检索结果-内蒙古大学图书馆

Device Intelligence, Computing and Communication Technologies, (DICCT), International Conference on

作者： Rahema Naaz Shafeeq Ahmad Department of Computer Science & Engineering Azad Institute of Engineering and Technology Lucknow India

ISBN: (数字)9798331543358

ISBN: (纸本)9798331543365

The Electrocardiogram (ECG) is very important signal generated from human body that provides information for assessment of variation in cardiac activities. These ECG data are generally distorted due to high power line or magnetic field associated noise that results as a problem in error during diagnosis of heart related disorders on analysis through biomedical analysis software. This work contributes for very significant stage that is introduced to reduce the anomaly in the ECG signals to perform accurate automated diagnosis. This work follows a methodology of an automated machine learning algorithm is developed for accurate estimation of ECG data segment cycle using clustering approach integrated with Discrete Wavelet Transform (DWT). The key findings of this works cover the development and analysis of an approach to overcome the errors in detection of T-wave using Implantable Cardioverter Defibrillator (ICD). The work reports the solution of issues using fuzzy C-means clustering behind prediction of fatal Ventricular Arrhythmias (VA) for performing standard classifications.

关键词： Machine learning algorithms Accuracy Databases Arrhythmia Clustering algorithms Transforms Electrocardiography Discrete wavelet transforms Classification algorithms Standards

来源：评论

学校读者我要写书评

暂无评论

A Robust and Secure Framework for an AI-Assisted Academic Writing Platform 23rd

A Robust and Secure Framework for an AI-Assisted Academic...

引用

23rd International Conference on Web-Based Learning, ICWL 2024 was held in conjunction with the 9th International Symposium on Emerging Technologies for Education, SETE 2024

作者： Qureshi, Umair Mujtaba Tong, Esther Ka-Man Chen, Zili Val Deng, Chunrao Nandakumar, Gaya Division of Languages and Communication School of Professional Education and Executive Development The Hong Kong Polytechnic University China Computer Science and Engineering Department The Chinese University of Hong Kong China

ISBN: (纸本)9789819644063

The Artificial Intelligence (AI)-assisted academic writing platform is a digital tool that leverages the use of artificial intelligence (AI) technology to help the platform users, i.e., students, teachers, and professionals in various aspects of academic writing. This work reviews existing AI-assisted academic writing platforms, discusses core system design features that are important considerations in designing such frameworks, and provides a critical discussion of the strengths and weaknesses of existing platforms. This work also proposes a robust and secure framework for an AI-assisted academic writing platform based on Azure cloud services. The platform aims to provide comprehensive supervisory support, free from time and location constraints, to help its users e.g., teachers in terms of helping with their workload in assessing academic reports, and to students by providing support to enhance their academic writing. The proposed framework is based on Microsoft (MS) Azure cloud services because it provides reliability, scalability, and a wide range of services such as Web Server and Content Management System (CMS), Azure Database for MySQL and OpenAI Azure Service i.e., ChatGPT in a secure environment. In addition, the proposed framework integrates with a Private Cloud to further enhance the platform’s functionality and secure environment. The main objective of the platform is to deliver an interactive system that provides reliable feedback on English writing in a range of academic fields. The proposed platform is then evaluated by piloting on the PolyU SPEED academic course led by 16 teachers and tested on academic reports of 273 students. The survey-based evaluation results show that the proposed AI-assisted academic writing platform is easy to use and showcases the ability to identify issues related to specific genre-based content and coherence, provide assistance in grammar and vocabulary, and highlight issues in reference style with reasonably high accuracy.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Wildlife Detection and Management System for Agricultural Protection

AI-Driven Wildlife Detection and Management System for Agric...

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： K. Preethi A. Vinitha V. Vinothiga V. Mahalakshmi V. Kumararaja Department of Computer Science and Engineering K Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

Environmental harm, safety hazards, and large financial losses are all consequences of human-wildlife conflict, which continues to be a major obstacle to agricultural sustainability. Conventional deterrence techniques, like sound deterrents, personal intervention, and electric fence, have been shown to be ineffective, expensive, and frequently detrimental to wildlife. The AI-driven wildlife identification and deterrence system presented in this study addresses these problems by utilising computer vision, deep learning, IoT-based monitoring, and ultrasound deterrence techniques. Real-time animal detection from live video feeds is achieved by the suggested method using YOLO v11 and OpenCV, precisely identifying species that are a hazard to farmlands. When an animal is detected, an automated ultrasonic deterrence system is triggered, which releases high-frequency sound waves that successfully and safely ward off the animal .In order to help build long-term conservation and conflict mitigation methods, movement monitoring is also integrated to analyse animal migration patterns from reserve forests to places where humans live .Additionally, an Internet of Things-based real-time alert mechanism is included by the system, providing farmers and authorities with immediate notifications by SMS, email, and mobile applications so they may take prompt action. The complete system is made to be economical, environmentally friendly, and scalable, guaranteeing its widespread use in agricultural areas where wildlife intrusions are a problem.

关键词： YOLO Accuracy Ultrasonic imaging Animals Wildlife Real-time systems Hazards Sustainable development Protection Monitoring

来源：评论

学校读者我要写书评

暂无评论

Distinguishing Between Formal and Colloquial: A Multilingual BERT Approach to Bengali Language Classification

Distinguishing Between Formal and Colloquial: A Multilingual...

引用

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

作者： Sagor Aich Koshik Debanath Azmain Yakin Srizon Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

The Bengali language, rich in history and cultural significance, poses unique challenges in Natural Language Processing (NLP) due to its dual-register structure: Sadhu (formal) and Cholit (colloquial). These registers differ significantly in syntax, vocabulary, and usage, complicating tasks such as text classification, translation, and sentiment analysis. Language models not specifically trained to recognize these distinctions often misinterpret these variations, limiting the accuracy of Bengali NLP tools. To address this, a dataset from Mendeley was used to fine-tune the multilingual BERT (mBERT) model for distinguishing between Sadhu and Cholit registers. The fine-tuned model achieved an accuracy of 94.08%, effectively capturing the subtle lexical and syntactic differences between the two forms. This work advances Bengali NLP, enabling more precise applications in digital communication, automated translation, and linguistic analysis, while contributing to broader advancements in low-resource language processing.

关键词： Vocabulary Translation Accuracy Computational modeling Syntactics Transformers Digital communication Natural language processing Registers Multilingual

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effectiveness of Machine Learning in Cyber Attack Mitigation: A Review

Assessing the Effectiveness of Machine Learning in Cyber Att...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Gayathry V R. Sathya Bama Krishna Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Cyberattacks are currently one of the most active areas of research and a serious criminal offence. In many industries, the number of people using the internet is increasing too quickly. The amount of time spent online has increased dramatically, and people and businesses are now doing many of their everyday activities online rather than in person. Despite the quick rise in the quantity of websites and applications, they remain vulnerable to attacks. Due to modern attacks and prevention techniques, traditional security features like firewalls, interruption location frameworks, antivirus software, access control records, and so on are currently ineffective in identifying these sophisticated attacks. Therefore, it is imperative to discover novel and more workable ways to stop cyberattacks. This paper's main goals are to inform academics and engineers about current threats and stimulate research on cybersecurity countermeasures for digital attacks. This study outlined the principal themes, seminal works, and major author cohorts in the field of digital attack research. In the future, the results should aid in broadening the focus of research to include a variety of subfields in the study of digital threats.

关键词： Surveys Protocols Statistical analysis Reviews Prevention and mitigation Neural networks Machine learning Oral communication Cyberattack Network systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Tomato Leaf Disease Detection and Diagnosis Using Deep Learning-Based computer Vision Techniques

Real-Time Tomato Leaf Disease Detection and Diagnosis Using ...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： Kanakaprabha, S. Arulprakash, P. Kumar, G. Ganesh Udhayakumar, T. Janani, R. Department of Computer Science and Engineering Rathinam Technical Campus Anna University Coimbatore India Department of Information Technology Rathinam Technical Campus Anna University Coimbatore India Department of Information Technology Sri Krishna College of Engineering and Technology Coimbatore India

ISBN: (纸本)9783031513374

Tomato plants are vulnerable to numerous diseases, which can have significant impact their growth and yield. Early discovery and accurate analysis of these diseases are critical for implementing timely and operative control measures. In modern years, deep learning-based computer visualization methods have emerged as powerful tools for real-time tomato leaf disease recognition and diagnosis. The system utilizes a convolutional neural network (CNN) model to repeatedly categorize tomato leaves as healthy or diseased based on images taken in the field. The model is skilled on a dataset of labeled imageries of tomato leaves, with each image containing a specific disease or being healthy. The system is implemented on a portable device for real-time use in the field, allowing for rapid and accurate diagnosis of tomato leaf diseases. The investigational results show that the suggested system achieved high accuracy in disease classification, with an average precision of 98.11%. Furthermore, the system also successfully detects multiple diseases present in the same leaf, which is a significant improvement over traditional methods that often fail to detect multiple diseases. The proposed real-time tomato leaf disease detection and diagnosis system using deep learning-based computer vision procedures can effectively detect and diagnose multiple diseases in tomato leaves in real time. This technology can be used to improve the effectiveness and correctness of disease discovery, ultimately reducing the use of harmful pesticides and increasing crop yields. This chapter highlights the potential impact of real-time tomato leaf disease detection and diagnosis using deep learning-based computer vision performances. Early detection and diagnosis can facilitate timely interventions, leading to improved disease management, increased crop yield, and reduced reliance on chemical treatments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Unveiling Purchase Patterns: A Comparative Analysis of Apriori, FP-Growth, and Eclat Algorithms in Market Basket Analysis

Unveiling Purchase Patterns: A Comparative Analysis of Aprio...

引用

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

作者： Sohel Rana Md. Nazrul Islam Mondal Md. Rabiul Islam Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Market Basket Analysis (MBA) is a pivotal data mining technique aimed to discover the invaluable insights into consumer behavior through the exploration of transactional data in the retail market. This paper presents a comparative performance analysis of three prominent MBA algorithms: Apriori, FP-growth, and Eclat these are widely used for extracting frequent itemsets and generating association rules from retail transactional database. The study begins with a comprehensive overview of each algorithm with their fundamental principles and methodologies. It then proceeds to evaluate their performance across various metrics such as execution time, memory usage, and scalability using real-world transactional datasets. The dataset of this research has been generated from the transaction slips of a retail supermarket in Bangladesh. The experiments are conducted using different sizes of transactional data to assess how each algorithm handles varying data volumes. Special attention is given to the strategies employed by each algorithm to optimize the mining process and reduce the computational overhead. Our findings indicate that, the FP-growth based mining approach outperforms the Apriori and Eclat algorithms in terms of runtime efficiency and memory utilization, especially while the size of the dataset increases. For our transactional dataset of 100000 transactions alongside 2382 unique items, the Fp-growth algorithm beat the Apripri and Eclat in execution time by 4 and 1.87 times, respectively. However, the choice of algorithm can depend on specific dataset characteristics and the desired balance between mining speed and resource consumption.

关键词： Measurement Hands Runtime Itemsets Scalability Heuristic algorithms Memory management Association rule learning Performance analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Technique for Prediction of Carbon Stocks and Uncertainty Estimates in Tropical Forests

引用

SN computer science 2025年第4期6卷 1-21页

作者： Akinbiola, Sehinde Akinsola, Jide Ebenezer Taiwo Ajagbe, Sunday Adeola Salami, Ayobami Olubaju, Ayomide Awotoye, Olusegun Awoleye, Olusesan Micheal Department of Surveying and Geoinformatics First Technical University Ibadan Ibadan 200255 Nigeria Department of Computer Science First Technical University Ibadan Ibadan 200255 Nigeria Department of Computer Engineering First Technical University Ibadan Ibadan 200255 Nigeria Institute of Ecology and Environmental Studies Obafemi Awolowo University Osun State Ile Ife Nigeria African Institute for Science Policy and Innovation Obafemi Awolowo University Ile Ife Nigeria

The lack of a robust national forest inventory in tropical regions remains a major challenge to the assessment of forest productivity and the evaluation of the climate regulation potential of tropical forests. Therefore, many sampling procedures and models exist for estimating carbon stocks;albeit with varying levels of limitations because of their associated errors. Given the development in computing and modeling in environmental science, this study focuses on providing an Artificial Intelligence (AI)-based approach for predicting carbon stocks and uncertainty estimates in tropical forests. In this study, an artificial intelligence (AI) technique was used to model carbon stocks using machine learning (ML) paradigms. Four ML algorithms, namely, Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN), were considered based on biophysical variables;including tree height and diameter. The model was implemented in the Waikato Environment for Knowledge Analysis and Jupyter (6.1.4) using the Anaconda distribution of Python (3.00). Uncertainty estimates were evaluated using cost performance measures, including Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), to validate the reliability of the predicted carbon stock values. In addition, a comparative analysis was performed using 8 different performance measures for classification, while error estimation was performed for regression analysis. One of the models produced included the random forest machine learning algorithm with an accuracy of 98.3%, root mean square error of 0.02, and model building time of 0.13 s, which was chosen as the best algorithm for modeling carbon stocks. This study concluded that there is variation in carbon distribution among species which is not proportional to the volume of carbon stocks in the genus. The study recommends for further studies, the application of a multi-criteria decision-making approach in the selection of an opti

关键词： Artificial intelligence Carbon stock Global climate regulation Informatics Machine learning Tropical-forest productivity

来源：评论

学校读者我要写书评

暂无评论

Exploring Underwater Acoustic Propagation Based on Deep Sound Channel 5th

Exploring Underwater Acoustic Propagation Based on Deep Soun...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Rao, Ch Venkateswara Gottapu, Srinivasa Kiran Pareek, Prakash Pranav, V. Singh, Lokendra Kanuri, Srinivas Department of ECE Vishnu Institute of Technology Bhimavaram534202 India Engineering and Computer Science Department Benedict College ColumbiaSC United States Department of CSE Sir C R Reddy College of Engineering Eluru India Dehradun248002 India

ISBN: (纸本)9783031770777

In the realm of technical advancement, underwater acoustic communication emerges as a compelling and challenging field for engineers and researchers alike. Unlike terrestrial environments, the underwater domain provides a dynamic and intricate acoustic medium, significantly impacting the propagation of signals. The sound speed in underwater (function of temperature, salinity, and depth) majorly affects the signal propagation among the nodes and leads to high transmission losses. In addition, the sound propagation has been influenced in deep sound channel (existed around 800 to 1300 m), where the sound waves are directed towards the long-range propagation with low velocity. However, the sound propagation in deep sound channel is a complex phenomenon and is influenced by skip distance (SD), axis depth (daxis), mixed layer depth (MLD), and source node depth (SND). Therefore, it is essential to conduct a comprehensive analysis and gain a thorough understanding of the acoustic propagation characteristics deep sound channel for effectively deploy a network tailored for a specific application (habitat monitoring). As a result, the analysis and evaluation of the differences in sound propagation at various salinities, temperatures, and depths in the deep sound channel is the main goal of this work. Additionally, an evaluation of the transmission losses in the deep sound channel has been conducted. The simulation's findings show that a 12% decrease in transmission losses occurs when sound speed is increased from 1430 to 1570 m/s. Additionally, at moderate SND (500 m), transmission losses are higher compared to surface nodes (SND = 100 m) and bottom nodes (SND = 1000 m). © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

DFCON: ATTENTION-DRIVEN SUPERVISED CONTRASTIVE LEARNING FOR ROBUST DEEPFAKE DETECTION

arXiv

引用

arXiv 2025年

作者： Shanto, Sadik Hossain Dihan, Mahir Labib Ghosh, Souvik Anonto, Riad Ahmed Chowdhury, Hafijul Hoque Muhtasim, Abir Ahsan, Rakib Hassan, Tanvir Sojib, Roqunuzzaman Hakim, Sheikh Azizul Rahman, M. Saifur Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

This report presents our approach for the IEEE SP Cup 2025: Deepfake Face Detection in the Wild (DFWild-Cup), focusing on detecting deepfakes across diverse datasets. Our methodology employs advanced backbone models, including MaxViT, CoAtNet, and EVA-02, fine-tuned using supervised contrastive loss to enhance feature separation. These models were specifically chosen for their complementary strengths. Integration of convolution layers and strided attention in MaxViT is well-suited for detecting local features. In contrast, hybrid use of convolution and attention mechanisms in CoAtNet effectively captures multi-scale features. Robust pretraining with masked image modeling of EVA-02 excels at capturing global features. After training, we freeze the parameters of these models and train the classification heads. Finally, a majority voting ensemble is employed to combine the predictions from these models, improving robustness and generalization to unseen scenarios. The proposed system addresses the challenges of detecting deepfakes in real-world conditions and achieves a commendable accuracy of 95.83% on the validation dataset. © 2025, CC BY.

关键词： Contrastive 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：