检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wu, Juncheng Ni, Zhangkai Wang, Hanli Yang, Wenhan Zhou, Yuyin Wang, Shiqi School of Computer Science and Technology Tongji University China Pengcheng Laboratory China Department of Computer Science and Engineering University of California Santa Cruz United States Department of Computer Science City University of Hong Kong Hong Kong

Image deep features extracted by pre-trained networks are known to contain rich and informative representations. In this paper, we present Deep Degradation Response (DDR), a method to quantify changes in image deep features under varying degradation conditions. Specifically, our approach facilitates flexible and adaptive degradation, enabling the controlled synthesis of image degradation through text-driven prompts. Extensive evaluations demonstrate the versatility of DDR as an image descriptor, with strong correlations observed with key image attributes such as complexity, colorfulness, sharpness, and overall quality. Moreover, we demonstrate the efficacy of DDR across a spectrum of applications. It excels as a blind image quality assessment metric, outperforming existing methodologies across multiple datasets. Additionally, DDR serves as an effective unsupervised learning objective in image restoration tasks, yielding notable advancements in image deblurring and single-image super-resolution. Our code is available at: https://***/eezkni/DDR. © 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

Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm

引用

Recent Patents on Engineering 2024年第9期18卷 24-33页

作者： Selvarajan, Shitharth Thirumalaisamy, Manikandan Manoharan, Hariprasath Devendiran, Ramkumar Lakshmi Narayanan, S. Kumar, Ashwani Department of Computer Science Kebri Dehar University Kebri Dehar250 Ethiopia School of Computer Science Engineering and technology Bennett University U.P India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Tamil Nadu Chennai600 123 India School of Computer Science and Engineering VIT-AP UNIVERSITY Andhra Pradesh Amaravathi522237 India Gojan School of Business and Technology Chennai India Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

Background: The majority of wearable technology that is present in various patents for Internet of Medical Things (IoMT) health monitoring systems is introduced to recognize various bodily indicators. The enumerated patents indicate that monitored values are sent to a central server, where they are all treated by experts at the appropriate moment. Therefore, a new patent technique by expanding the use of wireless devices, has been discovered that such communication technologies can recognize specific depression traits and mood swings. Objectives: The major objective of the proposed method is to analyze the disputes that arise in the characteristics of an individual by observing the leveling periods that are identified from the processed image. In addition, the rate of data transfer in case of any dispute is maximized therefore recognition problem is solved at a minimized distance. Further, the steady state probability values are achieved at low delay thus minimizing the dropout packets in the monitored system using IoMT and LSTM. Methods: A balanced record with four distinct parameters—such as livelihood, self-reliance, correlation, and precision—is employed with the projected model on IoMT for depression identification. As a result, high data transfer rates and low distance separation are used to process the identification framework. Additionally, by combining an original matrix representation with the input feature set using LSTM, a novel framework with great efficiency is created. Results: In order to assess the results of IoMT using LSTM, four situations are split apart and their probability ratios are calculated. The results of each situation are then contrasted with the current methodology, and it is found that when there is a low dropout ratio, depression in a person is quickly diagnosed. Conclusion: The comparison analysis demonstrates that the proposed method, when compared to the current method, offers the best-compromised outcomes at roughly 64%. © 2024 B

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

ElectroBlock: Reinforcement Learning and Blockchain-based Energy Trade to Optimize Tariffs 7

ElectroBlock: Reinforcement Learning and Blockchain-based En...

引用

7th Conference on Cloud and Internet of Things, CIoT 2024

作者： Islam, Ridwan Arefin Rezwan-Ul-Islam Shatabda, Swakkhar Islam, Salekul McGill University School of Computer Science Montréal Canada United International University Department of Computer Science and Engineering Dhaka Bangladesh Brac University Department of Computer Science and Engineering Dhaka Bangladesh North South University Department of Electrical and Computer Engineering Dhaka Bangladesh

ISBN: (纸本)9798350356717

Energy prices have increased by more than 62% globally on average, while power companies are trying to provide more affordable energy with different options: fixed-rate, slab-based tariffs, and Time-of-Use pricing. This article aims to combine blockchains, smart contracts, smart grids, energy forecasting through reinforcement learning, and energy trading between closed communities, bringing consumer savings. Our proposed model, ElectroBlock, uses the first 25 days of each month's energy usage history along with seasonal and exogenous factors to forecast the final end-of-month usage. Then with the forecast we can predict which customers are the most likely to be pushed to the next energy consumption slab and be charged at a higher rate for the remaining month. This allows these customers to be buyers, and seamlessly buy energy units from users who would sell, the energy units they are predicted to leave unused by the end of the month. Moreover, trading is done with WalletCoins, at a coin per kilowatt hour, but could also be traded directly for fiat currency. Furthermore, the power company makes a profit on every trade through transaction fees. Hence there is great incentive for both customers and power companies to adopt our proposed model. We integrated Hyperledger Fabric into our ElectroBlock prototype to store all customer data and prevent tampering with WalletCoin and consumption records. Finally, we did a performance analysis, on the actual cost savings based on a real-world dataset;and a scalability test for concurrency and customer bases on our prototype. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Exploring the possibilities of integration of cyber-psychology for human behaviour in a smart city

引用

International Journal of Information and Communication Technology 2024年第2期25卷 150-167页

作者： Wen, Liping Ting, Zhou Zheng, Huang Alfred Daniel, J. Antonidoss, A. Department of Psychology University of Chinese Academy of Sciences Beijing100101 China Institute of Psychology Chinese Academy of Sciences Beijing100101 China Department of Medical Psychology School of Health Humanities Peking University Beijing100191 China Department of Computer Science & Engineering SNS College of Technology India Department of Computer Science and Engineering Hindustan Institute of Technology and Science India

The smart city idea differs between cities and nations. In all meanings and characteristics of a smart city, public involvement is the only thing that remains common. Therefore, it is a very significant field to study human behaviour and development in smart cities. This paper presents a framework for identifying qualities necessary for people to be classified as intelligent persons and to integrate these human behavioural characteristics in cyber technology. Human behaviour in a smart city has been analysed using the machine learning algorithm and big data analytics. The integrated machine learning and big data analytics framework (iML-BD) classifies the cyber behaviour of intelligent persons in a smart city by observing the cyber activities performed by the individuals. Furthermore, this paper handles the risk factors for cyber-acquired and cyber-dependant crime violence and abuse that vulnerable internet and public access devices using blockchain technology. Blockchain is a method of storing data that takes too long to alter, modify, or manipulate. A blockchain is an electronic accounting system that is reproduced and spread through the Bitcoin protocol’s entire communication network. The case study performed on iML-BD has resulted in the highest performance in terms of prediction accuracy of 94.98%. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

HyPRETo: Hybrid Pre-trained Ontology Approach for Contextual Relation Classification on Mosquito Vector Biocontrol Agents 8th

HyPRETo: Hybrid Pre-trained Ontology Approach for Contextual...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Jeyakodi, G. Bala, P. Shanthi Department of Computer Science School of Engineering and Technology Pondicherry University Puducherry India

ISBN: (纸本)9783031736162

Pre-trained Language Model facilitates contextual relation classification by capturing contextual information, addressing word ambiguity, encoding global sentence context, enabling transfer learning, handling out-of-vocabulary words, and improving performance with limited labelled data. Existing pre-training approaches suffer in size, bias, interpretability, generalization, and the lack of domain specificity. To address this, HyPRETo, the hybrid model that combines the strength of token replacement and dynamic masking is proposed to achieve upgraded performance to increase classification accuracy. The Mosquito Vector Biocontrol Agents data is used for implementing the model for a contextual relation classification task. HyPRETo uses ontology to provide structured knowledge. HyPRETo is pre-trained by ELECTRA and fine-tuned by RoBERTa models. Feedforward and softmax activation function is used for classification. The Natural Language Processing technique and SQL database are used to develop an automated question-answering system. The HyPRETo was evaluated with state-of-art models and achieved 98.42% accuracy. As a contribution, the manually annotated input dataset on the mosquito vector control agent is prepared for the classification task. Subsequently, the enhanced model is developed. The interface for an automated question-answering system for mosquito vector biocontrol agents is developed to assist public health applications such as mosquito vector control, disease control, ecosystem management, environmental conservation, and so on. © IFIP International Federation for Information Processing 2025.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Recent Trends for Text Summarization in Scientific Documents 9

Recent Trends for Text Summarization in Scientific Documents

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Sukmandhani, Arief Agus Arifin, Yulyani Zarlis, Muhammad Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350370126

Text summarization is a natural language processing (NLP) technique in artificial intelligence that has been studied in recent years. Every document containing text is tested to get a good summary result. In producing a good summary, proper accuracy is required;therefore, various techniques and methods are used, and another challenge is the use of language in the documents being tested. Various types of documents have been used as research for text summarization, including scientific documents, so researchers are interested in studying them more intensely to get the state of the art in research. This research was conducted to review previous research using literature studies from various publications that published research on text summarization in scientific documents. The researcher collected data from several publishers who had published this type of research from 1988 to 2023 quarter 1 and obtained three hundred and eleven articles, then the researcher analyzed the data using the Kitchenham method to get the right literature to answer the research question. Thirty-seven articles were selected for further in-depth analysis. In addition, the researcher found some interesting findings beyond the research question, including other techniques used to solve the text summarization problem and other types of output that are not commonly produced so that it can increase knowledge in researching text summarization. © 2023 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning 24

Unleashing the Power of Knowledge Graph for Recommendation v...

引用

33rd ACM Web Conference, WWW 2024

作者： Wang, Shuyao Sui, Yongduo Wang, Chao Xiong, Hui School of Data Science University of Science and Technology of China China Hong Kong The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Guangzhou Hkust Fok Ying Tung Research Institute Hong Kong

ISBN: (纸本)9798400701719

Knowledge graph (KG) demonstrates substantial potential for enhancing the performance of recommender systems. Due to its rich semantic content and associations among interactive entities, it can effectively alleviate inherent limitations in collaborative filtering (CF), such as data sparsity or cold-start issues. However, most existing knowledge-aware recommendation models indiscriminately aggregate all information in KG, without considering information specifically relevant to the recommendation task. Such indiscriminate aggregation could introduce additional noisy knowledge into representation learning, which can distort the understanding of users' genuine preferences, thereby sacrificing the recommendation quality. In this paper, we introduce the principle of invariance to the knowledge-aware recommendation, culminating in our Knowledge Graph Invariant Learning (KGIL) framework. It aims to discern and harness the task-relevant knowledge connections within KG to enhance the recommendation models. Specifically, we employ multiple environment generators to simulate diverse noisy KG-environments. Then we devise a novel attention learning mechanism for KG and user-item interaction graph, aiming to learn environment-invariant subgraphs. Leveraging an adversarial optimization strategy, we enhance the diversity of the environments, meanwhile, promote invariant representation learning across environments. We conduct extensive experiments on three datasets and compare KGIL with state-of-the-art methods. The experimental results further demonstrate the superiority of our approach. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Robust Hybrid Machine Learning Model for Financial Fraud Detection in Credit Card Transactions 2

Robust Hybrid Machine Learning Model for Financial Fraud Det...

引用

2nd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Jahnavi, Dingari Mona, A. Pulata, Sandeep Sami, Sasank Vakamullu, Bharadwaj Mohan Bharathi, G. Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

Financial fraud is a rising problem that affects both organizations and people, necessitating cutting-edge solutions to lessen its effects. The majority of machine learning models used now in the field of fraud detection include Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF). While these traditional models frequently lack sensitivity, have trouble figuring out complex fraud patterns, and are rigid in their ability to adjust to new threats. To overcome them, this research work provides a significant advancement by combining Decision Trees and Logistic Regression into a hybrid model, boasting an impressive accuracy of 98.1%. The proposed methodology not only improves the system's ability to detect fraud accurately but also makes it more flexible to the changing fraud strategies. Additionally, a thorough comparison analysis highlights the approach's undeniable benefits. In a nutshell, this work provides a method for detecting financial fraud using a hybrid model that expertly strikes a compromise between sensitivity and accuracy. In addition to improving fraud detection, this innovation also strengthens the security of financial systems. © 2024 IEEE.

关键词： Comparison analysis Contemporary world Financial fraud Flexibility Fraudulent transactions Hybrid model

来源：评论

学校读者我要写书评

暂无评论

A Study of Machine Learning Techniques for Predictive Analysis of Suicidal Tendency Across Different Age Groups 4

A Study of Machine Learning Techniques for Predictive Analys...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Zumma, Md. Thoufiq Rahaman, Md. Anikur Muneem, Mohammad Abdul Khan, Obyed Ullah Islam Prova, Nuzhat Noor Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Washington University Science and Technology Department of Computer Science NewYork United States Wilmington University Department of Computer Science NewYork United States Pace University Department of Seidenberg School of Csis NewYork United States

ISBN: (纸本)9798331540364

Suicide is a serious public health concern, and life-saving early identification and prevention are essential. When it comes to forecasting suicide, risk based on a variety of criteria and signs, machine learning algorithms have shown encouraging results in recent years. This study uses machine learning techniques to predict suicide tendencies in various age groups. The first step in the research is to collect pertinent datasets including sociodemographic, clinical, behavioral, and psychiatric data on people who have attempted or succeeded in suicide. Preprocessing is done on these datasets to guarantee data quality, handle missing values, and normalize characteristics. Using evaluation measures such as accuracy, precision, recall, and F1-score, the best performing models are chosen to serve as the best suicide prediction classifiers. The findings show that suicide risk may be accurately, sensitively, and specifically predicted using machine learning techniques. With the help of the found predictive traits, at-risk people may get personalized treatments and support networks, as well as insights into the risk factors linked to suicide conduct. This study uses five different algorithms, wherein the support vector machine (SVM) emerges as the technique that performs the best, offering an accuracy of 0.89. The decision tree classifier comes as a close second, delivering the same accuracy. Following that, random forest obtains an accuracy of 0.84, KNN comes in second with 0.81, and gaussian naive bayes comes in third with 0.53. © 2024 IEEE.

关键词： Adversarial machine learning

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：