检索结果-内蒙古大学图书馆

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

Crop Damage Detection using Machine Learning Approaches 6

Crop Damage Detection using Machine Learning Approaches

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Nair, Priyanka C Sampath, Nalini Reddy, P Praneeth Shruthi, P Sai Department of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (纸本)9798350381689

Agriculture is of vital importance to human life as it is the main source of livestock production and contributes significantly to the country's employment opportunities and economy. Ensuring high standards of production quality is essential. Recent technological advances are merging agricultural and machine learning techniques to help improve crop quality. The main objective of this work is to make use of machine learning approaches to identify the healthy status of the crop. Multi-class classification is applied to the dataset which helps classify crop conditions. As there is an imbalance of data of the 3 classes, Random under- sampling and Tomek under-sampling methods are applied on the dataset. A combination of Tomek undersampling and Smote undersampling has also been performed on this dataset. Various algorithms like Gradient Boosting, Gaussian Naïve Bayes, Neural Network (MLP) and k-Nearest Neighbors were performed on the dataset which helped show that Randomforest was the best model in terms of accuracy and F1 score. © 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

Parameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction

引用

Neural computing and Applications 2024年第27期36卷 16911-16940页

作者： Abu Talib, Manar Bou Nassif, Ali Azzeh, Mohammad Alesh, Yaser Afadar, Yaman Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics Sharjah United Arab Emirates King Hussein School for Computing Sciences Princess Sumaya University for Technology Amman Jordan

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Beyond Search: A Network-Based Exploration of Buyer Behavior in the OLX Car Market 4

Beyond Search: A Network-Based Exploration of Buyer Behavior...

引用

4th International Conference on Multimedia Processing, Communication and Information Technology, MPCIT 2024

作者： Ashvath, Y. Moin Ramya, G.R. Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350375466

The information on used cars offers a thorough analysis of the second-hand car industry. This dataset may be utilized to construct predictive models that can estimate the price of a used car based on its characteristics, including the make, model, year, mileage, fuel type, and condition. This dataset enables comprehensive data analysis to extract insights into market trends, pricing dynamics, and buyer-seller behavior. The main goals are to examine price patterns depending on different characteristics, assess the influence of fuel type and geographical factors on pricing and demand, investigate the correlation between mileage and resale value, and determine the most popular automobile models. Furthermore, the dataset enables the development of predictive models that can estimate both selling prices and the amount of time it takes to sell a product. Methodologies encompass the processes of data cleaning and exploratory data analysis (EDA). The results will assist in identifying communities or clusters within the dataset, uncovering groups of cars with similar attributes or market characteristics. The results aim to offer comprehensive market insights, improve comprehension of buyer behavior, and create predictive tools to assist sellers, buyers, and platform operators in decision-making. Ultimately, this will optimize strategies and operations in the used car market. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Hidden Emotion Detection using Speech, Text, Facial Expressions and Neural Networks 5

Hidden Emotion Detection using Speech, Text, Facial Expressi...

引用

5th IEEE International Conference on Communication, computing and Industry 6.0, C2I6 2024

作者： Reddy, Ravula Tarun Palaniswamy, Suja Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350379884

Understanding and recognition of human emotions are very crucial in various fields. This paper proposes a new approach to show the different feelings that are hidden using multi-modalities like video, audio, and textual data. A custom dataset AED-FST has been used in this work which has nearly 317 samples each consisting of some audio clip, some visual media, and a question-and-answer pair. From all these entirely diverse sources, the goal is to create a model that could possibly detect emotional cues. It found hidden emotions with a 67% accuracy, representing how well it could pick up on these weak cues from all different modalities. This method contributes immensely to emotion detection in extremely wide fields, including psychological diagnoses and human-computer interaction, to mention just a few. © 2024 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Code Insights through Semantic Change Impact Evaluation 15

Enhancing Code Insights through Semantic Change Impact Evalu...

引用

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

作者： Vyshnavi, Chellu Raj, Chukka Mishal Gopakumar, Gokul Prasanna, Guddeti Bindu Belwal, Meena Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

In software development, system integrity is a measure of the impact code changes have on them. It is determined by the team's comprehension. However, rapid evolution of change commits and interaction in complex code bases create problems. By evaluating the effect of reflection changes, this study contributes to the improvement of the comprehension of code, a critical success factor for quality and efficiency. This addresses issues by using semantic analysis, change detection, refactoring detection, and semantic change detection and diffing. Our approach documents the semantic differences between the original and changed source code and gives pragmatic conclusions on how to enhance code quality and maintainability. Specifically, we divide the code into AST files using simple python scripts for semantic analysis and compare them for differences to find implications. It executes the method through the focus on development workflows and major projects as it includes the past information while still simplifying argument parsing and file processing. Based on our study findings, a better understanding of code can help developers to improve their decision-making capacity and protect the performance during the enhancement activity of the program. © 2024 IEEE.

关键词： Abstract Syntax Trees (ASTs) change detection refactoring detection semantic analysis semantic changes

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning in Stock Trading: Evaluating DDPG and DQN Strategies 6

Deep Reinforcement Learning in Stock Trading: Evaluating DDP...

引用

6th IEEE International Conference on Emerging Smart computing and Informatics, ESCI 2024

作者： Kodurupaka, Nithin Basavadeepthi, H.M. Pecheti, Shiva Teja Amudha, J. Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350306613

This study presents a comparative analysis of the Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithms in the context of stock trading, focusing on historical stock price data of S&P 500 stock index. The primary objective is to evaluate the effectiveness of these RL algorithms in making trading decisions and achieving financial performance relative to a passive buy-And-hold strategy. The assessment revolves around key metrics, with a special emphasis on the buy, hold, and sell indications as essential signals for trading actions. Results indicate that DQN outperforms DDPG, showcasing a smaller total loss during the evaluation period. This suggests that DQN may offer superior capabilities in limiting financial losses and making effective trading decisions compared to DDPG, providing valuable insights into algorithm selection for dynamic trading environments. It is crucial to recognize the significance of buy, hold, and sell indications as key elements in assessing the performance of RL algorithms in stock trading scenarios. © 2024 IEEE.

关键词： Algorithmic Trading Buy-And-Hold Strategy DDPG Trading Agent Deep Neural Networks Deep Reinforcement Learning DQN Portfolio Performance Total Return

来源：评论

学校读者我要写书评

暂无评论

Neural Networks and Evolutionary Algorithms Based Approaches for engineering Recommendation Systems - A Comprehensive Review 2

Neural Networks and Evolutionary Algorithms Based Approaches...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Priyadharshini, B. Apoorva, N. Alekhya, Arvapalli Sagar, Gajula Sujan Jeyakumar, G. Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350328202

Recommendation systems are the subset of data filtering techniques and focus on providing personalized suggestions to the users. The systems rely on the data to provide insightful suggestions. Over the years, recommendation system has gained huge prominence in boosting e-commerce platforms, and online personalized services to users. Along with their popularity, these systems also face challenges such as data sparsity, time constraints, and scalability. As a result, various approaches are opted along with the traditional techniques to optimize the process. This paper reviews the various approaches followed in engineering the recommendation systems and analyzes their efficiencies. The approaches focus primarily on understanding the involvement of neural networks and evolutionary algorithms and their performance compared to other systems involved with approaches like clustering techniques, linear-based techniques, probabilistic models, etc. This paper also provides insights into the various hybrid approaches followed by the different recommender systems involving neural networks and evolutionary algorithms. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Approach to Automatic Car Reliability System Prediction with Probabilistic Modeling and Machine Learning 3

A Graph-Based Approach to Automatic Car Reliability System P...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Krishna, Kaivaram Sivarama Kumar, Bommala Deepak Reddy, Morumpalli Deekshith Varun, Bheema Sai Murali, K. Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350369083

Reliability prediction in automotive systems undoubted represents a substantial part of safety and customer satisfaction. a new graph-based probabilistic method and machine learning algorithm for the automotive system reliability prognosis. By breaking complex dependency among vehicles' components into a hierarchy and using past failure data, the method improves on prediction error. Real-world automotive datasets show excellent results with better resolution and higher accuracy for the enhanced components compared to existing techniques while at the same time providing interpretability by visualizing the dependency of the components. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MAESTRO-EP: Multi-Architecture Ensemble System for Temporal Reasoning and Outcome Prediction in Event Processing 8

MAESTRO-EP: Multi-Architecture Ensemble System for Temporal ...

引用

8th IEEE International Conference on Information and Communication Technology, CICT 2024

作者： Shekar, Vaibhav Devaraja, G. Mahadevan, Anbazhagan Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331531539

MAESTRO-EP (Multi-Architecture Ensemble System for Temporal Reasoning and Outcome Prediction in Event Processing) is an innovative deep learning framework designed to model and predict outcomes in complex event-driven systems. This paper introduces a novel multi-head ensemble architecture that leverages diverse neural network models, including RNNs, LSTMs, CNNs, Transformers, and GRUs, to capture intricate temporal patterns in event sequences. Our approach utilizes a minimal event schema, allowing the model to organically learn complex behaviors across various domains, from supply chain networks to game environments. We evaluate MAESTRO-EP on multiple datasets, including supply chain simulations, Tic-Tac-Toe, and pathfinding algorithms, demonstrating its superior performance in context output accuracy. The system's highly scalable and adaptable architecture provides a robust framework for future research in adaptive AI systems and digital twin simulations, with the potential to significantly advance event sequence modeling capabilities in dynamic multi-agent environments, particularly in complex supply chain networks. © 2024 IEEE.

关键词： Multi agent systems

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：