G. Vijay Kumar, M. Sreedevi, Arvind Yadav, B. Aruna
Now at present development the entire world using vast variety of smart devices associated among sensors & handful of actuators. There is an enormous progress within the field of electronic communication; processing the data through devices and the bandwidth in internet technologies makes very easy to access and to interact with the variety of devices all over the whole world. There is a wide range research in the area of Internet of Things (IoT) along Cloud Technologies making to build incredible data which are creating from this type of heterogeneous environments and can be able to transform into a valuable knowledge with the help of data mining techniques. The knowledge that is generated will takes a crucial role in making intellectual decisions and also be a best possible resource management and services. In this paper we organized a comprehensive assessment on various data mining techniques engaged with small and large scale IoT applications to make the environment smart.
{"title":"A Comprehensive Assessment on IOT Devices with Data Mining Techniques","authors":"G. Vijay Kumar, M. Sreedevi, Arvind Yadav, B. Aruna","doi":"10.3233/apc210211","DOIUrl":"https://doi.org/10.3233/apc210211","url":null,"abstract":"Now at present development the entire world using vast variety of smart devices associated among sensors & handful of actuators. There is an enormous progress within the field of electronic communication; processing the data through devices and the bandwidth in internet technologies makes very easy to access and to interact with the variety of devices all over the whole world. There is a wide range research in the area of Internet of Things (IoT) along Cloud Technologies making to build incredible data which are creating from this type of heterogeneous environments and can be able to transform into a valuable knowledge with the help of data mining techniques. The knowledge that is generated will takes a crucial role in making intellectual decisions and also be a best possible resource management and services. In this paper we organized a comprehensive assessment on various data mining techniques engaged with small and large scale IoT applications to make the environment smart.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128714555","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}
R. Kabilan, K. Lakshmi Narayanan, M. Venkatesh, V. Vikram Bhaskaran, G. Viswanathan, S.G. Yogesh Rajan
This report outlines a human searching device that takes the form of a robotic car and serves as a backup mechanism for saving lives in the event of a disaster. The temperature sensor, in general, detects the thermal image of the human body, and there has been extensive research into human searching with the gas and humidity sensor. In the intelligent robot device’s study, achieving accurate and reliable human detection and tracking is a difficult challenge. The architecture of human detection and tracking mechanisms over non-overlapping field of views is examined in this paper. To compensate for their respective flaws, a search method is proposed. The proposed method’s rate and accuracy of human detection was tested in an experimental setting. We may guide the robot’s movement by commanding it to move left, right, forward, or backward. We plan to equip the robot with sensors that will enable us to track and detect humans behind the wall.
{"title":"Live Human Detection Robot in Earthquake Conditions","authors":"R. Kabilan, K. Lakshmi Narayanan, M. Venkatesh, V. Vikram Bhaskaran, G. Viswanathan, S.G. Yogesh Rajan","doi":"10.3233/apc210286","DOIUrl":"https://doi.org/10.3233/apc210286","url":null,"abstract":"This report outlines a human searching device that takes the form of a robotic car and serves as a backup mechanism for saving lives in the event of a disaster. The temperature sensor, in general, detects the thermal image of the human body, and there has been extensive research into human searching with the gas and humidity sensor. In the intelligent robot device’s study, achieving accurate and reliable human detection and tracking is a difficult challenge. The architecture of human detection and tracking mechanisms over non-overlapping field of views is examined in this paper. To compensate for their respective flaws, a search method is proposed. The proposed method’s rate and accuracy of human detection was tested in an experimental setting. We may guide the robot’s movement by commanding it to move left, right, forward, or backward. We plan to equip the robot with sensors that will enable us to track and detect humans behind the wall.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126490678","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}
We are at the dawn of quantum era; research efforts are been made on quantum information transmission techniques. Properties of quantum mechanics poses unique challenges in terms of wave collapse function, No cloning theorem and reversible operations. Quantum teleportation and quantum entanglement swapping based architecture are utilized to transmit qubit. In this paper we propose an approach to transmit qubits using controlled NOT gate (CNOT) gates and implement it on quantum machine.
{"title":"Quantum Information Transmission Using CNOT Gate","authors":"Ankit Sharma, M. Nene","doi":"10.3233/apc210219","DOIUrl":"https://doi.org/10.3233/apc210219","url":null,"abstract":"We are at the dawn of quantum era; research efforts are been made on quantum information transmission techniques. Properties of quantum mechanics poses unique challenges in terms of wave collapse function, No cloning theorem and reversible operations. Quantum teleportation and quantum entanglement swapping based architecture are utilized to transmit qubit. In this paper we propose an approach to transmit qubits using controlled NOT gate (CNOT) gates and implement it on quantum machine.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126621110","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}
Communication between soldier at border line is crucial. Existing system used for communication between soldiers at border line in military consumes a lot of power. The greatest difficulties in Indian armed forces operation is the Soldiers are not able to do transmission of messages with headquarters base station controller in case of emergency or when needed any help. Also, the current status and location of the soldiers cannot be detected with this system. The proposed methodology gives us Long Range (LoRa) based medical supervision and emplacement trailing and tracking system for soldiers. This type of advanced design can be mounted on the soldier’s shoe to ensure their safety. In case of death of the soldier, the controller intimates to the camp office control along with soldier’s location. The proposed system includes sensors, GPS, and transmission modules, as well as miniaturized wearable physiological equipment. Hence, it is possible to implement a low-cost mechanism to provide needed help in the battlefield.
{"title":"Regenerative and LoRa Based Trooper Monitoring System for Armed Forces","authors":"Hema R, Dathathreya P, Athitya V, Anumitha B","doi":"10.3233/apc210265","DOIUrl":"https://doi.org/10.3233/apc210265","url":null,"abstract":"Communication between soldier at border line is crucial. Existing system used for communication between soldiers at border line in military consumes a lot of power. The greatest difficulties in Indian armed forces operation is the Soldiers are not able to do transmission of messages with headquarters base station controller in case of emergency or when needed any help. Also, the current status and location of the soldiers cannot be detected with this system. The proposed methodology gives us Long Range (LoRa) based medical supervision and emplacement trailing and tracking system for soldiers. This type of advanced design can be mounted on the soldier’s shoe to ensure their safety. In case of death of the soldier, the controller intimates to the camp office control along with soldier’s location. The proposed system includes sensors, GPS, and transmission modules, as well as miniaturized wearable physiological equipment. Hence, it is possible to implement a low-cost mechanism to provide needed help in the battlefield.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123861112","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}
K. Dinesh, Lakshmi Priya. A, Preethi. T, Sandhya. M, Sangeetha. P
Solar power is the burgeoning method of continual energy. The assignment is designed and carried out the use of dual axis sun tracker system. In order to maximise power era from solar, it’s important to introduce sun ray monitoring systems into solar electricity production. A dual-axis tracker can boom power through monitoring solar rays from switching photovoltaic cells in various directions. These photovoltaic cells can rotate in all directions. The LDR (Light Dependent Resistor) have been used to feel the depth of mild at 30 degree every or at 180 degree general and ship the information to microcontroller. This assignment also can be used to experience rain drop, temperature and humidity using sensor and they may be displayed on LCD. We can save the Solar energy in battery.
{"title":"IoT Based Solar Panel Tracking System with Weather Monitoring System","authors":"K. Dinesh, Lakshmi Priya. A, Preethi. T, Sandhya. M, Sangeetha. P","doi":"10.3233/apc210282","DOIUrl":"https://doi.org/10.3233/apc210282","url":null,"abstract":"Solar power is the burgeoning method of continual energy. The assignment is designed and carried out the use of dual axis sun tracker system. In order to maximise power era from solar, it’s important to introduce sun ray monitoring systems into solar electricity production. A dual-axis tracker can boom power through monitoring solar rays from switching photovoltaic cells in various directions. These photovoltaic cells can rotate in all directions. The LDR (Light Dependent Resistor) have been used to feel the depth of mild at 30 degree every or at 180 degree general and ship the information to microcontroller. This assignment also can be used to experience rain drop, temperature and humidity using sensor and they may be displayed on LCD. We can save the Solar energy in battery.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124403158","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}
R. Ganesh Babu, S. Yuvaraj, A. Vedanthsrivatson, T. Ramachandran, G. Vikram, N. Niffarudeen
IoT systems create a multi-hop organizational structure among mobile devices in required to send on data groups. The remarkable properties of gadgets frameworks cause communications to interconnect among competing handheld devices. Most physiological directing displays don’t believe secure associations all through bundle communication to organize high communicate ability and genetic blocks that also prompts increased delay as well as bundle decreasing in mastermind. Only with continued growth and transformation of IoT networks, attacks on such IoT systems are increasing at an alarming rate. Our purpose will provide researchers with a research resource on latest research patterns in IoT security. As the primary driver of with us research problem concerning IoT security as well as machine learning. This analysis of the literature among the most research literature in IoT security recognized some very key current research which will generate organizational investigations. Only with fast emergence of different IoT threats, it is essential to develop frameworks that could integrate cutting-edge big data analytics and machine learning advanced technologies. Effectiveness are critical quality variables in shaping the best methods and algorithms for detecting IoT threats in real-time or close to real time.
{"title":"Machine Learning Using Big Data Link Stability Based Node Observation for IoT Security","authors":"R. Ganesh Babu, S. Yuvaraj, A. Vedanthsrivatson, T. Ramachandran, G. Vikram, N. Niffarudeen","doi":"10.3233/apc210299","DOIUrl":"https://doi.org/10.3233/apc210299","url":null,"abstract":"IoT systems create a multi-hop organizational structure among mobile devices in required to send on data groups. The remarkable properties of gadgets frameworks cause communications to interconnect among competing handheld devices. Most physiological directing displays don’t believe secure associations all through bundle communication to organize high communicate ability and genetic blocks that also prompts increased delay as well as bundle decreasing in mastermind. Only with continued growth and transformation of IoT networks, attacks on such IoT systems are increasing at an alarming rate. Our purpose will provide researchers with a research resource on latest research patterns in IoT security. As the primary driver of with us research problem concerning IoT security as well as machine learning. This analysis of the literature among the most research literature in IoT security recognized some very key current research which will generate organizational investigations. Only with fast emergence of different IoT threats, it is essential to develop frameworks that could integrate cutting-edge big data analytics and machine learning advanced technologies. Effectiveness are critical quality variables in shaping the best methods and algorithms for detecting IoT threats in real-time or close to real time.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116882335","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}
Raz Mohammad Sahar, Dr. T. Srivinasa Rao, Dr. S. Anuradha, Dr. B. Srinivasa, Rao
Gender classification is amongst the significant problems in the area of signal processing; previously, the problem was handled using different image classification methods, which mainly involve data extraction from a collection of images. Nevertheless, researchers over the globe have recently shown interest in gender classification using voiced features. The classification of gender goes beyond just the frequency and pitch of a human voice, according to a critical study of some of the human vocal attributes. Feature selection, which is from a technical point of view termed dimensionality reduction, is amongst the difficult problems encountered in machine learning. A similar obstacle is encountered when choosing gender particular features—which presents an analytical purpose in analyzing a human’s gender. This work will examine the effectiveness and importance of classification algorithms to the classification of gender via voice problems. Audial data, for example, pitch, frequency, etc., help in determining gender. Machine learning offers encouraging outcomes for classification problems in all domains. An area’s algorithms can be evaluated using performance metrics. This paper evaluates five different classification Algorithms of machine learning based on the classification of gender from audial data. The plan is to recognize gender using five different algorithms: Gradient Boosting, Decision Trees, Random Forest, Neural network, and Support Vector Machine. The major parameter in assessing any algorithm must be performance. Misclassifying rate ratio should not be more in classifying problems. In business markets, the location and gender of people are essentially related to AdSense. This research aims at comparing various machine learning algorithms in order to find the most suitable fitting for gender identification in audial data.
{"title":"Performance Analysis of ML Algorithms to Detect Gender Based on Voice","authors":"Raz Mohammad Sahar, Dr. T. Srivinasa Rao, Dr. S. Anuradha, Dr. B. Srinivasa, Rao","doi":"10.3233/apc210192","DOIUrl":"https://doi.org/10.3233/apc210192","url":null,"abstract":"Gender classification is amongst the significant problems in the area of signal processing; previously, the problem was handled using different image classification methods, which mainly involve data extraction from a collection of images. Nevertheless, researchers over the globe have recently shown interest in gender classification using voiced features. The classification of gender goes beyond just the frequency and pitch of a human voice, according to a critical study of some of the human vocal attributes. Feature selection, which is from a technical point of view termed dimensionality reduction, is amongst the difficult problems encountered in machine learning. A similar obstacle is encountered when choosing gender particular features—which presents an analytical purpose in analyzing a human’s gender. This work will examine the effectiveness and importance of classification algorithms to the classification of gender via voice problems. Audial data, for example, pitch, frequency, etc., help in determining gender. Machine learning offers encouraging outcomes for classification problems in all domains. An area’s algorithms can be evaluated using performance metrics. This paper evaluates five different classification Algorithms of machine learning based on the classification of gender from audial data. The plan is to recognize gender using five different algorithms: Gradient Boosting, Decision Trees, Random Forest, Neural network, and Support Vector Machine. The major parameter in assessing any algorithm must be performance. Misclassifying rate ratio should not be more in classifying problems. In business markets, the location and gender of people are essentially related to AdSense. This research aims at comparing various machine learning algorithms in order to find the most suitable fitting for gender identification in audial data.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123721142","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}
Swagata B. Sarkar, Siva Nagappan, Shafin Kadhir Badhusha
Millimetre Wave frequencies (30–300 GHz) can be used for different major applications of modern world like telecommunications, security screening, imaging, automotive radars, military applications, remote sensing, radio astronomy and many more. The internationally reserved frequency spectrum is used for Radio Frequency Energy. In this work 64 GHz antennas are compared with different design and a comparative study is taken. In this work Microstrip patch antenna with carpet architecture, and fractal island are designed and compared. The general comparative parameters for antenna are directivity, gain, return loss, bandwidth, specific absorption rate etc. After the comparison, it is found that return loss gave better result for carpet design at 64 GHz compare to fractal island design.
{"title":"Design and Analysis of 64 GHz Millimetre Wave Microstrip Patch Antenna","authors":"Swagata B. Sarkar, Siva Nagappan, Shafin Kadhir Badhusha","doi":"10.3233/apc210262","DOIUrl":"https://doi.org/10.3233/apc210262","url":null,"abstract":"Millimetre Wave frequencies (30–300 GHz) can be used for different major applications of modern world like telecommunications, security screening, imaging, automotive radars, military applications, remote sensing, radio astronomy and many more. The internationally reserved frequency spectrum is used for Radio Frequency Energy. In this work 64 GHz antennas are compared with different design and a comparative study is taken. In this work Microstrip patch antenna with carpet architecture, and fractal island are designed and compared. The general comparative parameters for antenna are directivity, gain, return loss, bandwidth, specific absorption rate etc. After the comparison, it is found that return loss gave better result for carpet design at 64 GHz compare to fractal island design.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121226796","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}
In today’s era Big data classification is a very crucial and equally widely arise issue is many applications. Not only engineering applications but also in social, agricultural, banking, educational and many more applications are there in science and engineering where accurate big data classification is required. We proposed a very novel and efficient methodology for big data classification using Deep stack encoder and Rider chaotic biogeography algorithms. Our proposed algorithms are the combinations of two algorithms. First one is Rider Optimization algorithm and second one is chaotic biogeography-based optimization algorithm. So, we named it as RCBO which is integration is ROA and CBBO. Our proposed system also uses the Deep stack auto encoder for the purpose of training the system which actually produced the accurate classification. The Apache spark platform is used initial distribution of the data from master node to slave nodes. Our proposed system is tested and executed on the UCI Machine learning data set which gives the excellent results while comparing with other algorithms such as KNN classification, Extreme Learning Machine Random Forest algorithms.
{"title":"DSAE – Deep Stack Auto Encoder and RCBO – Rider Chaotic Biogeography Optimization Algorithm for Big Data Classification","authors":"A. Brahmane, D. B. C. Krishna","doi":"10.3233/apc210198","DOIUrl":"https://doi.org/10.3233/apc210198","url":null,"abstract":"In today’s era Big data classification is a very crucial and equally widely arise issue is many applications. Not only engineering applications but also in social, agricultural, banking, educational and many more applications are there in science and engineering where accurate big data classification is required. We proposed a very novel and efficient methodology for big data classification using Deep stack encoder and Rider chaotic biogeography algorithms. Our proposed algorithms are the combinations of two algorithms. First one is Rider Optimization algorithm and second one is chaotic biogeography-based optimization algorithm. So, we named it as RCBO which is integration is ROA and CBBO. Our proposed system also uses the Deep stack auto encoder for the purpose of training the system which actually produced the accurate classification. The Apache spark platform is used initial distribution of the data from master node to slave nodes. Our proposed system is tested and executed on the UCI Machine learning data set which gives the excellent results while comparing with other algorithms such as KNN classification, Extreme Learning Machine Random Forest algorithms.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125589505","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}
Mayuri Karvande, Apoorv Katkar, Nikhil Koli, Amit D. Joshi, S. Sawant
In today’s world, the security of every individual has become an important aspect. There is a need for constant monitoring in public places. A Manual operating camera system is an unreliable and very basic and poor method for this purpose. Intelligent Video Surveillance is an approach where multiple CCTVs constantly record the scenes and proper algorithms are deployed in order to detect and monitor activities. Deep Learning frameworks and algorithms like Kera’s, YOLO, Convolutional Neural Networks or backbones for image detection like VGG16, Mobile net, Resnet101 have been used for human and weapon detection. The paper focuses on deep learning techniques and threading to collectively develop a Parallel Deep Learning Framework for Video Surveillance that aims at striking the right balance between accuracy and system performance or stability. Threading is used in terms of implementation of a uniquely proposed Dynamic Selection Algorithm that uses two backbones for object detection and switches between them based on the queue status for achieving system stability. A uniquely designed logistic regression filter is also implemented that boosts the system performance.
在当今世界，每个人的安全已经成为一个重要的方面。公共场所需要持续的监控。手动操作相机系统是一种不可靠的、非常基本的、很差的方法。智能视频监控是一种多台闭路电视持续记录场景并部署适当算法以检测和监控活动的方法。深度学习框架和算法，如Kera, YOLO，卷积神经网络或骨干图像检测，如VGG16, Mobile net, Resnet101已用于人类和武器检测。本文重点研究了深度学习技术和线程，共同开发了一个用于视频监控的并行深度学习框架，旨在在准确性和系统性能或稳定性之间取得适当的平衡。线程用于实现一种独特的动态选择算法，该算法使用两个主干网进行对象检测，并根据队列状态在它们之间切换，以实现系统稳定性。设计独特的逻辑回归滤波器，提高了系统的性能。
{"title":"Parallel Deep Learning Framework for Video Surveillance System","authors":"Mayuri Karvande, Apoorv Katkar, Nikhil Koli, Amit D. Joshi, S. Sawant","doi":"10.3233/apc210191","DOIUrl":"https://doi.org/10.3233/apc210191","url":null,"abstract":"In today’s world, the security of every individual has become an important aspect. There is a need for constant monitoring in public places. A Manual operating camera system is an unreliable and very basic and poor method for this purpose. Intelligent Video Surveillance is an approach where multiple CCTVs constantly record the scenes and proper algorithms are deployed in order to detect and monitor activities. Deep Learning frameworks and algorithms like Kera’s, YOLO, Convolutional Neural Networks or backbones for image detection like VGG16, Mobile net, Resnet101 have been used for human and weapon detection. The paper focuses on deep learning techniques and threading to collectively develop a Parallel Deep Learning Framework for Video Surveillance that aims at striking the right balance between accuracy and system performance or stability. Threading is used in terms of implementation of a uniquely proposed Dynamic Selection Algorithm that uses two backbones for object detection and switches between them based on the queue status for achieving system stability. A uniquely designed logistic regression filter is also implemented that boosts the system performance.","PeriodicalId":429440,"journal":{"name":"Recent Trends in Intensive Computing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126992449","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：