检索结果-内蒙古大学图书馆

aiAA science and Technology Forum and Exposition, aiAA SciTech Forum 2025

作者： Otte, Noah Satpute, Sumeet Gajanan Banerjee, Avijit Nikolakopoulos, George Robotics and AI research group Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper introduces a novel, computationally efficient, random-search based path-planning algorithm specifically designed to enhance the dexterous accessibility of autonomous lunar rovers operating on highly cluttered obstacle-dense planetary surfaces. The proposed pathplanning framework employs a Quadtree-based cell decomposition to enhance the performance of sampling-based path-planning algorithms, specifically those in the category of Rapidlyexploring Random Trees (RRT) and its optimized variant, RRT*. In the process of generating the path through an occupancy grid map, the obstacle-free cells are utilized as discrete sampling points for the RRT* algorithm. A unique non-uniform sampling approach is employed to favour larger cells with a higher degree of safety, thereby enabling seamless navigation through the obstacle-dense map. Additionally, the non-uniform sampling approach enhances the overall computational efficiency of the framework, making it suitable for fast, lightweight onboard implementation. The efficacy of the proposed planning framework is demonstrated through numerous simulation scenarios. © 2025, American Institute of Aeronautics and Astronautics Inc, aiAA. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

DCBLCCG NET: A Fusion Approach For Enhanced Pepper Leaf Disease Identification With Hybrid Deep Learning

DCBLCCG NET: A Fusion Approach For Enhanced Pepper Leaf Dise...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Shaik Salma Asiya Begum Hussainbi Shaik Hussain Syed Department of CSE(AI&ML) LakiReddy Bali Reddy College of Engineering Mylavaram NTR District AP India School of Computer Science and Engineering VIT-AP University Amaravati AP India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

The agricultural sector in developing countries like Ethiopia heavily relies on crop health and productivity. Pepper, a crucial crop for global food security, faces significant threats from various diseases, including blight leaf disease, gray leaf spot, common rust, fruit rot, and powdery mildew. The existence of 34 different pepper diseases has resulted in an average reduction of 33% in crop productivity. Traditional disease detection methods, such as visual inspection by farmers, are prone to errors and are time-consuming Previous research has largely employed image processing and deep learning for disease classification in pepper plants. This study introduces a novel approach by combining a Deep Convolutional Neural Network (DCNN) with a Bidirectional Long Short-Term Memory (BILSTM) network. While DCNN excels at extracting spatial features, BILSTM captures the sequential growth patterns of pepper plants. This hybrid model achieved $\mathbf{1 0 0 \%}$ accuracy during training and performed exceptionally well on a dataset of pepper disease images. Utilizing features from pretrained CNNs like VGG16 and AlexNet, the model attained a top classification accuracy of $\mathbf{9 9. 5 \%}$, with grayscale datasets and segmented images achieving $\mathbf{9 8. 9 \%}$ and $\mathbf{9 9. 3} \%$, respectively. This robust model is a powerful tool for rapid and accurate pepper disease identification, improving disease management and agricultural productivity.

关键词： Productivity Image segmentation Accuracy Microorganisms Transfer learning Bidirectional long short term memory Crops Gray-scale Feature extraction Diseases

来源：评论

学校读者我要写书评

暂无评论

A novel approach to detect, analyze and block adversarial web pages

引用

International Journal of Information Technology (Singapore) 2024年第6期16卷 3617-3622页

作者： Kumar, M. Ranjith Naik, Darshana A. Kapila, Neha Mohan, Chinnem Rama Prasad, Ch Raghava Shelke, Chetan Rao, C. V. Guru School of Computer Science and Engineering Vellore Institute of Technology Department of Computer Science and Engineering M S Ramaiah Institute of Technology Department of Electronics and Electrical Engineering Lovely Professional University Department of Computer Science and Engineering Narayana Engineering College Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Alliance College of Engineering and Design Alliance University School of CS & amp AI SR Universtity

The phenomenon of distraction is very common, and its adverse effects are seen among people. The major cause underlying this issue is the ease with which adversarial web sites and web pages can be accessed. It is of utmost importance to locate, evaluate, and actively block such web pages in an effort to comprehensively and globally solve this societal issue. Thus, the given paper proposes an extension or plug-in to detect, analyze, and block websites smartly. The proposed approach takes keywords entered by the user as input into consideration, which eventually leads to the generation of web pages and web links. The filtering of web links is done by the proposed extension, followed by the extraction of features, the utilization of support vector machines (SVM) for binary classification, and the summarization of textual data using natural language processing (NLP). Lastly, the precise results corresponding to relevant web links are presented to the users, which will increase their productivity, thereby reducing their distraction levels under all working circumstances. The performance of the proposed approach is validated against existing recent studies based on evaluation metrics such as adversarial website detection time (ms) and accuracy (%). © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Adversarial web pages Distraction Natural language processing (NLP) Support vector machine (SVM) Text summarization

来源：评论

学校读者我要写书评

暂无评论

A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning 25

A Case Study on Context-Aware Neural Machine Translation wit...

引用

25th Annual Conference of the European Association for Machine Translation, EAMT 2024

作者： Appicharla, Ramakrishna Gain, Baban Pal, Santanu Ekbal, Asif Bhattacharyya, Pushpak Department of Computer Science and Engineering Indian Institute of Technology Patna India Wipro AI Lab45 London United Kingdom School of AI and Data Science Indian Institute of Technology Jodhpur India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

ISBN: (纸本)9781068690709

In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies (Li et al., 2020) have shown that the context encoder generates noise and makes the model robust to the choice of context. This paper further investigates this observation by explicitly modelling context encoding through multi-task learning (MTL) to make the model sensitive to the choice of context. We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. Generation of the source from the context is considered an auxiliary task, and generation of the target from the source is the main task. We experimented with German-English language pairs on News, TED, and Europarl corpora. Evaluation results show that the proposed MTL approach performs better than concatenation-based and multi-encoder DocNMT models in low-resource settings and is sensitive to the choice of context. However, we observe that the MTL models are failing to generate the source from the context. These observations align with the previous studies, and this might suggest that the available document-level parallel corpora are not context-aware, and a robust sentence-level model can outperform the context-aware models. © 2024 The authors, © 2024 European Association for Machine Translation.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Mitigating Catastrophic Forgetting in Deep Learning Models for Sentiment Analysis

Mitigating Catastrophic Forgetting in Deep Learning Models f...

引用

International Conference on Advances in Information Technology (ICaiT)

作者： J. Ranjith Santhi Baskaran B. Adithya Department of Computer Science and Engineering Puducherry Technological University Puducherry India Department of Inofrmation Technology Puducherry Technological University Puducherry India Department of CSE(AI&ML) Geethanjali College of Engineering and Technology Hyderabad India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Deep learning models have been employed to evaluate sentiment analysis. However, the issue of catastrophic forgetting is frequently seen in these models. Cognitive decline occurs when the model's performance on previously learned tasks deteriorates as it acquires new ones. A study is conducted to investigate the impact of catastrophic forgetting on sentiment analysis algorithms and propose potential solutions to address this issue. This study evaluates the adaptability of Elastic Weight Consolidation (EWC) and Learning without Forgetting (LwF) in effectively handling novel sentiment analysis tasks while preserving the model's performance on previously acquired tasks. Experimental results on the Amazon Product Reviews dataset demonstrate that both EWC and LwF significantly reduce the impact of catastrophic forgetting, with LwF outperforming EWC in terms of sentiment classification accuracy. Our findings highlight the importance of addressing catastrophic forgetting in sentiment analysis models to ensure their robustness and reliability in real-world applications.

关键词： Deep learning Training Sentiment analysis Analytical models Adaptation models Accuracy Reviews Robustness Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

TOWARDS IMITATION LEARNING TO BRANCH FOR MIP: A HYBRID REINFORCEMENT LEARNING BASED SAMPLE AUGMENTATION APPROACH 12

TOWARDS IMITATION LEARNING TO BRANCH FOR MIP: A HYBRID REINF...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhang, Changwen Ouyang, Wenli Yuan, Hao Gong, Liming Sun, Yong Guo, Ziao Dong, Zhichen Yan, Junchi AI Lab Lenovo Research China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Branch-and-bound (B&B) has long been favored for tackling complex Mixed Integer Programming (MIP) problems, where the choice of branching strategy plays a pivotal role. Recently, Imitation Learning (IL)-based policies have emerged as potent alternatives to traditional rule-based approaches. However, it is nontrivial to acquire high-quality training samples, and IL often converges to suboptimal variable choices for branching, restricting the overall performance. In response to these challenges, we propose a novel hybrid online and offline reinforcement learning (RL) approach to enhance the branching policy by cost-effective training sample augmentation. In the online phase, we train an online RL agent to dynamically decide the sample generation processes, drawing from either the learning-based policy or the expert policy. The objective is to strike a balance between exploration and exploitation of the sample generation process. In the offline phase, a value function is trained to fit each decision's cumulative reward and filter the samples with high cumulative returns. This dual-purpose function not only reduces training complexity but also enhances the quality of the samples. To assess the efficacy of our data augmentation mechanism, we conduct comprehensive evaluations across a range of MIP problems. The results consistently show that it excels in making superior branching decisions compared to state-of-the-art learning-based models and the open-source solver SCIP. Notably, it even often outperforms Gurobi. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning

引用

ACM Transactions on Management Information Systems 2025年第2期16卷 1-24页

作者： Liu, Xiao-Yang Zhu, Rongyi Zha, Daochen Gao, Jiechao Zhong, Shan White, Matt Qiu, Meikang Department of Computer Science Rensselaer Polytechnic Institute Columbia University New York United States Department of Electrical Engineering Columbia University New York United States Department of Computer Science University of Rochester Rochester United States Department of Computer Science Rice University Houston United States Department of Computer Science University of Virginia Charlottesville United States Executive Director PyTorch Foundation Gm of AI Linux Foundation CA United States School of Computer and Cyber Sciences Augusta University Augusta United States

The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science. However, concerns regarding data privacy have emerged, especially when multiple stakeholders aim to collaboratively enhance LLMs using sensitive data. In this scenario, federated learning becomes a natural choice, allowing decentralized fine-tuning without exposing raw data to central servers. Motivated by this, we investigate how data privacy can be ensured in LLM fine-tuning through practical federated learning approaches, enabling secure contributions from multiple parties to enhance LLMs. Yet, challenges arise: (1) despite avoiding raw data exposure, there is a risk of inferring sensitive information from model outputs, and (2) federated learning for LLMs incurs notable communication overhead. To address these challenges, this article introduces DP-LoRA, a novel federated learning algorithm tailored for LLMs. DP-LoRA preserves data privacy by employing a Gaussian mechanism that adds noise in weight updates, maintaining individual data privacy while facilitating collaborative model training. Moreover, DP-LoRA optimizes communication efficiency via low-rank adaptation, minimizing the transmission of updated weights during distributed training. The experimental results across medical, financial, and general datasets using various LLMs demonstrate that DP-LoRA effectively ensures strict privacy constraints while minimizing communication overhead. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Prediction of Parkinson's Disease Progression using Voice Recordings 7

Deep Learning-based Prediction of Parkinson's Disease Progre...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Alagdeve, Vilas D. Thatipudi, Jayendra Gopal Roy, Priyanka Nithya, R. Anil Kumar, N. Ramesh, B. Yeshwantrao Chavan College of Engineering Department of Electronics Engineering Maharashtra Nagpur441110 India University of North Texas Department of Computer Science DentonTX76203 United States Vellore Institute of Technology Department of Electrical and Electronics Engineering Tamilnadu Vellore India Vivekanandha College of Engineering for Women Department of Computer Science and Engineering Tamilnadu Tiruchengode637205 India Mohan Babu University School of Engineering and Technology Department of Electronics and Communications Engineering Tirupati India St. Martin's Engineering College Department of Ai&ml Telangana Secunderabad Dhulapally500100 India

ISBN: (纸本)9798350341485

The main underlying factor behind Parkinson's Disease (PD) is the degeneration of brain cells responsible for producing dopamine, a neurotransmitter crucial for interconnecting brain cells. These dopamine-producing cells play a vital role in controlling adaptability, regulating movement, and facilitating fluency. The concept of active aging has emerged to enhance various aspects of fitness as individuals age, ultimately improving their overall quality of life. However, most efforts have concentrated on promoting normal aging, with limited attention given to the elderly population afflicted with chronic conditions like PD. This research focuses on the application of deep learning techniques for early detection and diagnosis of Parkinson's disease (PD). In the first experiment, this study utilizes the voice samples from healthy individuals and PD patients as a minimum training set for the Enhanced Deep Neural Network Model (EDNN) classifier, resulting in an optimal prediction model capable of identifying early onset PD. Subsequently, this study also investigates the effectiveness of transfer learning using the Convolutional Neural Network (CNN) architecture Alex Net for diagnosing Parkinson's disease from MR images in a second experiment. The results demonstrate the successful implementation of the EDNN classifier, showcasing its potential for early detection of Parkinson's disease, allowing for timely intervention and treatment. Moreover, by employing transfer learning with AlexNet, this study presents a novel approach for accurately diagnosing Parkinson's disease from MR images, representing a significant advancement in medical image analysis. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Harmful Insects in Agriculture: A Smart Framework Leveraging IoT, Machine Learning, and Blockchain

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4787-4798页

作者： Rahman, Wahidur Hossain, Muhammad Minoar Hasan, Md. Mahedi Iqbal, Md. Sadiq Rahman, Mohammad Motiur Fida Hasan, Khondokar Moni, Mohammad Ali Mawlana Bhashani Science and Technology University Department of Computer Science and Engineering Tangail1902 Bangladesh Uttara University Department of Computer Science and Engineering Dhaka1230 Bangladesh Prime University Department of Management and Information System Mirpur Dhaka1216 Bangladesh Bangladesh University Department of Computer Science and Engineering Dhaka1207 Bangladesh School of Professional Studies CanberraNSW2052 Australia Artificial Intelligence and Cyber FuturesInstitute Charles Sturt University AI & Digital Health Technology BathurstNSW2795 Australia

Paddy cultivation is a significant global economic sector, with rice production playing a crucial role in influencing worldwide economies. However, insects in paddy farms predominantly impact the growth rate and ecological equilibrium of the agricultural field. Hence, the precise and timely identification of insects in agricultural settings presents a potential strategy for addressing this issue. This study aims to implement an automated system for paddy farming by employing a real-time framework that incorporates the Internet of Things (IoT), blockchain technology, and Deep Learning (DL) algorithms. The primary emphasis of the DL-based system is on the timely identification of pests. In contrast, integrating the IoT and blockchain technologies facilitates stablishing a fully automated system with security within the agricultural domain. The DL-based system includes a secondary dataset of paddy insects, and then preprocessing, feature extraction, and identification have been performed. Besides, an IoT-based system is embodied with a camera module and microprocessor, accompanied by some apparatus required to automate the whole system. In addition, the research also includes the blockchain to secure each individual data transmission among the several IoT components and the cloud server. While examining the proposed solution, various experimental data have been systematically documented and analyzed. The proposed framework attained a peak accuracy of 98.91% using the VGG19 model and ensemble classifiers to detect the pest with a specificity of 99.14% and a precision of 98.21%. The study additionally quantifies the mean duration of the cloud response when integrated with IoT, yielding an average time of 1.71 s after pest identification. Nevertheless, the system has exhibited a high level of efficacy in the context of real-time monitoring and automation of paddy farms. © 2020 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition in Visual Art on Color and Texture Analysis using Improved Vision Transformer 1

Emotion Recognition in Visual Art on Color and Texture Analy...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Suma, K.G. Balasm, Zaed Sasirekha, N. Veera Manikandan, P. Sandhya, K. Vellore Institute of Technology School of Computer Science and Engineering Department of Ai & Ml Andhra Pradesh India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Sona College of Technology Department of Electronics and Communication Engineering Salem India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Electrical and Electronics Engineering Mamallapuram India Tirupati India

ISBN: (纸本)9798331529246

Nowadays, Emotion Recognition plays a key role in social communication interaction in which human emotions are interpreted from facial expressions and speech. Several challenges occur in emotion recognition such as capturing context of any emotion also facial attributes make the recognition process complex. To overcome these drawbacks Improved Vision Transformer (IViT) classifier is proposed for emotion recognition. Initially, the input data is collected from the Japanese Female Facial Expression (JAFFE) to collect color features and visual features. Then, the input data is processed using min max scaling method which normalizes pixel values. After that, colour and texture-based features are extracted by utilizing Rotation Invariant Local Binary Patterns (RI-LBP) with Hue Saturation and Value (HSV) and Red Green Blue (RGB). Finally, classification is performed by IViT, which processes images as sequences of patches. Hence, the proposed IViT model achieved better output when compared to existing Visual-Audio Attention Network (VAANet) in terms of accuracy by obtaining 96.6% respectively. © 2025 IEEE.

关键词： Local binary pattern

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：