检索结果-内蒙古大学图书馆

Next-Generation Computing, IoT and Machine Learning (NCIM), International Conference on

作者： Ashraful Islam Syeda Rafiatus Sama Raisa Nahiyan Habib Khan Ariful Islam Rifat Dept. of Computer Science and Engineering Sylhet Engineering College Sylhet Bangladesh Dept. of Computer Science and Engineering American International University-Bangladesh Dhaka Bangladesh

Bangladesh's economy is heavily dependent on agriculture, making the region an exceedingly crucial sector that requires great vigilance. In comparison to other vegetables, leafy greens have yet to garner as much attention as other crops that this study's large-scale analysis comes up with, particularly when categorizing readily available leafy vegetables and identifying the affected area and whether they are affected or not. Plant diseases can cause substantial losses in agricultural productivity, and many researchers are working to address the difficulties farmers encounter in identifying and treating these conditions while diagnosing their diseases. The purpose of this study is to develop a dependable and effective approach for classifying seven varieties of leafy vegetables and detecting seven types of plant diseases precisely in Bangladesh using machine learning and deep learning CNN models. To this end, this paper analyzed and provided solutions using a total of eight models: five classification models (VGG16, VGG19, ResNet50, YOLOv5, and YOLOv8) and three instance segmentation models (YOLOv5, YOLOv7, and YOLOv8). Two distinct datasets, “LeafyVclassify7BD” with 3306 images and “LeafyVdisease7BD” with 4493 images, were developed to classify leaves, segment the diseased area, and classify and detect damaged leaves. The research outputs will help strengthen the region's ability to control plant diseases more effectively while also cutting diagnostic costs and enhancing disease detection accuracy in the country's agricultural surroundings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Faulty Classes Prediction in Object-Oriented Programming Using Composed Dagging Technique

Faulty Classes Prediction in Object-Oriented Programming Usi...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Nagib Mahfuz Pintu Chandra Shill Dept. of Computer Science and Engineering North Western University Khulna Bangladesh Dept. of Computer Science and Engineering Khulna University of Engineering and Technology Khulna Bangladesh

Class is one of the fundamental concepts of the object-oriented paradigm and has been scrutinized since the developers moved on from procedural programming design. In software fault prediction, the legalization of software metrics is essential. As a handful of software metrics suites exist, it is a very hard task to predict the defective classes flawlessly using a particular set of metrics suites. However, it is a rational approach to use only the object-oriented metrics that are directly relatable to the class definitions in the code that helps the developers foresee the errors in defining the classes and minimize the errors as much as possible. This paper utilized twelve object-oriented metrics selected from various metrics suites. The dagging ensemble model is merged with three well-known classification algorithms (Naive Bayes, Multilayer Perceptron, J48 Decision Tree) individually and applied to twelve java projects. The study depicts that the proposed ensemble method gives improved outcomes that are statistically significant when merged with Naive Bayes and Multilayer Perceptron. The proposed ensemble method shows improvements up to 12.5% in accuracy and 15% in F-Score.

关键词： Measurement Software metrics Object oriented modeling Multilayer perceptrons Predictive models Software Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysis of Historical Weather of Karnataka, India for Insights in Climate Trends

Analysis of Historical Weather of Karnataka, India for Insig...

引用

Modeling, Simulation & Intelligent Computing (MoSICom), International Conference on

作者： B K Sanjana Anilloy Frank Dept. of Computer Science Engineering Presidency University Bangalore India Dept. of Electronics and Communication Engineering Presidency University Bangalore India

ISBN: (数字)9798331533311

ISBN: (纸本)9798331533328

Climate change in simpler words means the change in the long-term average weather parameters. Climate change is an important issue because its causing imbalance in the environment and affects the lives of all flora and fauna. The climate change is due to many factors, but the major factor is the human activities which are leading to global warming over the past decades. Numerous studies consider analysis of continental or global data, providing the overall insights in climatic changes continentally or globally respectively. The approach in this paper considers regional analysis to provide better insights to the local people needs so they get adapted to the changes that are taking place. This provides a warning to the people to take preventive and precautionary measures. The dataset of Karnataka region from 1951 to 2020 is used to study the regional climate change pattern. The main objective of the paper is to analyze the climate change and extending in the future. The results show that there is a gradual increase of average mean surface air temperature and gradual decrease of the precipitation over each decade between the years 1951 to 2020. The trend line extending to 2040 by analyzing the historical data gives insights about the climate change in the near future. Understanding the historical data and the future predictions are very important to the policy makers, people and researchers so that effective planning can be done for adapting and decreasing the climate change patterns.

关键词： Climate change Temperature distribution Precipitation Urban areas Data visualization Predictive models Market research Planning Spreadsheet programs Portals

来源：评论

学校读者我要写书评

暂无评论

Directed Adversarial Training for Comprehensive Robustification of CNNs

Directed Adversarial Training for Comprehensive Robustificat...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Bhuvi Ghosh Harsh Shetye Atharv Salian Nilesh Marathe Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Deep convolutional neural networks (CNNs), renowned for their high accuracy on clean datasets, remain notably vulnerable to adversarial attacks. This study assesses how the VGG16 and ResNet50 models withstand various white-box attacks when used for traffic sign classification. Despite their impressive standard accuracy, our findings reveal that these accuracies do not predict robustness against attacks. Techniques such as the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) substantially lowered model accuracy, while DeepFool and Carlini & Wagner (C&W) attacks were even more disruptive. In particular, ResNet50 was more prone to these attacks, with its accuracy dropping to as low as $\mathbf{1 2. 8 5 \%}$ under DeepFool and $\mathbf{1 7. 4 2 \%}$ under C&W at specific confidence levels. Retraining models with adversarial examples did enhance their resilience to certain attacks but at the expense of reduced effectiveness on clean data. These results highlight the critical need for developing more robust defense mechanisms that protect CNNs against a wide array of adversarial threats without compromising performance on standard inputs.

关键词： Training Accuracy Noise Robustness Data models Iterative methods Standards Residual neural networks Glass box Resilience

来源：评论

学校读者我要写书评

暂无评论

ML-Based Trading Strategy for Short-Term Price Reactions on Earnings Announcement Reports

ML-Based Trading Strategy for Short-Term Price Reactions on ...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Jin, Yiqun Bao, Siya Waseda University School of Commerce Japan Waseda University Dept. of Computer Science and Communications Engineering Japan

ISBN: (纸本)9781665480451

An earnings announcement report (EAR) contains the latest information about a company's financial situation and operating performance. Short-term stock price reacts strongly to such information. In this paper, to gain investment return from the short-term price reaction to EARs, we use 28 important variables from EARs and propose an ML-based trading strategy (MLTS) with random forest (RF). Results show that our strategy achieves the highest final investment return of 178.1%. © 2022 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Prioritized Semi-supervised Deep Embedded Clustering

Prioritized Semi-supervised Deep Embedded Clustering

引用

2022 International Conference on Innovative Trends in Information Technology, ICITIIT 2022

作者： Saladi, Pranita Guntupalli, Rishi Manudeep Puppala, Sudheer Kumar Pulabaigari, Viswanath Indian Institute of Information Technology Sri City Dept. Computer Science Engineering Sri City India

ISBN: (纸本)9781665406703

Clustering, to group similar objects, is an important problem. Recently deep learning-based methods like Deep Embedded Clustering (DEC) [6] and its semi-supervised version called Semi-supervised Deep Embedded Clustering (SDEC) [12], where partially labeled data or data with constraints is available, are shown to give promising results. Both DEC and SDEC learn a latent space where similar objects are closer and dissimilar are away. While promising results are shown, the information present in constraints or a labeled subset of the data is not fully utilized. This paper proposes to use priorities for constraints so that important constraints are given more weightage than unimportant ones. Those constraints with points that are far away, but should be clustered into a group, gets more weight than other labeled points. Similarly, those in different groups which are very close get more weightage. The appropriate loss function is used in the learning process. The proposed method is called Prioritized Semi-supervised Deep Embedded Clustering (PSDEC). The results are compared using a few standard data sets against recent and classical similar methods. PSDEC is found to achieve a better result than un-prioritized constraints. © 2022 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Opportunistic Balancing and Strategic Insights through Deep Reinforcement Learning in Asset Allocation

Opportunistic Balancing and Strategic Insights through Deep ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Harsh Shetye Vaidehi Shah Jay Chotalia Pradnya Saval Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Asset allocation, diversification of investments across various asset classes, presents significant challenges in accurately forecasting expected returns and adapting to dynamic market conditions. This research explores a novel approach, “Opportunistic Balancing and Strategic Insights through Deep Reinforcement Learning in Asset Allocation,” by leveraging Deep Reinforcement Learning (DRL) to optimize dynamic asset allocation strategies. Specifically, we investigate the Advantage Actor-Critic (A2C) Model, renowned for its stability and superior performance with large batch sizes. Our approach aims to capture short to medium-term market trends and anomalies, enabling strategic asset allocation to enhance risk-adjusted returns. We evaluate the DRL models’ performance against traditional benchmarks, including the portfolio index, the naive equal-weight allocation, and the maximum Sharpe strategy (mean-variance optimization). The DRL models exhibit relatively superior performance compared to the mean-variance portfolio during periods preceding 2020, with the A2C model outperforming the benchmark DJIA index across all considered market conditions. Notably, the A2C model demonstrated a Sharpe ratio of 0.733, surpassing the DJIA index’s Sharpe ratio of 0.406. Additionally, during the 2020 market downturn, the A2C model exhibited a faster recovery rate than the benchmark index, regaining positive returns swiftly.

关键词： Analytical models Uncertainty Stability criteria Benchmark testing Deep reinforcement learning Dynamic scheduling Resource management Indexes Portfolios Optimization

来源：评论

学校读者我要写书评

暂无评论

CA-CR: Context-Aware Congestion Resolution Method for Automated Guided Vehicles

CA-CR: Context-Aware Congestion Resolution Method for Automa...

引用

Applied Artificial Intelligence (ICAPAI), International Conference on

作者： Yigit Can Dundar Bernt Arild Bremdal Anne Håkansson Randi Karlsen Dept. of Computer Science UiT - The Arctic University of Norway Tromsø Norway Dept. of Computer Science and Computational Engineering UiT - The Arctic University of Norway Narvik Norway

ISBN: (数字)9798350349764

ISBN: (纸本)9798350349771

Modern logistics solutions use Automated Guided Vehicles (AGVs) in order to streamline logistics tasks in various work environments. While handling logistics tasks, AGVs can encounter congestions in the form of traffic or blockages which can cause slow-downs and deadlocks. Congestions can occur randomly and unexpectedly in work environments that are unknown to the AGVs. In unknown environments, access to environmental information is limited. Therefore, avoiding or resolving a congestion is a difficult task for AGVs. In order to compensate for the lack of environmental information, the contextual information of the congestion can be used. This paper presents the Context-Aware Congestion Resolution (CACR) method for AGVs in unknown work environments. The method uses contextual information in the form of number of agents, the vehicles’ current battery levels, task priorities and agent positioning to resolve congestions through a multi-agent negotiation. The negotiation uses the contextual information to find various solutions to random and unpredictable congestion scenarios. The negotiations are aided with reinforcement learning to train AGVs to move towards a collective utility maximizing behavior. To test the AGVs performance, the trained behavior is compared to a baseline, non-trained behavior for evaluation of reinforcement learning’s impact on optimizing the resolution of congestions. Findings indicate that the trained behavior shows better scaling with number of agents, better battery utilization and collective utility compared to baseline.

关键词： Training Remotely guided vehicles Reinforcement learning System recovery Batteries Resource management Proposals

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Classical and Quantum Algorithms for Portfolio Optimization: Enhancing Financial Decision-Making Through Quantum Computing

Empirical Analysis of Classical and Quantum Algorithms for P...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Krish Valecha Anuradha Yeole Atharv Salian Shruti Mathur Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

This research investigates the efficacy of quantum and classical algorithms in the context of portfolio optimization, focusing on a dataset comprising 20 equities from India's National Stock Exchange over a duration of three years. The study employs quantum methodologies such as the Quantum Approxi-mate Optimization Algorithm (QAOA), the Variational Quantum Eigensolver (VQE), and the Exact Minimum Eigen Solver, alongside conventional strategies including Mean-Variance Op-timization, Genetic Algorithms, and Simulated Annealing. The methodology for this study includes data preprocessing, issue designing, and performance evaluation based on metrics such as MSE, RMSE, and Mean Absolute Error. The results obtained show quantum algorithms exhibit better performance over the classical methods regarding prediction accuracy and risk-return profiles, especially the Exact Minimum Eigen hSolver and QAOA. The Exact Minimum Eigen Solver and QAOA had the lowest MSE values (0.006 and 0.005, respectively), whereas the best-performing classical technique, the Genetic Algorithm, had an MSE of 0.0105. These findings imply that quantum algorithms provide significant advantages in portfolio optimization problems, with the potential to revolutionize financial optimization tactics. The research can be further unfolded into avenues for future inquiry, including expansion of the choice of assets, alternative data sources integration, as well as hybrid quantum-classical models to efficiently enhance portfolio management strategies.

关键词： Quantum algorithm Accuracy Soft sensors Simulated annealing Transforms Prediction algorithms Stock markets Optimization Portfolios Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel CNN method for the accurate spatial data recovery from digital images

引用

Materials Today: Proceedings 2023年 80卷 1706-1712页

作者： Murugan, G. Moyal, Vishal Nandankar, Praful Pandithurai, O. John Pimo, Er.S. St John College Of Engineering and Management Maharashtra Palghar India SVKMs Institute of Technology Maharastra Dhule India Electrical Engineering Dept. Government College of Engineering Nagpur India Computer Science and Engineering Rajalakshmi Institute of Technology Poonamallee Tamilnadu Chennai India Department of CSE St. Xavier's Catholic College of Engineering Chunkankadai Tamil Nadu Nagercoil India

The parsing of floorplans has been an issue for a long time in automated document processing and with algorithmic methods until recent years. This problem has also improved output with the emergence of convolutionary neural networks (CNN). The job here is to obtain spatial and geometrical data from floorplans as accurately as possible. The aim of this project is to extract the most information from a floor plan image around instance segmentation models like Cascade Mask R-CNN. A new style of key point CNN is being implemented to supplement the segmentation to find correct corner positions. Then the resulting segmentation is combined in a post-processing stage. With a mean IoU of 72.7 percent versus 57.5 percent, the resulting segmentation scores surpass the existing baseline of the CubiCasa5k floorplan data base. Moreover, for almost every class, the mean IoU for each class is increased. Cascade Mask R-CNN has also been shown to be better suited to this role than Mask R-CNN. © 2021

关键词： E-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：