Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767159
Venkata Deepika Potu, Venkataiah Sunku, Mounika M., Priya S. B. M.
The fifth-generation wireless networks deployment has stared since 2020. We consider a Reconfigurable Intelligent Surface (RIS) aided multi-user multiple-input single-output (MISO) downlink system in this work. The RIS elements phase shift and beamforming matrices are optimized together to achieve maximum sum rate. The iterative optimization algorithms are adopted in most of the prior works to get suboptimal solutions, which are computationally complex. In this work, a deep learning based approach is proposed to decrease computational complexity for integrated active and passive beamforming with adequate performance. We propose an unsupervised two-stage neural network that can be trained and implemented online for real-time prediction.
{"title":"A Deep Learning Scheme for Integrated Active and Passive Beamforming in Reconfigurable Intelligent Surface Aided Wireless MISO Networks","authors":"Venkata Deepika Potu, Venkataiah Sunku, Mounika M., Priya S. B. M.","doi":"10.1109/wispnet54241.2022.9767159","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767159","url":null,"abstract":"The fifth-generation wireless networks deployment has stared since 2020. We consider a Reconfigurable Intelligent Surface (RIS) aided multi-user multiple-input single-output (MISO) downlink system in this work. The RIS elements phase shift and beamforming matrices are optimized together to achieve maximum sum rate. The iterative optimization algorithms are adopted in most of the prior works to get suboptimal solutions, which are computationally complex. In this work, a deep learning based approach is proposed to decrease computational complexity for integrated active and passive beamforming with adequate performance. We propose an unsupervised two-stage neural network that can be trained and implemented online for real-time prediction.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131053416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767103
Nithiyasri M., Ananthi G., Thiruvengadam S. J.
Diabetic Retinopathy (DR) is an ophthalmic condition in which the retinal blood vessels of the eye are repaired. The presence of a large amount of glucose in the blood vessels causes DR, which alters the microvasculature of the retina. The early warning signs of DR aid in the detection of visual loss. In order to anticipate DR, there are numerous processes to go through. Normal, Mild, Moderate, Severe, and Proliferative are the phases. The DR phases are determined by the type of retinal lesions that occur. To detect this deadly condition, the ophthalmologist examines the patient's fundus images. To detect DR phases, computer vision algorithms are presented. These techniques, on the other hand, are unable to encode the complicated Macular Edema characteristic and categorize DR stages with a lower level of accuracy. To encode the macular edema feature and improve classification in all five stages of DR, a ResNet 101 model with a hundred and one deep Convolutional Neural Network (CNN) is given in this study. The training set for analysis is 413 (80%) while the training set for analysis is 103 (20%). The suggested experimental automated approach for DR detection is critical for early identification of DR. The suggested deep learning method outperforms existing algorithms in terms of accuracy. The investigation was carried out using the publicly accessible fundus Indian DR Datasets. The findings demonstrate that the proposed method accurately detects different phases of DR and outperforms existing strategies. ResNet 101 deep CNN is implemented tested, and the accuracy of the method is compared to that of the ResNet 50 algorithm.
{"title":"Improved Classification of Stages in Diabetic Retinopathy Disease using Deep Learning Algorithm","authors":"Nithiyasri M., Ananthi G., Thiruvengadam S. J.","doi":"10.1109/wispnet54241.2022.9767103","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767103","url":null,"abstract":"Diabetic Retinopathy (DR) is an ophthalmic condition in which the retinal blood vessels of the eye are repaired. The presence of a large amount of glucose in the blood vessels causes DR, which alters the microvasculature of the retina. The early warning signs of DR aid in the detection of visual loss. In order to anticipate DR, there are numerous processes to go through. Normal, Mild, Moderate, Severe, and Proliferative are the phases. The DR phases are determined by the type of retinal lesions that occur. To detect this deadly condition, the ophthalmologist examines the patient's fundus images. To detect DR phases, computer vision algorithms are presented. These techniques, on the other hand, are unable to encode the complicated Macular Edema characteristic and categorize DR stages with a lower level of accuracy. To encode the macular edema feature and improve classification in all five stages of DR, a ResNet 101 model with a hundred and one deep Convolutional Neural Network (CNN) is given in this study. The training set for analysis is 413 (80%) while the training set for analysis is 103 (20%). The suggested experimental automated approach for DR detection is critical for early identification of DR. The suggested deep learning method outperforms existing algorithms in terms of accuracy. The investigation was carried out using the publicly accessible fundus Indian DR Datasets. The findings demonstrate that the proposed method accurately detects different phases of DR and outperforms existing strategies. ResNet 101 deep CNN is implemented tested, and the accuracy of the method is compared to that of the ResNet 50 algorithm.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134054045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767148
Athisaya Anushya T., L. T., Manimekalai T.
Future demands on higher data rate services and green communication systems expect higher spectral efficiency and energy efficiency respectively. The OFDM-IM is considered as one of the solutions in this direction. Even though it offers better energy efficiency, it requires further improvements in spectral efficiency particularly on the use of higher-order modulations. The recent research interests provide solutions by increasing the number of bits used for indexing. In this work, a zero padded approach has been used to improve energy efficiency and dual indexing with tri-mode has been introduced to improve the spectral efficiency by 0.25 bpcu for 50% of carrier use. The simulation results have proved the improvement in error performance along with an increment in spectral efficiency.
{"title":"Zero Padded Dual Index Trimode OFDM-IM","authors":"Athisaya Anushya T., L. T., Manimekalai T.","doi":"10.1109/wispnet54241.2022.9767148","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767148","url":null,"abstract":"Future demands on higher data rate services and green communication systems expect higher spectral efficiency and energy efficiency respectively. The OFDM-IM is considered as one of the solutions in this direction. Even though it offers better energy efficiency, it requires further improvements in spectral efficiency particularly on the use of higher-order modulations. The recent research interests provide solutions by increasing the number of bits used for indexing. In this work, a zero padded approach has been used to improve energy efficiency and dual indexing with tri-mode has been introduced to improve the spectral efficiency by 0.25 bpcu for 50% of carrier use. The simulation results have proved the improvement in error performance along with an increment in spectral efficiency.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767173
Sivasankar G., Aarthy Prem Anand, Susela Sruthi K.
It is extremely difficult to monitor and manage infected patients during the COVID-19 pandemic. This IoT wearable monitoring gadget is developed to measure the indicators of COVID-19. Patients' GPS data is used to notify medical authorities of their infection status. A wearable sensor is affixed to the body and connected to an edge node in the IoT cloud where the data is processed and analyzed in order to monitor health. A temperature sensor, GPS, SpO2 sensor, IR sensor, and accelerometer make up the system. The Arduino UNO processor is used in this gadget. The patient's body temperature is obtained using the temperature sensor. The location of the infected patient is tracked using a GPS sensor. Human movement is detected using an accelerometer. The SpO2 sensor measures the blood oxygen saturation level. The heart rate is detected using a pulse sensor. Information about preventive measures, warnings, and actions is stored in a cloud database. COVID-19 symptom readings are measured using this approach for monitoring and analysis.
{"title":"Internet of Things based Wearable Smart Gadget for COVID-19 Patients Monitoring","authors":"Sivasankar G., Aarthy Prem Anand, Susela Sruthi K.","doi":"10.1109/wispnet54241.2022.9767173","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767173","url":null,"abstract":"It is extremely difficult to monitor and manage infected patients during the COVID-19 pandemic. This IoT wearable monitoring gadget is developed to measure the indicators of COVID-19. Patients' GPS data is used to notify medical authorities of their infection status. A wearable sensor is affixed to the body and connected to an edge node in the IoT cloud where the data is processed and analyzed in order to monitor health. A temperature sensor, GPS, SpO2 sensor, IR sensor, and accelerometer make up the system. The Arduino UNO processor is used in this gadget. The patient's body temperature is obtained using the temperature sensor. The location of the infected patient is tracked using a GPS sensor. Human movement is detected using an accelerometer. The SpO2 sensor measures the blood oxygen saturation level. The heart rate is detected using a pulse sensor. Information about preventive measures, warnings, and actions is stored in a cloud database. COVID-19 symptom readings are measured using this approach for monitoring and analysis.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114776789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767176
Harsh J. Kiratsata, Deep P. Raval, Payal K. Viras, Punit Lalwani, Himanshu Patel, Panchal S. D.
Nowadays, in this COVID era, work from home is quietly more preferred than work from the office. Due to this, the need for a firewall has been increased day by day. Every organization uses the firewall to secure their network and create VPN servers to allow their employees to work from home. Due to this, the security of the firewall plays a crucial role. In this paper, we have compared the two most popular open-source firewalls named pfSense and OPNSense. We have examined the security they provide by default without any other attachment. To do this, we performed four different attacks on the firewalls and compared the results. As a result, we have observed that both provide the same security still pfSense has a slight edge when an attacker tries to perform a Brute force attack over OPNSense.
{"title":"Behaviour Analysis of Open-Source Firewalls Under Security Crisis","authors":"Harsh J. Kiratsata, Deep P. Raval, Payal K. Viras, Punit Lalwani, Himanshu Patel, Panchal S. D.","doi":"10.1109/wispnet54241.2022.9767176","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767176","url":null,"abstract":"Nowadays, in this COVID era, work from home is quietly more preferred than work from the office. Due to this, the need for a firewall has been increased day by day. Every organization uses the firewall to secure their network and create VPN servers to allow their employees to work from home. Due to this, the security of the firewall plays a crucial role. In this paper, we have compared the two most popular open-source firewalls named pfSense and OPNSense. We have examined the security they provide by default without any other attachment. To do this, we performed four different attacks on the firewalls and compared the results. As a result, we have observed that both provide the same security still pfSense has a slight edge when an attacker tries to perform a Brute force attack over OPNSense.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114834735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767150
Dipesh Singh, Garima Tiwari
An advanced, effective, and novel antenna array is presented in this paper. To improve the antenna's performance, a multilayer frequency selective surface (FSS) was integrated. This suggested FSS is accomplished utilizing periodic split-ring resonators (SSR). This multilayer FSS was superimposed over the antenna at a height of 5mm from the ground plane of the antenna. This gap created the fringing field, which reluctantly improved the characteristics by 15dB. A wideband of 27GHz was achieved for which RL is less than −10db for the entire range of frequencies. The proposed antenna is designed for 5G applications.
{"title":"FSS Incorporated MIMO Antenna for 5G and Wideband Applications","authors":"Dipesh Singh, Garima Tiwari","doi":"10.1109/wispnet54241.2022.9767150","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767150","url":null,"abstract":"An advanced, effective, and novel antenna array is presented in this paper. To improve the antenna's performance, a multilayer frequency selective surface (FSS) was integrated. This suggested FSS is accomplished utilizing periodic split-ring resonators (SSR). This multilayer FSS was superimposed over the antenna at a height of 5mm from the ground plane of the antenna. This gap created the fringing field, which reluctantly improved the characteristics by 15dB. A wideband of 27GHz was achieved for which RL is less than −10db for the entire range of frequencies. The proposed antenna is designed for 5G applications.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123687822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767119
Ishita Gupta, Sarishma Dangi, Sachin Sharma
Augmented reality and virtual reality are becoming increasingly prominent in academia and industry. A technology that superimposes additional information on top of the real world is known as augmented reality. Since augmented reality is inextricably linked to the natural world, it is regarded as a partially immersive component of reality. However, unlike virtual reality, augmented reality does not provide a completely immersive experience. Virtual reality has long been depicted as a medium defined by a bevy of technological devices, such as laptops, head-mounted displays, microphones, and motion-sensing gloves. The goal of this research is to conduct a comprehensive assessment of the literature on augmented reality and virtual reality-based Human Machine Interfaces in healthcare. The concept of a smart healthcare environment is gaining traction in industry and product development, resulting in the development of new and more intelligent solutions, technologies, and architectures. Cloud computing, the Internet of Things (IoT), data analytics, artificial intelligence, machine learning, augmented reality, and virtual reality are all being used by manufacturers and developers in their manufacturing and overall operations. The research will also examine the advantages of augmented reality in the medical field, as well as the problems these technologies face and where they are heading in the future.
{"title":"Augmented Reality Based Human-Machine Interfaces in Healthcare Environment: Benefits, Challenges, and Future Trends","authors":"Ishita Gupta, Sarishma Dangi, Sachin Sharma","doi":"10.1109/wispnet54241.2022.9767119","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767119","url":null,"abstract":"Augmented reality and virtual reality are becoming increasingly prominent in academia and industry. A technology that superimposes additional information on top of the real world is known as augmented reality. Since augmented reality is inextricably linked to the natural world, it is regarded as a partially immersive component of reality. However, unlike virtual reality, augmented reality does not provide a completely immersive experience. Virtual reality has long been depicted as a medium defined by a bevy of technological devices, such as laptops, head-mounted displays, microphones, and motion-sensing gloves. The goal of this research is to conduct a comprehensive assessment of the literature on augmented reality and virtual reality-based Human Machine Interfaces in healthcare. The concept of a smart healthcare environment is gaining traction in industry and product development, resulting in the development of new and more intelligent solutions, technologies, and architectures. Cloud computing, the Internet of Things (IoT), data analytics, artificial intelligence, machine learning, augmented reality, and virtual reality are all being used by manufacturers and developers in their manufacturing and overall operations. The research will also examine the advantages of augmented reality in the medical field, as well as the problems these technologies face and where they are heading in the future.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130393240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767181
R Rishikesh Mahadevan, A. A., P. M, R. R.
Parking slots in closed spaces like shopping malls and multistoried building etc. usually find it difficult to keep track of free space and required manual labor to do the same. This work aims at creating a parking system with multiple slots to mitigate the problem of tight parking spaces and high manual efforts to keep track of free space within a constrained area. The overall idea focuses mainly on the design of a car parking system by simulating Verilog code using the ModelSim software. Synthesis is targeted using Xilinx-20.1 Integrated Synthesis Environment (ISE). Asynchronized system of parking slots for vehicles using the concept of Finite State Machine are utilized. The proposed system shows less area utilization.
{"title":"Multi-Car Parking System Using Verilog","authors":"R Rishikesh Mahadevan, A. A., P. M, R. R.","doi":"10.1109/wispnet54241.2022.9767181","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767181","url":null,"abstract":"Parking slots in closed spaces like shopping malls and multistoried building etc. usually find it difficult to keep track of free space and required manual labor to do the same. This work aims at creating a parking system with multiple slots to mitigate the problem of tight parking spaces and high manual efforts to keep track of free space within a constrained area. The overall idea focuses mainly on the design of a car parking system by simulating Verilog code using the ModelSim software. Synthesis is targeted using Xilinx-20.1 Integrated Synthesis Environment (ISE). Asynchronized system of parking slots for vehicles using the concept of Finite State Machine are utilized. The proposed system shows less area utilization.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134421196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767128
V. M, D. R., P. S.
One of the major issues in the modern environment of complex data systems is authentication; several strategies are used to address this issue. Face recognition is regarded as one of the most dependable solutions. This research proposes a convolution neural network (CNN) for face detection and recognition that outperforms existing methods. To extract acceptable features from images, machine learning approaches necessitate expert knowledge and experience. To categorize images in an automated manner, a proposed deep learning-based strategy can be employed, which uses channel wise separable CNN to extract image features and also uses Support Vector Machine (SVM) and Softmax classifiers to classify the images. Face recognition was used to verify the accuracy of the proposed system by tracking student attendance. The public of the market tagged faces in the wild (LFW) dataset is used to train the face recognition system. On the testing data, the proposed system had a 98.11 percent accuracy rate. Furthermore, the data created by the smart classroom is processed and transferred through the use of an IoT-based edge computing approach.
{"title":"Group Face Recognition Smart Attendance System Using Convolution Neural Network","authors":"V. M, D. R., P. S.","doi":"10.1109/wispnet54241.2022.9767128","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767128","url":null,"abstract":"One of the major issues in the modern environment of complex data systems is authentication; several strategies are used to address this issue. Face recognition is regarded as one of the most dependable solutions. This research proposes a convolution neural network (CNN) for face detection and recognition that outperforms existing methods. To extract acceptable features from images, machine learning approaches necessitate expert knowledge and experience. To categorize images in an automated manner, a proposed deep learning-based strategy can be employed, which uses channel wise separable CNN to extract image features and also uses Support Vector Machine (SVM) and Softmax classifiers to classify the images. Face recognition was used to verify the accuracy of the proposed system by tracking student attendance. The public of the market tagged faces in the wild (LFW) dataset is used to train the face recognition system. On the testing data, the proposed system had a 98.11 percent accuracy rate. Furthermore, the data created by the smart classroom is processed and transferred through the use of an IoT-based edge computing approach.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134183700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767152
Arjun S. Dileep, Nabilah S. S., S. S, Farhana K., Surumy S.
Suspicious human activity detection is a major area of research and development that focuses on sophisticated machine learning techniques to reduce monitoring costs while enhancing safety. Since it is difficult for people to continually monitor public spaces, we need a real-time intelligent human activity recognition system that can identify suspicious activities. Current systems use low-accurate complex algorithms and techniques, making the system less reliable. This paper proposes a real-time suspicious human activity recognition with high accuracy by introducing a Convolutional Neural Network and using the 2D pose estimation technique to the system. This system can be used for home security, hospitals, and other areas of surveillance. Here, we are extracting skeletal images of humans from the input video frames using 2D pose estimation to identify the pose of humans in the videos. These poses are then passed to a pre-trained Convolutional Neural Network to classify different activities of humans like trespassing or not trespassing, fall or not fall, fighting, etc. After analyzing the pixels and activities, an alert can be produced through alarms, messages to phones, email the footage to the owner or security professional, and other techniques to prevent unusual activities. This system can be used in public places like shopping malls, railway stations, public roads, and even in homes, universities, and educational institutions.
{"title":"Suspicious Human Activity Recognition using 2D Pose Estimation and Convolutional Neural Network","authors":"Arjun S. Dileep, Nabilah S. S., S. S, Farhana K., Surumy S.","doi":"10.1109/wispnet54241.2022.9767152","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767152","url":null,"abstract":"Suspicious human activity detection is a major area of research and development that focuses on sophisticated machine learning techniques to reduce monitoring costs while enhancing safety. Since it is difficult for people to continually monitor public spaces, we need a real-time intelligent human activity recognition system that can identify suspicious activities. Current systems use low-accurate complex algorithms and techniques, making the system less reliable. This paper proposes a real-time suspicious human activity recognition with high accuracy by introducing a Convolutional Neural Network and using the 2D pose estimation technique to the system. This system can be used for home security, hospitals, and other areas of surveillance. Here, we are extracting skeletal images of humans from the input video frames using 2D pose estimation to identify the pose of humans in the videos. These poses are then passed to a pre-trained Convolutional Neural Network to classify different activities of humans like trespassing or not trespassing, fall or not fall, fighting, etc. After analyzing the pixels and activities, an alert can be produced through alarms, messages to phones, email the footage to the owner or security professional, and other techniques to prevent unusual activities. This system can be used in public places like shopping malls, railway stations, public roads, and even in homes, universities, and educational institutions.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132480464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：