检索结果-内蒙古大学图书馆

1st International Conference on Innovative Engineering sciences and Technological Research, ICIESTR 2024

作者： Wilfred Blessing, N.R. Pyingkodi, M. Wasim Haidar, S.K. Palarimath, Suresh Paravathavarthini, S. Balakumar, C. Sheeja Kumari, V. Sutherlin Subitha, G. Seldev Christopher, S. University of Technology and Applied Sciences-Ibri College of Computing and Information Sciences Ibri Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences-Salalah College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Technology Erode India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Saveetha Institute of Medical and Technical Sciences Department of Computational Intelligence Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Aruthenganvilai India St. Xavier's Catholic College of Engineering Department of Computer Science and Engineering Nagercoil India

ISBN: (纸本)9798350348637

Precision agriculture, driven by advancements in technology, aims to optimize farming practices by utilizing data and technology to enhance efficiency, productivity, and sustainability This research introduces an innovative pilot investigation centered on the convergence of two revolutionary technologies are the Internet of Things (IoT) and Deep Learning. With a specific focus on advancing precision agriculture, the primary objective of this study is to evaluate the combined effects of data collection facilitated by IoT and analytical capabilities of deep learning in enhancing and optimizing various agricultural processes. The integration of IoT in agriculture has revolutionized data acquisition, employing an array of sensors to monitor critical parameters such as soil moisture, temperature, and crop health. Concurrently, Deep Learning, a subset of artificial intelligence, exhibits the potential to glean actionable insights from voluminous datasets, offering advanced analytics and predictive capabilities. This study investigates the practical implementation and efficacy of this integration in a controlled agricultural setting. Sensors strategically positioned in the pilot study capture real-time data, while deep learning algorithms process and analyze this information. The primary objectives include evaluating the effectiveness of this combined technology in optimizing irrigation schedules, predicting crop yields, and identifying anomalies in crop health. Preliminary findings underscore the transformative potential of IoT and Deep Learning, empowering farmers with real-time data for informed decision-making. Key considerations encompassed in the study include IoT Sensors, Deep learning algorithms, and user adoption. The research not only sheds light on the technical intricacies of the integration but also delves into the challenges and opportunities inherent in merging these technologies within the agricultural landscape. As agriculture transitions towards the next

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning Strategy with Multi-dimensional Knowledge Distillation for One-stage Object Detection 22

Incremental Learning Strategy with Multi-dimensional Knowled...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Li, Yimeng Liu, Xuejiao Xiang, Xueshuang Tan, Yu-An Meng, Weizhi School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Qian Xuesen Laboratory of Space Technology China Academy of Space Technology Beijing China Department of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby Denmark

ISBN: (纸本)9798331527471

In practical applications, object detectors often encounter unknown classes samples. As object detection datasets undergo continuous development, the need arises for object detectors to adeptly recognize an escalating array of new classes while retaining the original detection capability. This paper introduces a new class incremental object detection learning framework with multi-dimensional knowledge distillation, using Yolov5 as the foundational detection model. Specifically, we utilize local feature distillation, attention distillation and global feature distillation to preserve information in the original model’s feature maps. Additionally, we employ response distillation to ensure the model remains responsive to previous classes. In comparison to the state-of-the-art methods, our approach achieves higher overall accuracy on PASCAL VOC 2007. Especially in the "19+1" incremental task, our approach gets the highest mAP@0.5 of 0.697 with a minimum mean AP decline rate of 4.45%. For the "4+3" and "6+1" tasks on KITTI, our approach preserves the model’s responsiveness to the original task more effectively while achieving the highest overall accuracy. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi Label Classification Algorithm Based on Conditional Local Correlations among Labels and Ensemble Learning 25

Multi Label Classification Algorithm Based on Conditional Lo...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Alazaidah, Raed Nasir, Ola Hadi, Wael Samara, Ghassan Al Daoud, Essam Aljaidi, Mohammad Khouj, Mohammed Talat Elsoud, Esraa Abu Alzoubi, Haneen Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Petra University Faculty of Information Technology Department of Cyber Security Amman Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Applied Science Private University Faculty of Information Technology Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

Multi-Label Classification (MLC) is an advanced form of traditional classification, where each data instance is simultaneously associated with multiple labels. The importance of MLC has increased significantly in recent years, due to its wide range of application areas. Modern algorithms, when faced with the challenge of multiple labels, continue to show suboptimal performance, conversely, they show significantly superior performance when processing single-label datasets. This paper proposes a new algorithm to deal with the problem of transforming datasets from multiple labels to single labels by exploiting conditional and local correlations between labels after applying the Apriori predictive algorithm to extract relationships. Six ensemble learning models: Voting Hard, Voting Soft, Voting Weighted, Stacking LR, Stacking RF, and Stacking SVM, along with four classification models: SMO, DecisionStump, Random Forest, and Random Committee, were applied to three datasets. The algorithm showed effective and good performance by comparing the results of the proposed Multi Label Classification algorithm based on Conditional Local Correlations among Labels (MLC-CLCL) with several popular algorithms for dealing with multiple labels. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PromptMap: An Alternative Interaction Style for AI-Based Image Generation 25

PromptMap: An Alternative Interaction Style for AI-Based Ima...

引用

30th International Conference on Intelligent User Interfaces, IUI 2025

作者： Adamkiewicz, Krzysztof Woźniak, Pawel Wojciech Dominiak, Julia Romanowski, Andrzej Karolus, Jakob Frolov, Stanislav Institute of Applied Computer Science Lodz University of Technology Lodz Poland Tu Wien Vienna Austria Lodz University of Technology Lodz Poland German Research Center for Artificial Intelligence Kaiserslautern Germany

ISBN: (纸本)9798400713064

Recent technological advances popularized the use of image generation among the general public. Crafting effective prompts can, however, be difficult for novice users. To tackle this challenge, we developed PromptMap, a new interaction style for text-to-image AI that allows users to freely explore a vast collection of synthetic prompts through a map-like view with semantic zoom. PromptMap groups images visually by their semantic similarity, allowing users to discover relevant examples. We evaluated PromptMap in a between-subject online study (n = 60) and a qualitative within-subject study (n = 12). We found that PromptMap supported users in crafting prompts by providing them with examples. We also demonstrated the feasibility of using LLMs to create vast example collections. Our work contributes a new interaction style that supports users unfamiliar with prompting in achieving a satisfactory image output. © 2025 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Design of Energy Efficient WSN Using a Noble SMOWA Algorithm

引用

computers, Materials & Continua 2022年第8期72卷 3585-3600页

作者： Avishek Banerjee Deepak Garg Victor Das Laxminarayan Sahoo Ira Nath Vijayakumar Varadarajan Ketan Kotecha Department of Computer Science and Engineering Bennett UniversityGreater Noida201310India Department of Information Technology Asansol Engineering CollegeAsansol713305India Department of Computer and Information Science Raiganj UniversityRaiganj733134India Department of Computer Science and Engineering JIS College of EngineeringKalyani741235India School of Computer Science and Engineering University of New South WalesSydneyAustralia Symbiosis Centre for Applied Artificial Intelligence Symbiosis International(Deemed University)PuneIndia

In this paper,the establishment of efficientWireless Sensor Network(WSN)networks has been projected to minimize the consumption of energy using a new Self-adaptive Multi-Objective Weighted Approach(SMOWA)algorithm for solving a multi-objective *** Different WSN nodes deployment policies have been proposed and applied in this paper to design an efficientWireless Sensor Network to minimize energy *** that,the cluster head for each cluster has been selected with the help of the duty *** configuring the WSN networks,the SMOWA algorithms have been developed to obtain the minimum energy consumption for the *** minimization,as well as the amount of day-saving,has been calculated for the differentWSNswhich has been configured through different deployment *** major finding of the research paper is to improve the durability of Wireless Sensor Network(i)applying different deployment strategies:(Random,S pattern and nautilus shell pattern),and(ii)using a new Meta-heuristic algorithm(SMOWA Algorithm).In this research,the lifetime of WSN has been increased to a significant *** choose the best result set from all the obtained results set some constraints such as“equivalent distribution”,“number of repetitions”,“maximum amount energy storage by a node”has been set to an allowable range.

关键词： Wireless Sensor Network(WSN) Self-adaptive Multi-Objective Weighted Approach(SMOWA) deployment strategies Meta-heuristicMethods energy minimization duty cycle

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Spectrum Sensing Data Falsification Attack (SSDF) in Cognitive Radio Network

引用

Journal of The Institution of Engineers (India): Series B 2022年第4期103卷 1249-1257页

作者： Banerjee, Subhasish Singh, Tinka Singh, Karam Ratan Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Arunachal Pradesh Jote791113 India Department of Computer Science and Engineering Indian Institute of Technology Guwahati Guwahati781039 India Department of Basic and Applied Science National Institute of Technology Arunachal Pradesh Arunachal Pradesh Jote791113 India

The most assuring technique to the spectrum scarcity problem is cognitive radio networks (CRN). In CRNs, the individual spectrum sensing by a single cognitive radio (CR) user lessens the reliability of the network. However, as far as cooperative spectrum sensing is concerned, precisely detecting the signal of the principal user (PU) is a major Challenge. Moreover, the cooperative sensing technique is less susceptible to the spectrum sensing data falsification (SSDF) attack. Therefore, to misguide other normal CR users, a malicious user transmits the deceived sensing information in order to make an inaccurate decision of the activity of PU. Thus, to take corrective measures for accurate cooperative spectrum sensing, the identification of the SSDF security attack is very crucial. In this paper, it has been proposed to eliminate the corrupted sensing information while sensing from the malicious SSDF intruders, such that a normal CR user can identify the functioning of PU in distributed cooperative spectrum sensing environment effectively. Finally, based on the simulation results, performance in cooperative sensing has also been carried out. © 2022, The Institution of Engineers (India).

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Spinal Abnormalities Using Machine Learning: A Data-Driven Approach 3

Diagnosing Spinal Abnormalities Using Machine Learning: A Da...

引用

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Ul Islam Nasir, Zia Khan, Khalil Asghar, Momna Islamabad Pakistan Pak-Austria Institute of Applied Science & Technology Department of Computer Software Engineering & Computer Science Haripur Pakistan University of Azad Jammu & Kashmir Department of Electrical Engineering A.K Muzaffarabad Pakistan

ISBN: (纸本)9798350322125

Low back pain is a predominant condition which can affects people from different diaspora. The goal of this work is to use machine learning approach to forecast spinal abnormalities. Extratreesclassifier is utilized as a data preprocessing stage to choose the dataset's most prominent features. On a dataset of 310 samples, spinal anomalies are diagnosed using machine learning algorithms like the Support Vector Machine (SVM) and the multilayer perceptron (MLP). The purpose of this study is to determine the most crucial factors that produce backbone abnormalities and to predict them using supervised machine learning techniques. The classification of normal and abnormal spinal patients is investigated in terms of various aspects, including testing and training accuracy, precision, and recall. The observed accuracies for SVM and MLP with 80% training data are 92% and 90%, respectively. The result shows that these models can achieve high accuracy in predicting spinal abnormalities, with the SVM model performing the better. The result suggest that this approach has the potential to significantly improve the efficiency and accuracy of spinal abnormality diagnosis, leading to better patient outcomes. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Exploration of Anomaly Detection, Classification, and Localization with Deep Learning: A Comprehensive Overview 3rd

An In-Depth Exploration of Anomaly Detection, Classification...

引用

3rd International Semantic Intelligence Conference, ISIC 2023

作者： Singh, Kamred Udham Kumar, Ankit Kumar, Gaurav Singh, Teekam Choudhury, Tanupriya Kotecha, Ketan Dehradun248007 India Department of Computer Science & Engineering Symbiosis Institute of Technology Symbiosis International University Lavale Campus Pune India Department of Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India Department of Computer Science & Engineering Symbiosis Institute of Technology Symbiosis International University Lavale Campus Pune India Symbiosis Centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International University Pune411045 India

ISBN: (纸本)9789819773558

The ability to identify trends in the data when one set of data is deviating from another is called Data Mining. The development of anomalies has made it possible to identify and avoid malware, as well as several other unlawful practices. Traditional detection strategies have shown strong results However, as deep learning progresses, important findings have emerged over the past few years. In order to summarize existing and the most cutting-edge fraud and intrusion detection strategies, we address these issues depending on the existence of neural networks, from broad to shallower. This paper provides an analysis of the published techniques for anomaly detection, especially on the contribution of deep learning to detection. Methods were sorted according to the kind of DNN included in this study. These classes helped us to categorize the deep learners by how often they’ve been using, in data representation and for differentiating between various types of anomalies. In addition, deep neural networks in specific anomaly detection tasks presented incontrovertible proof of their effective implementation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

CosineRecom: A KNN-Based Movie Recommendation System Using Cosine Similarity 4

CosineRecom: A KNN-Based Movie Recommendation System Using C...

引用

4th International Conference on Advancement in Electronics and Communication Engineering, AECE 2024

作者： Singh, Mandeep Mishra, Prafull Aggarwal, Nitin Kumar, Vinay Sharma, Pramod Kumar Yadav, Ritesh Bennett University School of Computer Science Engineering and Technology Greater Noida India Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Mfps Supervisor Oracle Development Database Admin Data Science PA United States Kiet Group of Institutions Department of Csit UP Ghaziabad India Kiet Group of Institute Department of Applied Science UP Ghaziabad India Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering Ghaziabad India

ISBN: (纸本)9798350364729

Information overload is a major problem for many people who use the internet. This is because there is so much information available that it can be hard to know where to start. Filtering tools, like the Recommender System, are needed to solve this problem. These tools give users access to relevant information and let them customise their search results based on their liking. The Collaborative Filtering Recommendation System finds the group of active users who are your closest neighbours. This study shows many ways to use the supervised machine learning algorithm (KNN) method for the Movie recommendation System with different similarity measures, such as the cosine metric, Squared Error Similarity, Linear Correlation Coefficient, and Baseline Predictor Correlation. For the movie recommender system, these many changes to the KNN algorithm were tested on real data from the given dataset and compared based on accuracy measures such as the number of matching pairs and different types of error like mean absolute error, squared mean error, and squared root mean error. By making changes to the web browser, this recommendation system processing tool could be used as a substitute in the real world. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Optimizing Spatial Pattern Analysis in Serial Remote Sensing Images through Empirical Mode Decomposition and Ant Colony Optimization

引用

Journal of Harbin Institute of technology(New Series) 2024年第4期31卷 52-60页

作者： J Srinivasan S Uma Saleem Raja Abdul Samad Jayabrabu Ramakrishnan Department of Computer Applications Madanapalle Institute of Technology&Science(MITS)Madanapalle 517325Andhra PradeshIndia Department of Information Technology Panimalar Engineering CollegeChennai 600123India Information Technology Department College of Computing and Information SciencesUniversity of Technology and Applied Sciences-Shinas 324Sultanate of Oman Department of Information Technology and Security College of Computer Science and Information TechnologyJazan UniversityJazan 45142Kingdom of Saudi Arabia

Serial remote sensing images offer a valuable means of tracking the evolutionary changes and growth of a specific geographical area over *** the original images may provide limited insights,they harbor considerable potential for identifying clusters and *** aggregation of these serial remote sensing images(SRSI)becomes increasingly viable as distinct patterns emerge in diverse scenarios,such as suburbanization,the expansion of native flora,and agricultural *** a novel approach,we propose an innovative method for extracting sequential patterns by combining Ant Colony Optimization(ACD)and Empirical Mode Decomposition(EMD).This integration of the newly developed EMD and ACO techniques proves remarkably effective in identifying the most significant characteristic features within serial remote sensing images,guided by specific *** findings highlight a substantial improvement in the efficiency of sequential pattern mining through the application of this unique hybrid method,seamlessly integrating EMD and ACO for feature *** study exposes the potential of our innovative methodology,particularly in the realms of urbanization,native vegetation expansion,and agricultural activities.

关键词： spatial pattern analysis EMD ACO

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：