Many sports have a high risk of climatic ailments, such as hypothermia, hyperthermia, and heatstroke. The measurement of a sportsperson's body core temperature (Tc) may have an impact on their performances and it assists them to avoid injuries as well. To avoid complications like electrolyte imbalances or infections, it's essential to precisely measure the core body temperature during targeted temperature control when spontaneous circulation has returned. Previous approaches on the other hand, are intrusive and difficult to use. The usual technique, an oesophageal thermometer, was compared to a disposable non-invasive temperature sensor that used the heat flux methodology. This research indicates that, non-invasive disposable sensors used to measure core body temperature are very reliable when used for targeted temperature control after overcoming a cardiac arrest successfully. The non-invasive method of temperature measurement has somewhat greater accuracy than the invasive approach. The results of this study must be confirmed by more clinical research with various sensor types to figure out if the bounds of agreement could be increased. This will ensure that the findings are accurate based on core temperature.
{"title":"Comparative Analysis of Temperature Measurement Methods based on Degree of Agreement","authors":"N. Shetty","doi":"10.36548/jei.2021.3.005","DOIUrl":"https://doi.org/10.36548/jei.2021.3.005","url":null,"abstract":"Many sports have a high risk of climatic ailments, such as hypothermia, hyperthermia, and heatstroke. The measurement of a sportsperson's body core temperature (Tc) may have an impact on their performances and it assists them to avoid injuries as well. To avoid complications like electrolyte imbalances or infections, it's essential to precisely measure the core body temperature during targeted temperature control when spontaneous circulation has returned. Previous approaches on the other hand, are intrusive and difficult to use. The usual technique, an oesophageal thermometer, was compared to a disposable non-invasive temperature sensor that used the heat flux methodology. This research indicates that, non-invasive disposable sensors used to measure core body temperature are very reliable when used for targeted temperature control after overcoming a cardiac arrest successfully. The non-invasive method of temperature measurement has somewhat greater accuracy than the invasive approach. The results of this study must be confirmed by more clinical research with various sensor types to figure out if the bounds of agreement could be increased. This will ensure that the findings are accurate based on core temperature.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82439529","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 : 2021-11-01DOI: 10.36548/jitdw.2021.3.005
Judy Simon
Computer vision, also known as computational visual perception, is a branch of artificial intelligence that allows computers to interpret digital pictures and videos in a manner comparable to biological vision. It entails the development of techniques for simulating biological vision. The aim of computer vision is to extract more meaningful information from visual input than that of a biological vision. Computer vision is exploding due to the avalanche of data being produced today. Powerful generative models, such as Generative Adversarial Networks (GANs), are responsible for significant advances in the field of picture creation. The focus of this research is to concentrate on textual content descriptors in the images used by GANs to generate synthetic data from the MNIST dataset to either supplement or replace the original data while training classifiers. This can provide better performance than other traditional image enlarging procedures due to the good handling of synthetic data. It shows that training classifiers on synthetic data are as effective as training them on pure data alone, and it also reveals that, for small training data sets, supplementing the dataset by first training GANs on the data may lead to a significant increase in classifier performance.
{"title":"Image Augmentation based on GAN deep learning approach with Textual Content Descriptors","authors":"Judy Simon","doi":"10.36548/jitdw.2021.3.005","DOIUrl":"https://doi.org/10.36548/jitdw.2021.3.005","url":null,"abstract":"Computer vision, also known as computational visual perception, is a branch of artificial intelligence that allows computers to interpret digital pictures and videos in a manner comparable to biological vision. It entails the development of techniques for simulating biological vision. The aim of computer vision is to extract more meaningful information from visual input than that of a biological vision. Computer vision is exploding due to the avalanche of data being produced today. Powerful generative models, such as Generative Adversarial Networks (GANs), are responsible for significant advances in the field of picture creation. The focus of this research is to concentrate on textual content descriptors in the images used by GANs to generate synthetic data from the MNIST dataset to either supplement or replace the original data while training classifiers. This can provide better performance than other traditional image enlarging procedures due to the good handling of synthetic data. It shows that training classifiers on synthetic data are as effective as training them on pure data alone, and it also reveals that, for small training data sets, supplementing the dataset by first training GANs on the data may lead to a significant increase in classifier performance.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"64 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90273329","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 : 2021-11-01DOI: 10.36548/jucct.2021.3.006
R. Kanthavel
The era of Electric Vehicles (EVs) has influenced the very make and manufacture of vehicles resulting in low pollution and advanced battery life. On the other hand, the internet of things has also expanded allowing a number of devices to stay connected using the internet. Massive drawbacks faced by EVs today are the limitation in battery swapping and charging stations and limitation in the range of batteries used. This proposed paper aims to efficiently manage the best battery system apart from building the essential infrastructure. In some cases battery swapping option is also provided through other EV drivers or at registered stations. Hence a complete database of the EV network is required so that it is possible to swap and charge batteries successfully. An EV management using two blockchains as a data layer and network of the application is implemented in this work. The first step involves the development of a blockchain framework using Ethereum and the next step entails a direct acyclic graph. When integrated, these two methodologies prove to be an efficient platform that offers a viable solution for battery management in Electric Vehicles.
{"title":"Ethereum and IOTA based Battery Management System with Internet of Vehicles","authors":"R. Kanthavel","doi":"10.36548/jucct.2021.3.006","DOIUrl":"https://doi.org/10.36548/jucct.2021.3.006","url":null,"abstract":"The era of Electric Vehicles (EVs) has influenced the very make and manufacture of vehicles resulting in low pollution and advanced battery life. On the other hand, the internet of things has also expanded allowing a number of devices to stay connected using the internet. Massive drawbacks faced by EVs today are the limitation in battery swapping and charging stations and limitation in the range of batteries used. This proposed paper aims to efficiently manage the best battery system apart from building the essential infrastructure. In some cases battery swapping option is also provided through other EV drivers or at registered stations. Hence a complete database of the EV network is required so that it is possible to swap and charge batteries successfully. An EV management using two blockchains as a data layer and network of the application is implemented in this work. The first step involves the development of a blockchain framework using Ethereum and the next step entails a direct acyclic graph. When integrated, these two methodologies prove to be an efficient platform that offers a viable solution for battery management in Electric Vehicles.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82260634","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 : 2021-10-29DOI: 10.36548/jitdw.2021.3.004
J. Chen, Lu-Tsou Yeh
Waiting for anything is undesirable by most of the human beings. Especially in the case of digital money transactions, most of the people may have doubtful thoughts on their mind about the success rate of their transactions while taking a longer processing time. The Unified Payment Interface (UPI) system was developed in India for minimizing the typographic works during the digital money transaction process. The UPI system has a separate UPI identification number of each individual consisting of their name, bank name, branch name, and account number. Therefore, sharing of account information has become easier and it reduces the chances of typographic errors in digital transaction applications. Sharing of UPI details are also made easy and secure with Quick Response (QR) code scanning methods. However, a digital transaction like UPI requires a lot of servers to be operated for a single transaction same as in National Electronic Fund Transfer (NEFT) and Immediate Payment Services (IMPS) in India. This increases the waiting time of digital transactions due to poor server communication and higher volume of payment requests on a particular server. The motive of the proposed work is to minimize the server communications by employing a distributed blockchain system. The performance is verified with a simulation experiment on BlockSim simulator in terms of transaction success rate and processing time over the traditional systems.
{"title":"Enhancing the Speed of Response in Digital Money Transactions using Distributed Blockchain System","authors":"J. Chen, Lu-Tsou Yeh","doi":"10.36548/jitdw.2021.3.004","DOIUrl":"https://doi.org/10.36548/jitdw.2021.3.004","url":null,"abstract":"Waiting for anything is undesirable by most of the human beings. Especially in the case of digital money transactions, most of the people may have doubtful thoughts on their mind about the success rate of their transactions while taking a longer processing time. The Unified Payment Interface (UPI) system was developed in India for minimizing the typographic works during the digital money transaction process. The UPI system has a separate UPI identification number of each individual consisting of their name, bank name, branch name, and account number. Therefore, sharing of account information has become easier and it reduces the chances of typographic errors in digital transaction applications. Sharing of UPI details are also made easy and secure with Quick Response (QR) code scanning methods. However, a digital transaction like UPI requires a lot of servers to be operated for a single transaction same as in National Electronic Fund Transfer (NEFT) and Immediate Payment Services (IMPS) in India. This increases the waiting time of digital transactions due to poor server communication and higher volume of payment requests on a particular server. The motive of the proposed work is to minimize the server communications by employing a distributed blockchain system. The performance is verified with a simulation experiment on BlockSim simulator in terms of transaction success rate and processing time over the traditional systems.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86164782","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 : 2021-10-27DOI: 10.36548/jitdw.2021.3.003
R. Asokan, T. Vijayakumar
Noise can scramble a message that is sent. This is true for both voicemails and digital communications transmitted to and from computer systems. During transmission, mistakes tend to happen. Computer memory is the most commonplace to use Hamming code error correction. With extra parity/redundancy bits added to Hamming code, single-bit errors may be detected and corrected. Short-distance data transmissions often make use of Hamming coding. The redundancy bits are interspersed and evacuated subsequently when scaling it for longer data lengths. The new hamming code approach may be quickly and easily adapted to any situation. As a result, it's ideal for sending large data bitstreams since the overhead bits per data bit ratio is much lower. The investigation in this article is extended Hamming codes for product codes. The proposal particularly emphasises on how well it functions with low error rate, which is critical for multimedia wireless applications. It provides a foundation and a comprehensive set of methods for quantitatively evaluating this performance without the need of time-consuming simulations. It provides fresh theoretical findings on the well-known approximation, where the bit error rate roughly equal to the frame error rate times the minimal distance to the codeword length ratio. Moreover, the analytical method is applied to actual design considerations such as shorter and punctured codes along with the payload and redundancy bits calculation. Using the extended identity equation on the dual codes, decoding can be done at the first instance. The achievement of 43.48% redundancy bits is obtained during the testing process which is a huge proportion reduced in this research work.
{"title":"Design of Extended Hamming Code Technique Encryption for Audio Signals by Double Code Error Prediction","authors":"R. Asokan, T. Vijayakumar","doi":"10.36548/jitdw.2021.3.003","DOIUrl":"https://doi.org/10.36548/jitdw.2021.3.003","url":null,"abstract":"Noise can scramble a message that is sent. This is true for both voicemails and digital communications transmitted to and from computer systems. During transmission, mistakes tend to happen. Computer memory is the most commonplace to use Hamming code error correction. With extra parity/redundancy bits added to Hamming code, single-bit errors may be detected and corrected. Short-distance data transmissions often make use of Hamming coding. The redundancy bits are interspersed and evacuated subsequently when scaling it for longer data lengths. The new hamming code approach may be quickly and easily adapted to any situation. As a result, it's ideal for sending large data bitstreams since the overhead bits per data bit ratio is much lower. The investigation in this article is extended Hamming codes for product codes. The proposal particularly emphasises on how well it functions with low error rate, which is critical for multimedia wireless applications. It provides a foundation and a comprehensive set of methods for quantitatively evaluating this performance without the need of time-consuming simulations. It provides fresh theoretical findings on the well-known approximation, where the bit error rate roughly equal to the frame error rate times the minimal distance to the codeword length ratio. Moreover, the analytical method is applied to actual design considerations such as shorter and punctured codes along with the payload and redundancy bits calculation. Using the extended identity equation on the dual codes, decoding can be done at the first instance. The achievement of 43.48% redundancy bits is obtained during the testing process which is a huge proportion reduced in this research work.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87853721","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 : 2021-10-25DOI: 10.36548/jitdw.2021.3.002
S. Shakya
Greenhouses are designed to provide the desired climatic condition for the growth of certain plants to obtain better yield. Most of the greenhouses are developed with adequate windows that allows the natural air to reach the plants to maintain the ideal temperature. The windows are usually operated manually by verifying the greenhouse temperature and the surrounding temperature. In a few cases, the manual operations are extended to control the natural light levels and the humidity inside the greenhouse. In order to improve the performances of such climatic control in a greenhouse, certain automatic systems were developed in recent years. In the proposed work, the operations are controlled using a microcontroller module and a sensor unit. The information collected from the sensors placed inside and outside the greenhouse is forwarded to a feedback gained Artificial Neural Network (FBANN) for making the desirable operation on window and light control modules. The performances of the proposed work is verified with RMSE values observed from the manually operated controller.
{"title":"A Smart Climatic Control Strategy for Optimizing Vegetable Crop Cultivation in Greenhouse using FBANN","authors":"S. Shakya","doi":"10.36548/jitdw.2021.3.002","DOIUrl":"https://doi.org/10.36548/jitdw.2021.3.002","url":null,"abstract":"Greenhouses are designed to provide the desired climatic condition for the growth of certain plants to obtain better yield. Most of the greenhouses are developed with adequate windows that allows the natural air to reach the plants to maintain the ideal temperature. The windows are usually operated manually by verifying the greenhouse temperature and the surrounding temperature. In a few cases, the manual operations are extended to control the natural light levels and the humidity inside the greenhouse. In order to improve the performances of such climatic control in a greenhouse, certain automatic systems were developed in recent years. In the proposed work, the operations are controlled using a microcontroller module and a sensor unit. The information collected from the sensors placed inside and outside the greenhouse is forwarded to a feedback gained Artificial Neural Network (FBANN) for making the desirable operation on window and light control modules. The performances of the proposed work is verified with RMSE values observed from the manually operated controller.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"65 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91441465","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 : 2021-10-20DOI: 10.36548/jucct.2021.3.005
I. Jacob, P. Darney
A blood bank is the organisation responsible for storing blood to transfuse it to the patients in need. The primary goal of a blood bank is to be reliable and ensure that patients get the relevant non-toxic blood to avoid transfusion-related complications since blood is a critical medicinal resource. It is difficult for the blood banks to offer high levels of precision, dependability, and automation in the blood storage and transfusion process if blood bank administration includes many human processes. This research framework is proposing to maintain blood bank records using CNN model classification method. In the pre-processing of CNN method, the datasets are tokenized and set the donor’s eligibility. It will make it easier for regular blood donors to donate regularly to charitable people and organizations. A few machine learning techniques offer the automated website updation. Jupyter note book has been used to analyze the dataset of blood donors using decision trees, neural networks, and von Bays techniques. The proposed method operates online through a website. Moreover, the donor's eligibility status with gender, body mass index, blood pressure level, and frequency of blood donations is also maintained. Finally, the comparison of different machine learning algorithms with the suggested framework is tabulated.
{"title":"Design of Data Mining Techniques for Online Blood Bank Management by CNN Model","authors":"I. Jacob, P. Darney","doi":"10.36548/jucct.2021.3.005","DOIUrl":"https://doi.org/10.36548/jucct.2021.3.005","url":null,"abstract":"A blood bank is the organisation responsible for storing blood to transfuse it to the patients in need. The primary goal of a blood bank is to be reliable and ensure that patients get the relevant non-toxic blood to avoid transfusion-related complications since blood is a critical medicinal resource. It is difficult for the blood banks to offer high levels of precision, dependability, and automation in the blood storage and transfusion process if blood bank administration includes many human processes. This research framework is proposing to maintain blood bank records using CNN model classification method. In the pre-processing of CNN method, the datasets are tokenized and set the donor’s eligibility. It will make it easier for regular blood donors to donate regularly to charitable people and organizations. A few machine learning techniques offer the automated website updation. Jupyter note book has been used to analyze the dataset of blood donors using decision trees, neural networks, and von Bays techniques. The proposed method operates online through a website. Moreover, the donor's eligibility status with gender, body mass index, blood pressure level, and frequency of blood donations is also maintained. Finally, the comparison of different machine learning algorithms with the suggested framework is tabulated.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"78 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85920284","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 : 2021-10-18DOI: 10.36548/jucct.2021.3.004
R. Sharma
It's well-known that industrial safety is now a top concern. Nowadays, accidents caused by flammable gases occur frequently in our everyday lives. Gas cylinders, which are used for household purposes, wide range of businesses, and vehicles are often reported to be on the verge of exploding. Explosions have left a large number of individuals seriously wounded or could also be lethal in certain cases. This project's goal is to use a HOG features for SVM classifier which is used to identify pipeline gas leaks and keep tabs on them. In addition, the system utilises an image processing technique to identify pipeline fractures. Early detection and identification of pipeline flaws is a predominant aspect of this study. According to the suggested design, the robot capture the image down the pipe, looking for any signs of gas leakage by the Eddy Current method. This type of recognition has proved superior to other traditional methods. The methods with efficiency parameters and the results were compared and are tabulated in the results section. In the future, the data in the course of detection could be sent through GSM to a mobile application.
{"title":"Gas Leakage Detection in Pipeline by SVM classifier with Automatic Eddy Current based Defect Recognition Method","authors":"R. Sharma","doi":"10.36548/jucct.2021.3.004","DOIUrl":"https://doi.org/10.36548/jucct.2021.3.004","url":null,"abstract":"It's well-known that industrial safety is now a top concern. Nowadays, accidents caused by flammable gases occur frequently in our everyday lives. Gas cylinders, which are used for household purposes, wide range of businesses, and vehicles are often reported to be on the verge of exploding. Explosions have left a large number of individuals seriously wounded or could also be lethal in certain cases. This project's goal is to use a HOG features for SVM classifier which is used to identify pipeline gas leaks and keep tabs on them. In addition, the system utilises an image processing technique to identify pipeline fractures. Early detection and identification of pipeline flaws is a predominant aspect of this study. According to the suggested design, the robot capture the image down the pipe, looking for any signs of gas leakage by the Eddy Current method. This type of recognition has proved superior to other traditional methods. The methods with efficiency parameters and the results were compared and are tabulated in the results section. In the future, the data in the course of detection could be sent through GSM to a mobile application.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82396034","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}
Transistor sizing is one the developing field in VLSI. Many researches have been conducted to achieve automatic transistor sizing which is a complex task due to its large design area and communication gap between different node and topology. In this paper, automatic transistor sizing is implemented using a combinational methods of Graph Convolutional Neural Network (GCN) and Reinforcement Learning (RL). In the graphical structure the transistor are represented as apexes and the wires are represented as boundaries. Reinforcement learning techniques acts a communication bridge between every node and topology of all circuit. This brings proper communication and understanding among the circuit design. Thus the Figure of Merit (FOM) is increased and the experimental results are compared with different topologies. It is proved that the circuit with prior knowledge about the system, performs well.
{"title":"Transistor Sizing using Hybrid Reinforcement Learning and Graph Convolution Neural Network Algorithm","authors":"P. Karthigaikumar","doi":"10.36548/jei.2021.3.004","DOIUrl":"https://doi.org/10.36548/jei.2021.3.004","url":null,"abstract":"Transistor sizing is one the developing field in VLSI. Many researches have been conducted to achieve automatic transistor sizing which is a complex task due to its large design area and communication gap between different node and topology. In this paper, automatic transistor sizing is implemented using a combinational methods of Graph Convolutional Neural Network (GCN) and Reinforcement Learning (RL). In the graphical structure the transistor are represented as apexes and the wires are represented as boundaries. Reinforcement learning techniques acts a communication bridge between every node and topology of all circuit. This brings proper communication and understanding among the circuit design. Thus the Figure of Merit (FOM) is increased and the experimental results are compared with different topologies. It is proved that the circuit with prior knowledge about the system, performs well.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"17 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91485680","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 : 2021-10-16DOI: 10.36548/jucct.2021.3.003
R. Asokan, T. Vijayakumar
Recently, the use of different social media platforms such as Twitter, Facebook, and WhatsApp have increased significantly. A vast number of static images and motion frame pictures posted on such platforms get stored in the device folder making it critical to identify the social network of the downloaded images in the android domain. This is a multimedia forensic job with major cyber security consequences and is said to be accomplished using unique traces contained in picture material (SNs). Therefore, this proposal has been endeavoured to construct a new framework called FusionNet to combine two well-established single shared Convolutional Neural Networks (CNN) to accelerate the search. Moreover, the FusionNet has been found to improve classification accuracy. Image searching is one of the challenging issues in the android domain besides being a time-consuming process. The goal of the proposed network's architecture and training is to enhance the forensic information included in the digital pictures shared on social media. Furthermore, several network designs for the categorization of WhatsApp pictures have been compared and this suggested method has shown better performance in the comparison. The proposed framework's overall performance was measured using the performance metrics.
{"title":"Design of WhatsApp Image Folder Categorization Using CNN Method in the Android Domain","authors":"R. Asokan, T. Vijayakumar","doi":"10.36548/jucct.2021.3.003","DOIUrl":"https://doi.org/10.36548/jucct.2021.3.003","url":null,"abstract":"Recently, the use of different social media platforms such as Twitter, Facebook, and WhatsApp have increased significantly. A vast number of static images and motion frame pictures posted on such platforms get stored in the device folder making it critical to identify the social network of the downloaded images in the android domain. This is a multimedia forensic job with major cyber security consequences and is said to be accomplished using unique traces contained in picture material (SNs). Therefore, this proposal has been endeavoured to construct a new framework called FusionNet to combine two well-established single shared Convolutional Neural Networks (CNN) to accelerate the search. Moreover, the FusionNet has been found to improve classification accuracy. Image searching is one of the challenging issues in the android domain besides being a time-consuming process. The goal of the proposed network's architecture and training is to enhance the forensic information included in the digital pictures shared on social media. Furthermore, several network designs for the categorization of WhatsApp pictures have been compared and this suggested method has shown better performance in the comparison. The proposed framework's overall performance was measured using the performance metrics.","PeriodicalId":10896,"journal":{"name":"Day 1 Tue, September 21, 2021","volume":"77 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83309826","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：