检索结果-内蒙古大学图书馆

Advanced Detection of Diabetic Foot Ulcers Using Hamiltonian Quantum GANs and Cell Attention Networks, with Genghis Khan Shark Optimization

引用

Biomedical Materials and Devices 2025年 1-17页

作者： Bapu, B. R. Tapas Sivamuni, Kalaimagal Samiappan, Dhandapani Sathiya, R.R. Department of Electronics and Communication Engineering S.A. Engineering College Poonamallee-Avadi Main Road Thiruverkadu Tamil Nadu Chennai 600077 India Department of AI & DS Panimalar Engineering College Varadharajapuram Poonamallee Tamil Nadu Chennai 6000123 India Department of Electronics and Communication Engineering Saveetha Engineering College Tamil Nadu Chennai 602105 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Diabetic Foot Ulcers (DFUs) are a severe difficulties of diabetes, often resulting from peripheral vascular disease, neuropathy, and poor glycemic control. If left undetected, DFUs can lead to severe infections, amputations, and increased mortality rates. Despite advancements in deep learning for medical image analysis, existing DFU detection methods suffer from low accuracy, high false-positive rates, and limited generalizability, making them unsuitable for real-world clinical deployment. To point out this challenge, this study proposes a novel DFU detection framework Cell Attention Networks with Genghis Khan Shark Optimization (CANet-GKSOpt) which integrates multiple cutting-edge ai techniques to enhance diagnostic precision. The proposed method utilizes Block-Batching Domain-Guided Filtering (2B-DGF) for noise reduction and image enhancement, followed by feature extraction using Hamiltonian Quantum Generative Adversarial Networks (HQGANet) to capture complex ulcer patterns. Cell Attention Networks (CANet) are then employed for refined classification by focusing on critical image regions. To further optimize accuracy and computational efficiency, the Genghis Khan Shark Optimization (GKSO) algorithm is applied for parameter tuning. The model is evaluated on the DFU2020 dataset and achieves a satisfying accuracy around 99% and 99.8% of sensitivity, significantly outperforming existing state-of-the-art methods. These results demonstrate the robustness of CANet-GKSOpt in accurately detecting DFUs, reducing false positives, and improving classification efficiency. The proposed approach contributes to the evolution of a highly effective ai-assisted diagnostic tool, which, with further validation on multi-center datasets and real-world clinical settings, has the potential to revolutionize DFU detection and management. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Block-batching domain-guided filtering cell attention networks DFUs detection Genghis Khan shark optimization Hamiltonian quantum generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Collaborative Feature Maps of Networks and Hosts for ai-driven Intrusion Detection

Collaborative Feature Maps of Networks and Hosts for AI-driv...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Jinxin Liu Murat Simsek Burak Kantarci Mehran Bagheri Petar Djukic School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada AI and Analytics Ciena Corp. Ottawa Canada

ISBN: (纸本)9781665435413

Intrusion Detection Systems (IDS) are critical secu-rity mechanisms that protect against a wide variety of network threats and malicious behaviors on networks or hosts. As both Network-based IDS (NIDS) or Host-based IDS (HIDS) have been widely investigated, this paper aims to present a Combined Intrusion Detection System (CIDS) that integrates network and host data in order to improve IDS performance. Due to the scarcity of datasets that include both network packet and host data, we present a novel CIDS dataset formation framework that can handle log files from a variety of operating systems and align log entities with network flows. A new CIDS dataset named SCVIC-CIDS-2021 is derived from the meta-data from the well-known benchmark dataset, CIC-IDS-2018 by utilizing the proposed framework. Furthermore, a transformer-based deep learning model named CIDS-Net is proposed that can take network flow and host features as inputs and outperform baseline models that rely on network flow features only. Experimental results to evaluate the proposed CIDS-Net under the SCVIC-CIDS-2021 dataset support the hypothesis for the benefits of combining host and flow features as the proposed CIDS- N et can improve the macro F1 score of baseline solutions by 6.36 % (up to 99.89%).

关键词： Deep learning Operating systems Intrusion detection Benchmark testing Transformers Feature extraction Entropy

来源：评论

学校读者我要写书评

暂无评论

The Optimization of COVID-19 Detection Based on DesNet Model

The Optimization of COVID-19 Detection Based on DesNet Model

引用

International Conference on computer Research and Development (ICCRD)

作者： Liu Mingchen Fu Jikun Chen Zhongxin Teoh Teik Toe School of Software Engineering HuaZhong University of Science and Technology Wuhan China Microelectronics Science and Engineering HuaZhong University of Science and Technology Wuhan China School of Computer Science and Technology HuaZhong University of Science and Technology Wuhan China NTU Business AI Lab Nanyang Technological University Singapore

In recent years, with the pandemic of COVID-19, how to identify the positive cases of COVID-19 accurately and rapidly from patients has become the key to block the spread of the epidemic and assist clinical diagnosis. In this paper, a COVID-19 detection model was constructed for the purpose to identify the positive cases from patients with other lung diseases as well as the normal using the chest X-ray images. The basic structure of the detection system is a CNN model based on DesNet with some optimization algorithms and the accuracy has reached 94.2%. We also applied three multi-sample data augmentation methods: SMOTE, mixup and CutMix to the model to analyze their performance. By applying these methods, the model finally reached 97.9 % on test set and showed a good generalization on other datasets, which could reach over 80% without extra training. The results show that using transfer learning and some muli-sample data augmentation methods can significantly improve the accuracy and overcome overfitting problem of fewshot learning, while others may not be so effective.

关键词： COVID-19 Training Pandemics Pulmonary diseases Computational modeling Transfer learning Data models

来源：评论

学校读者我要写书评

暂无评论

Architecture for ai-Based Validation of Wastewater Management Using Open Data Exchange Technique

Architecture for AI-Based Validation of Wastewater Managemen...

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： William, P. Oyebode, Oluwadare Joshua Ramu, Gandikota Gupta, Manish Alzubaidi, Laith H. Srivastava, Arun Pratap Sanjivani College of Engineering Savitribai Phule Pune University Department of Information Technology Pune India Afe Babalola University Civil and Environmental Engineering Ekiti State Ado-Ekiti Nigeria Institute of Aeronautical Engineering Department of Computer Science and Engineering Hyderabad500043 India Lovely Professional University Division of Research and Development Phagwara India The Islamic University Faculty of Engineering Najaf Iraq Lloyd Institute of Engineering and Technology Department of CSE Uttar Pradesh Greater Noida201308 India

ISBN: (纸本)9798350333244

To processing plant-wide data, it is not uncommon for there to be issues with sensors. Some examples of these issues include sensor failures, sensor calibration difficulties, sensor fouling and blockage, and connection problems between sensors, actuators, and the data management system. These problems may have an effect on the quality of the data, which will make it more difficult to implement sophisticated data-driven monitoring and control of (crucial) water operations. A method for the intelligent validation of data is provided in this article. The sensor data coming from a wastewater treatment plant are validated and verified by this process. The application for data validation has been integrated, tested, and put into production at the water utility known as Water Net. The method of validation is predicated on an anomaly detector that, in the event that an anomaly is found, combines (statistical) threshold-based procedures, (ai-based) autoencoder model predictions, and a component for data reconciliation. This occurrence repeats itself whenever an anomaly of some kind is found. In spite of the signal's volatility, the autoencoder models displayed outstanding levels of accuracy and great reconciliation performance. In addition, signals for both verified and raw data are provided in a way that is extremely near to real time to a dashboard. This keeps the dashboard up to date with the most recent information. Validated data may also be utilized as a screening tool for data that is being ingested by another ai-based model in order to monitor and intelligently manage the wastewater treatment plant, as well as to minimize greenhouse gas emissions and energy consumption while maintaining effluent water quality requirements. These goals may be accomplished while still meeting all applicable criteria. If this were done, it would be in compliance with the regulations for maintaining the effluent water's quality. © 2023 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Optoelectronic device based failure management using content based multispectral image retrieval and deep learning model

引用

Optical and Quantum Electronics 2024年第2期56卷 239-239页

作者： Bhukya, Raghuram Arunsundar, B. Tatini, Narendra Babu Sadala, Triveni Mohan Elshafie, Hashim Qamar, Shamimul Deaprtment of Computer Science and Engineering Kakatiya Institute of Technologey and Science Telangana Warangal India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu Kattankulathur India Department of Internet of Things Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur India Department: CS & AI SR UNIVERSITY Telungana Warangal India Department of Computer Engineering College of Computer Science King Khalid University Main Campus Al Farah Abha 61421 Saudi Arabia Computer Science and Engineering College of Sciences and Arts King Khalid University Dhahran Al Janoub Campus Abha 64261 Saudi Arabia

The need for optoelectronic devices is growing right now, but the production of these devices is having a difficult time keeping up with the advancement of the machinery, instruments, and manufacturing techniques they support. Pictures from big, unlabeled image collections are commonly retrieved using a technique called content-based image retrieval (CBIR). The availability of photographs is also growing as internet growth and transmission networks increase. This study suggests brand-new image retrieval methods for multispectral images used in Optoelectronic device monitoring that are based on image segmentation and classification methods with deep learningtechniques for failure management. Optoelectronic device Monitoring field-based multispectral images were used as the input, which was then processed for noise removal, resizing, and *** c-means clustering-based image segmentation was used to divide up this processed image into its component parts. Following that, a hybrid multilayer transfer learning perception was used to classify the clustered segmented picture. The proposed technique has an accuracy of 95%, precision of 85%, recall of 75%, F-1 score of 63%, error rate of 51%, MAP of 55%;existing MRCN accuracy of 85%, precision of 75%, recall of 63%, F-1 score of 55%, error rate of 45%, MAP of 51%, OC-LBP accuracy of 89%, the precision of 79%, recall of 71%, F-1 score of 59%, error rate of 49%, MAP of 53%. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Classification Deep learning Failure management Multispectral image retrieval Optoelectronic device Monitoring Segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Lane Detection based on Feature Aggregation for Advanced Driver Assistance Systems

Efficient Lane Detection based on Feature Aggregation for Ad...

引用

International Conference on Advanced Robotics and Intelligent Systems (ARIS)

作者： Sin-Ye Jhong Ching-Hsiang Ko Yi-Feng Su Kai-Lung Hua Yung-Yao Chen Dept. of Engineering Science National Cheng Kung University Tainan Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Research and Development Division Automotive Research and Testing Center Changhua Taiwan Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan

As we enter the era of smart cars and electric vehicles, the significance of autonomous driving systems, especially crucial components like lane detection technology, increases dramatically. However, advanced solutions often face daunting challenges, especially under adverse environmental and lighting conditions, yielding varying detection results. This variability prompts automakers to enforce numerous restrictions on auxiliary functions, often deterring potential customers from upgrading relevant services. This study addresses these limitations and introduces a sophisticated deep learning-based lane detection model to supersede existing technologies. The model fuses an efficient feature extraction network with a Recurrent Feature-Shift Aggregator (RESA) and a Bilateral Up-Sampling Decoder (BUSD). These elements work harmoniously, enabling enhanced global information extraction and fortifying detection capability under challenging conditions. The methodology of this study is segregated into three parts: Efficient Backbone and Neck for feature extraction, Global Feature Enhancement Decoder for maximizing feature map details, and the actual implementation of a Lane Assist System. These modules collectively help us calculate high-accuracy lane coordinates, thereby overcoming the limitations of previous lane detection methods. Following the successful creation and validation of the model, the study extends the implementation to the Hexagon vehicle control platform, where the Lane Departure and Lane Keeping assistance systems are deployed. The proposed technology is validated through rigorous experiments and analyses, utilizing the highly recognized TuSimple dataset, custom-collected Taiwanese scene data, and actual road tests. Results illustrate high and consistent detection performance under diverse environmental conditions, validating the technology’s effectiveness and feasibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Estimation of Growth Parameters and Total Phenolic Contents for Different Lettuce Cultivars Using RGB Images

SSRN

引用

SSRN 2024年

作者： Jeon, Juseok Jeon, Sangki Ha, Seungun Lim, Sungsu Park, Jongseok Department of Bio-AI Convergence Chungnam National University Daejeon34134 Korea Republic of Department of Computer Science and Engineering Chungnam National University Daejeon34134 Korea Republic of Department of Horticultural Science Chungnam National University Daejeon34134 Korea Republic of

Traditional methods for measuring growth parameters and phenolic contents in lettuce are often destructive, inefficient, and subjective. To overcome these challenges, this study proposed a non-destructive approach that combines computer vision and machine learning to estimate growth parameters such as fresh weight (FW), dry weight (DW), and leaf number (LN), along with total phenolic contents (TPC), in 34 lettuce cultivars from RGB images. Employing a U-Net-based multi-class segmentation model, we achieved a mIoU of 0.989 and an accuracy of 0.998, enabling precise segmentation of lettuce and a color card. Using the mask of the segmented color card, color correction and pixel size calculation were performed, allowing the extraction of a total of 16 phenotypic features related to size, morphology, and color. Then, SVR, RF, and XGB were used as prediction models. Predictions for growth parameters and TPC yielded R2 values of 0.907 (FW), 0.861 (DW), 0.815 (LN), and 0.734 (TPC). Analysis using feature importance and SHAP values revealed that size-related variables were important for FW and DW predictions, size and morphology for LN, and size and color for TPC. Our approach demonstrated reliable results across various lettuce cultivars, independent of camera positioning, type, and lighting conditions, and enables automatic non-destructive estimation of lettuce traits and phenotyping. © 2024, The Authors. All rights reserved.

关键词： Lettuce

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired VCSEL-based Optical Parallel Feedback System for Large-Scale Combinatorial Optimization

Quantum-Inspired VCSEL-based Optical Parallel Feedback Syste...

引用

OptoElectronics and Communications Conference, OECC

作者： Soon Thor Lim Dewen Zhang Zifeng Yuan Thanh Xuan Hoang Ching Eng Png Aaron Danner Electronics and Photonics Nano & Quantum Photonics/AI Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A⋆STAR) Singapore Singapore Dept. of Electrical and Computer Engineering National University of Singapore Singapore Singapore

ISBN: (数字)9798350308396

ISBN: (纸本)9798350308402

Photonic Ising computers hypothetically allow fast solutions to intractable combinatorial optimization problems. We have identified a possible physical implementation involving arrays of injection-locked Vertical Cavity Surface Emitting Lasers and an optical feedback mechanism which allows all-to-all bit connectivity without separate components along each connection path. Time-domain simulations indicate system stability up to at least 16 bits. Experimental realization of polarization switching in injection-locked VCSELs is also demonstrated as a proof-of-concept.

关键词： computers Stimulated emission Optical feedback Qubit Stability analysis Vertical cavity surface emitting lasers Time-domain analysis Semiconductor laser arrays Optimization Optical arrays

来源：评论

学校读者我要写书评

暂无评论

A Mixing-Accelerated Primal-Dual Proximal Algorithm for Distributed Nonconvex Optimization

A Mixing-Accelerated Primal-Dual Proximal Algorithm for Dist...

引用

American Control Conference (ACC)

作者： O. Zichong Chenyang Qiu Dandan Wang L. Jie School of Information Science and Technology Shanghaitech University Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA USA Shanghai Engineering Research Center of Energy Efficient and Custon AI IC Shanghai China

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

In this paper, we develop a distributed mixing-accelerated primal-dual proximal algorithm, referred to as MAP-Pro, which enables nodes in multi-agent networks to cooperatively minimize the sum of their nonconvex, smooth local cost functions in a decentralized fashion. The proposed algorithm is constructed upon minimizing a computationally inexpensive augmented-Lagrangian-like function and incorporating a time-varying mixing polynomial to expedite information fusion across the network. The convergence results derived for MAP-Pro include a sublinear rate of convergence to a stationary solution and, under the Polyak-Lojasiewics (P-L) condition, a linear rate of convergence to the global optimal solution. Additionally, we may embed the well-noted Chebyshev acceleration scheme in MAP-Pro, which generates a specific sequence of mixing polynomials with given degrees and enhances the convergence performance based on MAP-Pro. Finally, we illustrate the competitive convergence speed and communication efficiency of MAP-Pro via a numerical example.

关键词： Costs Network topology Chebyshev approximation Cost function Polynomials Convergence

来源：评论

学校读者我要写书评

暂无评论

Ensuring Security in Internet of Everything (IoT) With Smart Sensor Networking and Mobile Ad Hoc Network

Ensuring Security in Internet of Everything (IoT) With Smart...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Ashalatha. G Sanjay Modi Anil Kumar Dixit R. Ravi Kumar Hayder Al-Chilibi Malik Bader Alazzam Department of Computer Science – CS - DS & AI & DS VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad Telangana India Lovely Professional University Phagwara Uttaranchal Institute of Technology Uttaranchal University School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Computer Science and IT Al-Farahidi University Baghdad Iraq Information Technology College Ajloun National University Jordan

ISBN: (数字)9798350399264

ISBN: (纸本)9798350399271

A new age of connection is being ushered in by the Internet of Things (IoT), one that relies on a wide variety of objects and several modulation schemes to communicate. The followings will define this new era of correspondence: The IoT presents a substantially higher number of concerns, restrictions, and problems than do conventional computers since all of its items are interconnected and operate in unprotected contexts. This is because there are fewer linked elements in conventional computer systems. As a result, it is essential that cybersecurity be given priority in a new strategy, although that is not presently true of regular computer platforms. Two key elements in the development of an Internet of Everything system are the Smart Sensor Networking and also the Mobile Ad hoc Network. Sensing, pollution prevention, data collection, multimodal telecommunication networks, and data management are only a few of the many operations that employ this technology. IoT is vulnerable to the same types of safety concerns that other networks face since it combines elements of both Mobile ad hoc networks and Embedded system. A Suspension of Operation is a subtype of an onslaught known as a Delegates Entities Operation. The intruder delivers an unacceptably large number of command sessions that seem genuine. An SD operation is one of the various types of DoS attacks that are possible. This makes it far more difficult to identify this kind of assault than a straightforward one that drains the capacitors capability. The necessity to improve energy conservation and extend the life of Iot networks is one of the other major issues that occur in a networking throughout an SD attack. This is another important problem that develops in a network after an assault. Utilizing a Rng Generation with Heterogeneous Idss, often known as RNGHID, is advised. There are several distinct industries and regions that will make up the Web of Things economy. In order to detect any nodes within the netwo

关键词： computers Protocols Surveillance Organizations Software Safety 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：