Pub Date : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000174
R. Jisha, J. M. Amrita, Aswini R Vijay, G. Indhu
The introduction of new ideas with mobile applications can bring great change to people around the world. Nowadays Thousands of apps are developed to satisfy different needs of people such as for doing jobs, transactions, entertainment etc. and distributed over the Internet. So most of the existing app stores available might face difficulties for recommending a particular app to a particular user. So there is a need for recommending apps for the users according to their personal preferences and various other limitations. We made a mobile application recommendation system with ratings, Size, and Permission as parameters and we will recommend suitable apps to the user by evaluating these parameters. Here we are using Apkpure.com which is one of the famous android application markets and also makes use of Web Crawler which helps in collecting information about the website and helps in validating hyperlinks. After that by using the Clustering Algorithm, applications are grouped or clustered based on Popularity, Permission and Security aspects. This paper aims to provide a simple recommendation system without compromising rating, size and Permission aspects.
{"title":"Mobile App Recommendation System Using Machine learning Classification","authors":"R. Jisha, J. M. Amrita, Aswini R Vijay, G. Indhu","doi":"10.1109/ICCMC48092.2020.ICCMC-000174","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000174","url":null,"abstract":"The introduction of new ideas with mobile applications can bring great change to people around the world. Nowadays Thousands of apps are developed to satisfy different needs of people such as for doing jobs, transactions, entertainment etc. and distributed over the Internet. So most of the existing app stores available might face difficulties for recommending a particular app to a particular user. So there is a need for recommending apps for the users according to their personal preferences and various other limitations. We made a mobile application recommendation system with ratings, Size, and Permission as parameters and we will recommend suitable apps to the user by evaluating these parameters. Here we are using Apkpure.com which is one of the famous android application markets and also makes use of Web Crawler which helps in collecting information about the website and helps in validating hyperlinks. After that by using the Clustering Algorithm, applications are grouped or clustered based on Popularity, Permission and Security aspects. This paper aims to provide a simple recommendation system without compromising rating, size and Permission aspects.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129008287","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-00099
Rahul, Surabhi Adhikar, Monika
Due to the plethora of data available today, text summarization has become very essential to gain just the right amount of information from huge texts. We see long articles in news websites, blogs, customers’ review websites, and so on. This review paper presents various approaches to generate summary of huge texts. Various papers have been studied for different methods that have been used so far for text summarization. Mostly, the methods described in this paper produce Abstractive (ABS) or Extractive (EXT) summaries of text documents. Query-based summarization techniques are also discussed. The paper mostly discusses about the structured based and semantic based approaches for summarization of the text documents. Various datasets were used to test the summaries produced by these models, such as the CNN corpus, DUC2000, single and multiple text documents etc. We have studied these methods and also the tendencies, achievements, past work and future scope of them in text summarization as well as other fields.
{"title":"NLP based Machine Learning Approaches for Text Summarization","authors":"Rahul, Surabhi Adhikar, Monika","doi":"10.1109/ICCMC48092.2020.ICCMC-00099","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00099","url":null,"abstract":"Due to the plethora of data available today, text summarization has become very essential to gain just the right amount of information from huge texts. We see long articles in news websites, blogs, customers’ review websites, and so on. This review paper presents various approaches to generate summary of huge texts. Various papers have been studied for different methods that have been used so far for text summarization. Mostly, the methods described in this paper produce Abstractive (ABS) or Extractive (EXT) summaries of text documents. Query-based summarization techniques are also discussed. The paper mostly discusses about the structured based and semantic based approaches for summarization of the text documents. Various datasets were used to test the summaries produced by these models, such as the CNN corpus, DUC2000, single and multiple text documents etc. We have studied these methods and also the tendencies, achievements, past work and future scope of them in text summarization as well as other fields.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129196303","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000101
Satya Goutham Putrevu, M. Panda
Traffic sign recognition is one of the active areas of research in recent years. The automotive technology is moving towards automation in most of the aspects including traffic sign recognition. In an attempt to focus on driving and concentrate on road the driver often misses out the traffic signs, results of which may lead to catastrophic events. This can be avoided by automating the tasks of traffic sign detection and recognition. In this paper, we implement the traffic signs recognition through distributed ensemble technique (DEL), which is an efficient method to automate traffic sign detection. The primary goal of distributed ensemble learning is to decrease the complexity, reduce the training load on each model and improve the convergence. The impact of load distribution with respect to the number of workers has been studied and thereby understanding the trends of a distributed ensemble. Here we use an ensemble of CNN models to train with standard German data set. Keras is used for implementation of distributed ensemble in CNN. Detailed analysis on data distribution between workers and how it impacts the model accuracy is discussed.
{"title":"Traffic Sign Recognition Using Distributed Ensemble Learning","authors":"Satya Goutham Putrevu, M. Panda","doi":"10.1109/ICCMC48092.2020.ICCMC-000101","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000101","url":null,"abstract":"Traffic sign recognition is one of the active areas of research in recent years. The automotive technology is moving towards automation in most of the aspects including traffic sign recognition. In an attempt to focus on driving and concentrate on road the driver often misses out the traffic signs, results of which may lead to catastrophic events. This can be avoided by automating the tasks of traffic sign detection and recognition. In this paper, we implement the traffic signs recognition through distributed ensemble technique (DEL), which is an efficient method to automate traffic sign detection. The primary goal of distributed ensemble learning is to decrease the complexity, reduce the training load on each model and improve the convergence. The impact of load distribution with respect to the number of workers has been studied and thereby understanding the trends of a distributed ensemble. Here we use an ensemble of CNN models to train with standard German data set. Keras is used for implementation of distributed ensemble in CNN. Detailed analysis on data distribution between workers and how it impacts the model accuracy is discussed.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124545827","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-0005
Vivek Urankar, Chiranjit R Patel, B. A. Vivek, V. Bharadwaj
Signal processing and communication systems are widely dependent on the analog to digital converters [ADC]. Low power consumption remains as a considerable benefit from the layout design. This study presents a four bit flash ADC using CMOS 45nm technology. Operational amplifier design, which remains as the integral part of ADC is also discussed. To enable an improved performance of the ADC, a potent operational amplifier is designed with a frequency range ± 5MHz along with an operating voltage of 2.5 V for serving at the heart of Flash ADC. The thermometer encoder circuit is a logic-based encoder built upon XOR and OR gates. Cadence Virtuoso circuit and layout editor along with verification tools (LVS and DRC) are used to design different layouts and schematics. The 4-Bit Flash ADC uses 9 mW of power with a delay of $1.11 mu s$ in conversion.
{"title":"45nm CMOS 4-Bit Flash Analog to Digital Converter","authors":"Vivek Urankar, Chiranjit R Patel, B. A. Vivek, V. Bharadwaj","doi":"10.1109/ICCMC48092.2020.ICCMC-0005","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-0005","url":null,"abstract":"Signal processing and communication systems are widely dependent on the analog to digital converters [ADC]. Low power consumption remains as a considerable benefit from the layout design. This study presents a four bit flash ADC using CMOS 45nm technology. Operational amplifier design, which remains as the integral part of ADC is also discussed. To enable an improved performance of the ADC, a potent operational amplifier is designed with a frequency range ± 5MHz along with an operating voltage of 2.5 V for serving at the heart of Flash ADC. The thermometer encoder circuit is a logic-based encoder built upon XOR and OR gates. Cadence Virtuoso circuit and layout editor along with verification tools (LVS and DRC) are used to design different layouts and schematics. The 4-Bit Flash ADC uses 9 mW of power with a delay of $1.11 mu s$ in conversion.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123019767","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-0000111
M. K. Das, K. Rangarajan
Performance monitoring and failure prediction of industrial equipment plays a very important role not only in the quality of the manufactured material but also in the amount of time and money saved in the overall maintenance. This paper seeks to survey the general research development and advancement in the use of AI/ML techniques for equipment fault prediction in industries over time. The topics surveyed in this paper include various algorithms, use cases and concepts that pertain to the use of such technology in a wide range of industries including oil and gas, coal, automotive industry, etc. This survey addresses early research work done between the late 80s to the early 2000s, the recent research done between the early 2000s to 2017 and the latest research, the work done in the past two years. It can be concluded that this paper makes a thorough survey of different ML/AI methods used in the Industrial Manufacturing domain. Methods like LSTM, Bi-LSTM, ANNs and SVM classifiers were found to be some of the popular approaches used.
{"title":"Performance Monitoring and Failure Prediction of Industrial Equipments using Artificial Intelligence and Machine Learning Methods: A Survey","authors":"M. K. Das, K. Rangarajan","doi":"10.1109/ICCMC48092.2020.ICCMC-0000111","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-0000111","url":null,"abstract":"Performance monitoring and failure prediction of industrial equipment plays a very important role not only in the quality of the manufactured material but also in the amount of time and money saved in the overall maintenance. This paper seeks to survey the general research development and advancement in the use of AI/ML techniques for equipment fault prediction in industries over time. The topics surveyed in this paper include various algorithms, use cases and concepts that pertain to the use of such technology in a wide range of industries including oil and gas, coal, automotive industry, etc. This survey addresses early research work done between the late 80s to the early 2000s, the recent research done between the early 2000s to 2017 and the latest research, the work done in the past two years. It can be concluded that this paper makes a thorough survey of different ML/AI methods used in the Industrial Manufacturing domain. Methods like LSTM, Bi-LSTM, ANNs and SVM classifiers were found to be some of the popular approaches used.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123076388","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-00049
K. R. Kavitha, Avani Prakasan, P.J Dhrishya
Feature selection in machine learning can also be specified as attribute selection. It is a process of selection desired feature from a large amount of data set. A typical microarray data set has basic properties such as high-dimensionality and limited sample, which makes it less accurate for classification and also time-consuming. In order to increase the accuracy of the classification, we have to decrease the dimensionality of the dataset. To achieve this, there are two feature elimination methods namely, feature selection and feature extraction. The proposed study focuses on the filter-based feature selection method. The main aim of the proposed work is to decrease the computation time and increase the accuracy of classification and prediction. To achieve this, he proposed work reduces the dimensionality of data set and also the redundancy between various features. Several feature selection methods exist but most of them have increased computational time, so here we are using score-based criteria fusion method for feature selection, which improves the prediction accuracy and decreases the computational time.
{"title":"Score-Based Feature Selection of Gene expression Data for Cancer Classification","authors":"K. R. Kavitha, Avani Prakasan, P.J Dhrishya","doi":"10.1109/ICCMC48092.2020.ICCMC-00049","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00049","url":null,"abstract":"Feature selection in machine learning can also be specified as attribute selection. It is a process of selection desired feature from a large amount of data set. A typical microarray data set has basic properties such as high-dimensionality and limited sample, which makes it less accurate for classification and also time-consuming. In order to increase the accuracy of the classification, we have to decrease the dimensionality of the dataset. To achieve this, there are two feature elimination methods namely, feature selection and feature extraction. The proposed study focuses on the filter-based feature selection method. The main aim of the proposed work is to decrease the computation time and increase the accuracy of classification and prediction. To achieve this, he proposed work reduces the dimensionality of data set and also the redundancy between various features. Several feature selection methods exist but most of them have increased computational time, so here we are using score-based criteria fusion method for feature selection, which improves the prediction accuracy and decreases the computational time.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130809107","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-0007
Rupam Bhagawati
In this internet and digitalization age, information in any form is very important to perform a digital task. The processing of any information to obtain the desired results requires a specific medium and sometimes to accomplish various tasks related to that set of information like browsing, searching, sorting, retrieval and management. In order to perform those tasks on the information, which are present on various acquaintances, we need to analyze the information by performing an unsupervised clustering in the realm of quantum computation. Quantum clustering is the core technique used in quantum computation to perform clustering of information with several algorithms that have been introduced and studied till date to analyze the cluster for increasing the efficiency of information exploration, information retrieval, information management and browsing system. Hence, introducing a quantum clustering technique to form clusters which would include sentences from a set of informative data set and the formation of clusters would be carried out by performing Semantic Analysis.
{"title":"Clusters Analyzer Algorithm for Informative Acquaintances - Quantum Clustering Algorithm","authors":"Rupam Bhagawati","doi":"10.1109/ICCMC48092.2020.ICCMC-0007","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-0007","url":null,"abstract":"In this internet and digitalization age, information in any form is very important to perform a digital task. The processing of any information to obtain the desired results requires a specific medium and sometimes to accomplish various tasks related to that set of information like browsing, searching, sorting, retrieval and management. In order to perform those tasks on the information, which are present on various acquaintances, we need to analyze the information by performing an unsupervised clustering in the realm of quantum computation. Quantum clustering is the core technique used in quantum computation to perform clustering of information with several algorithms that have been introduced and studied till date to analyze the cluster for increasing the efficiency of information exploration, information retrieval, information management and browsing system. Hence, introducing a quantum clustering technique to form clusters which would include sentences from a set of informative data set and the formation of clusters would be carried out by performing Semantic Analysis.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126818486","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000119
M. Sathish Kumar, B. Indrani
Phishing is an online unlawful act which takes place when a malicious webpage impersonates as genuine webpage for acquiring confidential details about the user. The phishing attack maintains to acquire a crucial risk factor for web user and annoying threat in the domain of electronic commerce. This study proposes a brain storm optimization (BSO) based association rule mining (ARM) model called BSOARM model to detect of genuine and phishing URLs. Here, BSO algorithm is applied to optimize the rules generated by ARM. The rule attained is deduced to highlight the features which are further common in phishing URLs.To performance of the BSO-ARM model has been tested using a Phishing Dataset. The projected BSO-ARM model has optimized the number of generated rules as 45 and attained maximum accuracy of 86.35%, precision of 81.60%, recall of 86.81% and F-score of 84.13% respectively. These values ensured that the BSO-ARM model has offered better outcomes over the compared methods.
{"title":"Brain Storm Optimization based Association Rule Mining Model for Intelligent Phishing URLs Websites Detection","authors":"M. Sathish Kumar, B. Indrani","doi":"10.1109/ICCMC48092.2020.ICCMC-000119","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000119","url":null,"abstract":"Phishing is an online unlawful act which takes place when a malicious webpage impersonates as genuine webpage for acquiring confidential details about the user. The phishing attack maintains to acquire a crucial risk factor for web user and annoying threat in the domain of electronic commerce. This study proposes a brain storm optimization (BSO) based association rule mining (ARM) model called BSOARM model to detect of genuine and phishing URLs. Here, BSO algorithm is applied to optimize the rules generated by ARM. The rule attained is deduced to highlight the features which are further common in phishing URLs.To performance of the BSO-ARM model has been tested using a Phishing Dataset. The projected BSO-ARM model has optimized the number of generated rules as 45 and attained maximum accuracy of 86.35%, precision of 81.60%, recall of 86.81% and F-score of 84.13% respectively. These values ensured that the BSO-ARM model has offered better outcomes over the compared methods.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126840198","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000175
A. Visalatchi, T. Navasri, P. Ranjanipriya, R. Yogamathi
Computer vision and video analytics are the torrid research area in Machine learning and their establishment process traditionally starts with object detection and eventually tracking. In recent years, there is a tremendous growth in performing comprehensive study based on the field of object detection and Pattern Analysis. In our system we have improvised and experimented with detection method based on machine learning and deep learning approach in object recognition and pattern analysis. We assume object detection as a retrogression problem to spatially separated corresponding class probabilities and bounding boxes. Many prominent algorithms have been designed for object detection, Pattern Analysis and tracking, which also includes edge tracking, color segmentation and pattern matching. A single neural network is capable of predicting class probabilities and bounding boxes directly from the full image per cycle. Therefore we have used various neural network algorithms such as YOLOv3, Single Shot Multiple detection algorithm to carry out video analysis using object detection and drowsiness detection using pattern or behavior analysis with the help of Tensorflow. The framework will recognize object continuously, from the input perceived through camera where it can apparently capture a required frames to predict the object and also to match the pattern. It has been accomplished using real-time video processing and a single camera. The proposed system is versatile to operate in complex, real time, non-plain environment.
计算机视觉和视频分析是机器学习中的热门研究领域，它们的建立过程传统上从目标检测到最终跟踪开始。近年来，基于目标检测和模式分析的综合研究有了很大的发展。在我们的系统中，我们在物体识别和模式分析中即兴和实验了基于机器学习和深度学习方法的检测方法。我们假设目标检测是一个空间分离的对应类概率和边界框的回归问题。在目标检测、模式分析和跟踪方面，已经设计了许多突出的算法，其中还包括边缘跟踪、颜色分割和模式匹配。单个神经网络能够根据每个周期的完整图像直接预测类别概率和边界框。因此，我们使用了各种神经网络算法，如YOLOv3, Single Shot Multiple检测算法，利用目标检测进行视频分析，利用Tensorflow的模式或行为分析进行嗜睡检测。该框架将持续识别物体，从通过摄像头感知的输入中，它显然可以捕获所需的帧来预测物体并匹配模式。该系统采用实时视频处理和单摄像机实现。该系统具有通用性，可在复杂、实时、非平面环境下运行。
{"title":"Intelligent Vision with TensorFlow using Neural Network Algorithms","authors":"A. Visalatchi, T. Navasri, P. Ranjanipriya, R. Yogamathi","doi":"10.1109/ICCMC48092.2020.ICCMC-000175","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000175","url":null,"abstract":"Computer vision and video analytics are the torrid research area in Machine learning and their establishment process traditionally starts with object detection and eventually tracking. In recent years, there is a tremendous growth in performing comprehensive study based on the field of object detection and Pattern Analysis. In our system we have improvised and experimented with detection method based on machine learning and deep learning approach in object recognition and pattern analysis. We assume object detection as a retrogression problem to spatially separated corresponding class probabilities and bounding boxes. Many prominent algorithms have been designed for object detection, Pattern Analysis and tracking, which also includes edge tracking, color segmentation and pattern matching. A single neural network is capable of predicting class probabilities and bounding boxes directly from the full image per cycle. Therefore we have used various neural network algorithms such as YOLOv3, Single Shot Multiple detection algorithm to carry out video analysis using object detection and drowsiness detection using pattern or behavior analysis with the help of Tensorflow. The framework will recognize object continuously, from the input perceived through camera where it can apparently capture a required frames to predict the object and also to match the pattern. It has been accomplished using real-time video processing and a single camera. The proposed system is versatile to operate in complex, real time, non-plain environment.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130710497","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-00022
Fengsheng Zeng, Yan’e Zheng
Tourism recommendation system based on the knowledge graph feature learning is proposed and designed in this paper. The primary task for implementing a travel recommendation system is data collection, including user information, integrated user interaction records, tourist attraction information, and also contextual information. Among them, the user information primarily originates from the information entered by user in the registration process. The interaction record between the user and the system can be obtained from the system log, while the contextual information is entered by the user autonomously or obtained through various sensors. In this paper, a data processing and analytic framework is integrated to construct the novel scenario used for the recommendation. When compared the proposed model with the state-of-the-art research works, it has been proven that the proposed model can obtain the higher recommendation accuracy.
{"title":"Tourism Recommendation System based on Knowledge Graph Feature Learning","authors":"Fengsheng Zeng, Yan’e Zheng","doi":"10.1109/ICCMC48092.2020.ICCMC-00022","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00022","url":null,"abstract":"Tourism recommendation system based on the knowledge graph feature learning is proposed and designed in this paper. The primary task for implementing a travel recommendation system is data collection, including user information, integrated user interaction records, tourist attraction information, and also contextual information. Among them, the user information primarily originates from the information entered by user in the registration process. The interaction record between the user and the system can be obtained from the system log, while the contextual information is entered by the user autonomously or obtained through various sensors. In this paper, a data processing and analytic framework is integrated to construct the novel scenario used for the recommendation. When compared the proposed model with the state-of-the-art research works, it has been proven that the proposed model can obtain the higher recommendation accuracy.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114126158","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：