检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Runge, Tobias Bordis, Tabea Potanin, Alex Thüm, Thomas Schaefer, Ina Karlsruhe Institute of Technology Germany Institute of Software Engineering and Automotive Informatics TU Braunschweig Germany School for Data-Science and Computational Thinking Stellenbosch University South Africa School of Computing Australian National University Australia Institute of Software Engineering and Programming Languages University of Ulm Germany

Correctness-by-Construction (CbC) is an incremental program construction process to construct functionally correct programs. The programs are constructed stepwise along with a specification that is inherently guaranteed to be satisfied. CbC is complex to use without specialized tool support, since it needs a set of predefined refinement rules of fixed granularity which are additional rules on top of the programming language. Each refinement rule introduces a specific programming statement and developers cannot depart from these rules to construct programs. CbC allows to develop software in a structured and incremental way to ensure correctness, but the limited flexibility is a disadvantage of CbC. In this work, we compare classic CbC with CbC-Block and TraitCbC. Both approaches CbC-Block and TraitCbC, are related to CbC, but they have new language constructs that enable a more flexible software construction approach. We provide for both approaches a programming guideline, which similar to CbC, leads to well-structured programs. CbC-Block extends CbC by adding a refinement rule to insert any block of statements. Therefore, we introduce CbC-Block as an extension of CbC. TraitCbC implements correctness-by-construction on the basis of traits with specified methods. We formally introduce TraitCbC and prove soundness of the construction strategy. All three development approaches are qualitatively compared regarding their programming constructs, tool support, and usability to assess which is best suited for certain tasks and developers. © 2022, CC BY.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

DDCM: Cracking Anonymized Facial Images Using Denoising Diffusion Cryptanalytic Model

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Jiang, Donghua Ni, Jiangqun Alasbali, Nada Nafea, Ibtehal Liu, Qingliang Ahmad, Jawad Boulila, Wadii Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Cyber Science and Technology Shenzhen518107 China Peng Cheng Laboratory Department of New Networks Shenzhen518052 China King Khalid University College of Computer Science Department of Informatics and Computing Systems Abha61421 Saudi Arabia Taibah University College of Computer Science and Engineering Medina41477 Saudi Arabia Qingdao University of Science and Technology School of Mathematics and Physics Qingdao266061 China Prince Mohammad Bin Fahd University Cybersecurity Center Alkhobar Saudi Arabia Prince Sultan University Robotics and Internet-of-Things Laboratory Riyadh12435 Saudi Arabia

Currently, in consumer electronics industry, quite a number of E-healthcare products highly depend on consumers' facial biometrics for both disease diagnosis and identity authen-tication. In light of this, various facial privacy-preserving approa-ches oriented towards the internet of medical things have been proposed, including visual cryptography and desensitization tech-nique. Nevertheless, few attentions have been paid to investigating their countermeasure, i.e., facial privacy analysis, owning to significant distribution discrepancy between the original and anony-mized facial images. To this end, a general Denoising Diffusion Cryptanalytic Model (DDCM) is proposed in this paper to recon-struct the original facial images in a coarse-to-fine manner from their encrypted ones with diverse anonymous approaches. Spec-ifically, to accurately reconstruct the original facial image without any prior knowledge, a customized initial prediction module with an encoder-decoder structure is introduced by taking advantage of its leaked visual cues to generate the coarse face. Furthermore, the residual map between the original and coarse facial images is explicitly modeled with the output of the customized prediction module as a conditional prior, thereby obtaining a refined facial image. Finally, extensive experiments demonstrate that the propo-sed DDCM could not only effectively crack multiple handcrafted facial anonymization approaches, such as blurring, pixelation and thumbnail-preserving encryption, but also outperform the prev-ious works (e.g., Pix2Pix) in terms of image fidelity and attack success rate. © 1975-2011 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Based IDS Using Multi-objective Wrapper Feature Selection and Neural Network Classification 2nd

Metaheuristic Based IDS Using Multi-objective Wrapper Featur...

引用

2nd International Conference on Advances in Cyber Security, ACeS 2020

作者： Ghanem, Waheed Ali H. M. El-Ebiary, Yousef A. Baker Abdulnab, Mohamed Tubishat, Mohammad Alduais, Nayef A. M. Nasser, Abdullah B. Abdullah, Nibras Al-wesabi, Ola A. Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu Malaysia Faculty of Engineering and Faculty of Education-Aden and Saber Aden University Aden Yemen Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Kuala Terengganu Malaysia School of Computing and Technology Asia Pacific University of Technology and Innovation Kuala Lumpur Malaysia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja Malaysia Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang Pekan Malaysia National Advanced IPv6 Center Universiti Sains Malaysia Gelugor Malaysia Faculty of Computer Science and Engineering Hodeidah University Al Hudaydah Yemen

ISBN: (纸本)9789813368347

Due to the significant ongoing expansion of computer networks in our lives nowadays, the demand for network security and protection from cyber-attacks has never been more imperative to either clients or businesses alike, which signifies the key role of cyber intrusion detection systems in network security. This article proposes a cyber-intrusion detecting system classification with MLP trained by a hybrid metaheuristic algorithm and feature selection based on multi-objective wrapper method. The classifier, named as HADMLP is trained using a hybridization of the artificial bee colony along with the dragonfly algorithm. A multi-objective artificial bee colony model which is wrapper-based is used for selection of feature. Hence, collective name of the proposed technique referred as MO-HADMLP. For performance evaluation, the proposed method was assessed using ISCX 2012 and KDD CUP 99 datasets. The results of our experiments indicate a significant enhancement to the efficacy of network intrusion detection when compared to other approaches. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Early detection of plant diseases using spectral data 2020

Early detection of plant diseases using spectral data

引用

3rd International Conference on Applications of Intelligent Systems, APPIS 2020

作者： Owomugisha, Godliver Nuwamanya, Ephraim Quinn, John A. Biehl, Michael Mwebaze, Ernest University of Groningen Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence AK Groningen Netherlands Kampala Uganda Makerere University School of Computing and Informatics Technology Kampala Uganda

ISBN: (纸本)9781450376303

Early detection of crop disease is an essential step in food security. Usually, the detection becomes possible in a stage where disease symptoms are already visible on the aerial part of the plant. However, once the disease has manifested in different parts of the plant, little can be done to salvage the situation. Here, we suggest that the use of visible and near infrared spectral information facilitates disease detection in cassava crops before symptoms can be seen by the human eye. To test this hypothesis, we grow cassava plants in a screen house where they are inoculated with disease viruses. We monitor the plants over time collecting both spectra and plant tissue for wet chemistry analysis. Our results demonstrate that suitably trained classifiers are indeed able to detect cassava diseases. Specifically, we consider Generalized Matrix Relevance Learning Vector Quantization (GMLVQ) applied to original spectra and, alternatively, in combination with dimension reduction by Principal Component Analysis (PCA). We show that successful detection is possible shortly after the infection can be confirmed by wet lab chemistry, several weeks before symptoms manifest on the plants. © 2020 ACM.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Low-cost Modular Smart Home Controlling System for Minimising Energy Consumption: A Conceptual Study

Low-cost Modular Smart Home Controlling System for Minimisin...

引用

Visualization, informatics and technology Conference (IVIT), International

作者： Zaid Mujaiyid Putra Ahmad Baidowi Muhammad Danial Hakim Nazrin Izuan Gerard Ruwaida Ramly Mohd Rizal Mohd Isa Mohamad Yusof Darus Centre of Foundation Studies Universiti Teknologi MARA Cawangan Selangor Kampus Dengkil Dengkil Selangor Malaysia Universiti Kuala Lumpur Malaysian Institute of Information Technology Computer Science Department National Defence University of Malaysia Kuala Lumpur Malaysia School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA

ISBN: (纸本)9781665486491

Internet of Things (IoT) has become one of the popular topics in Information and Communication technology (ICT) recently. IoT has been widely used in many fields, and one of the most topics that had gained significant interest of many researchers is minimising energy consumption. IoT which is implemented in a wireless, connects multiple devices via the Internet. It allows data to be gathered and transferred without human intervention. In this paper, a new solution is to propose an automatic control of several electrical appliances such as air-conditioners, lights, and fans. These three electrical appliances contribute to the highest energy consumption. This paper aims to contribute to the solution of minimising energy consumption by deploying a low-cost modular system to be installed into readily houses. Thus, it can adapt any old infrastructure to an efficient home. Minimising power consumption has been studied in a smart home but less work deployed Arduino Nano 33 IoT as compared to the existing available Arduino system. Finally, this work is hoped lead to related studies in minimising energy consumption.

关键词： Wireless communication Energy consumption Fans Power demand Smart homes Control systems Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

arXiv

引用

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D Models and Animations for Cardiac Imaging Education

引用

Journal of Medical Imaging and Radiation Sciences 2024年第3期55卷 101547-101547页

作者： Dr Nur Hayati Jasmin Dr Wan Mohd Rizhan Wan Idris Miss Nur Awfa Mohd Hilmi Mr Mohammad Izzat Zulkifli Miss Nurul Ashikin Roslan Miss Siti Nur Athirah Mohd Azhar School of Medical Imaging Faculty of Health Sciences Universiti Sultan Zainal Abidin Terengganu Malaysia Centre of Multimedia Studies Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Terengganu Malaysia Centre of Information Technology Faculty of Informatics and Computing Terengganu Malaysia

Background Cardiac imaging is a specialized branch of medical imaging that focuses on capturing detailed images of the heart. The coronary angiography procedure is one of the cardiac imaging techniques where radiographers use different angles and projections to get a comprehensive view of the coronary arteries in the heart and assess any potential blockages or abnormalities. Radiography student needs to grasp the theoretical and practical knowledge of these procedures before attending their clinical attachments and working in the field. However, the current teaching relies on static visualization (eg. still illustrations and photographs) which is insufficient to deliver the complex concepts in cardiac imaging. Practical sessions are challenging due to the limited access to the facility and involve ionizing radiation. Integrating 3D models and animations into e-learning for teaching cardiac imaging can significantly enhance the learning experience and provide an immersive and interactive environment. Methods 3D models and animations were developed using Autodesk Maya software from creating 3D models to animations and rendering of coronary angiography procedures demonstrating different angles and projections. Results 3D models and animations provide a dynamic visualization of the complex imaging procedure. All animations also provide a short description of each angulation, projection, and image, as well as other important notes related to clinical applications and scenarios. This allows students to learn the real-life scenarios and situations they might encounter in imaging patients in the hospital. This study could be extended for visualization in augmented reality (AR) where students can turn the 3D models around and manipulate the model in their own hands to perform the coronary angiography procedure. Conclusion 3D models and animations in cardiac imaging education simplify abstract processes and enhance understanding, in line with the needs of the current generati

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized efficient attention-based network for facial expressions analysis in neurological health care

引用

Computers in Biology and Medicine 2024年 179卷 108822-108822页

作者： Munsif, Muhammad Sajjad, Muhammad Ullah, Mohib Tarekegn, Adane Nega Cheikh, Faouzi Alaya Tsakanikas, Panagiotis Muhammad, Khan Sejong University Seoul143-747 Korea Republic of Digital Image Processing Lab Department of Computer Science Islamia College Peshawar25000 Pakistan Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Institute of Communication and Computer Systems National Technical University of Athens Athens15773 Greece Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

Facial Expression Analysis (FEA) plays a vital role in diagnosing and treating early-stage neurological disorders (NDs) like Alzheimer's and Parkinson's. Manual FEA is hindered by expertise, time, and training requirements, while automatic methods confront difficulties with real patient data unavailability, high computations, and irrelevant feature extraction. To address these challenges, this paper proposes a novel approach: an efficient, lightweight convolutional block attention module (CBAM) based deep learning network (DLN) to aid doctors in diagnosing ND patients. The method comprises two stages: data collection of real ND patients, and pre-processing, involving face detection and an attention-enhanced DLN for feature extraction and refinement. Extensive experiments with validation on real patient data showcase compelling performance, achieving an accuracy of up to 73.2%. Despite its efficacy, the proposed model is lightweight, occupying only 3MB, making it suitable for deployment on resource-constrained mobile healthcare devices. Moreover, the method exhibits significant advancements over existing FEA approaches, holding tremendous promise in effectively diagnosing and treating ND patients. By accurately recognizing emotions and extracting relevant features, this approach empowers medical professionals in early ND detection and management, overcoming the challenges of manual analysis and heavy models. In conclusion, this research presents a significant leap in FEA, promising to enhance ND diagnosis and *** code and data used in this work are available at: https://***/munsif200/Neurological-Health-Care. © 2024 Elsevier Ltd

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SGUQ: Staged Graph Convolution Neural Network for Alzheimer’s Disease Diagnosis using Multi-Omics Data

arXiv

引用

arXiv 2024年

作者： Tao, Liang Xie, Yixin Deng, Jeffrey D. Shen, Hui Deng, Hong-Wen Zhou, Weihua Zhao, Chen Department of Computer Science Kennesaw State University MariettaGA30060 United States Department of Information Technology Kennesaw State University MariettaGA30060 United States Geisel School of Medicine Dartmouth College Hamover NH03755 United States Division of Biomedical Informatics and Genomics Tulane Center of Biomedical Informatics and Genomics Deming Department of Medicine Tulane University New OrleansLA70112 United States Department of Applied Computing Michigan Technological University HoughtonMI49931 United States Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States

Alzheimer’s disease (AD) is a chronic neurodegenerative disorder and the leading cause of dementia, significantly impacting cost, mortality, and burden worldwide. The advent of high-throughput omics technologies, such as genomics, transcriptomics, proteomics, and epigenomics, has revolutionized the molecular understanding of AD. Conventional AI approaches typically require the completion of all omics data at the outset to achieve optimal AD diagnosis, which are inefficient and may be unnecessary. To reduce the clinical cost and improve the accuracy of AD diagnosis using multi-omics data, we propose a novel staged graph convolutional network with uncertainty quantification (SGUQ). SGUQ begins with mRNA and progressively incorporates DNA methylation and miRNA data only when necessary, reducing overall costs and exposure to harmful tests. Experimental results indicate that 46.23% of the samples can be reliably predicted using only single-modal omics data (mRNA), while an additional 16.04% of the samples can achieve reliable predictions when combining two omics data types (mRNA + DNA methylation). In addition, the proposed staged SGUQ achieved an accuracy of 0.858 on ROSMAP dataset, which outperformed existing methods significantly. The proposed SGUQ can not only be applied to AD diagnosis using multi-omics data, but also has the potential for clinical decision making using multi-viewed data. Our implementation is publicly available at https://***/chenzhao2023/multiomicsuncertainty. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Community detection in networks using graph embeddings

引用

Physical Review E 2021年第2期103卷 022316-022316页

作者： Aditya Tandon Aiiad Albeshri Vijey Thayananthan Wadee Alhalabi Filippo Radicchi Santo Fortunato Luddy School of Informatics Computing and Engineering Indiana University Bloomington Indiana 47408 USA Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Kingdom of Saudi Arabia Indiana University Network Science Institute (IUNI) Bloomington Indiana 47408 USA

Graph embedding methods are becoming increasingly popular in the machine learning community, where they are widely used for tasks such as node classification and link prediction. Embedding graphs in geometric spaces should aid the identification of network communities as well because nodes in the same community should be projected close to each other in the geometric space, where they can be detected via standard data clustering algorithms. In this paper, we test the ability of several graph embedding techniques to detect communities on benchmark graphs. We compare their performance against that of traditional community detection algorithms. We find that the performance is comparable, if the parameters of the embedding techniques are suitably chosen. However, the optimal parameter set varies with the specific features of the benchmark graphs, like their size, whereas popular community detection algorithms do not require any parameter. So, it is not possible to indicate beforehand good parameter sets for the analysis of real networks. This finding, along with the high computational cost of embedding a network and grouping the points, suggests that, for community detection, current embedding techniques do not represent an improvement over network clustering algorithms.

关键词： Community structure Complex systems

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：