检索结果-内蒙古大学图书馆

A systematic literature review of visual feature learning: deep learning techniques, applications, challenges and future directions

引用

Multimedia Tools and Applications 2024年 1-58页

作者： Abdullahi, Mohammed Oyelade, Olaide Nathaniel Kana, Armand Florentin Donfack Bagiwa, Mustapha Aminu Abdullahi, Fatimah Binta Junaidu, Sahalu Balarabe Iliyasu, Ibrahim Ore-ofe, Ajayi Chiroma, Haruna Department of Computer Science Ahmadu Bello University Zaria Zaria Nigeria Department of Mechanical Engineering Ahmadu Bello University Zaria Nigeria Department of Computer Engineering Ahmadu Bello University Zaria Nigeria College of Computer Science and Engineering University of Hafr Al Batin Hafar Al-Batin31991 Saudi Arabia School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Belfast United Kingdom

Visual Feature Learning (VFL) is a critical area of research in computer vision that involves the automatic extraction of features and patterns from images and videos. The applications of VFL are vast, including object detection and recognition, facial recognition, scene understanding, medical image analysis, and autonomous vehicles. In this paper, we propose to conduct extensive systematic literature review (SLR) on VFL based on deep learning algorithms. The paper conducted an SLR covering deep learning algorithms such as Convolutional Neural Networks (CNNs), Autoencoders, and Generative Adversarial Networks (GANs) including their variants. The review highlights the importance of VFL in computer vision and the limitations of traditional feature extraction techniques. Furthermore, it provides an in-depth analysis of the strengths and weaknesses of various deep learning algorithms for solving problems in VFL. The discussion of the applications of VFL provides an insight into the impact of VFL on various industries and domains. The review also analyzed the challenges faced by VFL, such as data scarcity and quality, overfitting, generalization, interpretability, and explainability. The discussion of future directions for VFL includes hybrid techniques, unsupervised feature learning, continual learning, attention-based models, and explainable AI. These techniques aim to address the challenges faced by VFL and improve the performance of the models. The systematic literature review concludes that VFL is a rapidly evolving field with the potential to transform many industries and domains. The review highlights the need for further research in VFL and emphasizes the importance of responsible use of VFL models in various applications. The review provides valuable insights for researchers and practitioners in the field of computer vision, who can use these insights to enhance their work and ensure the responsible use of VFL models. © The Author(s), under exclusive licence to

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Trojan Detection in Network Traffic: A CNN-BiLSTM Approach 100

Deep Learning-Based Trojan Detection in Network Traffic: A C...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Hoque, Md Mozammal Alam, Khorshed Monir, Md Fahad Tarek Habib, Md University of Houston Department of Electrical and Computer Engineering United States Department of Computer Science & Engineering Bangladesh

ISBN: (纸本)9798331517786

Trojan detection from network traffic data is crucial for safeguarding networks against covert infiltration and potential data breaches. Deep learning (DL) techniques can play a pivotal role in detecting trojans from network traffic data by learning complex patterns and anomalies indicative of malicious behavior, thus enhancing detection accuracy and efficiency. This technique is pivotal in the context of data security, specifically in next-generation network architecture for its ability to effectively detect complex and evolving cyber threats, such as Trojan horse traffic, ensuring robust network protection. The research gap in detecting network Trojans lies in developing techniques capable of efficiently identifying stealthy and polymorphic variants while minimizing false positives. This study focuses on trojan detection from network traffic data, crucial for network security. Deep learning, specifically a combination of Convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks, is proposed to enhance accuracy and efficiency by learning complex patterns indicative of malicious behavior. Our proposed approach extracts features using CNNs to capture spatial dependencies and utilizes BiLSTM networks to process sequential dependencies, achieving 99% accuracy in trojan detection on real-world datasets. We validated this performance by comparing with previous approaches to ensure robustness in a common dataset. Making our work available open-source on, can enhance its accessibility and promote future research opportunities in Trojan Network Detection. After this work, we will work on detecting trojan networks from our institute's network data and will release the trojan network dataset, as there is a gap in open-source trojan network datasets. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Component library creation and pixel array generation with micromilled droplet microfluidics

引用

Microsystems & Nanoengineering 2025年第1期11卷 277-287页

作者： David McIntyre Diana Arguijo Kaede Kawata Douglas Densmore Biomedical Engineering Department Boston UniversityBostonMAUSA Biological Design Center Boston UniversityBostonMAUSA Electrical and Computer Engineering Department Boston UniversityBostonMAUSA

Droplet microfluidics enable high-throughput screening,sequencing,and formulation of biological and chemical systems at the *** devices are generally fabricated in a soft polymer such as polydimethylsiloxane(PDMS).However,developing design masks for PDMS devices can be a slow and expensive process,requiring an internal cleanroom facility or using an external ***,we present the first complete droplet-based component library using low-cost rapid prototyping and electrode *** fabrication method for droplet microfluidic devices costs less than$12 per device and a full design-build-test cycle can be completed within a *** microfluidic components for droplet generation,re-injection,picoinjection,anchoring,fluorescence sensing,and sorting were built and *** devices are biocompatible,low-cost,and *** show its ability to perform multistep workflows,these components were used to assemble droplet"pixel"arrays,where droplets were generated,sensed,sorted,and anchored onto a grid to produce images.

关键词： droplet microfluidics micromilled rapid prototyping electrode integrationthis soft polymer biocompatible component library pixel array

来源：评论

学校读者我要写书评

暂无评论

Efficient Bit-Plane Based Medical Image Cryptosystem Using Novel and Robust Sine-Cosine Chaotic Map

引用

computers, Materials & Continua 2025年第4期83卷 917-933页

作者： Zeric Tabekoueng Njitacke Louai A.Maghrabi Musheer Ahmad Turki Althaqafi Department of Electrical and Electronic Engineering College of Technology(COT)University of BueaBueaP.O.Box 63Cameroon Department of Software Engineering College of EngineeringUniversity of Business and TechnologyJeddah22246Saudi Arabia Department of Computer Engineering Jamia Millia IslamiaNew Delhi110025India Department of Computer Science School of EngineeringComputing and DesignDar Al-Hekma UniversityJeddah22246Saudi Arabia

This paper presents a high-security medical image encryption method that leverages a novel and robust sine-cosine *** map demonstrates remarkable chaotic dynamics over a wide range of *** employ nonlinear analytical tools to thoroughly investigate the dynamics of the chaotic map,which allows us to select optimal parameter configurations for the encryption *** findings indicate that the proposed sine-cosine map is capable of generating a rich variety of chaotic attractors,an essential characteristic for effective *** encryption technique is based on bit-plane decomposition,wherein a plain image is divided into distinct bit *** planes are organized into two matrices:one containing the most significant bit planes and the other housing the least significant *** subsequent phases of chaotic confusion and diffusion utilize these matrices to enhance *** auxiliary matrix is then generated,comprising the combined bit planes that yield the final encrypted *** results demonstrate that our proposed technique achieves a commendable level of security for safeguarding sensitive patient information in medical *** a result,image quality is evaluated using the Structural Similarity Index(SSIM),yielding values close to zero for encrypted images and approaching one for decrypted ***,the entropy values of the encrypted images are near 8,with a Number of Pixel Change Rate(NPCR)and Unified Average Change Intensity(UACI)exceeding 99.50%and 33%,***,quantitative assessments of occlusion attacks,along with comparisons to leading algorithms,validate the integrity and efficacy of our medical image encryption approach.

关键词： Image cryptosystem robust chaos sine-cosine map nonlinear analysis tools medical images

来源：评论

学校读者我要写书评

暂无评论

Optimizing MIMO-OFDM Communication Systems: A Comparative Analysis of LMMSE and LZF Equalizers under Varying Antenna Configurations

Optimizing MIMO-OFDM Communication Systems: A Comparative An...

引用

2024 Cognitive Models and Artificial Intelligence Conference, AICCONF 2024

作者： Al-Aanbagi, Sarah Koyuncu, Hakan Altinbas University Electrical and Computer Engineering Department Turkey Computer Engineering Department Altinbas university Turkey

ISBN: (纸本)9798400716928

Orthogonal Frequency Division Multiplexing (OFDM) has emerged as a fundamental modulation technique in modern broadband wireless communication systems, effectively addressing challenges arising from dispersive channels and random fading phenomena. By employing orthogonal subcarrier frequencies, OFDM enables the simultaneous transmission of multiple in-formation symbols, thereby mitigating Inter-Symbol Interference (ISI) often encountered in scenarios characterized by multi-path propagation. In contrast to traditional Frequency Division Multiplexing (FDM) methods, OFDM eliminates the need for guard bands between adjacent frequency bands, thereby improving spectral efficiency for high-speed data transmission. This paper conducts an extensive analysis of Zero Forcing (ZF) and Minimum Mean Squared Error (MMSE) equalizers in wireless Multi-Input Multi-Output (MIMO) systems employing BPSK, QPSK, and 16-PSK modulations. Lever-aging MATLAB-based simulations, diverse configurations involving multiple transmit and receive antennas are explored, yielding insightful findings concerning output Signal-to-Noise Ratio (SNR) and Bit Error Rate (BER). Our study underscores the efficacy of OFDM-MIMO systems with equalizers in enhancing communication performance across a spectrum of wireless scenarios, offering valuable insights for both theoretical exploration and practical implementation. © 2024 ACM.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Mitigating concept drift in data streams: an incremental decision tree approach

引用

Soft Computing 2024年 1-30页

作者： Tarazodar, Hadi Bagherifard, Karamollah Nejatian, Samad Parvin, Hamid Malekhosseini, Razieh Department of Computer Engineering Yasooj Branch Islamic Azad University Yasooj Iran Department of Electrical Engineering Yasooj Branch Islamic Azad University Yasooj Iran Department of Computer Engineering Nourabad Mamasani Branch Islamic Azad University Nourabad Mamasani Iran

While recognizing the significance of data in machine learning, we focus on addressing the challenge of concept drift, particularly in dynamic data streams. We propose an innovative incremental decision tree algorithm tailored for learning regression trees and model trees from evolving data streams. Vital to ensuring the quality and accuracy of predictive models is addressing this challenge. In this context, we present a novel solution: an incremental decision tree algorithm tailored for learning regression trees and model trees from time-varying data streams. Our algorithm is designed to operate at high speeds, effectively accommodating the influx of data at any scale, including scenarios with potentially unlimited data. Key innovations of our approach include a probabilistic defined sampling strategy that enhances the learning process and an advanced automatic method capable of handling non-stationary data distributions. However, the primary innovation lies in our methodology for detecting concept drift. Unlike conventional methods that reactively respond to increased errors, we introduce a proactive approach: monitoring the quality of individual subtrees by tracking their error evolution. This method allows us to detect changes in the objective function promptly, leading to timely adaptations in the model structure. Through extensive experimentation and evaluation, we demonstrate the effectiveness of our proposed algorithm in terms of prediction accuracy, model size, and change detection capabilities. Representing a significant advancement in the field of machine learning, particularly in addressing the challenge of concept drift in data streams, the proposed algorithm offers a competitive alternative to existing flow classifiers. Showcasing superior performance in terms of precision, recall, Fisher measure, and scalability, it underscores its potential to enhance decision-making processes across various domains by adapting swiftly to changing data patterns and m

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

A Study on the Explainability of Thyroid Cancer Prediction:SHAP Values and Association-Rule Based Feature Integration Framework

引用

computers, Materials & Continua 2024年第5期79卷 3111-3138页

作者： Sujithra Sankar S.Sathyalakshmi Department of Computer Applications Hindustan Institute of Technology and ScienceChennaiTamil NaduIndia Department of Computer Engineering Hindustan Institute of Technology and ScienceChennaiTamil NaduIndia

In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable *** predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce ***,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and *** paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present *** study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction *** the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the *** original dataset is used in trainingmachine learning models,and further used in generating SHAP values *** the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based *** new integrated dataset is used in re-training the machine learning *** new SHAP values generated from these models help in validating the contributions of feature sets in predicting *** conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making *** this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the *** study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of *** proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area un

关键词： Explainable AI machine learning clinical decision support systems thyroid cancer association-rule based framework SHAP values classification and prediction

来源：评论

学校读者我要写书评

暂无评论

Real-Time Prediction of Urban Traffic Problems Based on Artificial Intelligence-Enhanced Mobile Ad Hoc Networks(MANETS)

引用

computers, Materials & Continua 2024年第5期79卷 1903-1923页

作者： Ahmed Alhussen Arshiya S.Ansari Department of Computer Engineering College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Information Technology College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia

Traffic in today’s cities is a serious problem that increases travel times,negatively affects the environment,and drains financial *** study presents an Artificial Intelligence(AI)augmentedMobile Ad Hoc Networks(MANETs)based real-time prediction paradigm for urban traffic *** are wireless networks that are based on mobile devices and may *** distributed nature of MANETs and the power of AI approaches are leveraged in this framework to provide reliable and timely traffic congestion *** study suggests a unique Chaotic Spatial Fuzzy Polynomial Neural Network(CSFPNN)technique to assess real-time data acquired from various sources within *** framework uses the proposed approach to learn from the data and create predictionmodels to detect possible traffic problems and their severity in real ***-time traffic prediction allows for proactive actions like resource allocation,dynamic route advice,and traffic signal optimization to reduce *** framework supports effective decision-making,decreases travel time,lowers fuel use,and enhances overall urban mobility by giving timely information to pedestrians,drivers,and urban *** simulations and real-world datasets are used to test the proposed framework’s prediction accuracy,responsiveness,and *** results show that the suggested framework successfully anticipates urban traffic issues in real-time,enables proactive traffic management,and aids in creating smarter,more sustainable cities.

关键词： Mobile AdHocNetworks(MANET) urban traffic prediction artificial intelligence(AI) traffic congestion chaotic spatial fuzzy polynomial neural network(CSFPNN)

来源：评论

学校读者我要写书评

暂无评论

Number Plate Recognition Using OpenCV 6

Number Plate Recognition Using OpenCV

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Roopa Chandrika, R. Vanitha, K. Thahaseen, Aafiya Chandramma, R. Neerugatti, Vikram Mahesh, T.R. Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Al-Ameen Engineering College Department of Computer Science and Engineering Erode India Bangalore India Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350306613

The advancement of automated number plate recognition (ANPR) systems has garnered noteworthy attention in recent times owing to their diverse applications across multiple domains, including traffic management, parking management, and law enforcement. This paper presents an innovative ANPR method using OpenCV, an open-source computer vision library. Developing ANPR systems is a great fit for OpenCV since it offers a flexible platform for image processing and computer vision tasks. The suggested method effectively detects and recognizes number plates from images and video streams by utilizing OpenCV's capabilities for feature extraction, image preprocessing, and machine learning. Character segmentation, optical character recognitlon (OCR), and licence plate localization are important stages in the process. The ANPR system's accuracy and effectiveness are increased by using these strategies. A variety of real-world datasets, including different lighting conditions, camera angles, and vehicle types, are used in extensive experiments to assess the system's performance. The outcomes show how well the OpenCV-based ANPR system performs in tasks requiring license plate recognition, attaining high accuracy and resilience. Additionally, covered in the paper are possible uses for the ANPR system in security systems, vehicle tracking, and traffic monitoring. To make sure the system is workable in a variety of situations, scalability and real-time implementation are also taken into account. © 2024 IEEE.

关键词： machine learning number plate OpenCV recognition

来源：评论

学校读者我要写书评

暂无评论

Optimized deep autoencoder and BiLSTM for intrusion detection in IoTs-Fog computing

引用

Multimedia Tools and Applications 2025年第8期84卷 4907-4943页

作者： Alqahtani, Abdullah Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University KSA Al-Kharj16278 Saudi Arabia

Our world is rapidly evolving toward the Internet of Things (IoT), that connects all gadgets to digital services and simplifies our lives. As IoT devices expand, network vulnerabilities may rise, leading to more network threats. An intrusion detection system (IDS) with low latency and high accuracy is essential in this dynamic IoT environment to identify threats. Many IDSs utilize deep learning (DL) methods, but adjusting parameters for different environments can be challenging. This work proposes an improved hybrid Deep autoencoder (DAE) and Bidirectional long short-term memory (BiLSTM) for fog item installation to protect vital networks from prompt and efficient malicious threat detection. Determining the hyperparameters of complicated DL networks is tough. Low accuracy, efficiency, and performance in high-dimensional models afflict existing approaches. Therefore, the Sparrow Search Optimization Algorithm (SSOA) is adopted to enhance model hyperparameters. Employing IoT-based data, we assess the effectiveness of our suggested model. The outcome of the experiment obtained by analyzing the suggested IDS utilizing CICIDS2017 and BoT-IoT datasets attested to their supremacy over modern systems that are currently available in terms of precision, accuracy, FAR, error rate, and detection rate (DR). To learn more about how well our model works, added two additional metrics: Cohen's Kappa coefficients and Mathew correlation. The proposed optimization model demonstrated its ability to work well with various platforms, adapt to changing requirements, and handle larger workloads. In addition, it is possible to enhance the intrusion detection rate by minimizing both the error rate and computational time. Based on the experiments conducted, the proposed method yields superior results in terms of detection accuracy and reduced latency. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

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：