Pub Date : 2021-07-30DOI: 10.36548/jeea.2021.2.005
P. Hengjinda, J. Chen
The harbours using green ports have become a common mode of enabling the use of environment friendly energy consumption. In this paper, two major contributions are made: reduction of energy consumption in the ports by using ships; prediction of energy consumption with respect to a green port. The characteristics that will play a crucial role in energy consumption of ships are considered and a detailed analysis has been performed to predict the energy consumed by the ships. Deep learning methodologies such as, K-Nearest Regression (KNR), Linear Regression (LR), BP Network (BP), Random Forest Regression (RF) and Gradient Boosting Regression (GBR) are used to determine the different characteristics of the ships that are used while the external features of the ports are given as input. To determine the efficiency of the proposed work, k-fold cross validation is also incorporated. Based on feature importance, the crucial features of the algorithm are selected. The influence of different changing aspects on the ship's energy usage is identified, and reduction methods are implemented appropriately. According to the observed data, the most essential factors that may be utilised to estimate energy consumption of the ship are efficiency of facilities, actual weight, deadweight tonnage, and net tonnage. As the efficiency increases, there is also a significant reduction and the power consumption of the ship at the rate of 8% and 32% in port and berth respectively.
{"title":"Prediction of Energy Consumption by Ships at the port using Deep Learning","authors":"P. Hengjinda, J. Chen","doi":"10.36548/jeea.2021.2.005","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.005","url":null,"abstract":"The harbours using green ports have become a common mode of enabling the use of environment friendly energy consumption. In this paper, two major contributions are made: reduction of energy consumption in the ports by using ships; prediction of energy consumption with respect to a green port. The characteristics that will play a crucial role in energy consumption of ships are considered and a detailed analysis has been performed to predict the energy consumed by the ships. Deep learning methodologies such as, K-Nearest Regression (KNR), Linear Regression (LR), BP Network (BP), Random Forest Regression (RF) and Gradient Boosting Regression (GBR) are used to determine the different characteristics of the ships that are used while the external features of the ports are given as input. To determine the efficiency of the proposed work, k-fold cross validation is also incorporated. Based on feature importance, the crucial features of the algorithm are selected. The influence of different changing aspects on the ship's energy usage is identified, and reduction methods are implemented appropriately. According to the observed data, the most essential factors that may be utilised to estimate energy consumption of the ship are efficiency of facilities, actual weight, deadweight tonnage, and net tonnage. As the efficiency increases, there is also a significant reduction and the power consumption of the ship at the rate of 8% and 32% in port and berth respectively.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77685611","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 : 2021-07-30DOI: 10.36548/jeea.2021.2.006
J.S.K. Raj, G. Ranganathan
Due to the global energy crisis and environmental degradation, largely as a result of the increased usage of non-renewable energy sources, researchers have become more interested in exploring alternative energy systems, which may harvest energy from natural sources. This research article provides a comparison between various modeling of piezoelectric elements in terms of power generation for energy harvesting solutions. The energy harvesting can be computed and calculated based on piezoelectric materials and modeling for the specific application. The most common type of environmental energy that may be collected and transformed into electricity for several purposes is Piezoelectric transduction, which is more effective, compared to other mechanical energy harvesting techniques, including electrostatic, electromagnetic, and triboelectric transduction, due to their high electromechanical connection factor and piezoelectric coefficients. As a result of this research, scientists are highly interested in piezoelectric energy collection.
{"title":"Comparative Analysis of Modelling for Piezoelectric Energy Harvesting Solutions","authors":"J.S.K. Raj, G. Ranganathan","doi":"10.36548/jeea.2021.2.006","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.006","url":null,"abstract":"Due to the global energy crisis and environmental degradation, largely as a result of the increased usage of non-renewable energy sources, researchers have become more interested in exploring alternative energy systems, which may harvest energy from natural sources. This research article provides a comparison between various modeling of piezoelectric elements in terms of power generation for energy harvesting solutions. The energy harvesting can be computed and calculated based on piezoelectric materials and modeling for the specific application. The most common type of environmental energy that may be collected and transformed into electricity for several purposes is Piezoelectric transduction, which is more effective, compared to other mechanical energy harvesting techniques, including electrostatic, electromagnetic, and triboelectric transduction, due to their high electromechanical connection factor and piezoelectric coefficients. As a result of this research, scientists are highly interested in piezoelectric energy collection.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90748439","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 : 2021-07-30DOI: 10.36548/jeea.2021.2.004
R RajeshSharma
Diabetes is a major cause of organ failure in the human body, and it is one of the leading causes of organ failure. As of now, there is no preventive medicine or vaccine for diabetes. As a result, people all around the world are accustomed to living with diabetes for the rest of their lives. Medical practitioners advise diabetic patients to have a healthy lifestyle that includes regular exercise and a well-balanced diet in order to prevent the effects of diabetes from spreading to other organs of the human body. In most cases, the diabetes is spreading like a heredity disease to the infected people and even to children and it can’t be estimated priory. In recent days, the deep learning algorithms are widely used to estimate the forthcoming effects of several problems by using the data mining process. In the proposed work, the performance of deep ANN and back propagation ANN is considered for estimating diabetes from several primary data factors obtained from a publicly available dataset called Pima Indian diabetes dataset.
糖尿病是人体器官衰竭的主要原因，是导致器官衰竭的主要原因之一。到目前为止，还没有预防糖尿病的药物或疫苗。因此，全世界的人都习惯了与糖尿病一起度过余生。医生建议糖尿病患者保持健康的生活方式，包括经常锻炼和均衡的饮食，以防止糖尿病的影响扩散到人体的其他器官。在大多数情况下，糖尿病像遗传疾病一样传播给感染者甚至儿童，而且无法估计其先期。近年来，深度学习算法被广泛用于利用数据挖掘过程来估计一些问题即将产生的影响。在提出的工作中，考虑了深度神经网络和反向传播神经网络的性能，以从公开可用的数据集(称为Pima Indian diabetes dataset)中获得的几个主要数据因素来估计糖尿病。
{"title":"Energy Efficient Data Mining Approach for Estimating the Diabetes","authors":"R RajeshSharma","doi":"10.36548/jeea.2021.2.004","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.004","url":null,"abstract":"Diabetes is a major cause of organ failure in the human body, and it is one of the leading causes of organ failure. As of now, there is no preventive medicine or vaccine for diabetes. As a result, people all around the world are accustomed to living with diabetes for the rest of their lives. Medical practitioners advise diabetic patients to have a healthy lifestyle that includes regular exercise and a well-balanced diet in order to prevent the effects of diabetes from spreading to other organs of the human body. In most cases, the diabetes is spreading like a heredity disease to the infected people and even to children and it can’t be estimated priory. In recent days, the deep learning algorithms are widely used to estimate the forthcoming effects of several problems by using the data mining process. In the proposed work, the performance of deep ANN and back propagation ANN is considered for estimating diabetes from several primary data factors obtained from a publicly available dataset called Pima Indian diabetes dataset.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88099271","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 : 2021-07-30DOI: 10.36548/jeea.2021.2.003
A. Pandian
This research article surveys the most recent IoT healthcare system research articles as the integration of IoT models have been extended to healthcare systems, such as health monitoring, fitness routines, and other applications. Extensive research study has been conducted on Internet of Things (IoT) technology to enhance the monitoring efficiency. This research is aimed at investigating the Internet of Things [IoT] architecture with an emphasis on cloud-based applications. The most significant challenges in the Internet of Things [IoT] include different elements such as accuracy and energy consumption, wherein this research is focused on improving the performance of IoT-based medical equipment. In this research, data management techniques for the Internet of Things-based cloud healthcare system are also thoroughly investigated. The performance and limitations of the Internet of Things (IoT) health system are evaluated. The majority of studies are successful in detecting a wide range of markers and correctly predicting illness. The Internet of Things (IoT) health system is being developed as an effective solution to the health concerns of elderly population. The major drawbacks of current systems are their increased energy consumption, reduced availability of resources, and safety concerns resulting from the use of a large number of different pieces of equipment.
{"title":"A Review on future challenges and concerns associated with an Internet of Things based automatic health monitoring system","authors":"A. Pandian","doi":"10.36548/jeea.2021.2.003","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.003","url":null,"abstract":"This research article surveys the most recent IoT healthcare system research articles as the integration of IoT models have been extended to healthcare systems, such as health monitoring, fitness routines, and other applications. Extensive research study has been conducted on Internet of Things (IoT) technology to enhance the monitoring efficiency. This research is aimed at investigating the Internet of Things [IoT] architecture with an emphasis on cloud-based applications. The most significant challenges in the Internet of Things [IoT] include different elements such as accuracy and energy consumption, wherein this research is focused on improving the performance of IoT-based medical equipment. In this research, data management techniques for the Internet of Things-based cloud healthcare system are also thoroughly investigated. The performance and limitations of the Internet of Things (IoT) health system are evaluated. The majority of studies are successful in detecting a wide range of markers and correctly predicting illness. The Internet of Things (IoT) health system is being developed as an effective solution to the health concerns of elderly population. The major drawbacks of current systems are their increased energy consumption, reduced availability of resources, and safety concerns resulting from the use of a large number of different pieces of equipment.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86412774","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 : 2021-07-27DOI: 10.36548/jeea.2021.2.001
V. Bindhu
A customer relationship management (CRM) system based on Artificial Intelligence (AI) is used to discover critical success factors (CSF) in order to improve the automated business process and deliver better knowledge management (KM). Moreover, different factors contribute towards achieving efficient knowledge management in CRM systems with AI schemes. Identifying the key elements may be accomplished in a variety of ways. For this purpose, Delphi technique, nominal group technique, and brainstorming approach are used. Using the interpretive structural modelling (ISM) approach, ten key variables, significance degree, and interaction are determined. CSFs such as funding, leadership, and support are the most important of the ten variables identified for integrating KM, CRM, and AI. This approach has the potential to significantly improve the business processes.
{"title":"Artificial Intelligence based Business Process Automation for Enhanced Knowledge Management","authors":"V. Bindhu","doi":"10.36548/jeea.2021.2.001","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.001","url":null,"abstract":"A customer relationship management (CRM) system based on Artificial Intelligence (AI) is used to discover critical success factors (CSF) in order to improve the automated business process and deliver better knowledge management (KM). Moreover, different factors contribute towards achieving efficient knowledge management in CRM systems with AI schemes. Identifying the key elements may be accomplished in a variety of ways. For this purpose, Delphi technique, nominal group technique, and brainstorming approach are used. Using the interpretive structural modelling (ISM) approach, ten key variables, significance degree, and interaction are determined. CSFs such as funding, leadership, and support are the most important of the ten variables identified for integrating KM, CRM, and AI. This approach has the potential to significantly improve the business processes.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"3 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90060754","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 : 2021-07-27DOI: 10.36548/jtcsst.2021.2.006
Suma
The Internet of Things [IoT] is one of the most recent technologies that has influenced the way people communicate. With its growth, IoT encounters a number of challenges, including device heterogeneity, energy construction, comparability, and security. Energy and security are important considerations when transmitting data via edge networks and IoT. Interference with data in an IoT network might occur unintentionally or on purpose by malicious attackers, and it will have a significant impact in real time. To address the security problems, the suggested solution incorporates software defined networking (SDN) and blockchain. In particular, this research work has introduced an energy efficient and secure blockchain-enabled architecture using SDN controllers that are operating on a novel routing methodology in IoT. To establish communication between the IoT devices, private and public blockchain are used for eliminating Proof of Work (POW). This enables blockchain to be a suitable resource-constrained protocol for establishing an efficient communication. Experimental observation indicates that, an algorithm based on routing protocol will have low energy consumption, lower delay and higher throughput, when compared with other classic routing algorithms.
{"title":"SDN Controller and Blockchain to Secure Information Transaction in a Cluster Structure","authors":"Suma","doi":"10.36548/jtcsst.2021.2.006","DOIUrl":"https://doi.org/10.36548/jtcsst.2021.2.006","url":null,"abstract":"The Internet of Things [IoT] is one of the most recent technologies that has influenced the way people communicate. With its growth, IoT encounters a number of challenges, including device heterogeneity, energy construction, comparability, and security. Energy and security are important considerations when transmitting data via edge networks and IoT. Interference with data in an IoT network might occur unintentionally or on purpose by malicious attackers, and it will have a significant impact in real time. To address the security problems, the suggested solution incorporates software defined networking (SDN) and blockchain. In particular, this research work has introduced an energy efficient and secure blockchain-enabled architecture using SDN controllers that are operating on a novel routing methodology in IoT. To establish communication between the IoT devices, private and public blockchain are used for eliminating Proof of Work (POW). This enables blockchain to be a suitable resource-constrained protocol for establishing an efficient communication. Experimental observation indicates that, an algorithm based on routing protocol will have low energy consumption, lower delay and higher throughput, when compared with other classic routing algorithms.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74837589","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 : 2021-07-27DOI: 10.36548/jeea.2021.2.002
S. Shakya
Thermal imaging is utilized as a technique in agricultural crop water management due to its efficiency in estimating canopy surface temperature and the ability to predict crop water levels. Thermal imaging was considered as a beneficial integration in Unmanned Aerial Vehicle (UAV) for agricultural and civil engineering purposes with the reduced weight of thermal imaging systems and increased resolution. When implemented on-site, this technique was able to address a number of difficulties, including estimation of water in the plant in farms or fields, while considering officially induced variability or naturally existing water level. The proposed effort aims to determine the amount of water content in a vineyard using the high-resolution thermal imaging. This research work has developed an unmanned aerial vehicle (UAV) that is particularly intended to display high-resolution images. This approach will be able to generate crop water stress index (CWSI) by utilizing a thermal imaging system on a clear-sky day. The measured values were compared to the estimated stomatal conductance (sg) and stem water (s) potential along the Vineyard at the same time. To evaluate the performance of the proposed work, special modelling approach was used to identify the pattern of variation in water level. Based on the observation, it was concluded that both ‘sg’ and ‘s’ value have correlated well with the CWSI value by indicating a great potential to monitor instantaneous changes in water level. However, based on seasonal changes in water status, it was discovered that the recorded thermal images did not correspond to seasonal variations in water status.
{"title":"Unmanned Aerial Vehicle with Thermal Imaging for Automating Water Status in Vineyard","authors":"S. Shakya","doi":"10.36548/jeea.2021.2.002","DOIUrl":"https://doi.org/10.36548/jeea.2021.2.002","url":null,"abstract":"Thermal imaging is utilized as a technique in agricultural crop water management due to its efficiency in estimating canopy surface temperature and the ability to predict crop water levels. Thermal imaging was considered as a beneficial integration in Unmanned Aerial Vehicle (UAV) for agricultural and civil engineering purposes with the reduced weight of thermal imaging systems and increased resolution. When implemented on-site, this technique was able to address a number of difficulties, including estimation of water in the plant in farms or fields, while considering officially induced variability or naturally existing water level. The proposed effort aims to determine the amount of water content in a vineyard using the high-resolution thermal imaging. This research work has developed an unmanned aerial vehicle (UAV) that is particularly intended to display high-resolution images. This approach will be able to generate crop water stress index (CWSI) by utilizing a thermal imaging system on a clear-sky day. The measured values were compared to the estimated stomatal conductance (sg) and stem water (s) potential along the Vineyard at the same time. To evaluate the performance of the proposed work, special modelling approach was used to identify the pattern of variation in water level. Based on the observation, it was concluded that both ‘sg’ and ‘s’ value have correlated well with the CWSI value by indicating a great potential to monitor instantaneous changes in water level. However, based on seasonal changes in water status, it was discovered that the recorded thermal images did not correspond to seasonal variations in water status.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90515507","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 : 2021-07-23DOI: 10.36548/JTCSST.2021.2.005
J. Chen, S. Smys
In recent years, both developed and developing countries have witnessed an increase in the number of traffic accidents. Aside from a significant rise in the overall number of on-road commercial and non-commercial vehicles, advancements in transportation infrastructure and on-road technologies may result in road accidents, which generally result in high mortality. More than half of these fatalities are the result of delayed response by medical and rescue personnel. If an accident site receives quick medical treatment, an accident victim's chances of survival may improve considerably. Based on the IoT-based multiple-level vehicle environment, this study proposes a low-cost accident detection and alarm system. Vehicles are equipped with a "Black Box" board unit and an accident location identification module for the Global Positioning System (GPS), in addition to mechanical sensors (accelerometer, gyroscope) for accurate accident detection. This study has evaluated the proposed system with average packet delivery ratio (PDR) vs. relay nodes. Our simulation results have evaluated the evolution of relay nodes in the mobile / sensor node through internet gateway. It has also been demonstrated that the packet delivery ratio is inversely related to the incremental number of relay nodes.
{"title":"Construction of Black Box to Detect the Location of Road Mishap in Remote Area in the IoT Domain","authors":"J. Chen, S. Smys","doi":"10.36548/JTCSST.2021.2.005","DOIUrl":"https://doi.org/10.36548/JTCSST.2021.2.005","url":null,"abstract":"In recent years, both developed and developing countries have witnessed an increase in the number of traffic accidents. Aside from a significant rise in the overall number of on-road commercial and non-commercial vehicles, advancements in transportation infrastructure and on-road technologies may result in road accidents, which generally result in high mortality. More than half of these fatalities are the result of delayed response by medical and rescue personnel. If an accident site receives quick medical treatment, an accident victim's chances of survival may improve considerably. Based on the IoT-based multiple-level vehicle environment, this study proposes a low-cost accident detection and alarm system. Vehicles are equipped with a \"Black Box\" board unit and an accident location identification module for the Global Positioning System (GPS), in addition to mechanical sensors (accelerometer, gyroscope) for accurate accident detection. This study has evaluated the proposed system with average packet delivery ratio (PDR) vs. relay nodes. Our simulation results have evaluated the evolution of relay nodes in the mobile / sensor node through internet gateway. It has also been demonstrated that the packet delivery ratio is inversely related to the incremental number of relay nodes.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89193777","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 : 2021-07-17DOI: 10.36548/JTCSST.2021.2.004
R. Dhaya
The automated captioning of natural images with appropriate descriptions is an intriguing and complicated task in the field of image processing. On the other hand, Deep learning, which combines computer vision with natural language, has emerged in recent years. Image emphasization is a record file representation that allows a computer to understand the visual information of an image in one or more words. When it comes to connecting high-quality images, the expressive process not only requires the credentials of the primary item and scene but also the ability to analyse the status, physical characteristics, and connections. Many traditional algorithms substitute the image to the front image. The image characteristics are dynamic depending on the ambient condition of natural photographs. Image processing techniques fail to extract several characteristics from the specified image. Nonetheless, four properties from the images are accurately described by using our proposed technique. Based on the various filtering layers in the convolutional neural network (CNN), it is an advantage to extract different characteristics. The caption for the image is based on long short term memory (LSTM), which comes under recurrent neural network. In addition, the precise subtitling is compared to current conventional techniques of image processing and different deep learning models. The proposed method is performing well in natural images and web camera based images for traffic analysis. Besides, the proposed algorithm leverages good accuracy and reliable image captioning.
{"title":"Construction of reliable image captioning system for web camera based traffic analysis on road transport application","authors":"R. Dhaya","doi":"10.36548/JTCSST.2021.2.004","DOIUrl":"https://doi.org/10.36548/JTCSST.2021.2.004","url":null,"abstract":"The automated captioning of natural images with appropriate descriptions is an intriguing and complicated task in the field of image processing. On the other hand, Deep learning, which combines computer vision with natural language, has emerged in recent years. Image emphasization is a record file representation that allows a computer to understand the visual information of an image in one or more words. When it comes to connecting high-quality images, the expressive process not only requires the credentials of the primary item and scene but also the ability to analyse the status, physical characteristics, and connections. Many traditional algorithms substitute the image to the front image. The image characteristics are dynamic depending on the ambient condition of natural photographs. Image processing techniques fail to extract several characteristics from the specified image. Nonetheless, four properties from the images are accurately described by using our proposed technique. Based on the various filtering layers in the convolutional neural network (CNN), it is an advantage to extract different characteristics. The caption for the image is based on long short term memory (LSTM), which comes under recurrent neural network. In addition, the precise subtitling is compared to current conventional techniques of image processing and different deep learning models. The proposed method is performing well in natural images and web camera based images for traffic analysis. Besides, the proposed algorithm leverages good accuracy and reliable image captioning.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79258207","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 : 2021-07-14DOI: 10.36548/JTCSST.2021.2.003
Kottilingam Kottursamy
The role of facial expression recognition in social science and human-computer interaction has received a lot of attention. Deep learning advancements have resulted in advances in this field, which go beyond human-level accuracy. This article discusses various common deep learning algorithms for emotion recognition, all while utilising the eXnet library for achieving improved accuracy. Memory and computation, on the other hand, have yet to be overcome. Overfitting is an issue with large models. One solution to this challenge is to reduce the generalization error. We employ a novel Convolutional Neural Network (CNN) named eXnet to construct a new CNN model utilising parallel feature extraction. The most recent eXnet (Expression Net) model improves on the previous model's inaccuracy while having many fewer parameters. Data augmentation techniques that have been in use for decades are being utilized with the generalized eXnet. It employs effective ways to reduce overfitting while maintaining overall size under control.
{"title":"A Review on Finding Efficient Approach to Detect Customer Emotion Analysis using Deep Learning Analysis","authors":"Kottilingam Kottursamy","doi":"10.36548/JTCSST.2021.2.003","DOIUrl":"https://doi.org/10.36548/JTCSST.2021.2.003","url":null,"abstract":"The role of facial expression recognition in social science and human-computer interaction has received a lot of attention. Deep learning advancements have resulted in advances in this field, which go beyond human-level accuracy. This article discusses various common deep learning algorithms for emotion recognition, all while utilising the eXnet library for achieving improved accuracy. Memory and computation, on the other hand, have yet to be overcome. Overfitting is an issue with large models. One solution to this challenge is to reduce the generalization error. We employ a novel Convolutional Neural Network (CNN) named eXnet to construct a new CNN model utilising parallel feature extraction. The most recent eXnet (Expression Net) model improves on the previous model's inaccuracy while having many fewer parameters. Data augmentation techniques that have been in use for decades are being utilized with the generalized eXnet. It employs effective ways to reduce overfitting while maintaining overall size under control.","PeriodicalId":11075,"journal":{"name":"Day 1 Mon, June 28, 2021","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85674942","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：