Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009376
Jyothi Johnson, R. Chitra, A. Anusha Bamini
The latent ridge impressions (Finger Prints (FPs)) and DNA profiling have been regarded as mutually exclusive for the analysis of Forensic Evidence (FE). However, these dual evaluations were excluded due to the processing and sensitivity problems. Thus, effectual FP Analysis (FPA) and DNA profiling from similar latent evidence were proposed for forensic applications. The features from the FP and the DNA components within the FP are regarded here. The features were merged; then, it is inputted to the new Zone-out Regularization-centric Improved Artificial Neural Network (ZR-IANN) that exhibited precise predictions of whether the suspect is an imposter or a genuine one. The overall recognition accuracy of 98.54% was attained by the proposed technique. Hence, the proposed methodology surpasses other prevailing techniques.
{"title":"An Efficient Fingerprint Analysis and DNA Profiling from the Same Latent Evidence for the Forensic Applications","authors":"Jyothi Johnson, R. Chitra, A. Anusha Bamini","doi":"10.1109/STCR55312.2022.10009376","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009376","url":null,"abstract":"The latent ridge impressions (Finger Prints (FPs)) and DNA profiling have been regarded as mutually exclusive for the analysis of Forensic Evidence (FE). However, these dual evaluations were excluded due to the processing and sensitivity problems. Thus, effectual FP Analysis (FPA) and DNA profiling from similar latent evidence were proposed for forensic applications. The features from the FP and the DNA components within the FP are regarded here. The features were merged; then, it is inputted to the new Zone-out Regularization-centric Improved Artificial Neural Network (ZR-IANN) that exhibited precise predictions of whether the suspect is an imposter or a genuine one. The overall recognition accuracy of 98.54% was attained by the proposed technique. Hence, the proposed methodology surpasses other prevailing techniques.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131918795","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009372
Dharsinala Harikrishna, N. U. Kumar
Diabetic Retinopathy (DR) becomes the crucial disease in different disease groups and millions of people suffering with it every year rapidly. However, the conventional methods are failed to classify the DR in early stage due to complex architecture of eye fundus image. Therefore, this article is focused on implementation of deep learning convolutional neural network (DLCNN) based artificial intelligence approach for classifying multiple stages of DR. Initially, the hybrid features are extracted from IDRID dataset by using Local Binary Pattern (LBP), Local Gaussian Difference Extrema Pattern (LGDEP), and Histogram of Oriented Gradient (HOG) descriptors. Further, Linear Discriminant Analysis (LDA) is used to select the inter disease and intra disease dependent based optimal features. Then, DLCNN model is trained with these features for classification of DR grades for each test retinal image. The simulation results show that proposed DR classification results shows better subjective and object performance as compared to conventional machine learning and deep learning methods.
{"title":"Artificial Intelligence System for Classification of Diabetic Retinopathy","authors":"Dharsinala Harikrishna, N. U. Kumar","doi":"10.1109/STCR55312.2022.10009372","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009372","url":null,"abstract":"Diabetic Retinopathy (DR) becomes the crucial disease in different disease groups and millions of people suffering with it every year rapidly. However, the conventional methods are failed to classify the DR in early stage due to complex architecture of eye fundus image. Therefore, this article is focused on implementation of deep learning convolutional neural network (DLCNN) based artificial intelligence approach for classifying multiple stages of DR. Initially, the hybrid features are extracted from IDRID dataset by using Local Binary Pattern (LBP), Local Gaussian Difference Extrema Pattern (LGDEP), and Histogram of Oriented Gradient (HOG) descriptors. Further, Linear Discriminant Analysis (LDA) is used to select the inter disease and intra disease dependent based optimal features. Then, DLCNN model is trained with these features for classification of DR grades for each test retinal image. The simulation results show that proposed DR classification results shows better subjective and object performance as compared to conventional machine learning and deep learning methods.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134138502","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009539
R. K, T. Thirunavukkarasu, P. S, Puvisha. C, R. S
In this paper, we discuss overcoming the traditional invasive technique to capture glucose levels and overcome this by using a non-invasive method to monitor glucose levels and other related parameters to give doctors a clear insight on diabetes. The clearer picture which we mention includes the implementation of Machine Learning algorithms for the early prediction and diagnosis of diabetes. The parameters include glucose levels, temperature, and heart rate and it may be very essential to reveal diverse clinical parameters. In modern healthcare systems, the use of IoT plays a vital role in the accessibility and monitoring of diverse patient data. The Internet of things serves as a catalyst for healthcare and performs an outstanding position in a huge variety of healthcare applications. In this venture, the microcontroller is used as a gateway to speak to the diverse sensors which include a temperature sensor and heartbeat sensor, glucose sensor. The microcontroller processes the sensor records and sends them to the cloud and subsequently presents the real-time data tracking of the parameters such as heart rate, temperature, and glucose levels for doctors. The records may be accessed each time with the aid. The records which are stored in the cloud are later used in Machine Learning algorithms to monitor the glucose levels and get a valuable prediction out of it for further monitoring purposes.
{"title":"Machine Learning Based Non-Invasive Glucose Observation for Diabetes","authors":"R. K, T. Thirunavukkarasu, P. S, Puvisha. C, R. S","doi":"10.1109/STCR55312.2022.10009539","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009539","url":null,"abstract":"In this paper, we discuss overcoming the traditional invasive technique to capture glucose levels and overcome this by using a non-invasive method to monitor glucose levels and other related parameters to give doctors a clear insight on diabetes. The clearer picture which we mention includes the implementation of Machine Learning algorithms for the early prediction and diagnosis of diabetes. The parameters include glucose levels, temperature, and heart rate and it may be very essential to reveal diverse clinical parameters. In modern healthcare systems, the use of IoT plays a vital role in the accessibility and monitoring of diverse patient data. The Internet of things serves as a catalyst for healthcare and performs an outstanding position in a huge variety of healthcare applications. In this venture, the microcontroller is used as a gateway to speak to the diverse sensors which include a temperature sensor and heartbeat sensor, glucose sensor. The microcontroller processes the sensor records and sends them to the cloud and subsequently presents the real-time data tracking of the parameters such as heart rate, temperature, and glucose levels for doctors. The records may be accessed each time with the aid. The records which are stored in the cloud are later used in Machine Learning algorithms to monitor the glucose levels and get a valuable prediction out of it for further monitoring purposes.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122073376","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009554
A. Pandiaraj, N. Vinothkumar, R. Venkatesan
Cloud computing has the ability to work in a predestined manner. The main technology is virtualization. This generalizes the physical infrastructure. This helps us to manage easily. In this work, based on the needs the allocated resources are used. It supports the green computing concept. Dealing with the clients request is difficult for the interest of asset allotment. Virtual Machine is utilized for asset provisioning. By utilizing the virtualization climate will lessen the jib reaction time as well as it executes the undertaking as per the accessibility of assets. The viable and dynamic usage of the assets. This would help to balance the load and situations. The implementation uses the co-location approach. It is used to combine the small spaces and improve the performance of server. To reduce the wrong data based on time to live property. We use self-destruction approach. By developing the online prediction model we can estimate the sizes to reduce the task at run time.
{"title":"Virtual Machine Migration for Infrastructure Service in Cloud Network","authors":"A. Pandiaraj, N. Vinothkumar, R. Venkatesan","doi":"10.1109/STCR55312.2022.10009554","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009554","url":null,"abstract":"Cloud computing has the ability to work in a predestined manner. The main technology is virtualization. This generalizes the physical infrastructure. This helps us to manage easily. In this work, based on the needs the allocated resources are used. It supports the green computing concept. Dealing with the clients request is difficult for the interest of asset allotment. Virtual Machine is utilized for asset provisioning. By utilizing the virtualization climate will lessen the jib reaction time as well as it executes the undertaking as per the accessibility of assets. The viable and dynamic usage of the assets. This would help to balance the load and situations. The implementation uses the co-location approach. It is used to combine the small spaces and improve the performance of server. To reduce the wrong data based on time to live property. We use self-destruction approach. By developing the online prediction model we can estimate the sizes to reduce the task at run time.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123623207","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009341
P. K, D. S, D. R, Gomathi M, Dharshan K, D. M
The language of the hearing impaired people is a visual language. It has to transmit sound patterns in the form of signs. A person’s thoughts are expressed by hand signals and facial expressions. Deaf people normally get struggle by making conversation with normal people; The languages will be different for the various group of deaf people all over the world as well. Our project is to guide the hearing deaf or speech defected persons made communicating with normal persons. It automatically translates the speech in English into Indian sign language. It is the sign-language translating system. For the communication between the normal person and the impaired persons, it could be used as a translator for their natural way of speaking. It’s helpful for people who didn't understand sign language, the sign language gestures are emojis. Our proposed model brings the accuracy improvement by 10% compare to existing models of CNN based classification and SVM_HMM models. FPV and PPV improved by 23.52 % and 37.34 %.
{"title":"An Investigation on Speech to Sign Language Translator for Hearing Impaired (SSLT) using Machine Learning Techniques","authors":"P. K, D. S, D. R, Gomathi M, Dharshan K, D. M","doi":"10.1109/STCR55312.2022.10009341","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009341","url":null,"abstract":"The language of the hearing impaired people is a visual language. It has to transmit sound patterns in the form of signs. A person’s thoughts are expressed by hand signals and facial expressions. Deaf people normally get struggle by making conversation with normal people; The languages will be different for the various group of deaf people all over the world as well. Our project is to guide the hearing deaf or speech defected persons made communicating with normal persons. It automatically translates the speech in English into Indian sign language. It is the sign-language translating system. For the communication between the normal person and the impaired persons, it could be used as a translator for their natural way of speaking. It’s helpful for people who didn't understand sign language, the sign language gestures are emojis. Our proposed model brings the accuracy improvement by 10% compare to existing models of CNN based classification and SVM_HMM models. FPV and PPV improved by 23.52 % and 37.34 %.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122147650","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009243
Kadu N. B, P. Jadhav, Santoshi A. Pawar
To save energy, reduce resource usage, and ensure cloud data center quality of service (QoS), virtual machine migration has become a key requirement with the rapid expansion of cloud environments. Dynamic migration of virtual machines is a successful way to meet growing demand for resources such as processing, connectivity, and storage. This proposal examines the design of control algorithms and their performance models used for migration within a local area network (LAN) or within a data center. The existing methods are investigated to accommodate large numbers of cloud users, improve computing infrastructure, and reduce time and energy spent in cloud data centers. User mobility helps reduce network overhead during VM migration. A key element of this proposal will show you how to optimize data deduplication and peer-to-peer (P2P) file sharing to help further improve the efficiency of data migration for VM storage.
{"title":"Analysis on Optimal Resource Management Strategies: A Virtual Machine Migration Perspective","authors":"Kadu N. B, P. Jadhav, Santoshi A. Pawar","doi":"10.1109/STCR55312.2022.10009243","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009243","url":null,"abstract":"To save energy, reduce resource usage, and ensure cloud data center quality of service (QoS), virtual machine migration has become a key requirement with the rapid expansion of cloud environments. Dynamic migration of virtual machines is a successful way to meet growing demand for resources such as processing, connectivity, and storage. This proposal examines the design of control algorithms and their performance models used for migration within a local area network (LAN) or within a data center. The existing methods are investigated to accommodate large numbers of cloud users, improve computing infrastructure, and reduce time and energy spent in cloud data centers. User mobility helps reduce network overhead during VM migration. A key element of this proposal will show you how to optimize data deduplication and peer-to-peer (P2P) file sharing to help further improve the efficiency of data migration for VM storage.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130308394","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009191
S. Yadav, Krishna Bihari Yadav
This study focuses on optimized Fractional order PI controller (FOPI), which is integrated into a three-phase hybrid Renewable Energy Storage (RES) system, is to improve the power quality of the system (UPQC). Models are created for RES such PV arrays, BESS, and wind energy with the goal of supplying constant electricity. In general, the BESS can meet the full load demand when the PV array and wind turbine are not providing energy, which improves the distribution power system's stability. The UPQC model with series and shunt active filter compensator exists to reduce the grid's power quality difficulties and harmonics injected by the non-linear loads. In addition, UPQC that is integrated with PV, wind, and BESS can address power quality issues in the case of long voltage disruptions. Therefore, the goal of this research is to create a FOPI controller with iso-damping properties in order to manage the voltage of the DC link at the necessary level. A Seagull Optimization Algorithm (SOA) is used in particular to optimally tune the gain of the FOPI controller (Kp, Ki, λ,). In order to evaluate the results during voltage sag/swell, concerning the total harmonic distortion, the proposed method was implemented in MATLAB/Simulink. It's capable of producing competitive and promising outcomes.
{"title":"Seagull Optimization in FO-PI Controller of UPQC Integrated Hybrid RES System for Power Quality Improvement","authors":"S. Yadav, Krishna Bihari Yadav","doi":"10.1109/STCR55312.2022.10009191","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009191","url":null,"abstract":"This study focuses on optimized Fractional order PI controller (FOPI), which is integrated into a three-phase hybrid Renewable Energy Storage (RES) system, is to improve the power quality of the system (UPQC). Models are created for RES such PV arrays, BESS, and wind energy with the goal of supplying constant electricity. In general, the BESS can meet the full load demand when the PV array and wind turbine are not providing energy, which improves the distribution power system's stability. The UPQC model with series and shunt active filter compensator exists to reduce the grid's power quality difficulties and harmonics injected by the non-linear loads. In addition, UPQC that is integrated with PV, wind, and BESS can address power quality issues in the case of long voltage disruptions. Therefore, the goal of this research is to create a FOPI controller with iso-damping properties in order to manage the voltage of the DC link at the necessary level. A Seagull Optimization Algorithm (SOA) is used in particular to optimally tune the gain of the FOPI controller (Kp, Ki, λ,). In order to evaluate the results during voltage sag/swell, concerning the total harmonic distortion, the proposed method was implemented in MATLAB/Simulink. It's capable of producing competitive and promising outcomes.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129546378","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009173
Vijayalakshmi Aakaaram, Srinvas Bachu
Medical image fusion plays the major role in many applications including brain tumor segmentation, and classification. But the conventional methods are suffering with colour artifacts. Thus, this article proposes a novel magnetic resonance imaging (MRI) and computerized tomography (CT) based multi modal medical image fusion using synchronized anisotropic diffusion equation (SADE) with dual tree dual-tree complex wavelet transform (DT-CWT) decomposition. Initially, source images are divided into multiple bands by using DT-CWT approach. In addition, SADE process is applied to extract the approximate and detailed layers. Further, principal component analysis (PCA) is applied to extract the eigen vectors. Finally, PCA fusion rule is applied to get the fused outcome. The simulation results show that proposed fusion results shows better subjective and object performance as compared to conventional fusion methods.
{"title":"MRI and CT Image Fusion using Synchronized Anisotropic Diffusion Equation with DT-CWT Decomposition","authors":"Vijayalakshmi Aakaaram, Srinvas Bachu","doi":"10.1109/STCR55312.2022.10009173","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009173","url":null,"abstract":"Medical image fusion plays the major role in many applications including brain tumor segmentation, and classification. But the conventional methods are suffering with colour artifacts. Thus, this article proposes a novel magnetic resonance imaging (MRI) and computerized tomography (CT) based multi modal medical image fusion using synchronized anisotropic diffusion equation (SADE) with dual tree dual-tree complex wavelet transform (DT-CWT) decomposition. Initially, source images are divided into multiple bands by using DT-CWT approach. In addition, SADE process is applied to extract the approximate and detailed layers. Further, principal component analysis (PCA) is applied to extract the eigen vectors. Finally, PCA fusion rule is applied to get the fused outcome. The simulation results show that proposed fusion results shows better subjective and object performance as compared to conventional fusion methods.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121366089","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009232
Vemula Lakshmansai, Srinvas Bachu
Coronavirus Disease 2019 (COVID-19) becomes the crucial disease in recent times. Further, many variants of COVID-19 are evolving from the broad family of severe acute respiratory syndrome (SARS). Thus, the detection of all these variants by using Real-time polymerase chain reaction (RT-PCR) test is a difficult task and time taking. In addition, the conventional methods are failed to classify the COVID-19 in early stage due to complex architecture of chest x-ray (CXR) image. Therefore, this article is focused on implementation of deep learning convolutional neural network (DLCNN) based artificial intelligence approach for classifying COVID-19 disease. Initially, the hybrid features are extracted from CXR dataset by using Multi Block Local Binary Pattern (MB-LBP), and Weber local descriptor (WLD). Further, increment component analysis (ICA) is used to reduce features, which generates best features. Then, DLCNN model is trained with these features for classification of COVID-19 for each test CXR image. The simulation results show that proposed classification resulted in better subjective and object performance as compared to conventional machine learning and deep learning methods.
{"title":"Artificial Intelligence System for Classification of COVID-19 from CXR Images","authors":"Vemula Lakshmansai, Srinvas Bachu","doi":"10.1109/STCR55312.2022.10009232","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009232","url":null,"abstract":"Coronavirus Disease 2019 (COVID-19) becomes the crucial disease in recent times. Further, many variants of COVID-19 are evolving from the broad family of severe acute respiratory syndrome (SARS). Thus, the detection of all these variants by using Real-time polymerase chain reaction (RT-PCR) test is a difficult task and time taking. In addition, the conventional methods are failed to classify the COVID-19 in early stage due to complex architecture of chest x-ray (CXR) image. Therefore, this article is focused on implementation of deep learning convolutional neural network (DLCNN) based artificial intelligence approach for classifying COVID-19 disease. Initially, the hybrid features are extracted from CXR dataset by using Multi Block Local Binary Pattern (MB-LBP), and Weber local descriptor (WLD). Further, increment component analysis (ICA) is used to reduce features, which generates best features. Then, DLCNN model is trained with these features for classification of COVID-19 for each test CXR image. The simulation results show that proposed classification resulted in better subjective and object performance as compared to conventional machine learning and deep learning methods.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126231147","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009315
Pedro H. F. Mendes, André Mendes, Luís F. C. Duarte
Sensing the environment is a crucial task that robots have to perform to navigate autonomously. Furthermore, it must be well executed to make navigation safer and collision-free. As autonomous mobile robots are being deployed in several applications, they often encounter dynamic habitats, where sensing and perceiving the environment becomes harder. This work proposes integrating a wireless sensor network with the Robotic Operating System to incorporate data into layered costmaps used by the robot to navigate, feeding the algorithms with advanced information about the territory. The architecture was tested in simulation, where we could validate the structure and collect data showing improved paths calculated and reduced computational load through better parametrization. Thus, this strategy ensures that the advanced information about the environment has improved the navigation process.
{"title":"Integration of ROS Navigation Stack with Dynamic Environment Information in Gazebo Simulation","authors":"Pedro H. F. Mendes, André Mendes, Luís F. C. Duarte","doi":"10.1109/STCR55312.2022.10009315","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009315","url":null,"abstract":"Sensing the environment is a crucial task that robots have to perform to navigate autonomously. Furthermore, it must be well executed to make navigation safer and collision-free. As autonomous mobile robots are being deployed in several applications, they often encounter dynamic habitats, where sensing and perceiving the environment becomes harder. This work proposes integrating a wireless sensor network with the Robotic Operating System to incorporate data into layered costmaps used by the robot to navigate, feeding the algorithms with advanced information about the territory. The architecture was tested in simulation, where we could validate the structure and collect data showing improved paths calculated and reduced computational load through better parametrization. Thus, this strategy ensures that the advanced information about the environment has improved the navigation process.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114512814","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：