检索结果-内蒙古大学图书馆

Bangla Text Summarization Analysis Using Machine Learning: An Extractive Approach 1

2nd International Human engineering Symposium, HUMENS 2023

作者： Rahman, Mizanur Debnath, Sajib Rana, Masud Murad, Saydul Akbar Muzahid, Abu Jafar Md Rashid, Syed Zahidur Gafur, Abdul Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan26600 Malaysia Department of Computer Science and Engineering United International University Dhaka Bangladesh Information and Communication Engineering Noakhali Science and Technology University Noakhali Bangladesh Department of Electronic and Telecommunication Engineering International Islamic University Chittagong Chittagong Bangladesh

ISBN: (数字)9789819968909

ISBN: (纸本)9789819968893

A notable expansion of information in digital space provides quick access to these massive amounts of news, literature, and so on. Although maximum news is available in English, people are interested in reading in their language. Almost all Bangla newspapers now have their online version, so people prefer to read newspapers online. Without reading the whole news, it is not possible to obtain significant information and a summary from a news article. A news summary is a process of extracting the most significant information from a news article in a precise manner. In this case, we require an effective Bangla text summarizer tool to get insight from the news easily. Text summarizers use linguistic methods to generate and interpret text before uncovering natural concepts and phrases to represent the content by compressing the original text document into a shorter text that contains the most relevant information. Summarizing lengthy and important text by enforcing specific guidelines is a challenging task. Therefore, a method based on intelligent machine learning is widely anticipated in this content. This paper uses extractive automatic text summarization techniques to condense the source text into a shorter version by preserving the significant information of the original text. Here we have adopted two machine learning-based techniques (i.e., word2vec, and similarity matrix) and a rule-based technique (word count) for Bangla text summarization. The results show that the word2vec technique performs very well compared to the summary performed by other techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Object Detection Using a YOLOv4 Model in Video Surveillance 4

Object Detection Using a YOLOv4 Model in Video Surveillance

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Balamurugan, G. Arulalan, V. Premanand, V. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350300888

One of the most significant issues in surveillance videos is the detection of vehicles and objects at real time. Adverse weather conditions and lighting (illumination) variations are a few of the challenges faced while detecting objects through surveillance videos. In this work, a You Only Look Once v4 model, combined with a Spatial Pyramid Pooling and a Path Aggregation Network block and a contrast enhancement framework for effective detection of objects with higher accuracy is proposed. The video is converted to frames and is completely enhanced throughout using the Exposure Fusion Network. The brightness of the frames is equalized such that every point in the frame is clearly visible to the naked eye. Finally, the objects in the frames are detected using a YOLOv4 model, which is coupled with a SPP layer and a PAN network. The model generates an accuracy of 92.6%. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Morpho-contour exponential estimation algorithm for predicting breast tumor growth from MRI imagery

引用

International Journal of Information Technology (Singapore) 2024年 1-16页

作者： Kaladevi, P. Kanimozhi, N. Nirmala, B. Sivasankari, R. Department of Computer Science and Engineering K. S. Rangasamy College of Technology (Autonomous) Tamil Nadu Tiruchengode 637215 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai 603203 India Computer Science and Engineering Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Porur Chennai 600116 India Department of Computer Science Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai 600 048 India

Breast tumor grows rapidly have an elevated risk of progressing to a metastatic state, leading to the spread of tumor tissues to other regions of the body. Early detection of such metastatic sites can be facilitated by predicting these tumors' growth rate. In this context, we introduce a novel Morpho-Contour Exponential Estimation (MoCEE) method to estimate the potential growth rate of identified breast tumors using magnetic resonance imaging (MRI) datasets. This methodology not only effectively captures morphological traces but also pinpoints regions indicative of infectious spread. This precision is achieved by enhancing the Mask R-CNN with an active contour function, ensuring the accurate segmentation of the breast tumor. Once segmented, the tumor's growth rate is computed using the exponential growth model, which accurately determines the rate by analyzing the distance between two distinct random points on the tumor's segmented region. Subsequently, this derived information, processed through a gradient boosting approach, predicts the likelihood of tumor growth across two different breast tumor categories. In our study, we assessed the proposed MoCEE method from two crucial angles. Firstly, we rigorously evaluated its ability to accurately segment both benign and malignant breast tumors. Our analysis involved comparing MoCEE's performance to that of various deep learning networks, yielding impressive segmentation accuracy percentages, such as 93.12% and 92.22% for benign and malignant tumors in BUSnet, and even higher values for other networks. Secondly, we explored MoCEE's capability to estimate tumor size, considering different probability growth rates (k^=0.2, 0.3, 0.4, and 0.5). Notably, proposed MoCEE proved highly accurate in predicting tumor growth rates across this range of probabilities. These findings highlight MoCEE's versatility and robustness, making it a valuable tool for precise breast tumor analysis and prediction. © The Author(s), under exclusiv

关键词： And gradient boosting approach Breast tumors Exponential growth model Mask R-CNN Morpho-contour exponential estimation (MoCEE)

来源：评论

学校读者我要写书评

暂无评论

Optimizing Convolutional Neural Networks for Plant Disease Detection on ARM-M Microcontrollers

Optimizing Convolutional Neural Networks for Plant Disease D...

引用

2024 IEEE International Conference on Agrosystem engineering, Technology and Applications, AGRETA 2024

作者： Nugroho, Hermawan Xan, Chew Jing Siang, Tay Fei Eswaran, Sivaraman University of Nottingham Malaysia Department of Electrical and Electronic Engineering Semenyih Malaysia Swinburne University of Technology Sarawak Campus Faculty of Engineering Computing and Science Sarawak Malaysia Curtin University Malaysia Department of Electrical and Computer Engineering Miri Malaysia

ISBN: (纸本)9798350373660

Rice production in Malaysia is facing significant challenges due to plant diseases and environmental hazards, leading to a decline in the rice self-sufficiency ratio. To address these issues, this study explores the deployment of AI-driven plant disease detection models on ARM-M based microcontrollers, specifically the STM32H747I-DISCO Discovery kit. Utilizing Convolutional Neural Networks (CNNs) for image recognition, we aim to achieve real-time disease monitoring without relying on continuous internet connectivity. Our research evaluates five state-of-the-art models-FD-MobileNet, MobileNet V1, MobileNet V2, ResNet V1, and SqueezeNet V1-focusing on their suitability for resource-constrained environments. The results indicate that FD-MobileN et is the most resource-efficient model with the lowest number of Multiply-Accumulate operations (MACCs) and the shortest inference time, achieving an accuracy rate of 98.44%. However, SqueezeNet, despite having the highest accuracy at 99.22%, faces deployment challenges due to its large model size on the STM32H747I-DISCO board. This work highlights the potential of embedded AI applications in enhancing agricultural resilience and efficiency. © 2024 IEEE.

关键词： ARM-M microcontroller CNNs embedded systems plant disease detection

来源：评论

学校读者我要写书评

暂无评论

On the System Performance of Mobile Edge computing in an Uplink NOMA WSN With a Multiantenna Access Point Over Nakagami-m Fading

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 668-685页

作者： Van-Truong Truong Van Nhan Vo Dac-Binh Ha Chakchai So-In the Faculty of Electrical-Electronic Engineering Duy Tan University the Institute of Research and Development Duy Tan University the Faculty of Information Technology Duy Tan University IEEE the Applied Network Technology(ANT)Laboratory Department of Computer ScienceCollege of ComputingKhon Kaen University

In this paper,we study the system performance of mobile edge computing(MEC)wireless sensor networks(WSNs)using a multiantenna access point(AP)and two sensor clusters based on uplink nonorthogonal multiple access(NOMA).Due to limited computation and energy resources,the cluster heads(CHs)offload their tasks to a multiantenna AP over Nakagami-m *** proposed a combination protocol for NOMA-MEC-WSNs in which the AP selects either selection combining(SC)or maximal ratio combining(MRC)and each cluster selects a CH to participate in the communication process by employing the sensor node(SN)*** derive the closed-form exact expressions of the successful computation probability(SCP)to evaluate the system performance with the latency and energy consumption constraints of the considered *** results are provided to gain insight into the system performance in terms of the SCP based on system parameters such as the number of AP antennas,number of SNs in each cluster,task length,working frequency,offloading ratio,and transmit power ***,to determine the optimal resource parameters,i.e.,the offloading ratio,power allocation of the two CHs,and MEC AP resources,we proposed two algorithms to achieve the best system *** approach reveals that the optimal parameters with different schemes significantly improve SCP compared to other similar *** use Monte Carlo simulations to confirm the validity of our analysis.

关键词： Mobile edge computing(MEC) Nakagami-m fading offloading selection combining(SC)/maximal ratio combining(MRC) successful computation probability(SCP) uplink nonortho-gonal multiple access(NOMA) wireless sensor networks(WSNs)

来源：评论

学校读者我要写书评

暂无评论

Smart Happy Device with IoT : For those who suffer anxiety, stress, and depression 12

Smart Happy Device with IoT : For those who suffer anxiety, ...

引用

12th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2024

作者： Yakub, Fitri Azizan, Azizul Dhamanti, Inge Khudzari, Ahmad Zahran Md. Govindan, Niranjana Muljono, Muljono UTM Malaysia-Japan International Institute of Technology Electronic System Engineering Department Kuala Lumpur Malaysia Universiti Teknologi Malaysia Cyberphysical Research Group Embedded AI & ML Science Lab Faculty of Artificial Intelligence Kuala Lumpur Malaysia Universitas Airlangga Faculty of Public Health Department of Health Policy and Administration Surabaya Indonesia UTM Faculty of Engineering Department of Biosciences & Medical Engineering Johor Bahru Malaysia SRMIST Faculty of Engineering & Technology Department of Computing Technologies Chennai India Universitas Dian Nuswantoro Faculty of Computer Science Semarang Indonesia

ISBN: (纸本)9798350340204

Due to the rising cases of Covid-19 in the world especially in Malaysia, the impact had been hit hard for many people. Due to this all people must be isolated in their home. It has affected the well-being and working life of millions of people across the world. Due to this disease, the mental health among people has increased significantly for the past 2 years. According to MoH, out of 983 Malaysian students, about 20.4%, 6.6%, and 2.8% are experienced minimal to moderate, marked to severe, and most extreme levels of anxiety, respectively. The main stressors are the remote online teaching, and uncertainty about the future regarding study and career which can affect mental health. Thus, the main objective of this project is to develop a product that may provide different medication methods to its users by helping people who suffer anxiety, stress, and depression. We used aromatherapy, positive quotes, and music therapy in order to release stress. The user can also check his or her pulse rate by only touching the fingerprint through the sensor. The microcontrollers used in this project are Arduino Uno and Arduino Mega to build the project circuit. The experimental results can improve body health, mind and spirit which enhances both physical and emotional health. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Analysis and Treatment of Missing Data in Happiness Score Using Machine Learning 21

Analysis and Treatment of Missing Data in Happiness Score Us...

引用

21st IEEE International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT, HONET 2024

作者： Touati, Wassim El Touati, Yamen Hadj-Alouane, Nejib Ben Jemai, Abderrazek Polytechnic School of Tunisia Carthage University SERCOM Laboratory Tunis Tunisia Northern Border University Faculty of Computing and Information Technology Department of Computer Science Saudi Arabia ENIT University of Tunis EI Manar OASIS Laboratory Tunisia American University in Dubai Electrical Engineering and Computer Engineering Department Dubai United Arab Emirates

ISBN: (纸本)9798350378078

Machine learning, a vital part of artificial intelli-gence, improves our ability to make predictions from complex data. The success of these predictions relies heavily on the model's fit with its data and the data's consistency. Accurate predictions depend on closely matching the model to the data patterns. However, missing data can seriously disrupt the accuracy of predictions, causing errors. To address this, we recommend adopting a proposed framework that enhances predictions by effectively filling in missing data. Our objective is to refine the accuracy of our predictions, especially in scenarios where the data might be incomplete and features exhibit patterns of dependency. In the context of missing data, our approach concentrates on enhancing regression performance to minimize the effects of missing data as effectively as possible. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Silent Frontlines: Exploring the Impact of DDoS Hacktivism in the Russo-Ukrainian War 40

Assessing the Silent Frontlines: Exploring the Impact of DDo...

引用

40th Annual computer Security Applications Conference, ACSAC 2024

作者： Yilmaz, Yagiz Cetin, Orcun Ozturk, Omer Said Ekmekcioglu, Emre Arief, Budi Hernandez-Castro, Julio Faculty of Engineering and Natural Sciences Sabancı University Istanbul Turkey School of Computing University of Kent Canterbury United Kingdom Computer Systems Department Universidad Politécnica de Madrid Madrid Spain

ISBN: (纸本)9798331520885

This study assessed the impact and effectiveness of Distributed Denial of Service (DDoS) attacks during a period of about four months of the Russo-Ukrainian war, by observing the exchanges between the opposing sides. The data collection phase took place between the 28th of November 2022 and the 15th of April 2023. In total, we monitored 1,257 websites and web applications targeted in the conflict, with 633 targeted by pro-Russian and 624 by pro-Ukrainian entities. Only a small fraction (1.27%) of the targets remained unaffected, whereas 30.63% faced complete shutdowns. When considering the extent of the attacks conducted by the belligerents in the war, the attacks by pro-Russian entities showed a slightly more successful overall impact, with 36.18% of their targets were taken down, compared to 25.00% on the opposite side. Businesses demonstrated greater resilience against DDoS attacks compared to governmental and educational institutions. An in-depth analysis revealed significant differences in target categories, despite both sides primarily targeting businesses. Our findings regarding the usage of DDoS protection services among the 1,257 analysed targets showed that only 13.37% used such services. Among these minority of users, 70.24% had protection from the beginning of our analysis, while 29.76% adopted it only after experiencing attacks. We also looked into the use of geolocation-based access policies on websites targeted by pro-Ukrainian entities. Our findings indicated that most of these websites do not implement geolocation-based access restrictions. To an extent, such restrictions could have been useful for preventing some unsophisticated attacks. Surprisingly, only a small percentage (4.50%) restricted access to solely Russian addresses, while a fraction (12.56%) seemed to implement adaptive access policies in response to cyberattacks. Lastly, and quite surprisingly for us, we discovered that a significant number of targets on the Russian side were using an

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Boosting Cybersecurity Effectiveness through Machine Learning for Proactive Detection and Mitigation of New Threats 2

Boosting Cybersecurity Effectiveness through Machine Learnin...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Duraimutharasan, N. Rao, N. Venkatesvara Poongavanam, N. Kanimozhi, K.V. Manikandan, S.P. Faculty of Advanced Computing Sciences AMET UNIVERSITY Tamil Nadu Chennai India Department of Computer Science and Engineering J.N.N.INSTITUTE OF ENGINEERING Ushaa GardenKannigaipair Periyapalayam Highway Chennai India Saveetha University Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India School of Engineering and Technology CMR UNIVERSITY Karnataka Bengaluru India

ISBN: (纸本)9798350383867

Cybersecurity still remains an all-time issue before the technological age as the enterprises continue to deal with the evolving nature of the threats arising every day. Traditional cybersecurity approaches are becoming deficient in the situation of constantly improving, swiftly mutating threats, which leads to the revision and refocus of the current approaches to the preventative reactivity type. For that, machine learning (ML) has come into the arena as a strong tool for improving cybersecurity capacity through the ¨p roactivë recognition and the ¨mitigatioñ̈ of unknown threats. The focus of this paper is the function of ML in cyber security. Here is considered anomaly detection, malware classification, threat intelligence analysis, and security form adversarial attacks. We conduct literature search, detail a novel research methodology embracing data acquisition, preprocessing, ML model training, and deployment. We present experiments versus conventional security approaches from different ML domains used confirming the superiority in cybersecurity of the presented models. Moreover, resistance to chicanery such as adversarial attacks and the models understandability are discussed. Next, research vector and innovation directions in the ML cybersecurity are highlighted. As a whole, this study provides the example of how ML can strengthen previous alliance strategies to cybersecurity and prevent the risks associated with interchanging cyber threats. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Construction and optimization of a computational holographic lithography system 8

Construction and optimization of a computational holographic...

引用

8th International Conference on Speckle Metrology, Speckle 2023

作者： Chen, Rui Lin, Angyi You, Jianfeng Lin, Huixiang Zhao, Wenqing Zhang, Fucai School of Control and Computer Engineering North China Electric Power University Baoding071003 China The Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen518055 China Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education North China Electric Power University China

ISBN: (数字)9781510674592

ISBN: (纸本)9781510674585

Traditional lithography techniques are currently facing challenges, including high costs and the susceptibility of mask plates to damage. This research aims to elucidate the feasibility and technical constraints of a novel diffraction lithography approach. This method can reduce the size and cost of lithography machines, break through existing technological barriers, and offer new possibilities for the future development of lithography machines. We have built a basic computational holographic lithography system utilizing a 405nm laser and validated the system using holograms obtained with both classical GS algorithm and a newly proposed method. With the GS holograms, patterns with 700nm features have been successfully exposed on the photoresist. With our new algorithms, multiple holograms for the same target pattern can be generated with different settings in the algorithm. Sequential exposure of those holograms resulted in continuous lines 500 nm wide with reduced speckle artifacts, which was about a 1.4-time improvement over the result from the GS algorithm. Future research will focus on optimizing and enhancing the experimental system and the hologram calculation methods to reduce the line widths further and improve the exposure pattern quality. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Holograms

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：