检索结果-内蒙古大学图书馆

25th International Conference on computer and Information Technology, ICCIT 2022

作者： Jannat, Nusratul Das, Avishek Sharif, Omar Hoque, Mohammed Moshiul Chittagong University of Engineering & Technology Dept. of Computer Science and Engineering Chattagram Bangladesh

ISBN: (纸本)9798350346022

Advances in social media platforms led to the widespread adoption of memes, making them a powerful communication tool on the internet. Memes' visual aspect gives them a remarkable ability to influence users' opinions. However, individuals misemploy this popularity to foment animosity. The spread of these hostile memes can have a detrimental effect on people, causing depression and suicidal thoughts. Therefore, stopping inappropriate memes from spreading on the internet is crucial. However, identifying memes is di cult due to their multimodal nature. This paper proposes a deep-learning-based framework to classify sentiment (into 'positive' or 'negative') from multimodal memes in Bengali. Due to the unavailability of standard corpora, a Bengali meme corpus consisting of 1671 memes is developed to perform the memes' sentiment classification task. Five popular deep learning models (CNN, BiLSTM) and pre-trained models (VGG16, VGG19, InceptionV3) are investigated for textual and visual features. The framework is developed by combining visual and textual models. The comparative analysis confirms that the proposed model (BiLSTM + VGG19) achieved the highest f1-score (0.68) compared to other multimodal methods. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Accidental Prone Area Detection in Dhaka Metropolitan City Using Machine Learning Models

Accidental Prone Area Detection in Dhaka Metropolitan City U...

引用

Recent Trends in computer science and Technology (ICRTCST), International Conference on

作者： Foyjunnesa Jerin Amatul Bushra Akhi Mobin Mohtadi Tasin Naznin Sultana Md. Atef Akbar Shayla Sharmin Dept. of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Dept. of Computer Science and Engineering North South University Dhaka Bangladesh

ISBN: (数字)9798350351378

ISBN: (纸本)9798350351385

Dhaka, known for its status as one of the world's most densely populated areas, grapples with numerous challenges associated with urbanization and safety. This study identifies accident-prone zones within the Dhaka Metropolitan City by analyzing data collected from 2019 to 2023. Ten specific locations were investigated using various machine learning models: Decision Tree Classifier, Gradient Boosting Classifier, Random Forest, Gaussian Naive Bayes, and Logistic Regression. Evaluation metrics, including precision, recall, accuracy, F1-score, and standard deviation, were utilized, with the Random Forest classifier exhibiting the highest accuracy at 94.39%. The analysis encompassed both monthly and annual accident data, revealing trends and probabilities associated with different incident types. The study's implications suggest potential advancements in accident investigation by incorporating advanced machine learning techniques, integrating diverse datasets, and expanding the geographical coverage to encompass the entire metropolitan area. This comprehensive approach aims to bolster accident prevention measures and enhance urban safety. Overall, this research contributes to a deeper understanding of accident-prone regions and proposes strategies for targeted interventions to improve safety within metropolitan areas.

关键词： Accuracy Urban areas Urban planning Predictive models Market research Road safety Safety

来源：评论

学校读者我要写书评

暂无评论

Cascading Effects: Analyzing Project Failure Impact in the Maven Central Ecosystem

Cascading Effects: Analyzing Project Failure Impact in the M...

引用

International Mining Software Repositories, MSR

作者： Mina Shehata Saidmakhmud Makhkamjonoov Mahad Syed Esteban Parra Dept. of Math Computer Science and Data Science Belmont University Nashville TN USA

ISBN: (数字)9798331501839

ISBN: (纸本)9798331501846

This study examines failure propagation within the Maven Central ecosystem, a critical software dependency repository, through a comprehensive analysis of dependency networks using the Goblin framework. Our dual-sampling methodology, investigating both top dependencies and random libraries, revealed two distinct failure propagation patterns that pose significant risks to ecosystem stability. Core infrastructure failures, particularly evident in cases like the AWS SDK family, can create immediate and widespread disruption. These libraries have many direct dependents - averaging 20,402 projects that would break immediately if the library fails. Furthermore, these core libraries themselves have extensive dependencies, with the AWS SDK family depending on 377 other libraries itself. The impact of failures spreads deeply through the ecosystem, with dependency chains reaching an average of 90.80 levels. Our analysis of peripheral projects reveals their significant cascading effects, with higher average dependency dept.s of 54.25 levels and chain lengths extending to 116.74 levels, as exemplified by cases like ***:camel-swagger-java, which demonstrated a maximum chain length of 647 levels. Our findings highlight specific vulnerabilities in dependency network structures, showing that ecosystem resilience requires both protecting core infrastructure and managing dependency complexity.

关键词： Software maintenance Ecosystems Power system protection Focusing Libraries Stability analysis Complexity theory Protection Power system faults Resilience

来源：评论

学校读者我要写书评

暂无评论

Advancements in Animal Tracking: Assessing Deep Learning Algorithms

Advancements in Animal Tracking: Assessing Deep Learning Alg...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Tahmina Akter Avishek Majumder Tanjim Mahmud Israt Binteh Habib Mohammad Shahadat Hossain Karl Andersson Dept. of Computer Science and Engineering Port City International University Chittagong Bangladesh Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Dept. of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Dept. of Computer Science and Engineering University of Chittagong Chittagong Bangladesh Cybersecurity Laboratory Luleå University of Technology Luleå Sweden

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In the rapidly advancing field of computer vision, object detection has become crucial for various applications, including animal tracking, face detection, and surveillance systems. This study investigates the efficacy of contemporary object detection methodologies by evaluating the performance of the You Only Look Once (YOLO) models and TensorFlow Model Zoo architectures for animal tracking. YOLO models, known for their ability to process entire images in real-time and predict bounding boxes and class probabilities simultaneously, offer significant advantages over traditional methods such as Convolutional Neural Networks (CNNs) and Fast R-CNNs. This paper compares the performance of YOLOv5 and YOLOv7, alongside TensorFlow-based models like Faster R-CNN ResNetv152 and SSD ResNet101, using a dataset of animal images. Our findings reveal that YOLOv5 outperforms other models with a mean average precision (mAP) of 9 7.5%, demonstrating superior accuracy and efficiency in object detection tasks. YOLOv7 also shows strong performance with an mAP of 96.7%, while TensorFlow Model Zoo’s Faster R-CNN and SSD models lag behind with mAPs of 81.9% and 81.6%, respectively. The results highlight the significant advancements in deep learning and object detection algorithms, particularly the advantages of YOLO’s architecture in handling complex detection tasks in real-world scenarios.

关键词： YOLO Deep learning Animals Computational modeling Surveillance computer architecture Predictive models Real-time systems Face detection Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Dive into Electra: Transfer Learning for Fine-Grained Text Classification on SST-2 6

A Deep Dive into Electra: Transfer Learning for Fine-Grained...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Fikriansyah, Muhammad Nuha, Hilal Santriaji, Muhammad School of Computing Telkom University Bandung Indonesia University of Central Florida Dept. of Computer Science OrlandoFL United States

ISBN: (纸本)9798350358346

In the dynamic landscape of Natural Language Processing (NLP), a transformative revolution is underway, marked by the rapid evolution and proliferation of pre-Trained language models that have irrevocably reshaped the boundaries of text understanding and classification. Electra, a language model introduced by Clark et al. in 2020, stands out as an innovation with a distinctive pre-Training approach, particularly in fine-grained text classification tasks. This research aims to rigorously evaluate Electra's performance in fine-grained text classification, primarily focusing on sentiment analysis tasks within the SST-2 dataset. Additionally, the study seeks to provide invaluable guidance to researchers and practitioners by elucidating the most effective fine-Tuning strategies and configuration settings. The results highlight the significance of gradual fine-Tuning, with increased layer unfreezing positively impacting model accuracy. This underscores Electra's vast potential for NLP tasks and the importance of thoughtful fine-Tuning processes. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

PhishGuard: A Multi-Layered Ensemble Model for Optimal Phishing Website Detection

arXiv

引用

arXiv 2024年

作者： Ovi, Md Sultanul Islam Rahman, Md. Hasibur Hossain, Mohammad Arif Dept. of Computer Science George Mason University FairfaxVA United States Dept. of Computer Science and Engineering Green University of Bangladesh Bangladesh

Phishing attacks are a growing cybersecurity threat, leveraging deceptive techniques to steal sensitive information through malicious websites. To combat these attacks, this paper introduces PhishGuard, an optimal custom ensemble model designed to improve phishing site detection. The model combines multiple machine learning classifiers, including Random Forest, Gradient Boosting, CatBoost, and XGBoost, to enhance detection accuracy. Through advanced feature selection methods such as SelectKBest and RFECV, and optimizations like hyperparameter tuning and data balancing, the model was trained and evaluated on four publicly available datasets. PhishGuard outperformed state-of-the-art models, achieving a detection accuracy of 99.05% on one of the datasets, with similarly high results across other datasets. This research demonstrates that optimization methods in conjunction with ensemble learning greatly improve phishing detection performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Classification and Analysis of Textual data using Naive Bayes with TF-IDF 4

Classification and Analysis of Textual data using Naive Baye...

引用

4th International Conference on Electrical, Control and Instrumentation Engineering, ICECIE 2022

作者： Chingmuankim Jindal, Rajni Delhi Technological University Dept. of Computer Science Engineering New Delhi India

ISBN: (纸本)9781665480765

Text classification has become an emerging topic in this modern era as it allow us to extract meaningful information from the data and improve the performance of business and organization. Often termed as Text Tagging or Categorization, these textual data can be Structured, Semi-Structured and Unstructured. This work has utilized unstructured data with the help of twitter API. These unstructured data are then structured using NLP cloud API as the process of manual sorting is time consuming and tedious. The structured textual data comprises of a set of categorical data that is labelled on the basis of the content of the comments. Text Classification has various use cases such as Sentiment analysis, Polarity Checking, Natural Language Inference and accessing grammatical correctness. Earlier experimental work has been carried out using Naive Bayes with a Bag of Words (BOW) feature extraction technique by previous researchers. The objective of this work is to analyze the transformed structured imbalanced data and study the impact it has on the accuracy of Naive Bayes model using Term Frequency-Inverse Document Frequency (TF-IDF) technique. Naive Bayes is a linear, probabilistic and supervised machine learning classifier based on Bayesian theorem. On training and testing the data using the proposed model, it is found that there is an improvement in the overall accuracy with 2-3%. © 2022 IEEE.

关键词： Naive Bayes Polarity Checking Text Classification TF-IDF

来源：评论

学校读者我要写书评

暂无评论

Diagnosis, Treatment and Containment of Epilepsy Disease 7

Diagnosis, Treatment and Containment of Epilepsy Disease

引用

7th International Conference on Parallel, Distributed and Grid Computing, PDGC 2022

作者： Dhondiyal, Shiv Ashish Dimri, Sushil Chandra Graphic Era Deemed to Be University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9781665454018

The research work includes a thorough examination of the evolution of Epilepsy Disease, its symptoms, therapies, and progression, as well as algorithmic techniques for diagnosis. The majority of research on this condition is on identifying Epilepsy condition using EEG data and machine learning, and also on assessing the influence of medications on its development. Recent advances show that selection of features and optimization computation are often used to extract a group of best-performing characteristics that deliver high accuracy rates while rejecting other comparable parameters. Several research gaps have also been found in this work that might be investigated further in the future, including (i) identification of initial biomarkers of epilepsy disease from various types of available datasets, using Machine Learning techniques is required. (ii) Need to design a machine learning classifier based on the various data sources and the user inputs (symptoms) to fast and more accurate detection of epilepsy diseases. (iii) Selection of appropriate feature sets for classification of the epilepsy disease.(iv) case study of different medicines required to control and treat the epilepsy disease as early as possible. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Smart Medical Box using Arduino

Smart Medical Box using Arduino

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Sweadha. M M. Selvi Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

The Smart Medical Box is a sophisticated IoT-driven solution designed to enhance medication adherence by utilizing computer vision and machine learning. The system automates the identification and extraction of essential information from medication labels, ensuring precision in dosage reminders and reducing human error. It incorporates a high-resolution camera, an OCR engine, and an Arduino-based microcontroller to enable seamless image processing and real-time analysis. With an intuitive interface and GPS-enabled location services, users can efficiently manage their medication schedules while accessing nearby pharmacies when needed. This research focuses on designing and implementing a scalable and cost-effective system that improves medication compliance and minimizes health risks associated with missed or incorrect dosages. By integrating advanced image processing techniques and AI-driven recognition algorithms, the Smart Medical Box ensures high accuracy in identifying medications. Additionally, features such as automated alerts, real-time monitoring, and pharmacy locator tools enhance the system's usability and accessibility. This innovation is particularly beneficial for elderly individuals and patients with chronic conditions, offering a simplified and automated approach to medication tracking. Performance evaluations of the system indicate a significant improvement in medication adherence, a high recognition accuracy rate, and positive user feedback. Future enhancements, including AI-based OCR, voice assistance, and mobile application connectivity, are expected to further improve functionality and ease of use. This paper presents the conceptualization, development, and testing of the Smart Medical Box, highlighting its potential to revolutionize personal healthcare management by providing an intelligent, efficient, and user-friendly solution.

关键词： Accuracy Image recognition Microcontrollers Optical character recognition Medical services Real-time systems Usability Older adults Biomedical imaging Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

An Energy Recharging Scheme in Mobile Wireless Sensor Networks

An Energy Recharging Scheme in Mobile Wireless Sensor Networ...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Hu, ZhiJie Chang, Chih-Yung Shen, RuiBing Wu, Shih-Jung Xi'an Eurasia University School of Information Engineering Xi'an China Tamkang University Dept. of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350324174

With the development of the Internet of Things, applications of the wireless sensor network are more and more widespread. In wireless sensor networks, the sensor is basically stationary and performs sensing tasks at the deployed location. The mobile charger moves to the sensors for recharging them. However, the energy of the mobile charger is limited. It usually consumes lots of energy for moving and recharging. As a result, some sensors die due to the lack of timely recharged, which affects the monitoring quality and recharging efficiency. In this paper, the sensors are mobile. They can move to the recharging station in order to be recharged by the mobile charger, which reduces the cost of the mobile charger's traversal. At the same time, the proposed algorithm considers the cooperation of multiple mobile chargers, aiming to shorten the recharging cycle. In addition, the sensors also locally adjust their sensing frequencies for improving the sensing data quality according to the starting recharging time. Experimental results show that the proposed recharging algorithm improves the sensing quality compared to the existing algorithms. © 2023 IEEE.

关键词： Wireless sensor networks

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：