检索结果-内蒙古大学图书馆

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： P. M. Naidu M. Anjali K. Sri Vaishnavi S. Chandralekha K. Tejaswini Reddy Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

While numerous Agri-tech start-ups primarily focus on supply chain optimization and farm yield management, there is a growing need to address the unexplored challenge of managing agricultural stubble left after grain segregation. This project seeks to develop a solution for automating the stubble collection process, its transportation to designated sites, sending notifications about pickup and delivery, and facilitating the tracking of stubble disposal in an eco-friendly manner. The proposed Android application is versatile and can be utilized by various stakeholders, including farmers, transportation services, and small-scale industries. The application consists of modules to the specific needs of each user group, facilitating seamless interaction and problem resolution. The Agriculture Waste Management System Android application represents an innovative solution to efficiently and sustainably manage agricultural wastage. This system addresses the unique requirements of farmers, transporters, and industries, creating an interconnected ecosystem for responsible handling of surplus agricultural produce. Users can register, manage agricultural wastage, vehicles, and receive messages, enabling efficient information and resource flow within the agricultural supply chain. By digitizing and streamlining wastage management processes, this project aims to minimize waste, improve collaboration, and contribute to a more sustainable and interconnected agriculture. The Agriculture Waste Management System is not just a technological innovation but also a catalyst for positive change, promoting a greener, more efficient, and sustainable future for agriculture.

关键词： Waste management Technological innovation Supply chains Transportation Agriculture Registers Stakeholders Security Machinery Optimization

来源：评论

学校读者我要写书评

暂无评论

GRAPHTRaiL: Translating GNN Predictions into Human-Interpretable Logical Rules 38

GRAPHTRAIL: Translating GNN Predictions into Human-Interpret...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Armgaan, Burouj Dalmia, Manthan Medya, Sourav Ranu, Sayan Department of Computer Science University of Illinois Chicago United States Department of Computer Science & Engineering Yardi School of AI IIT Delhi India

Instance-level explanation of graph neural networks (GNNs) is a well-studied area. These explainers, however, only explain an instance (e.g., a graph) and fail to uncover the combinatorial reasoning learned by a GNN from the training data towards making its predictions. In this work, we introduce GRAPHTRaiL, the first end-to-end, post-hoc, global GNN explainer that translates the functioning of a black-box GNN model to a boolean formula over the (sub)graph-level concepts without relying on local explainers. GRAPHTRaiL is unique in automatically mining the discriminative subgraph-level concepts using Shapley values. Subsequently, the GNN predictions are mapped to a human-interpretable boolean formula over these concepts through symbolic regression. Extensive experiments across diverse datasets and GNN architectures demonstrate significant improvement over existing global explainers in mapping GNN predictions to faithful logical formulae. The robust and accurate performance of GRAPHTRaiL makes it invaluable for improving GNNs and facilitates adoption in domains with strict transparency requirements. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistically Inspired Discrepancy Detection for Anomalous Spatio-Temporal Graphs (Extended Abstract)

Statistically Inspired Discrepancy Detection for Anomalous S...

引用

International Conference on Data science and Advanced Analytics (DSAA)

作者： Atharv Tiwari Shreyash Chatterjee Siddharth Padmakumar Sushanth Nair Bhaskarjyoti Das Department of Computer Science and Engineering in AI & ML PES University Bangalore India

ISBN: (数字)9798350364941

ISBN: (纸本)9798350364958

Anomaly detection in dynamic graphs is a critical topic with applications in many fields, such as fraud detection and network security. This paper tackles the difficulties in locating abnormalities in time-varying graphs by presenting a novel divide-and-conquer method. We combine Graph Convolutional Networks (GCN) and Recurrent Neural Networks (RNN) to predict future node values on temporal graphs, followed by a macro and micro-level analysis. At the macro level, we present a novel algorithm to extract correlation-based subgraphs. The values obtained for each subgraph allow us to concentrate on subgraphs that show significant anomalies, effectively minimizing the challenges in node-level anomaly detection. This is followed by a micro-level analysis of the node contributions and temporal properties within the identified anomalous subgraphs. By combining macro and micro-level analysis with a machine learning-based approach, our method provides an efficient approach for zoning in on anomalies, significantly speeding up computation.

关键词： Recurrent neural networks Graph convolutional networks Network security Data science Prediction algorithms Fraud Computational efficiency Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Water Quality Prediction for Smart Aquaculture

Water Quality Prediction for Smart Aquaculture

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： R.Praveen Kumar T. Prabhu J. Sowmya A.Nithin Kumar Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

This work presents a unique hybrid approach combining different techniques for precise water quality prediction in smart aquaculture systems. The proposed model integrates the different algorithms with complex pattern recognition, resulting in a robust and efficient predictive system. Incorporating feature engineering and transfer learning enhances the model's adaptability to diverse aquaculture settings, ensuring accurate predictions of critical water parameters. Moreover, our methodology utilizes real-time sensor data, enabling proactive management of water quality conditions. Through comprehensive validation, our hybrid model outperforms existing methods, offering a groundbreaking solution for optimizing smart aquaculture operations. This research contributes to the advancement of predictive technologies, providing a novel and effective tool for sustainable aquaculture practices.

关键词： Adaptation models Accuracy Communication systems Transfer learning Water quality Predictive models Prediction algorithms Real-time systems Pattern recognition Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Advancements in Handwritten Text Recognition and Correction: Bridging the Gap Between Analog and Digital Writing 15th

Advancements in Handwritten Text Recognition and Correction:...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Mohan, J. S. Shyam Sathwik, Abbaraju Sai Ganesh, M.N.V.S. Tejaswi, M. Hema Naseeba, Beebi Madhavi, K. Reddy Department of Computer Science and Engineering GITAM University Bangalore India VIT-AP University Amaravati India Department of AI&ML School of Computing Mohan Babu University Tirupati India

ISBN: (纸本)9783031889912

Handwritten text recognition and correction is the process of converting handwritten text into digital form and correcting errors within the recognized text. Natural language processing tools, computer vision methods, and machine learning algorithms are combined to achieve this. The recognition process involves extracting features, and classifying characters or words. The correction process uses a language model to identify errors and suggest corrections based on context and grammar rules. Handwritten text recognition and correction has numerous applications in fields such as document digitization, signature verification, and historical document analysis. However, it remains a challenging task due to the variability of handwriting styles and the complexity of human language. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A Metaheuristic-Based Scientific Workflow Scheduling in IaaS Cloud 1

A Metaheuristic-Based Scientific Workflow Scheduling in IaaS...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Jaiprakash, Sahani Pooja Badal, Tapas Gupta, Indrajeet Kumar, Naween School of Computer Science Engineering and Technology Bennett Univarsity Greater Noida India Department of Computer Science and Engineering Bhubaneswar India School of Computer Science Engineering and AI SR Univarsity Warangal India

ISBN: (纸本)9798350361780

As cloud data centres expand and provide more services, they consume more energy and cause challenges for the environment. To address this, there is a focus on energy-saving scheduling approaches in cloud computing. This study proposes a novel method for scheduling workflows in cloud computing that is based on the MaxUtil framework. The proposed method integrates the well-known flower pollination algorithm (FPA), a meta-heuristic algorithm derived from natural phenomena. The suggested scheduling approach aims to reduce energy usage and workflow processing time. The suggested method consists of two stages: (i) job assignment to virtual machines (VMs) that are available, and (ii) task scheduling based on optimal criteria. Extensive research has been undertaken throughout five scientific procedures from diverse domains. Tests on various scientific workflows show that this method performs better than other common scheduling methods like PSO, GSA, and GA in most cases. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

A Global Medical Data Security and Privacy Preserving Standards Identification Framework for Electronic Healthcare Consumers

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 4379-4387页

作者： Mishra, Vinaytosh Gupta, Kishu Saxena, Deepika Singh, Ashutosh Kumar Thumbay Institute for Ai in Healthcare Gulf Medical University Ajman United Arab Emirates National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan The University of Aizu School of Computer Science and Engineering Aizuwakamatsu965 Japan University of Economics and Human Sciences Department of Computer Science Warsaw01-043 Poland Indian Institute of Information Technology Bhopal Department of Computer Science and Engineering Bhopal462003 India

Electronic Health Records (EHR) are crucial for the success of digital healthcare, with a focus on putting consumers at the center of this transformation. However, the digitalization of healthcare records brings along security and privacy risks for personal data. The major concern is that different countries have varying standards for the security and privacy of medical data. This paper proposed a novel and comprehensive framework to standardize these rules globally, bringing them together on a common platform. To support this proposal, the study reviews existing literature to understand the research interest in this issue. It also examines six key laws and standards related to security and privacy, identifying twenty concepts. The proposed framework utilized K-means clustering to categorize these concepts and identify five key factors. Finally, an Ordinal Priority Approach is applied to determine the preferred implementation of these factors in the context of EHRs. The proposed study provides a descriptive then prescriptive framework for the implementation of privacy and security in the context of electronic health records. Therefore, the findings of the proposed framework are useful for professionals and policymakers in improving the security and privacy associated with EHRs. © 1975-2011 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-Robot Interaction through Natural Language Processing and Speech Recognition Techniques 2

Enhancing Human-Robot Interaction through Natural Language P...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Veeranna, Thotakura Pavan Kumar, K. Aruna, Mahadeva Verma, Amit Kurian, Thanu B. Gangaram India Kadapa India Sai Spurthi Institute of Technology Computer Science and Engineering B. Gangaram India Dr. K N Modi University Department of Computer Science and Engineering Rajasthan Newai India New Horizon College of Engineering Department of Ai &ml Bangalore India

ISBN: (纸本)9798350364699

The rapid development of artificial intelligence (ai) has resulted in the gradual integration of robots into individuals' everyday lives and professional environments. The use of image recognition employing the robot's human-machine interface technology has become widespread. However, there are still some unresolved problems with the methods used for interaction between robots and machines, such as natural language processing (NLP) and speech recognition. Thus, building on previous research in the field, this work suggests a novel approach to robot-machine interaction by integrating the perceptron lexicon analysis model with the transfer dependence syntactic analysis model. To enhance interaction performance, researchers need to delve further into language-based human-machine interaction systems. An experimental evaluation of the structural perceptron model reveals a recall rate of 82%, an F1 value of 83%, and a testing accuracy of 96%. A maximum analysis of data speed of 751K/s is achieved using the data transfer dependence syntax analysis model. With superior robustness and reaction sensitivity, the novel technique for robot-machine interaction achieves a 93% accuracy rate in comparison to previous methods that have been tested in simulations. To conclude, research methodologies provide the foundation, both theoretically and practically, for better human-machine cooperation and enhanced robot interaction skills). © 2024 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning based Analysis of Chest X-rays for Accurate Lung Disease Detection and Interpretation 3

Transfer Learning based Analysis of Chest X-rays for Accurat...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Perla, Someswari Veledendi, Sudhakar Jaiswal, Pooja Muppidi, Satish Mandala, Jyothi Maram, Balajee Gmr Institute of Technology Department of Cse - Ai&ml Andhra Pradesh Rajam India Sr University School of Computer Science and Artificial Intelligence Warangal India Galgotias University India Gmr Institute of Technology Departnent of Computer Science and Engineering Rajam India University Department of Computer Science and Engineering Banglore India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India

ISBN: (纸本)9798331515911

This is a research paper based on a transfer learning approach with a primary aim at the analysis of chest Xrays for accurate detection and interpretation of lung diseases. The proposed method relies heavily on the use of pretrained deep learning models to enhance diagnostic accuracy and reduce the time and computational resources taken during training. Applying transfer learning to a large chest X-ray dataset, the model successfully detects key patterns associated with common lung diseases, such as pneumonia and tuberculosis. The manuscript encompasses data preprocessing, model finetuning, and performance evaluation and demonstrates huge improvements over the traditional methods both in terms of accuracy and interpretability. It has been experimentally proven that the model is competent enough to provide localization of disease areas, as it can be visualized through heatmaps obtained from predictions, which might further help the radiologists perform their diagnosis tasks. This work advocates for medical imaging automation for the early and efficient detection of lung disease. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Gaussian Multivariate Mixture Model and VGG19 Model for Classification and Detection of Motor Vehicle 2

A Gaussian Multivariate Mixture Model and VGG19 Model for Cl...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Deepa, N. Kumar, Bura Vijay Sowmya, M. Al-Jawahry, Hassan M. Bhushan, Yannam Bharath Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Sr University School of Computer Science and Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of Ai & Ds Bengaluru India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Bachupally Hyderabad India

ISBN: (纸本)9798350372892

In daily life, the moving vehicle plays a significant part in effective system of transportation and traffic visual surveillance systems. Most critical task is to detect the vehicle image and most of the existing method, concentrated on maximizing the prediction percentage only. Also it lacks in classifying the imbalance data. To overcome this kind of problem, the Gaussian Multivariate Mixture Model (G-MMM) and VGG19 model is implemented to detect and classify the vehicle types. The proposed method contained four process namely, preprocessing performed by Flexible Histogram Equalization method (FHE), vehicle detection using G-MMM, feature extraction using Steerable Pyramid Transform (SPT) and Weber Local Descriptor (WLD) and classification using VGG19 ensemble deep learning model. G-MMM significantly improves detection sensitivity and it transformed the correlation between attributes through the training process. VGG19 is pretrained model, so it allows the fast learning recognition on new images of vehicle. The proposed method tested on Beijing Institute of Technology (BIT) dataset and MIO vision traffic camera dataset. When compared to the others methods like modified AlexNet, Deep Convolution Neural Network (DCNN), this proposed G-MMM-VGG19 gives 99.47 % of output rate in classification phase. © 2024 IEEE.

关键词： Equalizers

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：