检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Sun, Xiangguo Cheng, Hong Li, Jia Liu, Bo Guan, Jihong Department of Systems Engineering and Engineering Management Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China School of Computer Science and Engineering Southeast University Purple Mountain Laboratories China Department of Computer Science and Technology Tongji University China

Recently, "pre-training and fine-tuning" has been adopted as a standard workflow for many graph tasks since it can take general graph knowledge to relieve the lack of graph annotations from each application. However, graph tasks with node level, edge level, and graph level are far diversified, making the pre-training pretext often incompatible with these multiple tasks. This gap may even cause a "negative transfer" to the specific application, leading to poor results. Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks. In this paper, we propose a novel multi-task prompting method for graph models. Specifically, we first unify the format of graph prompts and language prompts with the prompt token, token structure, and inserting pattern. In this way, the prompting idea from NLP can be seamlessly introduced to the graph area. Then, to further narrow the gap between various graph tasks and state-of-the-art pre-training strategies, we further study the task space of various graph applications and reformulate downstream problems to the graph-level task. Afterward, we introduce meta-learning to efficiently learn a better initialization for the multi-task prompt of graphs so that our prompting framework can be more reliable and general for different tasks. We conduct extensive experiments, results from which demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Effective Hybrid Precoder Logic with mm Wave Massive MIMO using Novel Deep Learning Scheme

Effective Hybrid Precoder Logic with mm Wave Massive MIMO us...

引用

International Conference on science Technology engineering and Management (ICONSTEM)

作者： Ranjith S P Jesu Jayarin A. Chandra Sekar Department of Electronics and Communication Engineering Jeppiaar Engineering College Chennai Tamilnadu India Department of Data Analytics Institute of IT Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences(SIMATS) Chennai India Department of Computer Science Engineering St. Joseph’s College of Engineering Chennai Tamilnadu India

For establishing a high efficient signal communications, a Millimeter-Wave-Massive-MIMO (mmWave-MMIMO) logics are helpful and more speculated. Although current hybrid precoding schemes are computationally complex, however, they are not using all of the spatial details. The combination of analog and digital precoding logics are considered to be a significant methodology to deal with complexities over hardware area and the higher consumption of energy in association with combination of signal elements. But the basic degradation of the traditional hybrid-precoding methodologies has some issues such as processing complexities and has a lacking to explore the spatial data regarding the channels. To address these limitations, this paper suggests a Novel Deep Learning Scheme (NDLS), in which it is enabled by mmWave-MMIMO system for successful Hybrid Precoder Logic (HDL). As well as each Precoder selection is used to obtain the The optimised-decoder is perceived in the Novel Deep Learning Scheme as a mapping relation. To be more precise, a Hybrid Precoder Logic is extracted via Novel Deep Learning Scheme training for optimizing the Millimeter- Wave-Massive-MIMO precoding method. Additionally, a detailed simulation results are presented to demonstrate the proposed scheme's superior efficiency and the resulting section demonstrate that the Novel Deep Learning Scheme based methodology is competent of lowering the Bit-Error- Rate (BER) and increasing the effectiveness of the frequency of Millimeter-Wave Massive-MIMO (mmWave- MMIMO), gaining a competitive advantage in faster convergence as compared to traditional schemes while significantly reducing the necessary computational difficulty.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Decentralized Identity Verification Systems Using Blockchain Technology: Opportunities and Challenges

Exploring Decentralized Identity Verification Systems Using ...

引用

Global Conference for Advancement in Technology (GCAT)

作者： V. Saravanan Sumalatha A Desidi Narsimha Reddy B. Shamreen Ahamed Udayakumar K Arthi Priyadharshini M Department of Nano Electronics Materials and Sensors Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of Computer Science Kristu Jayanti College Autonomous Bengaluru Data Consultant (Data Governance Data Analytics: Enterprise Performance Management AI&ML) Soniks Consulting LLC Texas USA Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Jeppiaar Nagar Chennai Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology India Department of CSE Dhanalakshmi College of Engineering Chennai

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

The rapid advancement of digital technologies has underscored the critical necessity for robust and reliable identity verification systems in today's interconnected world. Traditional centralized identity management systems encounter myriad challenges, from vulnerabilities to data breaches and privacy concerns, to inefficiencies inherent in verification processes. This paper delves into the transformative potential of decentralized identity verification systems using blockchain technology as a robust solution to these pressing issues. By harnessing blockchain's immutable, transparent, and secure characteristics, decentralized identity systems not only promise enhanced privacy, security, and user control over personal data but also foster a paradigm shift towards more efficient and user-centric identity management *** study rigorously examines the foundational principles of blockchain technology and its strategic application in decentralized identity verification. It highlights key opportunities such as strengthened security measures through cryptographic protocols, enhanced user autonomy in managing and sharing personal information, and streamlined verification processes that reduce operational complexities and costs. Additionally, the paper critically evaluates significant challenges that must be addressed, including scalability concerns as blockchain networks grow, complexities in navigating regulatory landscapes designed for centralized systems, and overcoming barriers to widespread user adoption. Through an exhaustive analysis of existing models, real-world case studies, and emerging trends, this paper aims to provide comprehensive insights into the feasibility and future prospects of decentralized identity verification systems. By contributing to the ongoing discourse on innovative identity management solutions in the digital age, this research seeks to pave the way for more secure, efficient, and equitable digital ecosystems.

关键词： data privacy Navigation Scalability Pressing Market research Blockchains Complexity theory Security Reliability Identity management systems

来源：评论

学校读者我要写书评

暂无评论

A Note on the Evaluation of Mutation Prioritization Algorithms

A Note on the Evaluation of Mutation Prioritization Algorith...

引用

IEEE Symposium Series on Computational Intelligence

作者： Dusan Popovic Jesse Davis Alejandro Sifrim Bart De Moor STADIUS Center for Dynamical Systems Signal Processing and Data Analytics Department of Electrical Engineering (ESAT) KU Leuven Department of Computer Science KU Leuven Wellcome Trust Sanger Institute Wellcome Trust Genome Campus

ISBN: (纸本)9781479975617

Recent developments in the field of gene sequencing technology greatly accelerated discovery of mutations that cause various genetic disorders. At the same time, a typical sequencing experiment generates a large number of candidate mutations, hence detecting single or few causative variants is still a formidable problem. Many computational methods have been proposed to assist this process, from which a large portion employ statistical learning in some form. Consequently, each newly designed algorithm is routinely compared to other competing systems in hope to demonstrate advantageous performance. In this work we review and discuss several issues related to the current practice of evaluation of mutation prioritization algorithms and suggest possible directions for improvements.

关键词： Statistical learning Hereditary Diseases Mutation Hopefulness algorithms Base Sequence Design Algorithm Note Taking computational methods

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning for Software Supply Chain Attacks: How Far Can We Go?

Quantum Machine Learning for Software Supply Chain Attacks: ...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Mohammad Masum Mohammad Nazim Md Jobair Hossain Faruk Hossain Shahriar Maria Valero Md Abdullah Hafiz Khan Gias Uddin Shabir Barzanjeh Erhan Saglamyurek Akond Rahman Sheikh Iqbal Ahamed Analytics and Data Science Institute Kennesaw State University USA Department of Computer Science Kennesaw State University USA Department of Software Engineering and Game Development Kennesaw State University USA Department Information Technology Kennesaw State University USA Electrical and Software Engineering Institute for Quantum Science and Technology University of Calgary Canada Department of Computer Science Tennessee Tech University USA Department of Computer Science Marquette University USA

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

Quantum Computing (QC) has gained immense popularity as a potential solution to deal with the ever-increasing size of data and associated challenges leveraging the concept of quantum random access memory (QRAM). QC promises-quadratic or exponential increases in computational time with quantum parallelism and thus offer a huge leap forward in the computation of Machine Learning algorithms. This paper analyzes speed up performance of QC when applied to machine learning algorithms, known as Quantum Machine Learning (QML). We applied QML methods such as Quantum Support Vector Machine (QSVM), and Quantum Neural Network (QNN) to detect Software Supply Chain (SSC) attacks. Due to the access limitations of real quantum computers, the QML methods were implemented on open-source quantum simulators such as IBM Qiskit and TensorFlow Quantum. We evaluated the performance of QML in terms of processing speed and accuracy and finally, compared with its classical counterparts. Interestingly, the experimental results differ to the speed up promises of QC by demonstrating higher computational time and lower accuracy in comparison to the classical approaches for SSC attacks.

关键词： computers Machine learning algorithms Supply chains Neural networks Qubit Software algorithms Support vector machine classification

来源：评论

学校读者我要写书评

暂无评论

Colon Cancer Tissue Classification Using ML

Colon Cancer Tissue Classification Using ML

引用

International Conference on Information Systems and computer Networks (ISCON)

作者： Ashish Tripathi Kuldeep Kumar Anuradha Misra Brijesh Kumar Chaurasia Department of Computer Science and Engineering Amity School of Engineering & Technology Amity University Lucknow Lucknow Uttar Pradesh India Center for Data Analytics Bond Business School Bond University Gold Coast Queensland Australia Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur Uttar Pradesh India

In this paper, the classification of colon cancer tissues by means of machine learning approaches is evaluated. In today’s world, a revolutionary advancement has come in the classification and diagnosis of diseases in the medical and healthcare sectors. Deep learning classifiers and machine learning methods are now broadly applied to accurately diagnose a number of diseases. Cancer is one of the world’s most significant roots of death, appealing to the lives of one person out of every six. As per the national library of medicine, the third leading cause of death worldwide is colorectal cancer. Identifying an illness at a premature stage increases the chances of survival. Automated diagnosis and the classification of tissues from images can be completed much more quickly with the use of artificial intelligence. A publicly available IoT dataset CRC–VAL–HE–7K consisting of 7180 images, distributed among nine types of colorectal tissues: background, lymphocytes, adipose, mucus, colorectal adenocarcinoma epithelium, normal colon mucosa, debris, cancer-associated stroma, and, smooth muscle is used after preprocessing. Feature extraction is done by applying Differential-Box-Count on all blocks of images. The dataset is evaluated by these Machine Learning (ML) procedures: K-Nearest Neighbor, Support Vector Machine, Decision Tree, Random Forest, Extreme Gradient Boosting, and Gaussian Naive Bayes. Results show that the performance of Extreme Gradient Boosting is the best and most viable approach.

关键词： Deep learning Support vector machines Machine learning algorithms Transfer learning Feature extraction Boosting Colon

来源：评论

学校读者我要写书评

暂无评论

Improved Dictionary Learning for FMRI data Analysis Capturing Common and Individual Activation Maps

Improved Dictionary Learning for FMRI Data Analysis Capturin...

引用

Asilomar Conference on Signals, Systems & computers

作者： Shuai Xu Rui Jin Seung-Jun Kim Tülay Adali Vince D. Calhoun Department of Computer Science and Electrical Engineering University of Maryland Baltimore County USA Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology and Emory University USA

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

A dictionary learning (DL)-based method for mul-tisubject functional magnetic resonance imaging (fMRI) data analysis is proposed. The method can incorporate group attributes to find the neural activation maps that are common across groups as well as those that are explanatory of the group differences. The key contribution is to significantly improve the map estimation performance by mitigating undesirable local optima obtained from a supervised DL formulation for fMRI data analysis. We introduce two novel ideas, namely, developing a variant of Fisher's discriminant cost, which is imposed on the non-discriminative features, and optimally permuting the dictionary and the sparse factor such that the solution is not trapped to unwanted local optima. Preliminary tests on synthetic and real data sets verify the effectiveness of the proposed approach.

关键词： computers data analysis Dictionaries Costs Estimation Machine learning Functional magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Dermatological Diagnostics: A Unified Deep Learning Framework for Skin Lesion and Cancer Classification

Dermatological Diagnostics: A Unified Deep Learning Framewor...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Vinod Kumar Isha Jain Durga Sritha Dongla Shivangi Rai Vani Rastogi Eva Kaushik Rohit Kaushik School of Engineering & Applied Science The George Washington University Washington D.C USA Computer Science & Engineering Department Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Computer Science & Engineering Department Gandhi Institute of Technology and Management Visakhapatnam Andhra Pradesh Data Scientist DXC Technology Noida India CS and Mathematics Department Data Analytics Program University of Illinois Springfield USA

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Skin pathologies encompass a spectrum of conditions, with malignancies such as melanoma representing a critical diagnostic urgency. This investigation delineates the deployment of Convolutional Neural Networks (CNNs) for the classification of dermatological anomalies, benchmarking CNN diagnostic fidelity against dermatological expert evaluations. The study underscores the efficacy of CNN classifiers in expediting the diagnostic workflow for various cutaneous disorders. Advocating for an automated diagnostic framework, the research introduces a CNN-based system aimed at reducing human diagnostic load, accelerating diagnostic timelines, and enhancing survival outcomes. Utilizing advanced image processing algorithms and deep learning architectures, the research presents an automated classification system for skin pathologies, addressing both benign and malignant presentations. The classification matrix includes nine dermatological conditions: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, nevus, seborrheic keratosis, squamous cell carcinoma, and vascular lesions. The objective is to engineer a CNN model with robust diagnostic performance across a diverse lesion dataset, ensuring accurate identification and categorization of dermatological conditions.

关键词： Deep learning Pathology Accuracy Melanoma computer architecture Benchmark testing Skin Convolutional neural networks Lesions Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid AI Framework for Real-Time Prediction and Risk Assessment of Vector-Borne Epidemics using Spatiotemporal data

A Novel Hybrid AI Framework for Real-Time Prediction and Ris...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Rajesh Munirathnam Meenakshi Maindola Bhargav H K Prachi Ramesh Patil Pooja Bhatt Natrayan L Data & Analytics Division TechnoGen Inc. New Jersey USA Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering Shridevi Institute of Engineering and Technology Industry Institute Interaction Cell(IIIC) Tumakuru India Department of Electronics and Telecommunication Engineering Jagdambha College of Engineering and Technology Yavatmal India Department of Computer science and Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Vadodara India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

Vector-borne epidemics constitute major threats to global health that call for improved modeling systems for managing diseases. In order to incorporate such factors into an actual model, a traditional forecasting process may fail to grasp the nature of disease transmission adequately. We present a hybrid AI system based on LSTM and GCN for forest bug outbreak detection in real time. The framework also integrated a spatial-temporal analysis of climate variability, vector population fluctuations, and human mobility with climate variables across 15 regions over a five-year period (2019–2023). The hybrid framework also produced superior results, achieving a 94.2% prediction rate for health risk disease outbreaks, compared to a 17.3% improvement in traditional machine learning. When used to distinguish between high-risk and low-risk zones, the model demonstrated the following metrics: sensitivity of 92.8% and specificity of 95.1%. Real-time risk assessment demonstrated 89.6% effectiveness in indicating early warning and the best prediction lead time average of 21 days. This framework significantly enhances the prediction of vector-borne diseases by offering a dependable, real-time platform for disease surveillance and risk assessment. Its high accuracy and early warning capabilities make the system a useful tool in epidemiological and public health campaigns and control measures.

关键词： Epidemics Accuracy Surveillance Real-time systems Vectors Spatiotemporal phenomena Risk management Public healthcare Long short term memory Diseases

来源：评论

学校读者我要写书评

暂无评论

Study of deep learning techniques for medical image analysis: A review

引用

Materials Today: Proceedings 2022年 56卷 209-214页

作者： Ayush Singhal Manu Phogat Deepak Kumar Ajay Kumar Mamta Dahiya Virendra Kumar Shrivastava Department of Computer Science Engineering Faculty of Engineering and Technology Shree Guru Gobind Singh Tricentenary University Gurugram 122505 Haryana India Department of Mechanical Engineering Faculty of Engineering & Technology Shree Guru Gobind Singh Tricentenary University Gurugram 122505 Haryana India Department of Big Data Analytics Adani Institute of Digital Technology Management Gandhinagar Gujarat 382423 India

Now, there is a lot of research going on in the field of medical image analysis by using deep convolutional networks. Deep learning uses various models to extract the information from the images provided to deep learning model. The deep learning is now widely used in the field of medical to detect and diagnose the disease and after diagnosing classifying it into particular category of the disease. The most widely model used for medical image analysis is Convolutional neural network. So, this review paper focusses on how deep learning uses deep networks to detect the disease by retrieving or extracting the information from the images provided to the network and also give information about the clinical applications in the medical fields and the limitations of deep learning in image analysis process is also highlighted.

关键词： Deep learning Medical image analysis Convolutional neural network

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：