检索结果-内蒙古大学图书馆

1st IEEE International Conference on Communications and computer science, InCCCs 2024

作者： Ravi, Kusum Meda Kiran, M.K. Umadevi, v. Department of Computer Science and Engineering B.M.S. College of Engineering Bangalore India

ISBN: (纸本)9798350358858

In this research, different techniques were explored to improve the accuracy of the classification of acne vulgaris into seven classes: whitehead, blackhead, fungal acne, papules, pustules, nodules, and acne fulminans. Three pre-trained deep learning models, viz., Inception-ResNet, MobileNet and EfficientNet were trained on the skin90 dataset. several experiments were conducted on the dataset using these models by utilising certain loss functions and exploring hyperparameters yielding higher values of metrics. Additional techniques employed include traditional data augmentation and augmentation using generative models like variational Auto-Encoder(vAE). The highest accuracy obtained on the original dataset was 89% by the EfficientNet model with a learning rate of 0.001. The best performance on the vAE-augmented dataset was observed on the EfficientNet model with a learning rate of 0.1 achieving an accuracy of 84%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Dysgraphia symptoms in Primary and Middle school Children 6

Automated Detection of Dysgraphia Symptoms in Primary and Mi...

引用

6th IEEE International Conference on Emerging smart Computing and Informatics, EsCI 2024

作者： Tushar, b.T. Goel, Umang Ms, varun Urs Kulkarni, vinay sooda, Kavitha B.M.S. College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350306613

Dysgraphia, a learning disability impacts hand-writing fluency and legibility, which significantly hinder's a child's academic progress and self-esteem. The proposed work utilizes pattern recognition techniques, employing preprocessing techniques like Canny Edge Detection, Watershed segmentation and various image enhancement techniques to analyze written characters and extract relevant features using character-wise bounding boxes. This detailed analysis allows the system to capture subtle variations in letter formation and spacing that are often indicative of dysgraphia. Furthermore, A MobileNet architecture has been proposed to assess the system's performance and classify dysgraphia risk levels into three categories: below Average(bA), Average(Av) and Above Average(AA). This categorization system provides valuable insights for educators and parents, enabling early intervention and tailored support for students struggling with dysgraphia. The model was trained using a data set of 940 images of handwriting samples from students studying in grades one to seven. students were asked to write 20 words through dictation and another 20 words copied from the board. The proposed system aims to demonstrate immediate results, highlighting its potential for early detection and intervention. © 2024 IEEE.

关键词： Deep Learning Dysgraphia Kannada Words Learning Disability MobileNet

来源：评论

学校读者我要写书评

暂无评论

Convolutional-Neural Network bases speaker Emotion Detection based on Human-computer Interaction 1

Convolutional-Neural Network Bases Speaker Emotion Detection...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Nithya, b. saranya, R. Joseph, Mary Josphineleela, R. Thirunagalingam, Arunkumar Kodali, Arun Kumar B.S. Abdur Rahman Crescent Institute of Science and Technology Dept of Computer Science and Engineering Chennai India V.S.B. Engineering College Department of Computer Science and Engineering Karur India St. Joseph's Institute of Technology OMR Department of IT Chennai119 India Panimalar Engineering College Department of Computer Science and Engineering India Mckesson Corporation United States Mphasis Corporation

ISBN: (纸本)9798331518578

The present investigation proposes a Convolutional Neural Network (CNN)-based method for human-computer interaction (HCI) speaker emotion identification. Optimising the user experience through clearer and sympathetic connections is made possible by emotional knowledge. Conventional techniques for detecting emotions depend on manually created characteristics, which are frequently laborious and less resilient to speech variability. by using CNNs' automatic feature extraction capabilities, the suggested system analyses speech signal spectrograms and extracts crucial emotional indicators. The method obtains notable gains in emotion classification accuracy by retraining the system on a varied collection of emotional speech samples. Important emotional states like happiness, anger, sadness, and neutrality are all successfully distinguished using the CNN model. This study demonstrates how deep learning can help develop emotion-sensitive HCI systems and promote more organic and contextually aware human-machine interactions. Applications in customer service, healthcare, and virtual assistants can benefit from the technique's adaptability and versatility. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithm for Handwritten Document Enhancement

引用

computers, Materials & Continua 2024年第3期78卷 3763-3786页

作者： shu-Chuan Chu Xiaomeng Yang Li Zhang václav snášel Jeng-shyang Pan College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China Faculty of Electrical Engineering and Computer Science VŠB-TU OstravaOstrava70080Czech Republic Department of Information Management Chaoyang University of TechnologyTaichung41349Taiwan

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. by amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.

关键词： Metaheuristic algorithm gannet optimization algorithm hybrid algorithm handwritten document enhancement

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis on Prediction Model of Hate speech Detection based on social Media Data Using Artificial Intelligence 4

Comparative Analysis on Prediction Model of Hate Speech Dete...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Kaware, Pravin D. Raut, Anjali b. Department of Computer Science & Engineering H.V.P.M's College of Engineering & Technology Amravati India

ISBN: (纸本)9798331530402

The exponential expansion of social media networking platforms has magnified the dissemination of hate speech, thereby requiring strong recognition systems to minimize its influence. The present work offers a comparative examination of many prediction models for the recognition of hate speech using social media data, employing Artificial Intelligence (AI) methodologies. The paper intends to assess the efficiency of several Machine Learning (ML) and Deep Learning (DL) algorithms for accurately detecting hate speech. The various strategies are evaluated using known datasets and measures including accuracy, recall, precision, and Fl-score. In addition, useful insights on the most effective methods for identifying hate speech are presented. The findings suggest that deep learning approaches are exceptionally effective at catching the contextual nuances of hate speech. Al-based hate speech detection apps improve accuracy and efficiency. such systems are critical for creating a safer and more inclusive online. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble Approaches for Offensive Language Detection in Kannada 3

Ensemble Approaches for Offensive Language Detection in Kann...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Monish, M.N. sooda, Kavitha B.M.S. College of Engineering Dept. of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350381931

In the realm of natural language processing, sentiment analysis remains a focal point due to its pivotal role in discerning and analyzing public sentiments. While past research has been dedicated to enhancing the performance of sentiment analysis models, this study delves into the potential benefits of ensemble techniques, with a special emphasis on Genetic Algorithm (GA) optimization, The main thrust of this research was to investigate whether merging multiple models and subsequently optimizing their weights via GA could elevate performance. Evaluations were thoughtfully conducted, focusing on the weighted precision, recall, and F1-scores of individual models. Additionally, the study compared the ensemble methods, both with and without GA optimization, The ensemble method, even without the GA optimization, secured an impressive F1-score of 0.73. Upon integrating the GA optimization, there was a gentle improvement in the ensemble's performance, achieving an F1-score of 0.75, In summing up, this study manifests a palpable enhancement in sentiment analysis outcomes when shifting from standalone models to a GA-optimized ensemble mechanism. The results, epitomized by an F1-score peaking at 0.75, underline the intrinsic merits of harnessing GA for weight optimization in ensemble constructs. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

'vulnerabilities in smart Contracts: A Detailed survey of Detection and Mitigation Methodologies'

'Vulnerabilities in Smart Contracts: A Detailed Survey of De...

引用

2024 IEEE International Conference on Emerging Technologies in computer science for Interdisciplinary Applications, ICETCs 2024

作者： Kumar, Nayantara K Honnungar, Niranjan v sharwari Prakash, M. Lohith, J.J. B.M.S. College of Engineering Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350372502

In the ever-changing world of blockchain technology, the emergence of smart contracts has completely transformed the way agreements are executed, offering the potential for automation and trust in decentralized systems. Despite their built-in security features, smart contracts still face persistent vulnerabilities, resulting in significant financial losses. While existing studies often approach smart contract security from specific angles, such as development cycles or vulnerability detection tools, this paper adopts a comprehensive, multidimensional perspective. It delves into the intricacies of smart contract security by examining vulnerability detection mechanisms and defense strategies. The exploration begins by conducting a detailed analysis of the current security challenges and issues surrounding smart contracts. It then delves into established frameworks for classifying vulnerabilities and common security flaws. The paper examines existing methods for detecting, and repairing contract vulnerabilities, evaluating their effectiveness. Additionally, it provides a comprehensive overview of the existing body of knowledge in smart contract security-related research. Through this systematic examination, the paper aims to serve as a valuable reference and provide a comprehensive understanding of the multifaceted landscape of smart contract security. © 2024 IEEE.

关键词： smart contract

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time series Forecasting for Cloud Machine Utilization 3

Multivariate Time series Forecasting for Cloud Machine Utili...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Naik, Archana sooda, Kavitha Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Computer Science and Engineering B.M.S. College of Engineering Bangalore India

ISBN: (纸本)9798331527549

The cloud machine utilization prediction using a multivariate time series model is explored in this study. The cloud machine usage data set samples are selected with varied patterns. The long sequence forecasting model Informer is investigated for the forecasting. The model results are benchmarked against LsTM, GRU, Prophet, and XGboost across the diverse datasets. The performance is evaluated using RMsE. Experimental results show that the Prophet model performs best overall due to its ability to capture both seasonal and irregular patterns accurately. The RMsE value for Informer is 0.13, Prophet is 0.097, XGboost is 0.096, LsTM is 0.1725, and GRU is 0.1547. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

AI Guarded Code Editor: verifying Authentic Human Input

AI Guarded Code Editor: Verifying Authentic Human Input

引用

2025 International Conference on Computing for sustainability and Intelligent Future, COMP-sIF 2025

作者： Raghunandan, Aditi Aishwarya, A.G. Khan, Mohammad Adnan Nishant, s. Panimozhi, K. B.M.S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331538538

AI Tools such as ChatGPT, GPT-4 and GitHub Copilot change the very nature of how developers build software by greatly helping in the quick generation of code. While this proves to be efficient for professionals, it poses challenges in the competitive programming space. Generative AI is greatly misused by candidates in coding tests and online interviews. We will design a guarded code editor that detects the probability of usage of GenAI in code submissions with specialized AI detection models that use unique metrics, such as long AI-generated keywords, unusual number of utility functions, and very verbose comments that have been shown to be associated with usual AI-generated content. We will focus on stylistic and structural markers such as redundant comments, too general or too redundant variable names, and predictable formatting to realize a lightweight and scalable detection framework that fits into a user-friendly code editor. Our system also includes mechanisms for immediate feedback that inform the users on the reasons for differences in AI-generated and human-written code, thereby promoting better integrity of code in their own practices. This solution addresses a few critical concerns identified in some recent work that detection tools have limitations to the availability of responding to a domain-specific method responsive to how it would likely be combated using misapplication of the AI system. In other words, with a code editor that does not accept the direct submission of AI-generated code, the proposed solution will most definitely prove effective in both bringing forward practicality and ethical means while ensuring originality and improvement of quality in academic and competitive programming. © 2025 IEEE.

关键词： File editors

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Deep Learning Methods for COvID-19 Detection and Classification

Comprehensive Analysis of Deep Learning Methods for COVID-19...

引用

2023 Annual International Conference on Emerging Research Areas: International Conference on Intelligent systems, AICERA/ICIs 2023

作者： Prabha, bindhu Divya, s.v. venkadesh, P. Noorul Islam Centre for Higher Education Dept. of Computer Applications Kanyakumari Tamil Nadu Kumarakovil India V.S.B College of Engineering Dept.of Cse Technical Campus Tamil Nadu Coimbatore India V.S.B College of Engineering Dept. of Ai & Ds Technical Campus Tamil Nadu Coimbatore India

ISBN: (纸本)9798350303452

The progress of precise recognition techniques and the evaluation of genetic connections are required because of the worldwide spread of COvID-19. As conventional techniques for COvID-19 detection are time-consuming and require accurate variables in order to minimize or cut short errors that could possibly occur, the COvID-19 epidemic's necessity for early diagnosis and surveillance led to the deployment of Deep Learning (DL) technology for efficient evaluation. Deep learning is a branch of artificial intelligence (AI) and Machine learning (ML), and due to its remarkable ability to assimilate new information, DL technology has quickly risen to prominence. Many DL architectures, like RNN, CNN, and long-term memory, can be utilized for forecasting, perdition, and classification of COvID-19. The intention of this paper is to conduct a comprehensive analysis of various deep learning methods, for detecting and classifying the COvID-19 virus using diverse data sources, such as chest X-rays, CT scans, and genomic sequences, to highlight their exceptional accuracy in identification. We also explore DL's involvement in analyzing the virus's genetic code, providing insight into how it evolved. It aims to deliver a summary of earlier research and its COvID-19 applications. © 2023 IEEE.

关键词： COvID-19

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：