检索结果-内蒙古大学图书馆

Neural model based collaborative filtering for movie recommendation system

International Journal of Information Technology (Singapore) 2022年第4期14卷 2067-2077页

作者： Jena, Kalyan Kumar Bhoi, Sourav Kumar Mallick, Chittaranjan Jena, Soumya Ranjan Kumar, Raghvendra Long, Hoang Viet Son, Nguyen Thi Kim Department of Computer Science and Engineering Parala Maharaja Engineering College (Govt.) Berhampur India Department of Basic Science (Mathematics) Parala Maharaja Engineering College (Govt.) Berhampur India Department of Computer Science and Engineering GIET University Gunupur India Faculty of Information Technology University of Technology-Logistic of Public Security Hanoi Viet Nam Faculty of Natural Sciences Hanoi Metropolitan University Hanoi Viet Nam

Due to the availability of enormous number of products of same domain is increasing day by day the possibility of getting your desire product is getting less. Therefore, a recommendation not only helps you find the best probable product according to your preference but also increases the efficacy to find the product for you in less time interval. Artificial neural network has been producing a tremendous result in the practical solutions like image classification, speech recognitions and various AI problems. The use of neural network to build recommendations system can also be used as an auto encoder in various sector. The neural network contains many layers and each layer contains many perceptron which holds the weight. While the network gets trained, the weights of each perception are optimized and get adjusted. Building a simple neural network model for predicting recommendations with high accuracy is the objective of this work. The dataset used in this recommendations model is contributed by the Movie-lens archive. Manipulating the data into a right form and format is the most important part of the model. The whole work is performed, experimented and evaluated in python as it consists of many predefined useful libraries. The result of the recommender model is evaluated by finding the Hit-Ratio. The Hit-ratio obtained by this model is 87. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Implicit data, Movie predictions Latent space Matrix factorization Neural-network

来源：评论

学校读者我要写书评

暂无评论

ANN-Based Model for Analysis and Determination of Crop Damage 9

ANN-Based Model for Analysis and Determination of Crop Damag...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Pant, Janmejay Pant, Pushpa Pant, Himanshu Dhanik, Saurabh Singh, Devendra Juyal, Amit Graphic Era Hill University Department of Computer Science and Engineering India Kumaun University M.B. Govt. P.G College Department of Geography Haldwani India Department of Computer Science Pal College of Technology and Management Haldwani India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350397376

An essential part of India's economy is agriculture. In rural areas, most people depend on agriculture for a living, growing cereals, vegetables, fruits, and spices. It affects a person's and country's economies since these products are very profitable. Still, crops can be damaged for various reasons, including crop diseases, pesticide damage, and other causes. It will be a significant loss for farmers. Aside from that, the country's economy is negatively affected by a lack of supply in the agricultural products market. So, crop damage assessment in the early stages will benefit farmers, as it allows them to take necessary action. This study presents an investigation into the utilization of machine learning (ML) methods within the agricultural industry. The study is centered on the categorization and prediction of crop impairment resulting from diseases and pests. The framework of Artificial Neural Network(ANN), which is a machine learning algorithm capable of categorizing crop damage, is introduces in this paper. The ANN results with 91.69% training accuracy and 83.48% testing accuracy. This trained model is used for crop damage assessment. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Sand Dune Computing (SDC): A New Framework for Efficient Execution of User Requests to Support Device-Server Model

Sand Dune Computing (SDC): A New Framework for Efficient Exe...

引用

Information Technology (OCIT), OITS International Conference on

作者： Sourav Kumar Bhoi Department of Computer Science and Engineering Parala Maharaja Engineering College (Govt.) Berhampur India

In the current world of computing, due to tremendous rise of smart devices all over the world it is difficult to get quick service from the limited servers in the heterogeneous environment as some servers are highly loaded with device requests. So, there should be a model or framework to analyze the requests and server traffic in the device-server model with some solution that can execute the device tasks very efficiently. Sand Dune Computing (SDC) is a new computing framework proposed whose main architecture is mainly motivated from a natural process in the environment that is formation of Sand Dunes in areas where the sand grains or smaller loose particles of sands are blown by wind, and accumulated as a temporary hill like structure called as Dune. Here, in the SDC architecture the Sand Grains are mainly considered as the device requests from multiple smart devices to get service from the servers, where server with more traffic is considered as the Sand Dune where the waited device requests are queued. Wind is assumed as the rate of requests from the smart devices. This architecture of SDC will help the current generation technologies or systems such as Internet of Things, cloud computing, edge/fog computing, osmotic computing, ad hoc and sensor networks, distributed computing, AI, etc. to analyze the device requests and server loads based on Sand Area, Dune Area, Dune Size, Dune Frequency, Wind Speed, and Wind Frequency. Also, in this paper some applications of SDC and research challenges are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Migraine Prediction Method Using Feature Selection with Hybrid Optimization Method

Migraine Prediction Method Using Feature Selection with Hybr...

引用

Innovations in Communications, Electrical and computer engineering (ICICEC), International Conference on

作者： Tushar Choudhary C Kunal InFeedo Tech Inc Gurugram India Department of Computer Science Govt. Engineering College Ajmer India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

Migraine is a common and painful neurological condition that is often characterized by one-sided, throbbing, and pulsating headaches. Unfortunately, a lot of people who suffer from migraines get misdiagnosed when the doctors use the conventional diagnostic criteria made by the IHS (International Headache Society). As a result, there is great interest in the development of automated methods that could assist in the diagnosis of migraines. This work offers a new method for diagnosing migraines through the integration of genetic algorithms and the PSO algorithm to select features, followed by classification using Random Forest. The achieved methodology demonstrates an accuracy of 99.63% which is superior to that of the conventional methods including SVM, XGBoost, Decision Tree, Random Forest, and the Stacking algorithms. Through this technique, the identification of malicious URLs is done with great accuracy as the false alarms and missed detections are minimized. An applicable scheme is the basis for the development of more sophisticated devices for the purposes of predicting migraines. In the case of everyday life, the upcoming work is going to focus on the assessment of the scalability and efficiency.

关键词： Support vector machines Accuracy Stacking Migraine Medical services Feature extraction Prediction algorithms Classification algorithms Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Detection of DDoS Attacks in SDN Environment with Big Data Distributed Frameworks - A Review

Detection of DDoS Attacks in SDN Environment with Big Data D...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Amandeep Kaur C. Rama Krishna Nilesh Vishwasrao Patil Aditya Bhardwaj Department of Computer Science & Engineering National Institute of Technical Teacher Training & Research Chandigarh India Department of Computer Engineering Govt. Polytechnic Chhatrapati Sambhajinagar Aurangabad India School of Computer Science Engineering & Technology (SCSET) Bennett University Greater Noida India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

Software-Defined Networking (SDN) represents a paradigm shift in network management, offering unprecedented control and flexibility. However, due to its architectural flaws, it remains vulnerable to various cyberattacks, such as Distributed Denial of Service (DDoS). This review critically analyzes existing literature on DDoS detection approaches within SDN environments, primarily focusing on the effectiveness of various big data distributed frameworks. We compare traditional detection methods with those deployed in Distributed big-data frameworks. It emphasizes the advantages of stream-processing frameworks such as Apache Flink, Apache Kafka Streams, Apache Spark Streaming, Apache Structured Streaming, Apache Storm and Eclipse StreamPipes. Our analysis reveals that distributed big data frameworks handle large-scale, high-traffic DDoS attacks more efficiently than traditional frameworks. By systematically contrasting the characteristics of these frameworks, we identify the most suitable use cases for each, providing insights into their applicability and effectiveness in detecting DDoS threats in the SDN environment.

关键词： Storms Reviews Big Data Denial-of-service attack Sparks Security computer crime Artificial intelligence Software defined networking Streams

来源：评论

学校读者我要写书评

暂无评论

GIDSL: Indian-Gujarati Isolated Dynamic Sign Language Recognition Using Deep Learning

引用

SN computer Science 2024年第5期5卷 527页

作者： Joshi, Jay M. Patel, Dhaval U. Electronics and Communication Engineering Department Government Engineering College Near K J Polytechnic Opp.- Govt. Guest House Old National Highway-8 Bholav Bharuch 392002 India Nr. Vishwakarma Government Engineering College Gujarat Technological University Nr. Visat Three Roads Visat-Gandhinagar Highway Chandkheda Gujarat Ahmedabad 382424 India

In today's connected world, effective communication is crucial. However, due to limited familiarity with sign language, the deaf and mute community often struggles with communication barriers. The state of Gujarat with over 60 million population, has a sizable population affected by deafness and muteness as revealed by the Indian census. To solve this challenge, we conducted a pioneering study of dynamic Gujarati Sign Language (GSL) recognition. Our study introduces a three-step approach to comprehensive sign language recognition. First, a robust dataset that has been accurately created using various signs important in everyday life. We then use the Mediapipe algorithm to extract key features and significantly reduce space complexity. We then build a novel 6 layer deep learning model consisting of Long Short-Term Memory (LSTM) and dense layers. In the last phase, we developed a real-time detection system and subjected it to rigorous testing on a wide data set. The performance evaluation included metrics such as accuracy, recall, F1 score and precision. The experimental results demonstrate the high accuracy of our proposed algorithm compared to state of the art Indian dynamic sign language recognition methods. This research not only fills a significant research gap, but also inspires hope to improve communication accessibility within the deaf community and chart a transformative trajectory toward inclusion. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Assistive technologies Deep Learning Gesture recognition Indian sign language Long short-term memory Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Strategies for Crop Assessment in Diverse Districts of Uttarakhand 2

Machine Learning-based Strategies for Crop Assessment in Div...

引用

2nd International Conference on Data Science and Information System, ICDSIS 2024

作者： Pant, Janmejay Pant, Pushpa Bhatt, Jaishankar Singh, Devendra Mohan, Lalit Pant, Hitesh Kumar Graphic Era Hill University Department Of Computer Science And Engineering Bhimtal Campus India M.B. Govt. P.G College Department Of Geography Haldwani India Graphic Era Deemed To Be University Department Of Computer Science And Engineering Uttarakhand Dehradun India Gl Bajaj Institute Of Technology And Management Noida India Kumaun University Department Of Management Studies Bhimtal India

ISBN: (纸本)9798350381665

Crop prediction has historically been influenced by farmers' needs, but the impact of climate change on crop yields has made traditional methods unreliable. Factors such as soil quality and environmental conditions are no longer sufficient for determining which crops to grow. Manual predictions have proven ineffective, prompting the need for accurate crop prediction methods. Machine learning has emerged as a crucial tool for this purpose, considering various factors like soil composition, geographical location, and climate conditions. Selecting the appropriate crop based on these attributes is essential for accurate predictions. This paper examines multi-class crop prediction models employing machine learning techniques. Specifically, Xgboost and Random Forest classifiers were utilized in our analysis. While both models demonstrate good accuracy, The findings of this study indicate that both Random Forest and Xgboost models achieve relatively high accuracy rates in predicting crops from the dataset. Specifically, the Xgboost model outperforms the Random Forest model slightly, with an accuracy of 83.25% compared to 82.5%. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Smart Residential Load Control Technique with Internet of Things and Pattern Recognition Based Load Identification 3

A Smart Residential Load Control Technique with Internet of ...

引用

3rd IEEE Applied Signal Processing Conference, ASPCON 2023

作者： Datta, Sayan Bhowmick, Shreerup Datta, Suman Chatterjee, Swastik Ghosh, Satwik Ganguly, Biswarup Chatterjee, Arunava Garai, Soumyadeep Meghnad Saha Institute of Technology Department of Electrical Engineering Kolkata700150 India National Institute of Technology Silchar Department of Electrical Engineering Assam Silchar788010 India Raghunathpur Govt. Polytechnic Department of Electrical Engineering India Jadavpur Univeristy School of Material Science and Nano Technology Kolkata700032 India

ISBN: (纸本)9798350325881

This paper presents a design of a smart home automation system (HAS) for non-intrusive load monitoring (NILM) with load identification. The proposed framework aims to develop an internet-of-things (IoT) based home automation system, where various home devices can be controlled with the help of voice activated remote control. The development of a firmware for smart control is done by minimizing human intervention for preserving the integrity for all electrical appliances in a smart home. NodeMCU based IoT platform has been employed for execution of the automation process. The proposed system possesses various sorts of sensors installed for operating loads based on the discomfort level of the individuals. Moreover, pattern recognition-based load identification is also proposed along with the control of home appliances. Experimental results of the proposed system outperform other IoT protocols in terms of energy consumption and cost reliability. The developed prototype supports user friendly interface with relatively low-cost design and ease of installation. The developed module is a generic one that could be a good contender for helping impaired people. © 2023 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Dense Captioning of Videos using Feature Context Integrated Deep LSTM with Local Attention 6

Dense Captioning of Videos using Feature Context Integrated ...

引用

6th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2022

作者： Jacob, Jaimon Devassia, V.P. Govt. Model Engineering College Computer Science and Engineering Department Kerala Kochi India St.Joseph's College of Engineering and Technology Electronics and Communication Engineering Department Kerala Pala India

ISBN: (数字)9781665469418

ISBN: (纸本)9781665469418

Dense captioning is a fast emerging area in video processing in natural language, that construe semantic contents present in an input video and. A traditional deep learning algorithm faces more challenges in solving this problem because it requires optimizing not just one set of values, but two sets, namely (1) event proposals, which are the timestamps for detecting an activity in a particular temporal region, and (2) natural language annotations for the detected proposals. Bidirectional LS TMs are used to predict event proposals based on information from the past and future of the event. Captions for detected events are also generated based on the past and future information associated with the event. The context vectors are augmented with original C3D video features in the decoder network in order to optimize the encoder network for proposals instead of captions. In this way, all the information necessary for the decoding network is provided. A local attention mechanism is added to the model so that it can focus on the relevant parts of the data to improve its performance. As a final step, captions will be generated with deep LSTMs. In order to verify the effectiveness of proposed model, a rigorous experiments have been conducted on the suggested innovations and demonstrated that it is remarkably effective at dense captioning events in videos with significant gains across a variety of metrics when it uses Feature Context Integrated (FC1) Deep LS TM with local attention. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimization Techniques Used in Machining Processes: A Review 1

引用

2nd International Conference on Advances in Materials and Manufacturing Technology, ICAMMT 2022

作者： Jaurker, Diksha Pradhan, M.K. Jaurker, Siddharth Malviya, Raj Shri G.S. Institute of Technology & Science Indore India Department of Mechanical Engineering National Institute of Technology Raipur India Govt. Polytechnic College Damoh India National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (数字)9789819929214

ISBN: (纸本)9789819929207

In the rapidly advancing and spontaneous manufacturing industry, optimizing methods in machining processes is critical for a production plant to adapt efficiently to intense competitiveness and rising global demand for premium products. Optimization techniques in machining processes are regarded as a critical instrument for the continuous enhancement of quality of output. These methods involve the modeling of parameters and their relationships and the calculation of optimal processing conditions. But, identifying ideal machining conditions using cost-effective mathematical models is a complicated research endeavor, and modeling and optimization approaches have experienced significant growth and extension over time. The strategic vision of numerous modeling and optimization methodologies in machining processes has been assessed in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：