检索结果-内蒙古大学图书馆

A deep decentralized privacy-preservation framework for online social networks

Blockchain(Research and Applications) 2024年第4期5卷 163-174页

作者： Samuel Akwasi Frimpong Mu Han Emmanuel Kwame Effah Joseph Kwame Adjei Isaac Hanson Percy Brown School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang212013China Department of Computer Engineering Ghana Communication Technology UniversityAccraPMB 100Ghana Department of Electrical&Electronic Engineering Ghana Communication Technology UniversityAccraPMB 100Ghana Department of Computer Science and Information Systems Ashesi UniversityAccra3042Ghana Department of Telecommunication Engineering Ghana Communication Technology UniversityAccraPMB 100Ghana

This paper addresses the critical challenge of privacy in Online Social Networks(OSNs),where centralized designs compromise user *** propose a novel privacy-preservation framework that integrates blockchain technology with deep learning to overcome these *** methodology employs a two-tier architecture:the first tier uses an elitism-enhanced Particle Swarm Optimization and Gravitational Search Algorithm(ePSOGSA)for optimizing feature selection,while the second tier employs an enhanced Non-symmetric Deep Autoencoder(e-NDAE)for anomaly ***,a blockchain network secures users’data via smart contracts,ensuring robust data *** tested on the NSL-KDD dataset,our framework achieves 98.79%accuracy,a 10%false alarm rate,and a 98.99%detection rate,surpassing existing *** integration of blockchain and deep learning not only enhances privacy protection in OSNs but also offers a scalable model for other applications requiring robust security measures.

关键词： Preprocessing Privacy-preservation Blockchain Deep learning Online social network

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Classification Using CNN and Random Forest 3

Lung Cancer Classification Using CNN and Random Forest

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hasan, Nowshad Sharif, Md. Maskat Islam, Md Saiful Chowdhury, Arafat Anam Rahman, Miskatur Khan, Md Rokibul Fahad Bahar, Anamul Chittagong University of Engineering and Technology Department of Electronics and Telecommunication Engineering Chittagong Bangladesh North South University Department of Computer Science Enginnering Dhaka Bangladesh International Islamic University Chittagong Department of Electronics and Telecommunication Engineering Chittagong Bangladesh University of London Department of Computer Science Enginnering London United Kingdom

ISBN: (纸本)9798331534400

Lung cancer is one of the leading causes of cancer-related mortality worldwide. Early detection of lung cancer is crucial for improving survival rates and enabling more effective treatment options. However, manually detecting and classifying various forms of lung cancers is time-consuming and can be inaccurate. Traditional classification methods rely on manual feature extraction, necessitating the experimenter's expertise and professional knowledge. This research introduces a streamlined feature selection method using a deep convolutional neural network (CNN) to effectively tackle the issue. The aim of this proposed lightweight deep CNN is to enhance accuracy while reducing the number of parameters. The established approach involves three key stages: pre-processing, feature extraction, and classification. In the pre-processing phase, K-fold cross-validation ensures robust classification, complemented by data augmentation to augment the image dataset. In the feature extraction stage, modified CNNs effectively extract pertinent features, followed by Random Forest (RF) utilization to distinguish various forms of lung cancer from CT scan images. The proposed Deep CNN-RF model demonstrates effective detection and classification of various types of lung cancer, achieving an impressive accuracy rate of 97.1%. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Identification of Software Bugs by Analyzing Natural Language-Based Requirements Using Optimized Deep Learning Features

引用

computers, Materials & Continua 2024年第3期78卷 4379-4397页

作者： Qazi Mazhar ul Haq Fahim Arif Khursheed Aurangzeb Noor ul Ain Javed Ali Khan Saddaf Rubab Muhammad Shahid Anwar Department of Computer Science and Engineering and International Bachelor’s Program in Informatics Yuan Ze UniversityZhongliTaoyuan320315Taiwan Department of Computer Science National University of PakistanRawalpindiPunjab46000Pakistan Department of Computer Software Engineering MCSNational University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Department of Computer Science School of PhysicsEngineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Department of AI and Software Gachon UniversitySeongnam-SI13120South Korea

Software project outcomes heavily depend on natural language requirements,often causing diverse interpretations and issues like ambiguities and incomplete or faulty *** are exploring machine learning to predict software bugs,but a more precise and general approach is *** bug prediction is crucial for software evolution and user training,prompting an investigation into deep and ensemble learning ***,these studies are not generalized and efficient when extended to other ***,this paper proposed a hybrid approach combining multiple techniques to explore their effectiveness on bug identification *** methods involved feature selection,which is used to reduce the dimensionality and redundancy of features and select only the relevant ones;transfer learning is used to train and test the model on different datasets to analyze how much of the learning is passed to other datasets,and ensemble method is utilized to explore the increase in performance upon combining multiple classifiers in a *** National Aeronautics and Space Administration(NASA)and four Promise datasets are used in the study,showing an increase in the model’s performance by providing better Area Under the Receiver Operating Characteristic Curve(AUC-ROC)values when different classifiers were *** reveals that using an amalgam of techniques such as those used in this study,feature selection,transfer learning,and ensemble methods prove helpful in optimizing the software bug prediction models and providing high-performing,useful end mode.

关键词： Natural language processing software bug prediction transfer learning ensemble learning feature selection

来源：评论

学校读者我要写书评

暂无评论

Transition-Aware Human Activity Recognition using Ensemble Learning and Neural Networks

Transition-Aware Human Activity Recognition using Ensemble L...

引用

2024 International Research Conference on Smart Computing and Systems engineering, SCSE 2024

作者： Wijewardhana, Thamali Goonetilleke, Sahani University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka University of Moratuwa Department of Electronic and Telecommunication Engineering Moratuwa Sri Lanka

ISBN: (纸本)9798350375688

Ubiquitous computing has captivated a significant interest due to its usefulness in various domains. Human activity recognition (HAR) is an important area in ubiquitous computing which identifies human activities using sensor data. In HAR, there is a noticeable lack of focus towards transition aware HAR and most systems have focused only on identifying basic activities. However, for effective HAR, it is necessary to identify transitions accurately. In this paper, we present a novel HAR method which focuses on recognizing both basic activities and transitional activities using accelerometer and gyroscope data. We have implemented a stacked-ensemble model for activity classification using both traditional machine learning algorithms and neural networks. Our method was evaluated using a public dataset and our stacked ensemble model has achieved an overall classification accuracy of 99.74 % with oversampling. Our model accurately identifies both basic and transitional activities. © 2024 IEEE.

关键词： Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Navigating the global stock market: correlation, prediction, and the influence of external factors

引用

Iran Journal of computer science 2024年第3期7卷 397-422页

作者： Islam, Mohammad Shariful Rony, Mohammad Abu Tareq Computer Science and Telecommunication Engineering (CSTE) Noakhali Science and Technology University Noakhali 3814 Bangladesh Department of Statistics Noakhali Science and Technology University Noakhali 3814 Bangladesh

Assessing a country’s economic health is a complex task that involves predicting stock price movements. The prices of stocks reflect the overall business climate and the performance of companies. This study examines the relationship between external factors such as weather conditions and pandemic-related data during COVID-19 and global stock prices to enhance comprehension of how worldwide occurrences impact the stock exchange. The analysis reveals that external factors influence stock prices differently, but correlations can provide valuable insights into market dynamics. The research focuses on daily time-series data for various stock indices, including NYSE COMPOSITE, TSX Composite, Nikkei 225, Global X DAX Germany, and HANG SENG INDEX, as well as weather and COVID-19 data. By identifying characteristics that can be correlated with financial market data, the study finds that some factors derived from COVID-19 and weather data have a strong and moderate correlation with daily stock prices. However, it’s important to note that correlation does not necessarily imply causation, even though these insights can be helpful to investors and researchers. For this, the study employs various machine learning and deep learning models to gain a deeper understanding of stock market dynamics in the context of global events. Linear Regression is identified as the top-performing model for NYSE COMPOSITE and TSX Composite in Canada, as well as Germany’s DAX index, with exceptional predictive accuracy. Gradient Boosting Regression proves effective for Japan’s Nikkei 225 index and China’s Hang Seng Index. These findings can be valuable tools for financial analysts and investors who want to enhance their predictive abilities. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： External factors Pandemic effect Price prediction Stocks Weather

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Person Re-identification for Service Robot 26

Cross-Modal Person Re-identification for Service Robot

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Uddin, Md. Kamal Kuri, Ratnadip Shamim, Faria Rafi Ul Islam, Md. Zasim Uddin, Md. Hasan, Mahmudul Noakhali Science and Technology University Department of Computer Science and Telecommunication Engineering Noakhali Bangladesh Begum Rokeya University Department of Computer Science and Engineering Rangpur Bangladesh Comilla University Department of Computer Science and Engineering Comilla Bangladesh

ISBN: (纸本)9798350359015

In computer vision, cross-modal person re-identification (Re-ID) is an important task to recognize a person across the different sensors of a camera network in low light or dark environments. Elderly monitoring for nursing home in dark environments, especially at night, is a difficult task for human. However, for 24-hours monitoring, it is possible to monitor in low light or dark conditions via surveillance camera through service robot. To overcome this problem, we take advantage of depth sensor-based RGB-D cameras (e.g., Microsoft Kinect and Intel RealSense Depth Camera), which can be incorporated into robot. These cameras can capture RGB images in normal lighting conditions and depth images in low lighting conditions. In this paper, we propose a novel idea to monitor elderly people at night by utilizing cross-modal person re-identification for service robot. To reduce the modality gap between RGB and depth images, we extract local features from both modalities using Histogram of Oriented Gradients (HOG) as it can extract local shape information within an image. We validate our proposed method by performing experiments on two benchmark cross-modal re-identification datasets and gain significant recognition accuracy in cross domain. © 2023 IEEE.

关键词： Cross-modal Person Re-identification Service Robot

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural Computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

Designing a Backstepping Integral Terminal Sliding Mode Controller for PEMFC System Employing a DC-DC Boost Converter 10

Designing a Backstepping Integral Terminal Sliding Mode Cont...

引用

10th IEEE International Conference on Power Systems, ICPS 2023

作者： Ferdusi, Zannatul Akter, Farzana Jewel, Ahamad Sazzad Tanzil, Md. Al. Mahedy Hasan, S.M. Hossain, Md. Rakib Datto, Sham Department of Electronics & Telecommunication Engineering Rajshahi6204 Bangladesh Department of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350318739

This paper presents a backstepping integral terminal sliding mode control (BITSMC) system tailored to manage the DC-DC boost converter's output voltage, solving the issue of proton exchange membrane fuel cells (PEMFCs) low voltage output which seamlessly integrates the attributes of both integral terminal sliding mode control (ITSMC) and backstepping control (BC) by effectively mitigating the limitations associated with these individual controllers. The controller is crafted using a representative model of the DC-DC boost converter, primarily aimed at precisely following a predetermined reference output voltage. The stability of the tracked voltage is confirmed through control Lyapunov analysis. To evaluate its effectiveness, extensive simulations are conducted on a Matlab/Simulink platform by considering various operating conditions and that is compared with an existing ITSMC. The comparative analysis underscores the superiority of the suggested controller in the areas of quicker reference tracing and mitigation of issues such as overshoot, undershoot, and settling time. © 2023 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Optimizing Underwater Acoustic Sensor Networks: Insights from Energy-Efficient, Reliable, and Void Issue-Based Routing Protocols 7

Optimizing Underwater Acoustic Sensor Networks: Insights fro...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Khan, Muhammad Umar Aamir, Muhammad Haider, Waleej Sir Syed University of Engineering and Technology Department of Telecommunication Engineering Pakistan Sir Syed University of Engineering and Technology Department of Computer Science and Information Technology Pakistan

ISBN: (纸本)9798331534271

The Underwater Acoustic Sensor Network (UASN) is based on the sensory elements that detect the environmental conditions of submerged regions and transmit the information through acoustic waves at the sink node placed on top of the water. All these sensory elements are battery-operated just like the Terrestrial Wireless Sensor Network (TWSN). However, these nodes are not stationary, unlike the nodes in TWSN. Thus, routing with limited energy and ever-changing topology decreases the reliability of the network and increases the chances of Void existence. This research paper focuses on the comparative analysis by critically reviewing some of the state-of-the-art routing protocols which are based on the effective usability of the limited energy resource, reliability of the network, and Void occurrence issues. An analytical method is employed to examine the strengths and shortcomings of existing routing protocols, with a specific emphasis on the identified difficulties. It provides a solid foundation related to UASN routing protocols which are primarily designed with a focus on resolving issues such as limited energy, low reliability, and high chances of void occurrence. The contribution of this comparative study helps the research partners from the academy and industry which are new to this field of study and would like to contribute. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Contention-Addressing Algorithm in WLAN Wake-Up-Based Radio Network Uplink 8th

Energy-Aware Contention-Addressing Algorithm in WLAN Wake-Up...

引用

8th International Congress on Information and Communication Technology, ICICT 2023

作者： Zubair, Suleiman Salihu, Bala Alhaji David, Michael Olayinka, Abdulkadir Abdulbaki Dare, Michael Tunde Zubair, Wali Momoh Department of Telecommunication Engineering Federal University of Technology Minna Minna Nigeria Computer Science Department Kaduna Polytechnic Kaduna Nigeria

ISBN: (纸本)9789819930425

The increased relevance of WLAN in upcoming wireless technology has made the efficient design of WLAN medium access control an open issue of concern especially in terms of energy. Energy efficiency primarily focuses on carrier sensing, false wake-ups, collision, and number of contention rounds. Research has proposed the use of low-power wake-up radio to perform carrier sensing operation which has the potential of making WLAN to have more energy and time for data transfer. However, the reduction of false wake-up and collision is still areas that consume node energy if not properly designed especially when contending stations are much. This work proposes an IEEE 802.11 wake-up radio algorithm for uplink that employs a hybrid contention-addressing to enhance energy in WLANs. Unlike other methods, the algorithm makes use of a distributed contention strategy to determine which station can wake up for data communication. Contention rounds are used to determine and queue up a set of stations chosen to transmit data. The algorithm greatly reduces false wake-ups which arise from delay between sleep and wake-up, by broadcasting the ACK frame after modulating the frame with a wake-up message (WuM), piggybacking the address of the next station to transmit. Simulation results show that the HCA–CSAM/CA algorithm is able to reduce energy overhead by 97%, which translates to 60 h increase in battery lifetime and 68.3% reduction in latency as compared with ESOC. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Medium access control

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：