With the rapid development of the Internet of Things(IoT),artificial intelligence,and big data,wastesorting systems must balance high accuracy,low latency,and resource efficiency.This paper presents an edge-friendly i...With the rapid development of the Internet of Things(IoT),artificial intelligence,and big data,wastesorting systems must balance high accuracy,low latency,and resource efficiency.This paper presents an edge-friendly intelligent waste-sorting system that integrates a lightweight visual neural network,a pentagonal-trajectory robotic arm,and IoT connectivity to meet the requirements of real-time response and high accuracy.A lightweight object detection model,YOLO-WasNet(You Only Look Once for Waste Sorting Network),is proposed to optimize performance on edge devices.YOLO-WasNet adopts a lightweight backbone,applies Spatial Pyramid Pooling-Fast(SPPF)and Convolutional Block Attention Module(CBAM),and replaces traditional C3 modules(Cross Stage Partial Bottleneck with 3 convolutions)with efficient C2f blocks(Cross Stage Partial Bottleneck with 2 Convolutions fast)in the neck.Additionally,a Depthwise Parallel Triple-attention Convolution(DPT-Conv)operator is introduced to enhance feature extraction.Experiments on a custom dataset of nine waste categories conforming to Shanghai’s sorting standard(7,917 images)show that YOLO-WasNet achieves a mean average precision(mAP50)of 96.8%and a precision of 96.9%,while reducing computational cost by 30%compared to YOLOv5s.On a Raspberry Pi 4B,inference time is reduced from 480 to 350 ms,ensuring real-time performance.This system offers a practical and viable solution for low-cost,efficient automated waste management in smart cities.展开更多
The integration of renewable energy sources into modern power systems necessitates efficient and robust control strategies to address challenges such as power quality,stability,and dynamic environmental variations.Thi...The integration of renewable energy sources into modern power systems necessitates efficient and robust control strategies to address challenges such as power quality,stability,and dynamic environmental variations.This paper presents a novel sparrow search algorithm(SSA)-tuned proportional-integral(PI)controller for grid-connected photovoltaic(PV)systems,designed to optimize dynamic perfor-mance,energy extraction,and power quality.Key contributions include the development of a systematic SSA-based optimization frame-work for real-time PI parameter tuning,ensuring precise voltage and current regulation,improved maximum power point tracking(MPPT)efficiency,and minimized total harmonic distortion(THD).The proposed approach is evaluated against conventional PSO-based and P&O controllers through comprehensive simulations,demonstrating its superior performance across key metrics:a 39.47%faster response time compared to PSO,a 12.06%increase in peak active power relative to P&O,and a 52.38%reduction in THD,ensuring compliance with IEEE grid standards.Moreover,the SSA-tuned PI controller exhibits enhanced adaptability to dynamic irradiancefluc-tuations,rapid response time,and robust grid integration under varying conditions,making it highly suitable for real-time smart grid applications.This work establishes the SSA-tuned PI controller as a reliable and efficient solution for improving PV system performance in grid-connected scenarios,while also setting the foundation for future research into multi-objective optimization,experimental valida-tion,and hybrid renewable energy systems.展开更多
Significance:Over 80%of cervical cancer cases occur in lower-to-middle income countries(LMIC’s).This is partly because current screening techniques lack affordability,accessibility,and/or reliability for use in LMIC...Significance:Over 80%of cervical cancer cases occur in lower-to-middle income countries(LMIC’s).This is partly because current screening techniques lack affordability,accessibility,and/or reliability for use in LMIC’s.Aim:To develop an optical technique for cervical cancer screening that is affordable,accessible,and reliable for use in LMIC’s.Approach:We developed a portable diffuse reflectance spectroscopy(DRS)system,which costs$<2500 USD to manufacture,and employs a Raspberry Pi to extract the absorption(μα)and reduced scattering(μ′s)coefficients of biological tissue.The system was subject to travel and intentional rough handling.It was further used to capture 320 DRS spectra taken from 64 tissue-mimicking phantoms.Two users collected phantom data,one“expert”,and one“novice”in biomedical optics.The system was also used to collect 335 spectra from colon,small intestine,and rectal tissue of a fresh ex vivo porcine specimen.A previously described artificial intelligence model was used to extract optical properties,and a GradientBoostingClassifier identified the organ of origin for ex vivo spectra.Results:System alignment was robust to intentional rough handling and travel.Phantomμαandμ′s were predicted with average root-mean square error of<10%,regardless of user.Regarding ex vivo data,the system predicted the organ of origin with 80–90%accuracy.Statistical differences between predicted wereμαobserved in all three organs(P<0.001–0.03),and betweenμ′s in two organs(P<0.001–0.07).Conclusions:The DRS system has the potential to be affordable,reliable,and accessible for cervical screening in LMIC’s.展开更多
Background Interconnection of different power systems has a major effect on system stability.This study aims to design an optimal load frequency control(LFC)system based on a proportional-integral(PI)controller for a ...Background Interconnection of different power systems has a major effect on system stability.This study aims to design an optimal load frequency control(LFC)system based on a proportional-integral(PI)controller for a two-area power system.Methods Two areas were connected through an AC tie line in parallel with a DC link to stabilize the frequency of oscillations in both areas.The PI parameters were tuned using the cuckoo search algorithm(CSA)to minimize the integral absolute error(IAE).A state matrix was provided,and the stability of the system was verified by calculating the eigenvalues.The frequency response was investigated for load variation,changes in the generator rate constraint,the turbine time constant,and the governor time constant.Results The CSA was compared with particle swarm optimization algorithm(PSO)under identical conditions.The system was modeled based on a state-space mathematical representation and simulated using MATLAB.The results demonstrated the effectiveness of the proposed controller based on both algorithms and,it is clear that CSA is superior to PSO.Conclusion The CSA algorithm smoothens the system response,reduces ripples,decreases overshooting and settling time,and improves the overall system performance under different disturbances.展开更多
A rudimentary aspect of human life is the health of an individual,and most commonly the wellbeing is impacted in a colossal manner through the consumption of food. The intake of calories therefore is a crucial aspect ...A rudimentary aspect of human life is the health of an individual,and most commonly the wellbeing is impacted in a colossal manner through the consumption of food. The intake of calories therefore is a crucial aspect that must be meticulously monitored. Various health gremlins can be largely circumvented when there is a substantial balance in the number of calories ingested versus the quantity of calories expended.The food calorie estimation is a popular domain of research in recent times and is meticulously analyzed through various image processing and machine learning techniques. However,the need to scrutinize and evaluate the calorie estimation through various platforms and algorithmic approaches aids in providing a deeper insight on the bottlenecks involved,and in improvising the bariatric health of an individual. This paper pivots on comprehending a juxtaposed approach of food calorie estimation through the use of employing Convolution Neural Network(CNN)incorporated in Internet of Things(IoT),and using the Django framework in Python,along with query rule-based training to analyze the subsequent actions to be followed post the consumption of food calories in the constructed webpage. The comparative analysis of the food calorie estimate implemented in both platforms is analyzed for the swiftness of identification,error rate and classification accuracy to appropriately determine the optimal method of use. The simulation results for IoT are carried out using the Raspberry Pi4B model,while the Anaconda prompt is used to run the server holding the web page.展开更多
文摘With the rapid development of the Internet of Things(IoT),artificial intelligence,and big data,wastesorting systems must balance high accuracy,low latency,and resource efficiency.This paper presents an edge-friendly intelligent waste-sorting system that integrates a lightweight visual neural network,a pentagonal-trajectory robotic arm,and IoT connectivity to meet the requirements of real-time response and high accuracy.A lightweight object detection model,YOLO-WasNet(You Only Look Once for Waste Sorting Network),is proposed to optimize performance on edge devices.YOLO-WasNet adopts a lightweight backbone,applies Spatial Pyramid Pooling-Fast(SPPF)and Convolutional Block Attention Module(CBAM),and replaces traditional C3 modules(Cross Stage Partial Bottleneck with 3 convolutions)with efficient C2f blocks(Cross Stage Partial Bottleneck with 2 Convolutions fast)in the neck.Additionally,a Depthwise Parallel Triple-attention Convolution(DPT-Conv)operator is introduced to enhance feature extraction.Experiments on a custom dataset of nine waste categories conforming to Shanghai’s sorting standard(7,917 images)show that YOLO-WasNet achieves a mean average precision(mAP50)of 96.8%and a precision of 96.9%,while reducing computational cost by 30%compared to YOLOv5s.On a Raspberry Pi 4B,inference time is reduced from 480 to 350 ms,ensuring real-time performance.This system offers a practical and viable solution for low-cost,efficient automated waste management in smart cities.
文摘The integration of renewable energy sources into modern power systems necessitates efficient and robust control strategies to address challenges such as power quality,stability,and dynamic environmental variations.This paper presents a novel sparrow search algorithm(SSA)-tuned proportional-integral(PI)controller for grid-connected photovoltaic(PV)systems,designed to optimize dynamic perfor-mance,energy extraction,and power quality.Key contributions include the development of a systematic SSA-based optimization frame-work for real-time PI parameter tuning,ensuring precise voltage and current regulation,improved maximum power point tracking(MPPT)efficiency,and minimized total harmonic distortion(THD).The proposed approach is evaluated against conventional PSO-based and P&O controllers through comprehensive simulations,demonstrating its superior performance across key metrics:a 39.47%faster response time compared to PSO,a 12.06%increase in peak active power relative to P&O,and a 52.38%reduction in THD,ensuring compliance with IEEE grid standards.Moreover,the SSA-tuned PI controller exhibits enhanced adaptability to dynamic irradiancefluc-tuations,rapid response time,and robust grid integration under varying conditions,making it highly suitable for real-time smart grid applications.This work establishes the SSA-tuned PI controller as a reliable and efficient solution for improving PV system performance in grid-connected scenarios,while also setting the foundation for future research into multi-objective optimization,experimental valida-tion,and hybrid renewable energy systems.
文摘Significance:Over 80%of cervical cancer cases occur in lower-to-middle income countries(LMIC’s).This is partly because current screening techniques lack affordability,accessibility,and/or reliability for use in LMIC’s.Aim:To develop an optical technique for cervical cancer screening that is affordable,accessible,and reliable for use in LMIC’s.Approach:We developed a portable diffuse reflectance spectroscopy(DRS)system,which costs$<2500 USD to manufacture,and employs a Raspberry Pi to extract the absorption(μα)and reduced scattering(μ′s)coefficients of biological tissue.The system was subject to travel and intentional rough handling.It was further used to capture 320 DRS spectra taken from 64 tissue-mimicking phantoms.Two users collected phantom data,one“expert”,and one“novice”in biomedical optics.The system was also used to collect 335 spectra from colon,small intestine,and rectal tissue of a fresh ex vivo porcine specimen.A previously described artificial intelligence model was used to extract optical properties,and a GradientBoostingClassifier identified the organ of origin for ex vivo spectra.Results:System alignment was robust to intentional rough handling and travel.Phantomμαandμ′s were predicted with average root-mean square error of<10%,regardless of user.Regarding ex vivo data,the system predicted the organ of origin with 80–90%accuracy.Statistical differences between predicted wereμαobserved in all three organs(P<0.001–0.03),and betweenμ′s in two organs(P<0.001–0.07).Conclusions:The DRS system has the potential to be affordable,reliable,and accessible for cervical screening in LMIC’s.
基金Supported by the Russian Science Foundation(Agreement 23-41-10001,https://rscf.ru/project/23-41-10001/).
文摘Background Interconnection of different power systems has a major effect on system stability.This study aims to design an optimal load frequency control(LFC)system based on a proportional-integral(PI)controller for a two-area power system.Methods Two areas were connected through an AC tie line in parallel with a DC link to stabilize the frequency of oscillations in both areas.The PI parameters were tuned using the cuckoo search algorithm(CSA)to minimize the integral absolute error(IAE).A state matrix was provided,and the stability of the system was verified by calculating the eigenvalues.The frequency response was investigated for load variation,changes in the generator rate constraint,the turbine time constant,and the governor time constant.Results The CSA was compared with particle swarm optimization algorithm(PSO)under identical conditions.The system was modeled based on a state-space mathematical representation and simulated using MATLAB.The results demonstrated the effectiveness of the proposed controller based on both algorithms and,it is clear that CSA is superior to PSO.Conclusion The CSA algorithm smoothens the system response,reduces ripples,decreases overshooting and settling time,and improves the overall system performance under different disturbances.
文摘A rudimentary aspect of human life is the health of an individual,and most commonly the wellbeing is impacted in a colossal manner through the consumption of food. The intake of calories therefore is a crucial aspect that must be meticulously monitored. Various health gremlins can be largely circumvented when there is a substantial balance in the number of calories ingested versus the quantity of calories expended.The food calorie estimation is a popular domain of research in recent times and is meticulously analyzed through various image processing and machine learning techniques. However,the need to scrutinize and evaluate the calorie estimation through various platforms and algorithmic approaches aids in providing a deeper insight on the bottlenecks involved,and in improvising the bariatric health of an individual. This paper pivots on comprehending a juxtaposed approach of food calorie estimation through the use of employing Convolution Neural Network(CNN)incorporated in Internet of Things(IoT),and using the Django framework in Python,along with query rule-based training to analyze the subsequent actions to be followed post the consumption of food calories in the constructed webpage. The comparative analysis of the food calorie estimate implemented in both platforms is analyzed for the swiftness of identification,error rate and classification accuracy to appropriately determine the optimal method of use. The simulation results for IoT are carried out using the Raspberry Pi4B model,while the Anaconda prompt is used to run the server holding the web page.
