检索结果-内蒙古大学图书馆

20th Principle and Practice of Data and Knowledge Acquisition Workshop, PKAW 2024, held in conjunction with the 21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Kitagawa, Nozomi Yamauchi, Koichiro Graduate school of Engineering Department of Computer Science Chubu University Kasugai Japan

ISBN: (纸本)9789819600250

Recent developments in artificial intelligence (AI) have increased the demand for high-performance computational devices. However, edge devices are highly restricted in terms of computational power and memory capacity. To address this, a learning engine called swap kernel regression (SKR) [Masaharu et al. 2019] was developed that enables both inference and learning using an edge device. The key feature of SKR is ability to extend beyond the real physical capacity by collaborating with a second storage device. SKR thereby enables the virtual construction of a large-scale learning machine on a tiny device. We developed an improved version of SKR that maximizes performance by solving the thrashing problem and further reduces the computational cost. Using this improved version, we aim to achieve few-shot class-incremental learning (FSCIL), which continuously adapts to new tasks with limited samples, envisioned for on-site implementation. The proposed method uses a kernel machine that operates in a restricted environment in collaboration with a secondary storage system. The kernel parameters, which are not essential for calculating the output values for upcoming inputs, are stored in secondary storage to create a space in the main memory. The essential kernel parameters stored in secondary storage are loaded into main memory when required. Using this strategy, the system can realize recognition or regression tasks without compromising its generalization capability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Stress-Adaptive Reading: A Machine Learning Approach with Galvanic Skin Response 2

IoT-Enhanced Stress-Adaptive Reading: A Machine Learning App...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Modak, Masooda Temgire, Devdatta Kaushik, Serin Kachare, Vaibhav Shriyan, Dheeraj SIES Graduate School of Technology Department of Computer Engineering Nerul India

ISBN: (纸本)9798350365269

In today's fast-paced educational landscape, understanding and addressing students' stress levels are paramount for fostering effective learning environments. This research introduces a novel approach to stress detection and adaptive reading, leveraging the Internet of Things (IoT), galvanic skin response (GSR) sensors, and machine learning techniques. By collecting real-time physiological data from students wearing GSR sensors during tests, our system aims to dynamically adapt reading materials based on individual stress levels. This paper details the methodology, including the creation of a customized dataset, data preprocessing, clustering, and the development of an IoT infrastructure using Raspberry Pi. The integration of Django web applications, WebSocket communication, and machine learning models further enhances the adaptability and responsiveness of the system. Our work contributes to the intersection of IoT, GSR, and machine learning in education, offering a promising avenue for personalized and stress-aware learning experiences. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Improving Diagnostic Accuracy: A Deep Dive into Random Forest Optimization for Clinical Data 3

Improving Diagnostic Accuracy: A Deep Dive into Random Fores...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Modak, Masooda Jadhav, Madhavi Kadam, Riya Arwade, Manasi Mane, Samiksha SIES Graduate School Of Technology Department of Computer Engineering Nerul India

ISBN: (纸本)9798350372120

The healthcare industry produces a large amount of patient data, which makes it possible to use a variety of analytical techniques on a large dataset. A predictive system that can recognize several diseases at once has been created by utilizing machine learning techniques. Grid Search and Randomized Search strategies are used to further enhance the model that was developed using the Random Forest algorithm. This contrasts with widely used systems that frequently display a numerous illness prediction system without improving the model, producing erroneous and subpar results. Reduced accuracy and erroneous results have serious consequences that could endanger the health of the patient. Our system's present focus is on two different diseases: Diabetes and Parkinson's disease. Especially, the architecture of the system makes it possible to easily incorporate other illnesses in later stages. Users are required to input various disease-specific parameters, after which the system promptly generates output indicating the presence or absence of the specified condition. This research work carried out demonstrates the disease prediction system developed using Optimized Machine learning algorithms such as Decision Tree classifier, Random forest classifier, Support Vector Machine (SVM) and Logistic Regression along with Optimization techniques Grid Search and Randomized Search. The primary objective of the model is to enhance its recall capabilities through the incorporation of advanced methodologies and optimization techniques. The paper also presents comparative study of the results of the above algorithms used. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A workflow based approach for task scheduling in cloud environment

引用

Materials Today: Proceedings 2023年 80卷 3305-3311页

作者： Patnaik, Harish Kumar Patra, Manas Ranjan Kumar, Rahul School of Computer Engineering KIIT University Bhubaneswar751024 India Department of Computer Science Berhampur University Berhampur760007 India

A Cloud computing environment provides a huge repository of computing resources which can be utilized for executing user tasks over the Internet. One of the challenges in such a computing paradigm is the optimal use of resources both from the cloud provider as well as consumer's point of view. Techniques have been developed to execute tasks with different level of complexity and size by assigning the tasks to the available resource pool which may span over a large geographical area. In this paper, we suggested a workflow approach to execute large number of interdependent tasks using a set of computing resources with heterogeneous capacity. The objective of this work is to allocate the tasks in such a way that the total time required to complete is minimized. The proposed technique is an extension of max–min algorithm applied on a Directed Acyclic Graph representing a set of interdependent tasks. The technique has been tested on standard scientific workflows and the results are found to be better compared to other similar works in terms of makespan. © 2021

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Multi-Class SVM & Random Forest Based Intrusion Detection Using UNSW-NB15 Dataset 15

Multi-Class SVM & Random Forest Based Intrusion Detection Us...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Jose, Anish Mathew Mukherjee, Avirup Saha, Joydeep Bhaumik, Anubhab Datta, Kamalesh Patra, Radhashyam Behura, Aradhana KIIT University BBSR School of Computer Engineering Odisha India VSSUT Department of Electronics and Telecommunication Engineering Sambalpur Odisha Burla India Universit BBSR School of Computer Engineering Odisha India

ISBN: (纸本)9798350370249

Intrusion Detection or malicious node detection (IDS) show a important role in safeguarding computer networks system from security threats. However, traditional IDS methods often struggle with high false positive rates and limited detection accuracy. This paper presents an advanced IDS that harnesses the power of a multi-class support vector machine (SVM) and integrates random forest technique for feature selection, specifically targeting the UNSW-NB15 dataset. The motivation behind this research is to enhance IDS performance by leveraging robust machine learning techniques. The research problem centers on improving the accuracy and efficiency of detecting various network attacks while reducing false positives. Our approach involves meticulously preprocessing network traffic data to extract relevant features, utilizing random forest to identify the most informative ones, and then employing these features to train a multi-class SVM classifier. This classifier effectively categorizes network traffic into different attack types. The results demonstrate a significant improvement in prediction accuracy and a decrease in rate of false positives, thereby enhancing the overall effectiveness of IDS in protecting computer networks against security threats. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Empowering data structure visualization through modification in Python 15

Empowering data structure visualization through modification...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Puvvadi, Harsha Vardhan Angala, Hari Prasad Swaroop, Bandi Vishnu Reddy, Busa Thanuj Sathwik Belwal, Meena Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

This article introduces a novel approach to data structure visualization through the development of a new programming language, utilizing Python's Lex-YACC library for lexical analysis and parsing, and the Turtle module for graphics in the backend. The proposed language enables users to visualize various data structures such as arrays, stacks, and queues, along with their operations, facilitating a deeper understanding of these fundamental concepts in computer science. By combining the power of a custom scripting language with Python's versatile libraries, this research aims to empower users to interactively explore and comprehend complex data structures through intuitive visualizations. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Enhanced Steel Defect Detection using U-Net Model with Attention Mechanism 5

Enhanced Steel Defect Detection using U-Net Model with Atten...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Sai, D. Gowtham Sri Mani Maheswari, Uma Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

In this research, detection of steel defects is a significant use of computer vision that can enhance industrial quality control. New prospects for automated defect segmentation are presented by recent developments in deep learning. This paper investigated the use of attention processes in a U-Net convolutional neural network architecture for improved steel flaw identification. Images of steel and matching defect masks from the Severstal Steel Defect Detection dataset were used to train the U-Net network. Preprocessing actions such as image rotation and scaling were performed in addition to data augmentation. When tweaked at various probability thresholds, the model produced defect mask predictions on a test set with good accuracy. When compared to ground truth masks, qualitative results showed that different defect types could be segmented well. Forecasts on fresh test pictures without any masks provided also shown a believable ability to identify flaws. According to this research, deep learning using attention blocks and U-Nets has the potential to improve automation in tasks related to semantic segmentation, such as steel inspection. To assess the model's efficacy on other defect types and steel materials, more work is required. The code and trained model serve as a basis for creating systems that are ready for production. © 2024 IEEE.

关键词： Attention mechanisms Convolutional neural networks Image processing Steel defect detection U-Net

来源：评论

学校读者我要写书评

暂无评论

AI-Generated Content-as-a-Service in IoMT-Based Smart Homes: Personalizing Patient Care With Human Digital Twins

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1-1页

作者： Akram, Junaid Aamir, Misha Raut, Roshani Anaissi, Ali Jhaveri, Rutvij H. Akram, Awais School of Computer Science The University of Sydney Camperdown NSW Australia Department of Information Technology Pimpri Chinchwad College of Engineering Savitribai Phule Pune University Pune India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University India COMSATS University Islamabad Vehari Pakistan

We introduce the AI-Generated Optimal Decision (AIGOD) algorithm and the Deep Diffusion Soft Actor-Critic (DDSAC) framework, marking a significant advancement in integrating Human Digital Twins (HDTs) with AI-Generated Content (AIGC) within IoMT-based smart homes. Our innovative AI-Generated Content-as-a-Service (AIGCaaS) architecture, optimized for IoMT environments, leverages network edge servers to enhance the selection of AI-Generated Content Service Providers (AISPs) tailored to the unique characteristics of individual HDTs. Extensive experiments demonstrate DDSAC’s HDT-centric approach outperforms traditional Deep Reinforcement Learning algorithms, offering optimal AIGC services for diverse healthcare needs. Specifically, DDSAC achieved a 20% improvement in task completion rates and a 15% increase in overall utility compared to existing methods. These findings highlight the potential of HDTs in personalized healthcare by simulating and predicting patient-specific medical outcomes, leading to proactive and timely interventions. This integration facilitates personalized healthcare, establishing a new standard for patient-centric care in smart home environments. By leveraging cutting-edge AI techniques, our research significantly contributes to the fields of IoMT and AIGC, paving the way for smarter and more responsive healthcare services. IEEE

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Predicting Customer Lifetime Value in E-commerce: A Data-Driven Approach to Enhance Customer Retention Strategies 3

Predicting Customer Lifetime Value in E-commerce: A Data-Dri...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dey, Sonali Radha, D. Kirthika Devi, V.S. Department of Computer Science Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Predicting Customer Lifetime Value (CLV) is one of the most critical tasks that businesses undertake in order to improve customer retention and optimize marketing strategies. The present paper proposes a predictive model for CLV using several machine learning techniques. The features considered include customer demographics, purchasing behavior, and transaction history. All these features were preprocessed using feature engineering and missing value handling. Several regression models, including Linear Regression, Decision Tree, and Random Forest Regressor, were compared in terms of predictive performance. The study includes the decision trees,hash tables as advance data structures such that they can handle large datasets effectively. Of the ones tested, Random Forest Regressor proved to be superior to the others, having the lowest Mean Squared Error (MSE) and highest R2 score, thereby validating its robustness in identifying the complex patterns within the data. The work highlights the time and space complexities of different models. This study contributes to the application of machine learning in customer analytics and provides a foundation for future research to integrate more diverse data sources and enhance model performance through hyperparameter optimization. Future work will also explore real-time prediction capabilities and the integration of multimodal data to further refine CLV forecasting. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Optimizing Hiring Practices: A Machine Learning Approach for Candidate Selection 3

Optimizing Hiring Practices: A Machine Learning Approach for...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dogiparthy, Naga Datta Radha, D. Kirthika Devi, V.S. Department of Computer Science and Engineering Amrita school of computing Amrita Vishwa Vidhyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Recruitment is one of the most crucial factors in shaping efficient and high-performing teams within organizations. However, the traditional recruitment processes are often plagued by biases and subjective judgments that lead to inconsistent and suboptimal hiring decisions. This project uses machine learning(ML) to make recruitment more objective, efficient, and data-driven. By taking the age, gender, education level, experience, interview scores, and personality traits of the applicants as key features, the model predicts candidate suitability without bias. The methodology uses robust preprocessing, Chi-Square feature selection, and the SMOTE technique to overcome class imbalance in the dataset. The proposed system uses various different machine learning algorithms like CatBoost, KD-Trees, Random Forest, and Logistic Regression and many more. All these models are trained and fine-tuned with GridSearchCV for hyperparameter optimization. Among them, the best model was CatBoost with 95% accuracy. This work shows how machine learning can change the recruitment game for organizations to make unbiased, data-driven hiring decisions and ultimately increase workforce efficiency and organizational success. © 2025 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：