检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Design, Modeling and Simulation of Cybercriminal Personality-Based Cyberattack Campaigns 24

Design, Modeling and Simulation of Cybercriminal Personality...

引用

Proceedings of the Winter Simulation Conference

作者： Jeongkeun Shin Geoffrey B. Dobson L. Richard Carley Kathleen M. Carley Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA Software and Societal Systems Department Carnegie Mellon University Pittsburgh PA USA Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA and Software and Societal Systems Department Carnegie Mellon University Pittsburgh PA USA

ISBN: (纸本)9798331534202

Cybersecurity challenges are inherently complex, characterized by both advanced technical elements and complex aspects of human cognition. Although extensive research has explored how victims' human factors affect their susceptibility to cyberattacks, the influence of cybercriminals' personalities on the pattern of cyberattack campaigns and the resulting damage to organizations has not received equivalent attention. To bridge this research gap through computer simulation, we introduce a cyberattack campaign designer that enables modelers to construct cyberattack campaigns. This tool allows modelers to define how the process or pattern of the cyberattack campaign can change based on the cybercriminal's personality and simulates how these personality differences influence the magnitude of cyberattack damage on the target organization. In this paper, through computer simulation, we demonstrate how cautious and reckless personalities result in variations in the cyberattack pattern and, consequently, affect the magnitude of cyberattack damage, despite identical cyberattack objectives and techniques used at each step.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Potential of Large Language Models

引用

Informatica (Slovenia) 2024年第8期48卷 1-16页

作者： Prasad, Shreya Gupta, Himank Ghosh, Arup Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Information Technology Graceland University LamoniIA United States

This study focuses on enhancing Natural Language Processing (NLP) in generative AI chatbots through the utilization of advanced pre-trained models. We assessed five distinct Large Language Models (LLMs): TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B, and LLAMA-2-13B to identify the most effective one. Our findings revealed that the LLAMA Model excels in comprehending user queries and delivering precise responses during conversations. The article elucidates the methodology employed to evaluate and select various models for our chatbot. Through rigorous testing, we determined that the LLAMA-2-13B model exhibits enhanced response time and accuracy. Additionally, we employed tools such as Facebook Artificial Intelligence Similarity Search (FAISS) and experimented with user interfaces like Streamlit and Chainlit to enhance the chatbot's user-friendliness. The research underscores the significance of selecting the appropriate model for crafting efficient chatbots. Ultimately, the LLAMA-13B model emerged as the standout performer, showcasing superior performance. Benchmark assessments, including HellaSwag and WinoGrande, which gauge common sense reasoning, were employed to evaluate our chatbot's capabilities. The study concludes that LLAMA-based models hold significant promise for the development of innovative and user-friendly chatbots in the future. Povzetek: Študija se osredotoča na izboljšanje obdelave naravnega jezika (NLP) v generativnih AI klepetalnicah z uporabo naprednih vnaprej usposobljenih modelov. Analizirali so pet modelov: TRANSFORMER MODEL, FALCON 7B, LAMINI-FLAN-T5-783M, LLAMA-2-7B in LLAMA-2-13B. Model LLAMA-13B se je izkazal kot najboljši z vrhunskimi rezultati na testih HellaSwag in WinoGrande. Raziskava uporablja orodja, kot je FAISS, in uporabniške vmesnike, kot sta Streamlit in Chainlit za izboljšanje uporabniške izkušnje. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Detection of Cardiovascular Diseases Using ECG Images

Deep Learning Based Detection of Cardiovascular Diseases Usi...

引用

International Conference on Communication and Electronics systems (ICCES)

作者： P Ananthi K Nirmala Devi Pradisa. T Department of Computer Technology Kongu Engineering College Perundurai TamilNadu Department of Computer Science(PG) Kristu Jayanti College Bangaluru MSc Software Systems Kongu Engineering College Perundurai TamilNadu

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

In today's world, cardiovascular disease is still a major concern. The electrocardiogram (ECG) is one of the most trustworthy non-invasive tools for identifying heart problems. ECG interpretation, however, takes a lot of effort and specialized knowledge. The quality and effectiveness of medical care are enhanced by the development of a revolutionary technique for early disease detection. Using a public dataset of ECG scans from cardiac patients, this study leveraged deep learning algorithms to predict two primary cardiac abnormalities: abnormal heartbeat and normal person classes. The low-scale pre-trained deep neural Alex Net was used to study the transfer learning process. To forecast cardiac issues, a novel Convolutional Neural Network (CNN) architecture was put out. We used the conventional deep learning methods, VGG-16, Resnet50, RNN, and LSTM, to feature-extracted data utilizing the previously mentioned pre-trained models and our suggested LSTM model. The experimental results show that the LSTM model outperforms the previous attempts in terms of performance measures.

关键词： Deep learning Transfer learning Medical services Electrocardiography Prediction algorithms Data models Convolutional neural networks Cardiovascular diseases Long short term memory Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Chest Radiographs Based Pneumothorax Detection Using Federated Learning

引用

computer systems Science & engineering 2023年第11期47卷 1775-1791页

作者： Ahmad Almadhor Arfat Ahmad Khan Chitapong Wechtaisong Iqra Yousaf Natalia Kryvinska Usman Tariq Haithem Ben Chikha Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand School of Telecommunication Engineering Suranaree University of TechnologyNakhon Ratchasima30000Thailand Department of Computer Science and Software Engineering International Islamic UniversityIslamabadPakistan Information Systems Department Faculty of ManagementComenius University in BratislavaOdbojárovBratislava440Slovakia Prince Sattam bin Abdulaziz University AlKharjSaudi Arabia

Pneumothorax is a thoracic condition that occurs when a person’s lungs collapse,causing air to enter the pleural cavity,the area close to the lungs and chest *** most persistent disease,as well as one that necessitates particular patient care and the privacy of their health *** radiologists find it challenging to diagnose pneumothorax due to the variations in *** learning-based techniques are commonly employed to solve image categorization and segmentation ***,it is challenging to employ it in the medical field due to privacy issues and a lack of *** address this issue,a federated learning framework based on an Xception neural network model is proposed in this *** pneumothorax medical image dataset is obtained from the Kaggle *** preprocessing is performed on the used dataset to convert unstructured data into structured information to improve the model’s ***-max normalization technique is used to normalize the data,and the features are extracted from chest Xray *** dataset converts into two windows to make two clients for local model *** neural network model is trained on the dataset individually and aggregates model updates from two clients on the server *** decrease the over-fitting effect,every client analyses the results three *** 1 performed better in round 2 with a 79.0%accuracy,and client 2 performed better in round 2 with a 77.0%*** experimental result shows the effectiveness of the federated learning-based technique on a deep neural network,reaching a 79.28%accuracy while also providing privacy to the patient’s data.

关键词： Privacy preserving pneumothorax disease federated learning chest x-ray images healthcare machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Brain-Brake: A Hybrid Brain-Operated computer Vision-Enabled System for Collision Avoidance

Brain-Brake: A Hybrid Brain-Operated Computer Vision-Enabled...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Omar Hatem Omar Sheta Abdallah Abdelaziz Ali Ashraf Hashem El Maleeh Mohamed Ali Mariam Gadallah Muhammad Habash Ahmed Moro Seif Eldawlatly Computer Science and Engineering Department The American University in Cairo Cairo Egypt Siemens Digital Industries Software Cairo Egypt Computer and Systems Engineering Department Ain Shams University Cairo Egypt

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

A major challenge in daily automotive use is the high incidence of car accidents, primarily attributed to human errors. This paper introduces Brain-Brake, an innovative brain-operated advanced driver-assistance system (ADAS) designed for collision avoidance. Utilizing electroencephalography (EEG) signals, Brain-Brake detects a driver's braking intention faster than traditional methods, addressing critical reaction time delays. It integrates a computer vision module that measures the proximity of objects to the vehicle, complementing the EEG- based intention detection for enhanced reliability. Implemented on embedded chips using the AUTOSAR framework, preliminary results indicate a significant reduction in reaction times during emergency braking scenarios, highlighting the system's potential to enhance road safety significantly.

关键词： computer vision Semiconductor device measurement Protocols Embedded systems Delay effects Force Electroencephalography Road safety Reliability Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

KRATT: QBF-Assisted Removal and Structural Analysis Attack Against Logic Locking

KRATT: QBF-Assisted Removal and Structural Analysis Attack A...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Levent Aksoy Muhammad Yasin Samuel Pagliarini Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Computer and Software Engineering National University of Sciences and Technology Islamabad Pakistan Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh USA

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

This paper introduces KRATT, a removal and structural analysis attack against state-of-the-art logic locking techniques, such as single and double flip locking techniques (SFLTs and DFLTs). KRATT utilizes powerful quantified Boolean formulas (QBFs), which have not found widespread use in hardware security, to find the secret key of SFLTs for the first time. It can handle locked circuits under both oracle-less (OL) and oracle-guided (OG) threat models. It modifies the locked circuit and uses a prominent OL attack to make a strong guess under the OL threat model. It uses a structural analysis technique to identify promising protected input patterns and explores them using the oracle under the OG model. Experimental results on ISCAS'85, ITC'99, and HeLLO: CTF'22 benchmarks show that KRATT can break SFLTs using a QBF formulation in less than a minute, can decipher a large number of key inputs of SFLTs and DFLTs with high accuracy under the OL threat model, and can easily find the secret key of DFLTs under the OG threat model. It is shown that KRATT outperforms publicly available OL and OG attacks in terms of solution quality and run-time.

关键词： Threat modeling Analytical models Hardware security Circuits Benchmark testing Complexity theory Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs 37

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Ve...

引用

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Cobb, Adam D. Roy, Anirban Elenius, Daniel Heim, F. Michael Swenson, Brian Whittington, Sydney Walker, James D. Bapty, Theodore Hite, Joseph Ramani, Karthik McComb, Christopher Jha, Susmit Computer Science Laboratory SRI International United States Mechanical Engineering Division Southwest Research Institute United States Intelligent Systems Division Southwest Research Institute United States Institute of Software Integrated Systems Vanderbilt University United States School of Mechanical Engineering Purdue University United States Department of Mechanical Engineering Carnegie Mellon University United States

ISBN: (纸本)9781713899921

We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these cyber-physical system (CPS) designs requires the use of scientific analytical and simulation models ranging from computer-aided design tools for structural and manufacturing analysis, computational fluid dynamics tools for drag and lift computation, battery models for energy estimation, and simulation models for flight control and dynamics. AircraftVerse contains 27, 714 diverse air vehicle designs - the largest corpus of engineering designs with this level of complexity. Each design comprises the following artifacts: a symbolic design tree describing topology, propulsion subsystem, battery subsystem, and other design details;a STandard for the Exchange of Product (STEP) model data;a 3D CAD design using a stereolithography (STL) file format;a 3D point cloud for the shape of the design;and evaluation results from high fidelity state-of-the-art physics models that characterize performance metrics such as maximum flight distance and hover-time. We also present baseline surrogate models that use different modalities of design representation to predict design performance metrics, which we provide as part of our dataset release. Finally, we discuss the potential impact of this dataset on the use of learning in aircraft design and, more generally, in CPS. AircraftVerse is accompanied by a data card, and it is released under Creative Commons Attribution-ShareAlike (CC BY-SA) license. The dataset is hosted at https://***/record/6525446, baseline models and code at https://***/SRI-CSL/AircraftVerse, and the dataset description at https://***/. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： computer aided logic design

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intrusion Detection for IoT Networks

Deep Learning Based Intrusion Detection for IoT Networks

引用

Ubiquitous Computing and Intelligent Information systems (ICUIS), International Conference on

作者： P. Ananthi K. Nirmaladevi Mothika G Department of Computer Technology-PG Kongu Engineering College Erode Tamilnadu Department of Computer Applications Madanapalle Institute of Technology &Science MSc Software Systems Kongu Engineering College Erode India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Intrusion detection is crucial for securing IoT networks amid the rapid proliferation of devices, posing significant security challenges. This study offers a unique intrusion detection model for IoT deep learning methods used in networks include Convolutional Neural Networks (CNN), TabNet, and the Transient Search Optimization (TSO) method. The project starts by developing and evaluating distinct intrusion detection components. CNN, specializing in feature extraction, analyzes network traffic for potential intrusions. TabNet, known for interpretability and effectiveness with structured data, captures intricate relationships. The novel TSO algorithm improves the system's ability to detect temporary anomalies. Each component's performance is assessed individually, highlighting unique strengths. TabNet excels in structured IoT data pattern identification, surpassing CNN. The TSO algorithm strengthens temporary anomaly recognition, enhancing IoT network security. An ensemble technique combines CNN and TabNet predictions, reducing false positives and negatives to elevate overall detection accuracy. The ensemble, using both CNN and TabNet, achieves an impressive accuracy rate exceeding 99%, demonstrating significant gains in intrusion detection performance.

关键词： Deep learning Accuracy Intrusion detection Telecommunication traffic Prediction algorithms Ubiquitous computing Convolutional neural networks Internet of Things Transient analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Simulating the Effects of Multi-platform Use on Misinformation Diffusion and Countermeasures 25

Simulating the Effects of Multi-platform Use on Misinformati...

引用

Proceedings of the 17th ACM Web Science Conference 2025

作者： Isabel Murdock Kathleen M. Carley Osman Yagan Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA Software and Societal Systems Carnegie Mellon University Pittsburgh PA USA

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：