检索结果-内蒙古大学图书馆

A classifier design for micro bubble generators based on deep learning technique

Materials Today: Proceedings 2023年 80卷 2684-2696页

作者： Qaddoori, Ayman S. Saud, Jamila H. Hamad, F.A. Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq College of Science Mustansiriyah University Baghdad Iraq School of computing Engineering and Digital Technology Teesside University Middlesbrough United Kingdom

This paper aims to study the sizes of bubbles generated by the micro-bubble generator device (MBGs) in the water because of its impact on the dissolved oxygen percentage in the water and we find this in aquaculture where oxygen is important for marine life and in many applications. Where we have designed a classifier for micro-bubbles of different sizes and the effectiveness of the device has been proven in generating bubbles whose size ranges from 20 to 50 and calculating their numbers in the image by converting the image from (RGB) to (HSV), it has proven its effectiveness in maintaining lighting and neglecting color information Which is not important in identifying bubbles in the image, as well as increasing the processing speed, and then finding edges in the image, using canny edge detection, which has proven its great effectiveness in finding weak and strong edges. Where we then used the (Circular Hough Transform) algorithm to identify the tiny bubbles in the image, calculate their average diameter and numbers in the image, and find the overlapping bubbles between them by using (Two Thresholds) one for the edge and the other for the center of the bubble and then making (Segmentation) for these bubbles and inserting them on (Gaussian Normal Distribution) Do not neglect the dark bubbles, because in most cases they are unreal bubbles and may be distortions in the image or reflections in the lighting. And then make (zero paddings) for the extracted images to make them equal in size and avoid the distortion that will happen in the image if another method is used to make all bubbles of equal dimensions to prepare them for classification. And then we calculated the (mean square error) of the resulting bubble images to avoid repeating the same bubble in (datasets). The efficiency of the classifier was calculated by using deep learning technology. Where we built a (Convolution Neural Network) consisting of (15) layers and then we trained these layers on the images resul

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

TCP Variants for Internet of Things: A Survey 4

TCP Variants for Internet of Things: A Survey

引用

4th International Conference on Distributed Sensing and Intelligent Systems, ICDSIS 2023

作者： Mansour, Youssef Alfalasi, Hamad Abbas, Sohail Talib, Manar Abu Department of Computer Science College of Computing and Informatics University of Sharjah United Arab Emirates

ISBN: (纸本)9781839539954

Due to its broad usage and predominance, TCP (Transmission Control Protocol) serves as the core of all Internet traffic. TCP is widely used because of its reliable connection-oriented architecture and capacity to manage congestion using different congestion control algorithms across a range of network loads and circumstances. The three phases of these congestion control algorithms—Slow Start, Congestion Avoidance, and Congestion Detection (Fast Recovery and Fast Retransmit)—are generally how they work. However, different TCP variants, such as Reno, New Reno, Tahoe, and more recent versions like FAST TCP, Cubic TCP, and Elastic TCP, implement these phases quite differently. Ever since these protocols were developed, the Internet environment has changed significantly, and they now have to deal with diverse set of challenges like high bandwidth demand problem and the requirement of fairness among various TCP flows. In this paper, we will review the most recent literature considering TCP variants for Internet of Things (IoT). Furthermore, we will analyze these techniques based on various factors, such as technology used, evaluation methodology and metrics, nodes type and mobility. © The Institution of Engineering & Technology 2023.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Multifactor Authentication Framework for Usability in Education Sectors in Uganda 1

引用

8th International Conference on Data Management, Analytics and Innovation, ICDMAI 2024

作者： Mpirirwe, Hilda Mirembe, Drake Patrick Lubega, Jude T. Agaba, Joab Nanyonga Clarke, Rose College of Computing and Information Sciences Makerere University Kampala Uganda School of Computing and Informatics Nkumba University Entebbe Uganda Clarke International University Kampala Uganda

ISBN: (数字)9789819732425

ISBN: (纸本)9789819732418

The reduction of academic dishonesty in e-assessment has been mentioned as a necessity for improved security, which can be achieved by implementing multifactor authentication. In e-assessment, learner authentication is a challenge that has grown significantly in importance. In order to counteract impersonation, the three authentication factors were coupled together to increase security in e-assessment were: biometric (facial recognition) and knowledge-based features (user name, password, and security questions generated from user profile). Data collection and analysis techniques used were;hybrid (qualitative and quantitative). The design science technique was used because it entails a systematic process of design, development, and evaluation. A methodical approach was used to create and build the Multifactor Authentication Framework. The framework's effectiveness at preventing identity fraud and ensuring the security of e-assessments was then evaluated in a simulated environment. Results show that;username and password was preferred because of effectiveness, takes a shorter time to login (72.1%), easy to use (73.4%), and is efficient thus gives accurate authentication results(79.6%);while the majority 77.8% of the respondents agreed that biometrics such as;fingerprints were easy to use, efficient to use (66.7%) thus giving accurate results and effective (66.7) requires a shorter time to login. By increasing the security factors of biometrics in e-assessment, the proposed multifactor authentication framework (E-MuAF) continually watches learners as they are being assessed while ensuring there is no impersonation. This paper proposes a Multifactor Authentication Framework in order to upgrade from single-factor to three-factor authentication systems. This framework strengthens authentication security in e-assessment where necessary. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Detecting Flood in Real-Time Weather Data Using Anomaly Detection Algorithm 4

Detecting Flood in Real-Time Weather Data Using Anomaly Dete...

引用

4th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2023

作者： Basheer, Muhammad Yunus Iqbal Ali, Azliza Mohd Hamid, Nurzeatul Hamimah Abdul Osman, Rozianawaty Nordin, Sharifalillah Ariffin, Muhammad Azizi Mohd College of Computing Informatics and Mathematics Universiti Teknologi Mara Selangor Shah Alam Malaysia

ISBN: (纸本)9798350318432

This paper presents flood detection using anomaly detection algorithms in real-time weather data. Nine different attributes are used to detect suspicious weather that can cause floods. The weather dataset was acquired from Kelantan, Malaysia. In this paper, the collected dataset will be sent from the chosen Internet of Things (IoT) pipeline to three different anomaly detection algorithms. These algorithms are multi-threaded autonomous anomaly detection (MAAD), robust random cut forest (RRCF), and outlier detection in feature-evolving data streams (xStream). Our evaluation demonstrates that the MAAD algorithm has a 68.5% precision score and a 0.01 false alarm rate, which is better than the RRCF and xStream for detecting floods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Assessing Web Performance of Malaysian University Website 8

Assessing Web Performance of Malaysian University Website

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Lehat, Mohd Lezam Abu Bakar, Nor Fauziah Jamil, Azura Abdul Mohd Shafee, Ct Munnirah Niesha Shamala, Palaniappan Rosnan, Suhanah Universiti Teknologi MARA Johor Branch College of Computing Informatics and Mathematics Johor Malaysia

ISBN: (纸本)9798350315516

University websites are gaining importance rapidly, making it crucial to ensure its well-designed, user-friendly, and perform optimally. However, there is a lack of research on the web performance of Malaysian university websites, making it challenging for universities to determine the necessary steps to enhance their websites' performance. The research aims to evaluate and enhance the web performance of Malaysian university websites. This study utilized an experimental approach by employing performance metrics from Google Lighthouse version 10.0.1 to measure the web performance of these websites and examine website design and content to identify factors that contributed to poor performance and user experience. The strategies were developed to improve website performance and enhance user experience through Web Content Accessibility Guidelines (WCAG) and Web Performance Index (WPI). This research will contribute to the existing knowledge on website performance and provide valuable insights and recommendations for enhancing the online presence and reputation of Malaysian universities. © 2023 IEEE.

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

An enhanced LSTM method for financial market forecasting 2

An enhanced LSTM method for financial market forecasting

引用

2nd International Conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Sun, Yu Mutalib, Sofianita Guangdong University of Science and Technology Guangdong Dongguan523083 China School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam40450 Malaysia

ISBN: (纸本)9781510689053

To effectively enhance the prediction accuracy of financial time series and improve the interpretability of the structural parameters of the prediction model, this paper proposes a long short-term memory (LSTM) stock price prediction model optimized in two stages based on Bayesian and Particle Swarm Optimization (BPSO-LSTM). This model represents an innovative advancement of the traditional LSTM framework, specifically designed to address complex nonlinear problems characterized by long-term dependencies, particularly in stock indices. Initially, the Bayesian algorithm is employed to optimize the core parameters of the LSTM model, establishing a foundation for subsequent Particle Swarm Optimization. Following this, an adaptive particle swarm algorithm is utilized to further refine the core parameters obtained through Bayesian Optimization, ensuring a high degree of compatibility between the characteristics of stock data and the network topology, thereby significantly improving the prediction accuracy of stock prices. Results from the prediction of the S&P 500 and Hang Seng Index indicate that the two-stage BPSO-LSTM model not only enhances prediction accuracy but also demonstrates strong universal applicability. © 2025 SPIE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Is Human Factors Being Studied in Software Testing?: Review of the Literature 8

Is Human Factors Being Studied in Software Testing?: Review ...

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Yahaya, Nursyuhaila Yusop, Nor Shahida Mohamad Rosli, Marshima Mohd Universiti Teknologi MARA College of Computing Informatics and Mathematics Selangor Shah Alam Malaysia

ISBN: (纸本)9798350315516

Software engineering is a human-centric activity influenced by human aspects such as age, gender, culture, language, attitudes, behaviors, and skills. While many of the studies in the software engineering area focused on the effect of human aspects in requirement engineering, design, and software development, only a limited number of studies are available investigating the relationship between human aspects and software testing. This study aims to explore the state of the art of human aspects in software testing, particularly to identify human factors studied in previous studies and how those human aspects affect software testing activities. A literature review was conducted on live reputable online databases, and we considered studies from 1994 to 2023. As a result, a total of 38 primary studies were identified. From the 38 studies, test execution was found to be the most researched software testing area related to human aspects, while test design and defect reporting were found to be the least researched. Among the seven categories of human aspects consisting of personality, experience, knowledge, hard skills, soft skills, personal characteristics, and teamwork values that we found, personality was the most studied. The results of this work are of interest to researchers in human-centric software engineering, particularly in software testing. Additionally, software organizations or employers can use the findings to support recruitment and staff management or improvise software testing processes for better software quality. © 2023 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

The Influence of Velocity over Network Dwelling in VANET V2R Communication 16

The Influence of Velocity over Network Dwelling in VANET V2R...

引用

16th IEEE Malaysia International Conference on Communication, MICC 2023

作者： Ramli, Nurshahrily Idura Mohamed Rawi, Mohd Izani Ibrahim, Mohd Faisal Noor, Noorhayati Mohamed Adnan, Rosanita College of Computing Informatics & Mathematics Universiti Teknologi MARA Selangor Shah Alam Malaysia

ISBN: (纸本)9798350304343

Delivering safety and non-safety applications and services, Vehicular Ad hoc Network or VANET is considered a technology that would flourish and advance for many years to come. Although there is more interest has been shown in VANET, in research, services, and even commercial, the limitations of VANET's connectivity have not been effectively reflected. Due to the ad hoc and ubiquitous nature of VANET, paired with the dynamic mobility of vehicles with dynamic velocity rates, the environment presents substantial challenges in network connectivity, hence influencing the performance of nodes communications. This paper covers to analyze the Network Dwelling Time (NDT) and the Network Dwelling Distance (NDD) between a vehicle and the Roadside Unit (RSU) in Vehicle-To-RSU (V2R) communication through simulation along the urban Federal Highway, Malaysia. The methodological approach used in this study utilizes several factors, including the RSU's transmission range, vehicular speed, road length and RSU's coordinates. To better understand the communication mechanisms in a VANET environment, the methodological approach starts by examining a simple scenario to detect the regions of NDT and NDD within the RSU coverage that certifies pervasive connectivity in V2R communication. The detection accuracy is verified mathematically and yields a reliable detection of NDT and NDD in V2R communication in VANET environment. Analysis is further undertaken in relating NDT and NDD of a vehicle based on its velocity to revealed that velocity is significant in determining the NDT and NDD and at a certain rate could cause meaningless data delivery from the RSU to the vehicle. © 2023 IEEE.

关键词： Roadsides

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm Augmented Inception-Net based Image Classifier Accelerated on FPGA

引用

Multimedia Tools and Applications 2023年第29期82卷 45097-45125页

作者： Kaziha, Omar Bonny, Talal Jarndal, Anwar Department of Electrical Engineering College of Engineering University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Deep learning models for computer vision applications specifically and for machine learning generally are now the state of the art. The growth of size and complexity of neural networks has made them more and more reliable, yet in greater need of computational power and memory as is evident from the heavy reliance on graphical processing units and cloud computing for training them. As the complexity of deep neural networks increases, the need for fast processing neural networks in real-time embedded applications at the edge also increases and accelerating them using reconfigurable hardware suggests a solution. In this work, a convolutional neural network based on the inception net architecture is first optimized in software and then accelerated by taking advantage of field programmable gate array (FPGA) parallelism. Genetic algorithm augmented training is proposed and used on the neural network to produce an optimum model from the first training run without re-training iterations. Quantization of the network parameters is performed according to the weights of the network. The resulting neural network is then transformed into hardware by writing the register transfer level (RTL) code for FPGAs with exploitation of layer parallelism and a simple trial-and-error allocation of resources with the help of the roofline model. The approach is simple and easy to use as compared to many complex existing methods in literature and relies on trial and error to customize the FPGA design to the model needed to work on any computer vision or multimedia application deep learning model. Simulation and synthesis are performed. The results prove that the genetic algorithm reduces the number of back-propagation epochs in software and brings the network closer to the global optimum in terms of performance. Quantization to 16 bits also shows a reduction in network size by almost half with no performance drop. The synthesis of our design also shows that the Inception-based classifier is cap

关键词： Genetic algorithms

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：