Pub Date : 2023-02-27DOI: 10.36548/jtcsst.2023.1.001
P. Ramya, B. Sathiyabhama
In the current scenario, the death rate due to the cause of skin cancer is increasing enormously. Diagnosis and prediction of Skin Cancer (SC) have become vital at an earlier stage. The main objective of this research is ensemble machine learning with enhanced genetic algorithm technique to achieve higher accuracy in the prediction of skin cancer at an earlier stage compared to other existing techniques. Although many machine learning and deep learning approaches implemented in detecting skin cancer at an earlier stage still there are few limitations. To overcome these problems in our proposed work, the CNN model, ResNet-16 usually produces successful results in extracting the features automatically and classifying the images very accurately. Therefore, the ResNet model used in our work obtains the deep features with the help of a fully connected layer. Later the feature selection is performed with the help of an Enhanced Genetic Algorithm (EGA) that produces optimized solutions by implementing operations like mutations, crossover, and ensemble with Extreme Learning Machine (EGA-ELM) to classify the images as either melanoma or non-melanoma. The proposed model certainly achieved higher accuracy and effective performance. Finally, the obtained results are to be compared with other popular classifying algorithms like Support Vector Machine (SVM) and various other models.
{"title":"Skin Cancer Prediction using Enhanced Genetic Algorithm with Extreme Learning Machine","authors":"P. Ramya, B. Sathiyabhama","doi":"10.36548/jtcsst.2023.1.001","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.1.001","url":null,"abstract":"In the current scenario, the death rate due to the cause of skin cancer is increasing enormously. Diagnosis and prediction of Skin Cancer (SC) have become vital at an earlier stage. The main objective of this research is ensemble machine learning with enhanced genetic algorithm technique to achieve higher accuracy in the prediction of skin cancer at an earlier stage compared to other existing techniques. Although many machine learning and deep learning approaches implemented in detecting skin cancer at an earlier stage still there are few limitations. To overcome these problems in our proposed work, the CNN model, ResNet-16 usually produces successful results in extracting the features automatically and classifying the images very accurately. Therefore, the ResNet model used in our work obtains the deep features with the help of a fully connected layer. Later the feature selection is performed with the help of an Enhanced Genetic Algorithm (EGA) that produces optimized solutions by implementing operations like mutations, crossover, and ensemble with Extreme Learning Machine (EGA-ELM) to classify the images as either melanoma or non-melanoma. The proposed model certainly achieved higher accuracy and effective performance. Finally, the obtained results are to be compared with other popular classifying algorithms like Support Vector Machine (SVM) and various other models.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125710928","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}
Future communication systems will demand the transmission of huge amounts of data, therefore will require a highly linear power amplifier. The Orthogonal Frequency Division Multiplexing (OFDM) technique is widely used in multimedia services for providing high data rates and providing high Quality of Service. The transmitter power amplifier's range of operation in a communication system is linear. Signal distortion happens when the input signal's amplitude exceeds the linear range of the transmitter power amplifier. Therefore, the transmitter's input signal has to have a low peak to average power ratio (PAPR). The OFDM system has been recognized as the high rate wireless radio channel transmission. Therefore, it will also be highly beneficial for the high-speed communication system. However, due to the extremely high PAPR issue, using the OFDM system in a communication system is not simple. It results in extremely low power efficiency. Therefore, it is crucial to lower the PAPR in the OFDM system in order to employ it in the communication system. By using a discrete Fourier matrix, the Discrete Fourier Transform spreading strategy may significantly lower the PAPR of an OFDM signal. This paper describes the PAPR reduction approach in OFDM signals and examines the effectiveness of OFDM.
{"title":"PAPR Reduction of OFDM with DFT Spreading Method","authors":"Chandanala Sravanya, Pasupuleti Sairam, Barupatla Srinika","doi":"10.36548/jtcsst.2022.3.008","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.008","url":null,"abstract":"Future communication systems will demand the transmission of huge amounts of data, therefore will require a highly linear power amplifier. The Orthogonal Frequency Division Multiplexing (OFDM) technique is widely used in multimedia services for providing high data rates and providing high Quality of Service. The transmitter power amplifier's range of operation in a communication system is linear. Signal distortion happens when the input signal's amplitude exceeds the linear range of the transmitter power amplifier. Therefore, the transmitter's input signal has to have a low peak to average power ratio (PAPR). The OFDM system has been recognized as the high rate wireless radio channel transmission. Therefore, it will also be highly beneficial for the high-speed communication system. However, due to the extremely high PAPR issue, using the OFDM system in a communication system is not simple. It results in extremely low power efficiency. Therefore, it is crucial to lower the PAPR in the OFDM system in order to employ it in the communication system. By using a discrete Fourier matrix, the Discrete Fourier Transform spreading strategy may significantly lower the PAPR of an OFDM signal. This paper describes the PAPR reduction approach in OFDM signals and examines the effectiveness of OFDM.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128670650","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 : 2022-09-27DOI: 10.36548/jtcsst.2022.3.007
Rukia Rahman, Bilal Ahmad Dar
In the present world, ‘information technology has brought about a virtual revolution’ would be an absolute understatement. In fact, every field or sphere of life, considered generally, has been infused with a fresh life, via the channel of information technology. Moreover, the field of education is not any exception, to the good signs of information technology. The use of Information and Communication Technology (ICT) has the potential to significantly alter how teachers and students, teach and learn. ICT aids in increasing educational possibilities, enhancing the integrity of instruction and learning, prolonging lifelong learning, and enhancing managerial effectiveness and efficiency. In many ways, it can be said that the two are inseparable or work hand-in-glove. The present study aims to understand how Information and Technology are ruling the entire education system, as learning online as per the users’ flexibility is gaining popularity day by day and most importantly due to the implementation of new education system in India, many ICT based programs have been included in NEP-2020 like vocational courses, skill labs and coding programs. ICT also expands students’ and teachers’ educational opportunities and affordances, and this ultimately will also shape the future of the education system. This paper reviews various online learning platforms such as National Programme on Technology Enhanced Learning, which is the most subscribed educational channel, having more than 1.5 million subscribers.
{"title":"Information Technology in Education: An Educational Offshoot and a Monumental Add-on in Return","authors":"Rukia Rahman, Bilal Ahmad Dar","doi":"10.36548/jtcsst.2022.3.007","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.007","url":null,"abstract":"In the present world, ‘information technology has brought about a virtual revolution’ would be an absolute understatement. In fact, every field or sphere of life, considered generally, has been infused with a fresh life, via the channel of information technology. Moreover, the field of education is not any exception, to the good signs of information technology. The use of Information and Communication Technology (ICT) has the potential to significantly alter how teachers and students, teach and learn. ICT aids in increasing educational possibilities, enhancing the integrity of instruction and learning, prolonging lifelong learning, and enhancing managerial effectiveness and efficiency. In many ways, it can be said that the two are inseparable or work hand-in-glove. The present study aims to understand how Information and Technology are ruling the entire education system, as learning online as per the users’ flexibility is gaining popularity day by day and most importantly due to the implementation of new education system in India, many ICT based programs have been included in NEP-2020 like vocational courses, skill labs and coding programs. ICT also expands students’ and teachers’ educational opportunities and affordances, and this ultimately will also shape the future of the education system. This paper reviews various online learning platforms such as National Programme on Technology Enhanced Learning, which is the most subscribed educational channel, having more than 1.5 million subscribers.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132537232","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 : 2022-09-21DOI: 10.36548/jtcsst.2022.3.006
S. S. Sivaraju
To autonomously identify cyber threats is a non-trivial research topic. One area where this is most apparent is in the evolution of evasive cyber assaults, which are becoming better at masking their existence and obscuring their attack methods (for example, file-less malware). Particularly stealthy Advanced Persistent Threats may hide out in the system for a long time without being spotted. This study presents a novel method, dubbed CapJack, for identifying illicit bitcoin mining activity in a web browser by using cutting-edge CapsNet technology. Thus far, it is aware that deep learning framework CapsNet is pertained to the problem of detecting malware effectively using a heuristic based on system behaviour. Even more, in multitasking situations when several apps are all active at the same time, it is possible to identify fraudulent miners with greater efficiency.
{"title":"An Insight into Deep Learning based Cryptojacking Detection Model","authors":"S. S. Sivaraju","doi":"10.36548/jtcsst.2022.3.006","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.006","url":null,"abstract":"To autonomously identify cyber threats is a non-trivial research topic. One area where this is most apparent is in the evolution of evasive cyber assaults, which are becoming better at masking their existence and obscuring their attack methods (for example, file-less malware). Particularly stealthy Advanced Persistent Threats may hide out in the system for a long time without being spotted. This study presents a novel method, dubbed CapJack, for identifying illicit bitcoin mining activity in a web browser by using cutting-edge CapsNet technology. Thus far, it is aware that deep learning framework CapsNet is pertained to the problem of detecting malware effectively using a heuristic based on system behaviour. Even more, in multitasking situations when several apps are all active at the same time, it is possible to identify fraudulent miners with greater efficiency.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116060790","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 : 2022-09-19DOI: 10.36548/jtcsst.2022.3.005
G. K. Vaidhya, C. A. S. Deiva Preetha
There are roughly 72 million ‘hard of hearing’ individuals all over the planet, and more than 80% of them live in developing countries, as indicated in a review by the World Federation for the Deaf. Their lives are hindered by hearing distortions which bar them from showing full interest in the public besides taking pleasure in enjoying identical privileges. Motion based communication is common for the people with hearing and speaking impairments. Communication through signs is a successful choice rather than talking, where the former is replaced by hand flags. One solution to this problem is to study text comprehension tasks for hearing impaired localities using Sign Language Recognition. Gesture-based communication is the most significant and centered approach of communication for deaf and dumb individuals. This paper gives a concise review of different examination works conducted thus far in this field.
据世界聋人联合会(World Federation for the Deaf)的一份报告显示，全球大约有7200万“重听”人士，其中80%以上生活在发展中国家。他们的生活受到听力扭曲的阻碍，这使他们除了享受同样的特权外，无法对公众表现出充分的兴趣。对于有听力和语言障碍的人来说，基于动作的交流是很常见的。通过手势交流是一种成功的选择，而不是说话，后者被手旗取代。解决这一问题的一种方法是使用手语识别来研究听力受损地区的文本理解任务。手势交际是聋哑人最重要、最核心的交际方式。本文简要回顾了迄今为止在这一领域进行的不同的考试工作。
{"title":"A Comprehensive Study on Sign Language Recognition for Deaf and Dumb people","authors":"G. K. Vaidhya, C. A. S. Deiva Preetha","doi":"10.36548/jtcsst.2022.3.005","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.005","url":null,"abstract":"There are roughly 72 million ‘hard of hearing’ individuals all over the planet, and more than 80% of them live in developing countries, as indicated in a review by the World Federation for the Deaf. Their lives are hindered by hearing distortions which bar them from showing full interest in the public besides taking pleasure in enjoying identical privileges. Motion based communication is common for the people with hearing and speaking impairments. Communication through signs is a successful choice rather than talking, where the former is replaced by hand flags. One solution to this problem is to study text comprehension tasks for hearing impaired localities using Sign Language Recognition. Gesture-based communication is the most significant and centered approach of communication for deaf and dumb individuals. This paper gives a concise review of different examination works conducted thus far in this field.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121735068","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 : 2022-08-29DOI: 10.36548/jtcsst.2022.3.004
K. G. Krishnan, Abhishek Mohan, S. Vishnu, Steve Abraham Eapen, Amith Raj, J. Jacob
In complex planning and control operations and tasks like manipulating objects, assisting experts in various fields, navigating outdoor environments, and exploring uncharted territory, modern robots are designed to complement or completely replace humans. Even for those skilled in robot programming, designing a control schema for such robots to carry out these tasks is typically a challenging process that necessitates starting from scratch with a new and distinct controller for each task. The designer must consider the wide range of circumstances the robot might encounter. This kind of manual programming is typically expensive and time consuming. It would be more beneficial if a robot could learn the task on its own rather than having to be preprogrammed to perform all these tasks. In this paper, a method for the path planning of a robot in a known environment is implemented using Q-Learning by finding an optimal path from a specified starting and ending point.
{"title":"Path Planning of Mobile Robot Using Reinforcement Learning","authors":"K. G. Krishnan, Abhishek Mohan, S. Vishnu, Steve Abraham Eapen, Amith Raj, J. Jacob","doi":"10.36548/jtcsst.2022.3.004","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.004","url":null,"abstract":"In complex planning and control operations and tasks like manipulating objects, assisting experts in various fields, navigating outdoor environments, and exploring uncharted territory, modern robots are designed to complement or completely replace humans. Even for those skilled in robot programming, designing a control schema for such robots to carry out these tasks is typically a challenging process that necessitates starting from scratch with a new and distinct controller for each task. The designer must consider the wide range of circumstances the robot might encounter. This kind of manual programming is typically expensive and time consuming. It would be more beneficial if a robot could learn the task on its own rather than having to be preprogrammed to perform all these tasks. In this paper, a method for the path planning of a robot in a known environment is implemented using Q-Learning by finding an optimal path from a specified starting and ending point.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132944727","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 : 2022-08-20DOI: 10.36548/jtcsst.2022.3.003
D. Sasikala, K. Venkatesh Sharma
Cybersecurity is an extensive and vivacious domain in the commercial progression of the ecosphere. By up-to-date inhabitants, networking settings and assets, cybersecurity fits with the exigent task to realize the necessities of the imminent populace. Intelligent cybersecurity / intellectual smart cybersecurity has risen as a pioneering tool to deal with latest ambiguities in programmed cybersecurity enduring capability by bringing together Artificial Intelligence (AI) in Cybersecurity Computerization. The mechanism that enterprises in this cutting-edge technology handles the mechanism capability to acquire via depleting Bootstrapped Meta-learning and reinforced with rewards as Supreme Cybersecurity vintages, besides least resource utilizations as well as time limits. AI empowered cybersecurity technology is a vital constituent of the imminent cybersecurity revolution ahead. During this operation, a proficient computerization of AI application in the arena of cybersecurity sustenance is ready for attaining the supreme output welfares as results, also inhibiting the real assets. Setting the precise real-time issues are trailed by cracking it for affluence and escalation or magnification of cybersecurity thus by prominent universal preeminent impending cybersecurity. A meta-learning/AI-based automated security strategy is vital in the protection of critical infrastructure, users and assets disinclined to outbreaks.
{"title":"Deployment of Artificial Intelligence with Bootstrapped Meta-Learning in Cyber Security","authors":"D. Sasikala, K. Venkatesh Sharma","doi":"10.36548/jtcsst.2022.3.003","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.003","url":null,"abstract":"Cybersecurity is an extensive and vivacious domain in the commercial progression of the ecosphere. By up-to-date inhabitants, networking settings and assets, cybersecurity fits with the exigent task to realize the necessities of the imminent populace. Intelligent cybersecurity / intellectual smart cybersecurity has risen as a pioneering tool to deal with latest ambiguities in programmed cybersecurity enduring capability by bringing together Artificial Intelligence (AI) in Cybersecurity Computerization. The mechanism that enterprises in this cutting-edge technology handles the mechanism capability to acquire via depleting Bootstrapped Meta-learning and reinforced with rewards as Supreme Cybersecurity vintages, besides least resource utilizations as well as time limits. \u0000AI empowered cybersecurity technology is a vital constituent of the imminent cybersecurity revolution ahead. During this operation, a proficient computerization of AI application in the arena of cybersecurity sustenance is ready for attaining the supreme output welfares as results, also inhibiting the real assets. Setting the precise real-time issues are trailed by cracking it for affluence and escalation or magnification of cybersecurity thus by prominent universal preeminent impending cybersecurity. A meta-learning/AI-based automated security strategy is vital in the protection of critical infrastructure, users and assets disinclined to outbreaks.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117200946","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 : 2022-08-18DOI: 10.36548/jtcsst.2022.3.002
A. Arun kumar, Radha Krishna Karne
Modern network and Industrial Internet of Things (IIoT) technologies are quite advanced. Networks experience data breaches annually. As a result, an Intrusion Detection System is designed for enhancing the IIoT security protection under privacy laws. The Internet of Things' structural system and security performance criteria must meet high standards in an adversarial network. The network system must use a system that is very stable and has a low rate of data loss. The basic deep learning network technology is picked after analysing it with a huge number of other network configurations. Further, the network is upgraded and optimised by the Convolutional Neural Network technique. Additionally, an IIoT anti-intrusion detection system is built by combining three network technologies. The system's performance is evaluated and confirmed. The proposed model gives a better detection rate with a minimum false positive rate, and good data correctness. As a result, the proposed method can be used for securing an IIoT data privacy under the law.
{"title":"IIoT-IDS Network using Inception CNN Model","authors":"A. Arun kumar, Radha Krishna Karne","doi":"10.36548/jtcsst.2022.3.002","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.002","url":null,"abstract":"Modern network and Industrial Internet of Things (IIoT) technologies are quite advanced. Networks experience data breaches annually. As a result, an Intrusion Detection System is designed for enhancing the IIoT security protection under privacy laws. The Internet of Things' structural system and security performance criteria must meet high standards in an adversarial network. The network system must use a system that is very stable and has a low rate of data loss. The basic deep learning network technology is picked after analysing it with a huge number of other network configurations. Further, the network is upgraded and optimised by the Convolutional Neural Network technique. Additionally, an IIoT anti-intrusion detection system is built by combining three network technologies. The system's performance is evaluated and confirmed. The proposed model gives a better detection rate with a minimum false positive rate, and good data correctness. As a result, the proposed method can be used for securing an IIoT data privacy under the law.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117085743","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 : 2022-08-01DOI: 10.36548/jtcsst.2022.3.001
Narayan Prasad Dahal, S. Shakya
Many types of research are based on students' past data for predicting their performance. A lot of data mining techniques for analyzing the data have been used so far. This research project predicts the higher secondary students' results based on their academic background, family details, and previous examination results using three decision tree algorithms: ID3, C4.5 (J48), and CART (Classification and Regression Tree) with other classification algorithms: Random Forest (RF), K-nearest Neighbors (KNN), Support Vector Machine (SVM) and Artificial Neural Network (ANN). The research project analyzes the performance and accuracy based on the results obtained. It also identifies some common differences based on achieved output and previous research work.
许多类型的研究都是基于学生过去的数据来预测他们的表现。到目前为止，已经使用了许多用于分析数据的数据挖掘技术。本研究利用ID3、C4.5 (J48)和CART (Classification and Regression tree)三种决策树算法，结合随机森林(RF)、k近邻(KNN)、支持向量机(SVM)和人工神经网络(ANN)四种分类算法，根据学生的学习背景、家庭背景和以前的考试成绩预测高中生的成绩。研究项目根据所得结果对其性能和精度进行了分析。它还根据已取得的成果和以前的研究工作确定了一些共同的差异。
{"title":"A Comparative Analysis of Prediction of Student Results Using Decision Trees and Random Forest","authors":"Narayan Prasad Dahal, S. Shakya","doi":"10.36548/jtcsst.2022.3.001","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.3.001","url":null,"abstract":"Many types of research are based on students' past data for predicting their performance. A lot of data mining techniques for analyzing the data have been used so far. This research project predicts the higher secondary students' results based on their academic background, family details, and previous examination results using three decision tree algorithms: ID3, C4.5 (J48), and CART (Classification and Regression Tree) with other classification algorithms: Random Forest (RF), K-nearest Neighbors (KNN), Support Vector Machine (SVM) and Artificial Neural Network (ANN). The research project analyzes the performance and accuracy based on the results obtained. It also identifies some common differences based on achieved output and previous research work.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"88 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116277859","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 : 2022-07-22DOI: 10.36548/jtcsst.2022.2.006
Sanketa Kulkarni, V. S. Krushnasamy
This research focuses on fruit and vegetables classification, recognition based on its health and quality by using Raspberry pi board, which is further integrated with digital image processing techniques and machine learning concepts. Convolutional Neural Networks (CNN) is generally used to perform image identification and categorization in the object recognition systems. The recent advancements in deep learning-based models assist in performing complex image recognition. This study also proposes an effective CNN-based method for performing fruit recognition, fruit maturity based categorization, and calorie estimation. Datasets are used to train the proposed machine learning model. The dataset used here is a combination of image data containing various types of fruit; here the proposed cost-effective yet powerful fruit quality maintenance method will be useful for fruit vendors and farmers.
{"title":"Survey Paper on Fruit Recognition, Classification and Quality Health Maintenance","authors":"Sanketa Kulkarni, V. S. Krushnasamy","doi":"10.36548/jtcsst.2022.2.006","DOIUrl":"https://doi.org/10.36548/jtcsst.2022.2.006","url":null,"abstract":"This research focuses on fruit and vegetables classification, recognition based on its health and quality by using Raspberry pi board, which is further integrated with digital image processing techniques and machine learning concepts. Convolutional Neural Networks (CNN) is generally used to perform image identification and categorization in the object recognition systems. The recent advancements in deep learning-based models assist in performing complex image recognition. This study also proposes an effective CNN-based method for performing fruit recognition, fruit maturity based categorization, and calorie estimation. Datasets are used to train the proposed machine learning model. The dataset used here is a combination of image data containing various types of fruit; here the proposed cost-effective yet powerful fruit quality maintenance method will be useful for fruit vendors and farmers.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122232676","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：