检索结果-内蒙古大学图书馆

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Sinichi, Parsa Bernabeu, Miguel O. Javidi, Malihe Department of Computer Engineering Faculty of Electronic and Computer Engineering Quchan University of Technology Quchan Iran Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom

ISBN: (纸本)9789819638628

Age-related Macular Degeneration (AMD) is a leading cause of visual impairment among the elderly worldwide. This study compares deep learning-based and classical feature extraction methods for AMD classification using colour fundus images, a cost-effective imaging modality. This comparative approach aims to evaluate the performance of advanced deep learning methods against traditional computer vision approaches in generating effective feature representation. To achieve this, we compared various classical feature extraction methods alongside deep learning-based approaches, specifically VGG16 pre-trained on ImageNet, RETFound and RETFound-Green, which are foundation models pre-trained on a significant number of retinal images. The results demonstrate that combinations of classical features still obtained notable performance and even outperformed the VGG16 model pre-trained on ImageNet. These results also highlight the need for deep learning models to be trained on domain-specific data to surpass classical approaches. In this regard, the pre-trained RETFound and RETFound-Green models yielded promising outcomes for AMD classification, and the highest performance was achieved using a fine-tuned RETFound model. Furthermore, the best proposed method was compared with the state-of-the-art methods. This approach achieved competitive results on the ADAM dataset, demonstrating its robustness and effectiveness in AMD classification while utilising a significantly simpler architecture. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CTGAN-based oversampling and cost-sensitive deep neural network to predict smart money activity in stock market

引用

International Journal of Information technology (Singapore) 2025年第3期17卷 1489-1499页

作者： Baro, Pranita Borah, Malaya Dutta Department of Computer Science and Engineering National Institute of Technology Assam Silchar 788010 India

Investment in the stock market has become a trend in today’s era. The primary force moving the market in a specific direction is the large buying and selling of hedge funds, pension funds, banks, etc. This paper proposes a deep learning strategy to predict smart money activity. Initially, a framework composed of technical analysis and quantitative analysis is considered to create a dataset. Then using this framework a comprehensive dataset is built from the data available in the National Stock Exchange of India (https://***/). In the proposed approach, minority samples in the dataset are first oversampled using Conditional Tabular Generative Adversarial Network based approach to even out class imbalance in the real-life dataset. Using the modified dataset, a cost-sensitive deep neural network is trained to predict smart money activity in the stock market. The proposed method is assessed using different evaluation metrics and the findings validate the superiority of the proposed methodology. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Conditional Tabular Generative Adversarial Networks Cost-sensitive Imbalance classification Neural network Smart money

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-GEC an Energy-Aware Hybrid Task Scheduling on the Cloud 2nd

Fuzzy-GEC an Energy-Aware Hybrid Task Scheduling on the Clou...

引用

2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, ADCIS 2023

作者： Lalitha Devi, K. Deepa Thilak, K. Shanmuganathan, C. Kalaiselvi, K. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9789819995172

In an infrastructure cloud environment, task scheduling should focus on optimizing execution time and saving energy. The data center consumes a large amount of energy during the execution of the task. Energy-saving techniques reduce the amount of energy consumed based on proper task scheduling approaches. The existing fuzzy-based hybrid genetic algorithm considers job length to optimize the makespan. However this fuzzy genetic encoded chromosome (fuzzy-GEC) algorithm considers both makespan and energy consumption to optimize the calculation of fitness value for assigning the task to the virtual machine (VM) by considering the characteristics of the task and VM. According to these characteristics, a fuzzy genetic rule-based encoding scheme is developed to schedule the tasks onto the virtual machines to minimize makespan and energy consumption. The effectiveness of the new technique is evaluated against FCFS and conventional genetic scheduling algorithm using Google Cloud trace workload. The results show the efficiency of the developed approach for makespan and energy consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

On the simulation of hypervisor instructions for accurate timing simulation of virtualized systems

引用

International Journal of Information technology (Singapore) 2024年 1-10页

作者： Mhatre, Swapneel Chandran, Priya Department of Computer Science and Engineering National Institute of Technology Calicut Kerala India

Architectural simulators help in better understanding the behaviour of existing architectures and the design of new architectures. Virtualization has regained importance and this has put a pressing demand for the simulation of virtualized systems. Existing full-system simulators for virtualized systems simulate the application program instructions and the operating system instructions but abstract the hypercalls or traps to the hypervisor. This leads to inaccuracy in the simulation. This paper proposes an approach to simulate hypervisor instructions in addition to operating system instructions for accurate timing simulation of virtualized systems. The proposed approach is demonstrated by simulating RISC-V binary instructions. The simulator is an execution-driven, functional-first, software-based simulator coded in Python. Three programs—searching (linear search), sorting (bubble sort) and ***_ir workload from SPEC CPU2017 benchmarks are simulated using the developed simulator. It is seen that the number of instructions executed when the simulator is configured for a virtualized system are higher than the number of instructions executed when the simulator is configured for a non-virtualized system. This is due to the hypervisor instructions that get executed in a virtualized system. The paper concludes that the proposed approach leads to accurate timing simulation of virtualized systems. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Architecture Hypercall Hypervisor Operating system Simulation Virtualization

来源：评论

学校读者我要写书评

暂无评论

Extensive examination of hyper-parameters setting using neural-based methods for limited resources language: Nyishi-English

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 3901-3911页

作者： Kakum, Nabam Sambyo, Koj Department of Computer science and Engineering National Institute of Technology Arunachal Pradesh India

Taking advantage of the enormous advancement of the transformer model using a neural-based approach for text translation, we extent another research project into the extremely limited resources of the Indian language, Nyishi-English. In this work, we compare the quality of translation between the baseline RNN and Transformer model by employing the fine-tune hyperparameter optimization technique. Further, the quality of system prediction has been judged using both automatic metrics evaluation (BLEU) and human evaluation methods based on sentence length. Each parameter combination has been scrutinized, and the translation quality has been identified using BLEU. The human evaluation method has been used to verify the system prediction based on simple, complex and long sentences. The study concluded with the identification of the optimal hyperparameter optimization combination utilizing the limited resource language Nyishi. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： BLEU Hyperparameters NMT Nyishi Transformer model

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired Optimization Algorithm in Machine Learning and Practical Applications

引用

SN computer Science 2024年第8期5卷 1081页

作者： Juneja, Shallu Taneja, Harsh Patel, Ashish Jadhav, Yogesh Saroj, Anita Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Department of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Engineering SVM Institute of Technology Bharuch India ATLAS SkillTech University UGDX School of Technology Mumbai India

Software fault prediction is critical to ensuring system reliability and user satisfaction while minimizing financial losses. This research paper presents a novel and comprehensive technique for predicting software faults by integrating a Genetic Algorithm (GA) with an ensemble KNN and XG Boost algorithms classifier. The proposed approach is evaluated on 24 datasets, including 12 open-source Java projects and 12 NASA Metrics Data Program datasets, with the NASA Metrics Data Program datasets serving as macroscale datasets and open-source Java projects datasets serving as microscale datasets. By optimizing the selection and combination of fault-related metrics, the integrated GA on the ensemble classifier demonstrates enhanced accuracy in fault prediction compared to existing methods. The experimental results highlight the effectiveness of the proposed approach, establishing its superiority in predictive accuracy. This study significantly contributes to software engineering, offering an efficient technique for identifying and mitigating potential software faults, thereby elevating software reliability and quality assurance processes. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Genetic Algorithm JAVA open-source projects Machine learning NASA MDP PROMISE Stacking ensemble model of k-nearest neighbors (KNN) SVM XG boost

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Unleashed: Leveraging VADER for Evaluation of Public Opinion 11

Sentiment Analysis Unleashed: Leveraging VADER for Evaluatio...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Arora, Suhawni Malhotra, Ashmit Kumar, Amit Singh, Ninni University Department of Computer Science Engineering & Technology Dehradun India Cmr Institute of Technology Department of Computer Science Engineering & Technology Telangana Hyderabad India

ISBN: (纸本)9798350350357

Digital reviews provide real-world feedback on products and services in an era of online commerce and access to information. Providing feedback fosters trust and credibility among potential customers, enabling them to make informed purchasing decisions. In review classification, sentiment analysis is a key component that assesses the emotional tone of the reviews. Businesses can prioritize responses, manage their reputation, and extract actionable insights by categorizing reviews as positive, negative, or neutral. The study also includes neutral feedback, which includes suggestions for incremental improvement, which assists in continuous product refinement. In the proposed work, more than 5,68,455 reviews are divided into positive negative, and neutral sentiments by sentiment analysis. The results demonstrate VADER's robustness and versatility, showing its capacity to accurately gauge public sentiment across different contexts and types of language, including slang, emojis, and colloquial expressions. We also compare VADER's performance with other sentiment analysis algorithms, underscoring its advantages in handling informal online communication. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Optimal Disassembly Sequence Planning for Complex Products using Enhanced Deep Reinforcement Learning Framework

引用

SN computer Science 2024年第5期5卷 581页

作者： Chand, Mirothali Ravi, Chandrasekar Department of Computer Science and Engineering National Institute of Technology Puducherry Karaikal India

Disassembly Sequence Planning (DSP) is a crucial problem in the field of repair and maintenance. There is a pressing need for an efficient technique to solve the Complete Disassembly Sequence Planning (CDSP) problem for large, highly complex products without compromising time and computational resources. Since exact methods fail to handle complex products, and meta-heuristic approaches often do not produce optimal results, its solution requires a deep reinforcement learning approach. This work proposes a novel Enhanced Deep Reinforcement Learning (EDRL) approach in which the Actor-Critic Networks with an attention mechanism is employed in both networks to assign weightage to important actions, generating optimal sequences based on these actions. To further improve the model and accurately predict the loss value, a hybrid loss function is developed by combining the Categorical Cross-entropy and Log-Cosh loss functions. This work considers DSP attributes like stability, liaison, geometric feasibility, and precedence for experiments on various products. The proposed EDRL-CDSP method outperforms existing techniques in terms of optimality while requiring less time to generate the solution. The optimized disassembly sequence, when followed, consumes less time for the total disassembly of all the parts of the product. These findings suggest that the proposed EDRL-CDSP approach can effectively address the challenges in DSP and provide practical benefits for industrial applications. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Disassembly Hybrid loss function Optimal sequence planning Optimization

来源：评论

学校读者我要写书评

暂无评论

Tri-factorized Modular Hypergraph Autoencoder for Multimodal Semantic Analysis

引用

SN computer Science 2024年第7期5卷 867页

作者： Malik, Shaily Dhand, Geetika Sheoran, Kavita Jatain, Divya Garg, Vaani Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology Delhi India

For image-to-text and text-to-image classifications, the features of data collected from various imaging devices, sensors, and their text descriptions must be mapped into a common latent space with reduced dimensions. The low-dimensional features are supposed to provide the most information with the least amount of *** this paper we propose a cross-modal semantic autoencoder that uses nonnegative matrix factorization (NMF) to factorize the features into a lower rank. Due to two matrix factorization, the traditional NMF is unable to translate all of the information into lower space. This is addressed by a unique tri-factorized NMF with hypergraph regularization. Instead of using the feature adjacency matrix in hypergraph regularization, a more information-rich modularity matrix is suggested. The Wiki dataset is used to evaluate this tri-factorized hypergraph regularized multimodal autoencoder for image-to-text and text-to-image conversion. In order to lower the feature dimension, Multimodal Conditional Principal label space transformation (MCPLST) is also enabled by this novel autoencoder. Comparing the proposed autoencoder against the semantic autoencoder, the former showed an improvement in classification accuracy of up to 1.8%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multimodal retrieval Multimodality Nonnegative matrix factorization Semantic analysis TriNMF Wiki dataset

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s disease diagnosis using deep learning model by analyzing the channels of electroencephalography signals from substansia niagra and ventral tegmental area regions of human brain

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 2129-2152页

作者： Kumar, Kaushal Ghosh, Rajib Department of Computer Science and Engineering National Institute of Technology Patna Patna 800005 India

Parkinson’s disease (PD) is a progressive neurological disorder primarily affecting motor functions and mobility. Early diagnosis is crucial for reducing disease progression and treatment costs. This paper proposes a bi-directional long short-term memory (BLSTM)-based system for PD diagnosis using electroencephalography (EEG) signals collected exclusively from the substantia nigra (SN) and ventral tegmental area (VTA), key brain regions associated with dopamine production. Mel-frequency cepstral coefficients (MFCC) features are extracted from the EEG data, and the BLSTM classifier is employed to differentiate PD subjects from healthy individuals. The performance of the proposed system is evaluated on three public datasets, namely, the University of Iowa (UI) dataset, Parkinson’s Disease Gait (PDG) dataset, and the UC San Diego Resting State (USDRS) dataset, demonstrating superior classification accuracy compared to existing methods. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： Electroencephalography signal Mel-frequency cepstral coefficients features Parkinson’s disease Recurrent neural network Substansia niagra and ventral tegmental area

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：