检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Anders, Christopher J. Neumann, David Samek, Wojciech Müller, Klaus-Robert Lapuschkin, Sebastian Machine Learning Group Department of Electrical Engineering and Computer Science Technische Universität Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Fraunhofer Heinrich Hertz Institute Berlin Germany Machine Learning and Communications Group Department of Electrical Engineering and Computer Science Technische Universität Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institut für Informatik Saarbrücken Germany

Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable artificial intelligence (XAI), approaches are available to explore the reasoning behind those complex models’ predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore model reasoning using attribution approaches and beyond: (1) Zennit – a highly customizable and intuitive attribution framework implementing LRP and related approaches in PyTorch, (2) CoRelAy – a framework to easily and quickly construct quantitative analysis pipelines for dataset-wide analyses of explanations, and (3) ViRelAy – a web-application to interactively explore data, attributions, and analysis results. With this, we provide a standardized implementation solution for XAI, to contribute towards more reproducibility in our field. © 2021, CC BY-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Holographic Convolutional Network for Speech Emotion Recognition Using Korean Audio

Two-Stream Holographic Convolutional Network for Speech Emot...

引用

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

作者： N. Venkateswaran Balaji. Mudadla R. Rajitha Jasmine J Nalini M Rajasekar T. Jayasudha Department of Master of Business Administration Panimalar Engineering College Chennai Tamil Nadu India Department of Computer Science And Engineering (Artificial Intelligence & Machine Learning) CMR Technical Campus Hyderabad Telangana India Department of Information Technology R.M.K. Engineering College Kavaraipettai Tamil Nadu India Department of Computer Science Vignan's Institute of Engineering for Women Visakhapatnam Andhra Pradesh India Department of Computer Science And Application Saveetha College of Liberal arts and Sciences Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of English KPR Institute of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Speech Emotion Recognition (SER) has become an important area of research in the AI domain, helping systems comprehend people's feelings with speech, in such areas as healthcare, automated customer support, and virtual companionship. Emotion detection from Korean speech raises learning issues and demand an understanding of all high-frequency spectrum and time selective features. Despite that these layers work effectively, typical convolutional networks may lose phase information which is so important for emotion distinction especially in languages with tone and phonetics. For this research, the AI-Hub Speech Emotional Database, a large scale Korean speech dataset, is employed to create a Two-Stream Holographic Convolutional Network (TSHCN) for SER. However, the TSHCN architecture employed a two-path structure in which one branch encoded the spectral feature and the other branch encoded the temporal dynamics in sequence, while the phase information was retained using holodynamic convolutions for better classification of emotions. In order to increase the efficiency of the model, the Kookaburra Optimization Algorithm (KOA) is used on the parameters of the weight network, reducing the number of mistakes and the load of calculations as well as increasing the accuracy of the model. As more evident from the previously discussed results, SER performance is notably enhanced by the use of TSHCN with KOA; specifically, the accurate representation of Korean speakers' speech emotions will help pave the way for the development of SER for the Korean language and other complex languages as well. This study thus takes up the shortcoming in the conventional approaches to the task and proposes an optimal and language-independent SER model. The introduced approach attains higher accuracy as 99%.

关键词： Emotion recognition Accuracy Speech recognition Computer architecture Medical services Phonetics Feature extraction Convolutional neural networks Optimization Load modeling

来源：评论

学校读者我要写书评

暂无评论

Brain Cancer Tumor Detection by U-Net Deep learning Algorithm from MRI Images

Brain Cancer Tumor Detection by U-Net Deep Learning Algorith...

引用

Annual Information Technology, Electromechanical engineering and Microelectronics Conference (IEMECON)

作者： Utpal Chandra Das Watit Benjapolakul Manoj Gupta Chanyanan Somthawinpongsai Timporn Vitoonpong Pannee Suanpang Sujin Butdisuwan Aziz Nanthaamornphong Department of Electrical Engineering Center of Excellence in Artificial Intelligence Machine Learning and Smart Grid Technology Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Guru Ghasidas Vishwavidyalaya Bilaspur Chhattisgarh India Shinawatra University Pathum Thani Thailand Dept. of Rehabilitation Medicine King Chulalongkorn Memorial Hospital and Dept. of Rehabilitation Medicine Faculty of Medicine Chulalongkorn University Bangkok Thailand Department of Information Technology Faculty of Science and Technology Suan Dusit University Bangkok Thailand College of Computing Prince of Songkla University Phuket Thailand

ISBN: (数字)9798350387315

ISBN: (纸本)9798350387322

This research looks at the genomic subtypes of low-grade glioma tumors and their shape characteristics by deep learning magnetic resonance image (MRI) segmentation. We analyzed preoperative imaging and genetic data from 110 patients with low-grade glioma from the Cancer Genome Atlas. Three shape features were recovered to quantify the two- and three-dimensional aspects of the malignancies. Based on gene expression, DNA copy number, IDH mutation, 1p/19q co-deletion, DNA methylation, and microRNA, previously identified clusters were found in genomic data. We used the exact trait test to investigate the connection between chromosomal clusters and imaging traits. Our findings show a significant correlation between the margin fluctuation-bounding ellipsoid volume ratio and the RNA Seq clusters. Furthermore, a correlation was discovered between RNA-seq clusters and angular standard deviation. The U-net deep learning algorithm demonstrated a test accuracy of 94\% and a mean Dice coefficient of 90\%. These findings suggest that tumor shape characteristics derived from MRI can be projected through genomic subtypes in lower-grade gliomas

关键词： Deep learning Image segmentation Correlation Shape Magnetic resonance imaging Genomics DNA Clustering algorithms Bioinformatics Standards

来源：评论

学校读者我要写书评

暂无评论

A Novel Python Based Fake Jobs Post Identification And Analysis Methodology Using Elevated learning Strategy

A Novel Python Based Fake Jobs Post Identification And Analy...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Vijayalakshmi V Anni Princy B Vijay Anand Kandaswamy S. Sujatha Sarva Naveen Kumar Aruna V Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Panimalar Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai Tamil Nadu India Department of EEE Sri Sairam College of Engineering Bangalore Karnataka India Department of ECE MLR Institute of Technology Hyderabad India Department of Management Studies St.Joseph's Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

Online job boards and portals have grown in popularity in recent years, making it easier and more effective for people to look for work. False job ads have proliferated with the advent of digital transformation, which is both an opportunity and a threat. People looking for work may fall victim to these misleading listings, which can lead them astray, waste their time, and expose them to scams. The research presents Elevated learning based Fake Job Prediction (ELFJP), a claim that utilizes learning based classification algorithms to stop fake job advertisements on the internet. To assess the effectiveness of the suggested method, it is cross-validated using a traditional learning model known as Random Forest Classifier (RFC). We find the best job fraud detection model by comparing the results of different classifiers. Web fraud may be detected and prevented with the help of these classifiers. In a sea of seemingly legitimate job ads, it helps to single out the fraudulent ones. This system is able to identify fake job ads on the web by integrating classifiers with an ensemble learning model and then comparing and evaluating the results. In light of the ever-changing strategies used by con artists, the research stresses the significance of being proactive. To keep up with ever-changing fraud tactics, machine learning models are continuously improved and adjusted. The ultimate aim of this proposed approach is to help make a safer online job market by reducing the likelihood of fraudulent ads and increasing confidence among those looking for work.

关键词： Technological innovation Digital transformation Employment Forestry Lead Fraud Ensemble learning Stress Random forests Portals

来源：评论

学校读者我要写书评

暂无评论

Society Security App

Society Security App

引用

Advances in Science and Technology (ICAST), International Conference on

作者： Reshma Kanse Harish Motekar Vinod Rathod Supriya Ajagekar Dhwaniket R. Kamble Trupti Patil Santosh Rathod Deparment of Artificial Intelligence and Machine Learning Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India Department of Computer Science and Engineering Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India Department of Computer Science and Business Systems Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India

ISBN: (纸本)9781665492645

In the housing society, daily life in urban areas has significant things to manage. Our daily necessities, such as water supply, electricity, security, and a variety of other things that are essential in residential life, fall under the purview of housing society management. In the majority of cases, society management practices a traditional method of correspondence. This absolutely has a few limitations and inconveniences. Everyday notices, month-to-month gatherings, comprehensive developments, various contacts for day-to-day needs, security alarms, high-priority communication, and numerous others may not be conveyed as expected in the ongoing situation, as the greater part of the things are getting dealt with physically. To overcome the issues caused by this time- consuming manual framework, an automated framework should be created to decrease human efforts. In most societies, work is done physically. Resident's contact information is noted on the papers. As all work is done on paper, it is undeniably challenging to oversee and monitor basically everything related to work expenses in society. This cooperative society management system will automate the entire daily life of the society. This system likewise keeps the contacts of specialized individuals or organizations that offer various types of assistance, like labour, housekeeping, pest control, equipment maintenance, and so on. There is no automated framework for all of the things that happen in society, so people can understand what's going on. This framework likewise raises invoices against all residents. This process for sustaining a society is designed to address the most widely recognized issues in societies. Utilizing this framework Advance installments or halfway instalments can be effortlessly noted and followed at any level. They require coordination among the society's management and the vendors, which offer some types of assistance, so the appropriate convenience can be given. In this maintenance bi

关键词： Urban areas Manuals Organizations Maintenance engineering Pest control Security Monitoring

来源：评论

学校读者我要写书评

暂无评论

Leveraging Digital Twin Technology to Combat Cardiovascular Disease: A Comprehensive Review

Leveraging Digital Twin Technology to Combat Cardiovascular ...

引用

artificial intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Induni Nayodhara Weerarathna Praveen Kumar Prateek Verma David Raymond Anurag Luharia Gaurav Mishra Department of Biomedical Sciences Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Radiotherapy Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Radiodiagnosis Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

The innovative Digital Twin (DT) technology, which constructs a copy of objects, has emerged as a groundbreaking approach in various sectors, including the healthcare industry. This thorough examination delves into the potential of utilizing DT technology to address disease (CVD), a prominent cause of illness and death globally. By combining real-time data, sophisticated analytics and machine learning algorithms, DTs provide a platform for monitoring, diagnosing and enhancing health. The document explores the background and evolution of DT technology, its role in precision medicine, and its transformative impact on managing CVD. It also sheds light on how digital twins replicate, forecast and analyze the functions and performance of systems to offer insights into prevention, therapy options and personalized care. Furthermore, it discusses the obstacles and constraints of incorporating DT technology in healthcare settings, such as data security concerns, interoperability challenges, and ethical considerations. The paper showcases case studies that highlight the applications of DTs in research and treatment to underscore the potential of this technology in transforming patient outcomes. The evaluation concludes with prospects stressing the importance of research efforts and collaborative initiatives to surmount existing hurdles and fully leverage the advantages of DT technology in addressing cardiovascular disease.

关键词： Industries Data privacy Precision medicine Data integration Medical services Real-time systems Digital twins Cardiovascular diseases Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

Big Data Analysis on Intelligent Traffic Surveillance by Incorporating Sensors and IoT Devices on Roads

Big Data Analysis on Intelligent Traffic Surveillance by Inc...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： A Devi Akanksha Kapruwan Manish Shrimali Vengalapudi Appalakonda Ramya Maranan Amit Barve Department of Computer Applications Dr. SNS Rajalakshmi College of Arts and Science (Autonomous) Coimbatore Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and IT Janardan Rai Nagar Rajasthan Vidyapeeth (Deemed to be University) Udaipur Rajasthan India Department of Artificial Intelligence and Machine Learning Aditya Engineering College (A) Kakinada Andhra Pradesh India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Department of Computer Science and Engineering Parul Institute of Technology Faculty of Engineering and Technology Parul University Gujarat India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Rather than relying on public transportation, people are increasingly comfortable driving their automobiles to satisfy their mobility needs. Reasons for this include the automobiles' accessibility and the fact that they can be used whenever needed. Because of this, many cities around the world experience terrible traffic congestion and long wait periods at traffic signals. Smarter and more effective traffic management is possible through the integration of big data, the Internet of Things (IoT), and a cloud platform with a network of linked vehicles and sensors. The objective of this study is to estimate traffic conditions along a route and provide updates to the user. Initially, Deep learning (DL) models such as YOLO (You Only Look Once) and SSD (Single-Shot Object Detection) are developed and tested to detect vehicles. YOLO produces outstanding performance in vehicle detection, with an 89.5% mean Average Precision (mAP) and an 83.98% Intersection over Union (IoU). This model is then pushed to the cloud. A Global Positioning System (GPS) module is used to determine the user's current location. Based on the user's location, the nearest camera is enabled, and the recorded video is sent to the cloud. The cloud-deployed YOLO model is used to detect and count vehicles. To improve the user experience, this study has created a mobile application. The software contains a navigation map function that allows users to specify the maximum number of vehicles expected along their route. The created system counts the number of vehicles on their path, and if the count exceeds the specified threshold, the mobile app notifies the user about traffic conditions.

关键词： YOLO Cloud computing Clouds Roads Urban areas Big Data Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Implementation of an Effective Methodology to Avoid DDoS Attacks using Cybersecurity Norms

Implementation of an Effective Methodology to Avoid DDoS Att...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： R Balamurugan B. Anni Princy D. Kanchana M. Murugesan A Josphin Selsia M Dinesh Department of Artificial Intelligence and Machine Learning AJK College of Arts and Science Coimbatore Tamil Nadu India Department of Computer and Communication Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of Computer Applications SRM Institute of Science and Technology Chennai Tamil Nadu India Department of CSE Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Tamil Nadu India Department of ECE Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

Today’s world wouldn't function without the Internet. Because the internet is a universal resource for information gathering, its accessibility is crucial. This research focuses on the Distributed Denial of Service (DDoS) attack because of the severe impact it has on network availability. DDoS attacks work by flooding the target with a large amount of unauthorized data, thereby occupying its available bandwidth as well as preventing genuine traffic from passing throughout. Modern cyber attacks are highly complex and difficult to detect in a decentralized network. In a distributed context, Denial of Service (DoS) and Distributed Denial of Service (DDoS) assaults induce resource unavailability. This has spurred the scientific community to develop viable ways in dispersed situations as a means of minimizing such attacks. This research focuses on the Distributed Denial of Service assault due to its devastating effects on network accessibility as a result of its flood of illegal data that usurps the victim’s bandwidth and stifles the flow of lawful traffic. This paper introduces a new method for detecting DDoS attacks, the Novel Attack Detection Protocol (NADP), and validates its effectiveness by comparing it to a more traditional routing protocol, Dynamic Source Routing (DSR). We have also detailed the various methods used in distributed denial of service attacks on Internet service providers. The goal of this project is to identify potential solutions to this problem, including methods for preventing and mitigating these attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ROBUST EARLY-learning: HINDERING THE MEMORIZATION OF NOISY LABELS 9

ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY L...

引用

9th International Conference on learning Representations, ICLR 2021

作者： Xia, Xiaobo Liu, Tongliang Han, Bo Gong, Chen Wang, Nannan Ge, Zongyuan Chang, Yi Trustworthy Machine Learning Lab School of Computer Science The University of Sydney Australia Department of Computer Science Hong Kong Baptist University Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology China ISN State Key Laboratory School of Telecommunications Engineering Xidian University China Medical AI Group Faculty of Engineering Monash University Australia Airdoc Research Monash University Australia School of Artificial Intelligence Jilin University China

The memorization effects of deep networks show that they will first memorize training data with clean labels and then those with noisy labels. The early stopping method therefore can be exploited for learning with noisy labels. However, the side effect brought by noisy labels will influence the memorization of clean labels before early stopping. In this paper, motivated by the lottery ticket hypothesis which shows that only partial parameters are important for generalization, we find that only partial parameters are important for fitting clean labels and generalize well, which we term as critical parameters;while the other parameters tend to fit noisy labels and cannot generalize well, which we term as non-critical parameters. Based on this, we propose robust early-learning to reduce the side effect of noisy labels before early stopping and thus enhance the memorization of clean labels. Specifically, in each iteration, we divide all parameters into the critical and non-critical ones, and then perform different update rules for different types of parameters. Extensive experiments on benchmark-simulated and real-world label-noise datasets demonstrate the superiority of the proposed method over the state-of-the-art label-noise learning methods. © 2021 ICLR 2021 - 9th International Conference on learning Representations. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Revolutioning Healthcare: A Superficial learning Approach to Predict Heart Diseases by Using artificial intelligence (AI) Logic

Revolutioning Healthcare: A Superficial Learning Approach to...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Rohini S Thiyaneswaran B Durga Devi S Revathi K Jayant Giri Mohammad Omar Sabri Department of CSE R.M.K. Engineering College Kavaraipettai Chennai Department of ECE Sona College of Technology Salem Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Department of Artificial intelligence and Machine Learning - CSE (AIML) S.A. Engineering College Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Division of Research and Development Lovely Professional University Phagwara India Department of Business Information Technology Faculty of Economic Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The prevalence of cardiovascular illnesses is on the rise, making early disease prediction all the more crucial and worrisome. Making this diagnosis is no easy feat; it requires speed and accuracy. The primary objective of the study article is to identify the patient subset most at risk for cardiovascular disease using a battery of medical diagnostic criteria. By analyzing the patient's medical history, we developed a technique to forecast the likelihood of a heart disease diagnosis. Clinical decision support systems have made extensive use of AI approaches for the accurate prediction and diagnosis of a wide range of disorders. Here, we present Superficial Neural Health learning (SNHL), an AI-based method for accurate heart disease prediction, and we cross-validate it with K-Nearest Neighbor (KNN), a traditional learning method, to see how well it works. Many of the observable risk factors are shared by heart disease patients and can be utilized to make a good diagnosis. A system that takes these risk factors into account might be useful for both doctors and patients; it could alert them to the possibility of heart disease before they incur the expenses associated with unnecessary hospital visits or expensive checkups. In order to diagnose and categorize the patient with cardiac illness, we employed various deep learning algorithms, including KNN and SNHL. In order to control the model's applicability and enhance the accuracy of heart attack prediction in any person, a very helpful technique was applied. When compared to earlier classifiers like naïve bayes, etc., the suggested model's strength in predicting if a person has heart disease using KNN and SNHL was rather satisfying. Applying the provided model to determine the classifier's likelihood of correctly and precisely identifying the heart condition has thus relieved a considerable amount of strain. Both the quality and affordability of medical treatment are improved by the given heart disease prediction system

关键词： Heart Accuracy Transforms Nearest neighbor methods Predictive models Software Medical diagnosis Medical diagnostic imaging Diseases Strain

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：