. Inertial or motion sensors can measure physiognomies such as acceleration and angular velocity of body movement while performing the activities and we can use them to learn the models capable of activity recognition. Over the past decades, many state-of-the-art activity recognition systems have been developed but there is still room to improve. In this paper, we have proposed a novel approach to identify human activity from motion sensor data by employing an enormous analysis of sensor data. Based on data analysis, we yielded quality data by preprocessing using a preprocessing chain for human activity recognition (PC-HAR) which also includes the Synthetic Minority Over-sampling Technique to balance the data of the dataset. As a recognition model, we proposed an ensemble of three different deep learning algorithms, namely, modified DeepConvLSTM, modified InceptionTime, and modified ResNet which is named ‘Ensem-DeepHAR’. The outcome of the proposed model is carried out by stacking predictions from each of the mentioned models and then a Random Forest as a meta-model uses those predictions to recognize the final activity. We evaluated our method on both person-dependent and person-independent cases and achieved 99.31 %, 99.08 %, and 97.52 % accuracies for the former case and 97.95 %, 98.11 %, and 99.51 % accuracies for the latter case using three common benchmark datasets: WISDM_ar_v1.1, PAMAP2, and UCI-HAR respectively. The various performance metrics and measures of experimental results establish the supremacy of the proposed model over the state-of-the-arts.
{"title":"Ensem-DeepHAR: Identification of human activity in smart environments using ensemble of deep learning methods and motion sensor data","authors":"S.M. Mohidul Islam, Kamrul Hasan Talukder","doi":"10.1016/j.measen.2024.101398","DOIUrl":"10.1016/j.measen.2024.101398","url":null,"abstract":"<div><div>Recognizing human activity plays a crucial role in many applications such as medical care services in smart healthcare environments. Inertial or motion sensors can measure physiognomies such as acceleration and angular velocity of body movement while performing the activities and we can use them to learn the models capable of activity recognition. Over the past decades, many state-of-the-art activity recognition systems have been developed but there is still room to improve. In this paper, we have proposed a novel approach to identify human activity from motion sensor data by employing an enormous analysis of sensor data. Based on data analysis, we yielded quality data by preprocessing using a preprocessing chain for human activity recognition (PC-HAR) which also includes the Synthetic Minority Over-sampling Technique to balance the data of the dataset. As a recognition model, we proposed an ensemble of three different deep learning algorithms, namely, modified DeepConvLSTM, modified InceptionTime, and modified ResNet which is named ‘Ensem-DeepHAR’. The outcome of the proposed model is carried out by stacking predictions from each of the mentioned models and then a Random Forest as a meta-model uses those predictions to recognize the final activity. We evaluated our method on both person-dependent and person-independent cases and achieved 99.31 %, 99.08 %, and 97.52 % accuracies for the former case and 97.95 %, 98.11 %, and 99.51 % accuracies for the latter case using three common benchmark datasets: WISDM_ar_v1.1, PAMAP2, and UCI-HAR respectively. The various performance metrics and measures of experimental results establish the supremacy of the proposed model over the state-of-the-arts.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"36 ","pages":"Article 101398"},"PeriodicalIF":0.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528532","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号