检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Vishnuvarthan, K. Renugadevi, R. Santhi, S. Kit - Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Grapes are among the most extensively cultivated fruit crops globally, with over 10,000 varieties. They serve as a significant economic resource for many nations due to their diverse applications, including wine production, fresh juice consumption, raisin production, and juice manufacturing. However, grape diseases pose a severe threat to the viticulture industry, leading to substantial financial losses and a decline in wine quality. Manual evaluation is the foundation of traditional disease detection techniques, which are error-prone in addition to saving time. This highlights the need for an automated system capable of analyzing plant health, identifying diseases, and addressing undernourishment efficiently and reliably. Accurate disease diagnosis and timely control measures are crucial for mitigating these challenges. Many scholars have studied various algorithms such as CNN, SVM, Neural Networks, Random Forests, etc., yet each has disadvantages. So we have proposed an automated deep learning-based approach that integrates the Honey Badger Algorithm (HBA) with Convolutional Neural Networks (CNN) for the detection of grape diseases. A phenomenal 95% accuracy rate was attained by the prototype after it was trained on a dataset of 10,000 photos. Its performance was evaluated across various grape varieties and environmental conditions, demonstrating its robustness and adaptability. © 2025 IEEE.

关键词： Wine

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Attention Deficit/Hyperactivity Disorder using Machine Learning and Deep Learning Algorithms 1

Comprehensive Analysis of Attention Deficit/Hyperactivity Di...

引用

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

作者： Sindhu, T.N. Sujatha, S.R. Sri Siddhartha Institute of Technology Department of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798331529246

Attention deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects children from childhood to adulthood. The symptoms of ADHD include attention deficit, impulsive behaviour, hyperactivity, and early diagnosis and treatment are imperative, especially for children as it continues into adulthood. ADHD detection is generally carried out using the existing methods such as Machine Learning (ML) and Deep Learning (DL) methods. The ML methods such as Linear Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Linear Discriminative Analysis (LDA), Linear Regression (LR), Random Forest (RF), and Least Square SVM (LS-SVM) are used for the detection and analysis of ADHD. The existing DL methods such as Deep Convolutional Neural Network (DCNN), Graph Recurrent Unit (GRU), Convolutional Long Short-Term Memory (ConvLSTM), and Bidirectional LSTM are also employed for the detection of ADHD. The ML and DL algorithms enhance ADHD detection and diagnosis by automatically determining large patterns in data, thereby offering higher accuracy. The performance of the existing techniques is evaluated in terms of evaluation metrics: accuracy, precision, sensitivity, and F1-score to assess their effectiveness. © 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

Vision Aid For Blind People Using YOLOV8 2

Vision Aid For Blind People Using YOLOV8

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： More, Priyanka Sangamkar, Satvik Vishwakarma Institute Of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350367461

This assistive system for the visually impaired integrates real-time YOLOv8 object detection with distance estimation and text-to-speech conversion, empowering users with enriched environmental awareness. Leveraging robust datasets and architectures, it identifies over 90 everyday objects amidst clutter while concurrently approximating object proximity through trigonometric translations of size metrics. Audio cues enunciate recognized items and distances in real time for accessibility. This combination of precise visual recognition, spatial metrics, and assistive feedback holds promise for enhanced mobility, independence, and safety during navigation for visually impaired individuals. © 2024 IEEE.

关键词： Vision aids

来源：评论

学校读者我要写书评

暂无评论

Development and Implementation of Advanced Text Autocorrection via Probabilistic Methods Using Levenshtein Distance and Jaccard Similarity 5

Development and Implementation of Advanced Text Autocorrecti...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Saunshimath, Nirmala J Upadhyaya, Dipankar Raj Yadav, Abiskar Kumar Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331522100

The paper aims at creating an advanced autocorrection system specifically for the Nepali language. This system uses sophisticated natural language processing (NLP) techniques to automatically rectify typographical errors of Nepali texts. The autocorrection system suggests the most likely corrections for misspelt words using the Levenshtein Distance and Jaccard Similarity algorithms. This paper aims to improve the efficiency and user experience across a variety of text-based applications, such as social media, document editing, and messaging, by decreasing the amount of time needed for text editing and increasing text accuracy. The groundwork for future developments in NLP applications for the Nepali language is laid by this effort. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

TCIP: Transformed Colour Intensity Profiles analysis for fault detection in power line insulators

引用

Multimedia Tools and Applications 2025年第8期84卷 4503-4534页

作者： Tomaszewski, Michal Gasz, Rafal Kasana, Singara Singh Osuchowski, Jakub Singh, Simranjit Zator, Slawomir Department of Computer Science Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Prószkowska 76 Opole45-758 Poland Department of Computer Science and Information Technology Central University of Haryana Haryana Mahendergarh123031 India Department of Information Technology Dr B. R. Ambedkar National Institute of Technology Punjab Jalandhar India Department of Safety Engineering and Technical Systems Faculty of Production Engineering and Logistics Opole University of Technology Prószkowska 76 Opole45-758 Poland

In response to the escalating demand for electricity, the aging process and inherent failures in power lines have become unavoidable challenges in their operational integrity. This research addresses the imperative need for a robust method to detect damage in power insulator disc images, introducing a novel feature extraction technique grounded in color intensity profile transformation and ensemble learning. For the purposes of the research, a specific dataset was developed based on publicly available images of power insulators. The collection consists of 9232 images of insulator discs which included 2184 images of damaged discs. The discernible damages include breakages and burnouts. Two distinct analysis variants were employed. In the first variant (V1), two classification groups were selected: disc with damages and disc without damages. In the second variant (V2), three classification groups were selected: discs without damage, broken discs, and burnout discs. The described research was divided into two successive stages. In the first of them (S1), the transformed color intensity profiles for the prepared data set were built and various machine learning models for their classification were trained and evaluated. In the next stage (S2), previously developed, highest efficient machine learning models, were used to make the detection of various damaged types of overhead line insulator discs. For the first stage of research high-performance results and a high value of the F1 score parameters were obtained (F1 score = 0.999 for the first variant (S1V1) and F1 score = 0.992 for the second variant (S1V2). In the second stage of research and the first variant (S2V1), the highest result of the F1 score was 0.932 and for the second variant (S2V2) F1 score was 0.930. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Articulation Node Based Mobile Node Routing Protocol in a Hybrid IoT Network 2

Articulation Node Based Mobile Node Routing Protocol in a Hy...

引用

2nd IEEE International Conference on Recent Advances in Information technology for Sustainable Development, ICRAIS 2024

作者： Leelavathi, R. Vidya, A. Vivekananda Institute of Technology Computer Science and Engineering Department Bengaluru India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354461

In static IoT networks, fixed sensor nodes can create a bottleneck at central hubs, leading to congestion and rapid energy depletion, which may result in network partitioning or failure. Existing routing protocols, such as RPL, are not well-equipped to handle these issues effectively. To overcome these challenges, we propose the Articulation Node-Based Mobile Node Routing Protocol for LLNs (AMRPL), designed to address the limitations of traditional static networks. AMRPL dynamically identifies articulation nodes, which are critical for maintaining connectivity, and instructs mobile nodes to balance the load by moving towards these points. This approach mitigates the congestion and energy depletion issues found in traditional methods. Simulation results, conducted in the Cooja environment, demonstrate that AMRPL outperforms RPL by improving Packet Delivery Ratio (PDR), reducing End-to-End delay, and lowering energy consumption through efficient load distribution by mobile nodes. These improvements underscore the protocol's capability to enhance the overall performance and reliability of hybrid IoT networks. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Growth Testing Effort Function Model Dependent on Machine Learning and Neural Network Algorithm

Software Reliability Growth Testing Effort Function Model De...

引用

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

作者： Farooq, Refath Chishti, Mohammad Ahsan National Institute of Technology Department of Computer Science Engineering Srinagar India

ISBN: (纸本)9798350372229

The quantification of dependency stands as a crucial element in programming quality. The Software Reliability Growth Model (SRGM) is a commonly utilized tool for evaluating reliability across diverse and challenging scenarios. However, the accuracy of traditional time-sensitive SRGMs may be compromised when test execution extends over a prolonged period. In response to this limitation, the SRGM approach is adapted to center around testing practices rather than relying exclusively on the progression of time. Earlier methods proposed restricted testing capabilities, but the notion of unlimited test time introduces an infinite testing scenario, rendering it impractical. To overcome this, the method introduces Neural Heterogeneous Poisson Process (NHPP) models, which operate without being bound by time limitations. Furthermore, the approach incorporates Artificial Neural Networks (ANNs) to model program failures based on available information. The application of an AI model selection method ensures precise representation of both historical and future load fitting location information Artificial Neural Networks (ANNs) showcase an adept capacity for effective generalization from the input provided to a comparable model, proficiently capturing patterns from prior instances of failure data. Through the integration of common-sense information into programming failure indicators, the suggested Testing Effort Function (TEF) and Software Reliability Growth Model (SRGM) proficiently depict extensive failure data. The incorporation of Machine Learning (ML) and Artificial Neural Networks (ANN) notably enhances the precision of traditional boundary estimation when compared to release time, thereby ensuring robust software reliability. © 2024 IEEE.

关键词： ANN Machine Learning NHPP SRGM Testing Effort Function (TEF)

来源：评论

学校读者我要写书评

暂无评论

Exploring Dual-Module Approaches for Sentiment Analysis in Call Recordings 5

Exploring Dual-Module Approaches for Sentiment Analysis in C...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Dhobale, Nikita Dinkar Elle, Krisha Ramesh Deshmukh, Pratiksha Vilas Nirne, Sakshi Sidram Jarali, Prof. Ashwini International Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350379945

The system entails the development of a sentiment analysis system consisting of two integral modules aimed at analysing audio recordings of calls. The first module predicts sentiment-positive, negative, or neutral-by converting speech to text using speech-to-text APIs and subsequently applying machine learning algorithms including Random Forest, Naive Bayes, SVM, and Logistic Regression. The second module employs audio processing techniques utilising Librosa for feature extraction and Convolutional Neural Networks (CNNs) for emotion recognition. The system facilitates comparisons between the results obtained from both modules for call recordings. Users, starting with system administrators, can choose between two options: browsing for uploading pre-recorded audio files or live recording. In both scenarios, the system executes sentiment analysis and emotion detection, presenting results derived from speech-to-text and audio processing analyses. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using Mel-Frequency Cepstral Coefficients & Convolutional Neural Networks 2

Speech Emotion Recognition Using Mel-Frequency Cepstral Coef...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Kadam, Shubhan Jani, Jay Kudtarkar, Aniket Koshy, Reeta Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798350327533

Speech emotion recognition (SER) plays a key role in human-computer interaction, affective computing, mental health diagnosis, and natural language processing (NLP). This paper presents a groundbreaking approach to SER utilizing Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction and a hybrid architecture combining Convolutional Neural Networks (CNN) and transformers. While early methods relied on handcrafted features and traditional machine learning algorithms, recent advancements introduced recurrent neural networks (RNNs). However, limitations in capturing long-term dependencies prompted the exploration of alternative architectures. The proposed method integrates CNNs to capture spectral features and transformers to model long -range dependencies, mitigating existing shortcomings. Evaluation on a publicly available dataset showcases improved accuracy and reduced computational complexity. Comparative analysis against conventional RNN-based models validates the efficacy of the hybrid architecture. The study significantly enhances SER systems, enabling precise emotion analysis in diverse NLP applications. Utilizing CNN for spatial feature representation and the Transformer for sequence encoding, an 80.44% accuracy is achieved on a held-out test set derived from the RAVDESS dataset. This hybrid approach is capable of capturing both local and global speech features, holds promise for real-time emotion prediction in applications like speech therapy, human-robot interaction, and customer service sentiment analysis. © 2024 IEEE.

关键词： Convolutional Neural Networks (CNN) Deep Learning Human-computer Interaction Mel-frequency Cepstral Coefficients (MFCC) Natural Language Processing Speech Emotion Recognition Transformers

来源：评论

学校读者我要写书评

暂无评论

Sorted Range Selection and Range Minima Queries 2nd

Sorted Range Selection and Range Minima Queries

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Akram, Waseem Saxena, Sanjeev Department of Computer Science and Engineering Indian Institute of Technology Kanpur208016 India

ISBN: (纸本)9783031845420

Given an array A[1 : n] of n elements drawn from an ordered set, the sorted range selection problem is to build a data structure that can be used to answer following queries: Given a pair of indices i, j(1≤i≤j≤n), and a positive integer k, report the k smallest elements from the sub-array A[i : j] in sorted order. Brodal et al. (Brodal, G. S., Fagerberg, R., Greve, M., and López-Ortiz, A., Online sorted range reporting. Algorithms and Computation (2009) pp. 173–182) introduced the problem and gave a solution that can answer a query in O(k) time. The preprocessing takes O(nlogn) time and O(n) space. In this paper, we propose the only other possible optimal trade-off for the problem. After preprocessing using O(n) time and space, we can answer a range selection query in O(klogk) time. Moreover, the proposed algorithm reports the output elements individually in non-decreasing order. Our solution is simple and practical. We also study the problem in a dynamic setting. We also describe an extremely simple method for the range minima queries (most of whose parts are known), which takes almost (but not exactly) linear time. We believe that this method may be, in practice, faster and easier to implement in most cases. Moreover, we also give a simple dynamic solution to the range minimum problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization

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：