检索结果-内蒙古大学图书馆

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Guefrachi, Sarra Ben Jabra, Marwa Alsharabi, Naif A. Ben Othman, Mohamed Tahar Alharabi, Yasser O. Alkholidi, Abdulsalam Hammam, Habib Université de Moncton Faculty of Engineering MonctonNBE1A3E9 Canada Spectrum of Knowledge Production & Skills Development Sfax3027 Tunisia Computer Engineering University of Ha'il Computer Science Amran University Yemen Ha'il55476 Saudi Arabia College of Computer Qassim University Department of Computer Science Buraydah51452 Saudi Arabia College of Computer Sc. & Engneering Ha'il University Computer Science and Information Ha'il Saudi Arabia Canadian Institute of Technology College Department of Software Engineering Tirana Albania International Institute of Technology and Management Commune d'Akanda BP Libreville1989 Gabon School of Electrical Engineering University of Johannes-burg Dept of Electrical and Electronic Eng. Science Tirana Albania

ISBN: (纸本)9798350347050

Recent advances in DeepFake face-swapping technology have made it simple to create fake videos that appear remarkably real. Since it has been employed in numerous instances for deceit, extortion, and the falsification of facts, its widespread use has generated a huge social, security, and political risk. Its use on websites and social media has become more widespread. Detecting this crime is becoming more and more important due to the potential harm false videos may inflict on a global scale. This research offers a method for building a deep learning model that really can tell the difference between authentic and false videos. The article describes how to create new models based on the VGG16 neural network, a previously created neural network that does image categorization, using transfer learning in the computer vision field. Deep learning is still becoming better at both producing and spotting DeepFakes. DeepFake detection algorithms are developed using dated public datasets, and as a result, they may become obsolete with time. and require continual updating. The research findings are encouraging, and our results reached an accuracy rate of over 90%. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Comparison of Multimodal Features for Detecting Driver Drowsiness using different dataset 5

Comparison of Multimodal Features for Detecting Driver Drows...

引用

5th International Conference on Trends in Electronics and Informatics, ICOEI 2021

作者： Vijay Priya, V. Uma, M. Srm Institute of Science and Technology Department of Computer Science and Engineering Kattankulathur India Srm Institute of Science and Technology Department of Software Engineering Kattankulathur India

ISBN: (纸本)9781665415712

Road accidents are increasing day by day. One of the major causes of road accidents is drowsiness and distraction of the driver. Due to human faults, a greater number of death and injuries occurs around the world. Drowsiness and distraction while driving is now identified as one of the reasons behind fatal crashes and highway accidents caused by drivers. If an alert is given before the driver becomes drowsy the number of road accident can be prevented and crashes can be avoided. This paper mainly focuses on different drowsiness methods to detect driver's drowsiness, driver's fatigue and driver distraction. This paper conducts a detailed study on different methods such as the Behavioural method, Vehicle method, Physiological method and Hybrid method that relate to drowsiness, fatigue and distraction. The purp ose of the study is to identify the significant features from the different methods to detect driver drowsiness. A study is based on Different datasets like YawnDD and NTHU-DDD, Different methods like Behavioural methods, Vehicle method, Physiological method and Hybrid method with different features like Eye state like Blinking, PERCLOS, Mouth state like Yawning, wearing glasses and illumination conditions and different classifiers like Support Vector Machine (SVM), Convolutional Neural Network (CNN) are compared to predict the best dataset and best features for monitoring driver drowsiness. compared to the multimodal features like PERCLOS and Blinking, Yawning and Blinking produces 85%-99% of accuracy other than the single features like PERCLOS, Blinking, Yawning produces around 75%- 90% of accuracy. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Application of Neural Network Keyword Extraction Methods for Student’s CV Compilation from Discipline Work programs

Application of Neural Network Keyword Extraction Methods for...

引用

International Conference on Soft Computing and Measurements (SCM)

作者： Ivan I. Kholod Pavel V. Korytov Maria V. Sorochina Department of Computer Science and Engineering Saint-Petersburg Electrotechnical University “LETI” Saint-Petersburg Russia Department of Software Engineering and Computer Applications Saint-Petersburg Electrotechnical University “LETI” Saint-Petersburg Russia

The paper considers application of natural language processing methods (NLP) to solve the task of identifying the core skills acquired by students in the process of education. An ensemble solution, consisting of models WikiNEuRAL, KBIR-Inspec, ruGTP3Large, word2vec, and other NLP methods, is used to extract and process Russian language keywords. The described method was developed to automate the compilation of a student’s CV in the information system called “Partner’s Account” of the LETI” university.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Apply Masked-attention Mask Transformer to Instance Segmentation in Pathology Images 6

Apply Masked-attention Mask Transformer to Instance Segmenta...

引用

6th International Symposium on computer, Consumer and Control, IS3C 2023

作者： Sheng, Jia-Chun Liao, Yi-Sheng Huang, Chun-Rong National Chung Hsing University Department of Computer Science and Engineering Taichung402 Taiwan National Cheng Kung University Cross College Elite Program Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan701 Taiwan

ISBN: (纸本)9798350301953

Instance segmentation can be applied for the discrimination and diagnosis of cancer cells in pathology images. Accurate segmentation of each pathological cell in the pathology images can improve the efficiency of clinical diagnosis. In this paper, we aim to evaluate the state-of-the-art transformer-based instance segmentation method, masked-attention mask transformer (Mask2Former)[1], on pathology datasets. With the pretrained model of Mask2Former on the natural image instance segmentation dataset, we show that Mask2Former can be adaptive to small pathological datasets and achieve comparable or even better instance segmentation performance compared with the state-of-the-art task-specific pathology image instance segmentation methods. © 2023 IEEE.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Ontological Model for Cohesive Smart Health Services Management

引用

computers, Materials & Continua 2023年第2期74卷 3679-3695页

作者： Muhammad Raza Naqvi Muhammad Waseem Iqbal Syed Khuram Shahzad M.Usman Ashraf Khalid Alsubhi Hani Moaiteq Aljahdali Le Laboratoire Génie de Production de l’École Nationale d’Ingénieurs de Tarbes(LGP-INP-ENIT) Universitéde ToulouseCEDEXTarbes65016France Department of Software Engineering Superior UniversityLahore53700Pakistan Department of Informatics&Systems University of Management&TechnologyLahore54000Pakistan Department of Computer Science University of Management and TechnologySialkot51310Pakistan Department of Computer Science King Abdul-Aziz UniversityJeddah21577Saudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21577Saudi Arabia

Health care has become an essential social-economic concern for all stakeholders(e.g.,patients,doctors,hospitals etc.),health needs,private care and the elderly class of *** massive increase in the usage of health care Internet of things(IoT)applications has great technological evolvement in human *** are various smart health care services like remote patient monitoring,diagnostic,disease-specific remote treatments and *** applications are available in a split fashion and provide solutions for variant diseases,medical resources and remote service *** main objective of this research is to provide a management platform where all these services work as a single unit to facilitate the *** ontological model of integrated healthcare services is proposed by getting requirements from various existing healthcare *** were 26 smart health care services and 26 smart health care services to classify the knowledge-based ontological *** proposed ontological model is derived from different classes,relationships,and constraints to integrate health care *** model is developed using Protégébased on each interrelated/correlated health care service having different *** querying SPARQL protocol and RDF query language(SPARQL)were used for knowledge *** Pellet Reasoner is used to check the validity and relations coherency of the proposed ontology *** to other smart health care services integration systems,the proposed ontological model provides more cohesiveness.

关键词： Ontology internet of things smart health services integration

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Laplace Distribution Noise Background Modeling for Sperm Detection in Microscopic Images 9

Heterogeneous Laplace Distribution Noise Background Modeling...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Tian, Manqing Zhao, Yang Zeng, Ni Kang, Xiaomei Pei, Jihong Yang, Xuan Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China Huazhong University of Science and Technology Tongji Medical College Department of Reproductive Maternal and Child Health Hospital of Hubei Province Wuhan China

ISBN: (纸本)9798350317251

Semen quality assessment is a very important tool for the timely detection and treatment of infertility disorders. Many artificial intelligence methods for sperm image analysis have emerged in recent years. Sperm detection in sperm microscopy is the first step in semen quality assessment. However, the acquisition of sperm electron microscopy images can produce a variety of different background lighting situations. The performance of established methods is susceptible to changes in background illumination. Therefore, a sperm detection method with heterogeneous Laplacian distribution noise background modeling (HLDNBM) is proposed. In this paper the method uses background illumination surface fitting to eliminate the effect of illumination in a single sperm image, and realizes the segmentation of sperm head and sperm tail with different grayscale by upper and lower segmentation threshold surfaces to achieve complete sperm image segmentation and multi-target detection in a single image. This method effectively avoids the degradation of target detection performance caused by sudden changes in illumination in other background modeling methods. Moreover, this method shows strong adaptability for images with different lighting backgrounds, and is friendly to small datasets as well. The experimental results show that the accuracy and sensitivity of the algorithm for sperm detection in images with different grayscale characteristics are very promising, with high universality and robustness. © 2023 IEEE.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

Online Container Scheduling for Data-intensive Applications in Serverless Edge Computing

Online Container Scheduling for Data-intensive Applications ...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xiaojun Shang Yingling Mao Yu Liu Yaodong Huang Zhenhua Liu Yuanyuan Yang Department of Electrical and Computer Engineering Stony Brook University USA College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Applied Mathematics and Statistics Stony Brook University USA

Introducing the emerging serverless paradigm into edge computing could avoid over- and under-provisioning of limited edge resources and make complex edge resource management transparent to application developers, which largely facilitates the cost-effectiveness, portability, and short time-to-market of edge applications. However, the computation/data dispersion and device/network heterogeneity of edge environments prevent current serverless computing platforms from acclimating to the network edge. In this paper, we address such challenges by formulating a container placement and data flow routing problem, which fully considers the heterogeneity of edge networks and the overhead of operating serverless platforms on resource-limited edge servers. We design an online algorithm to solve the problem. We further show its local optimum for each arriving container and prove its theoretical guarantee to the optimal offline solution. We also conduct extensive simulations based on practical experiment results to show the advantages of the proposed algorithm over existing baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling Situation-Aware Formalism Using BDI Reasoning Agents 9th

Modelling Situation-Aware Formalism Using BDI Reasoning Agen...

引用

9th EAI International Conference on Context-Aware Systems and Applications, ICCASA 2020 and 6th EAI International Conference on Nature of Computation and Communication, ICTCC 2020

作者： Saleem, Kiran Ul Haque, Hafiz Mahfooz Department of Computer Science University of Lahore Lahore Pakistan Department of Software Engineering University of Lahore Lahore Pakistan

ISBN: (纸本)9783030671006

Natural or man-made disasters are unavoidable situations that can occur anytime and anywhere. Timely disaster response plays a vital role in reducing its after-effects and can save countless lives. Over the years, people have been developing the guidelines and processes to cope up with such kinds of hazardous situations. In recent years, situation-awareness has been considered to be the most fascinating approach for the situation assessment and provides decision support accordingly. Situation-aware systems observe/perceive dynamic changes in the environment, understand/comprehend the situation, and perform actions according to the environment. Although state-of-the-art formalisms have been developed to handle such kinds of hazardous situations intelligently and rescue the victims. However, there are still many uncontrolled challenging issues. In this paper, we present a Belief-Desire-Intention (BDI) based multi-agent formalism to model the context-aware decision support system dynamically in order to achieve the desired goals. To illustrate the use of the proposed formalism, we develop a simple case study in which BDI agents are modeled and simulated to present results in terms of agents’ reasoning processes. The behavior of the system has been tested using the NetLogo simulation environment to rigorously evaluate the validity of the system. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Emotion and Mentality Monitoring Assistant (EMMA)

Emotion and Mentality Monitoring Assistant (EMMA)

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Ishini Kiridena Dayan Marasinghe Ruvini Karunarathne Kavindu Wijethunga Harinda Fernando Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

Human emotions, psychology, and social well-being are all parts of mental health. It has an impact on how people feel, think, and act. It aids in figuring out how individuals act under pressure, interact with each other, and arrive at decisions. Every period of life, from childhood and adolescence to maturity, is vital for mental health. There are several elements that affect mental health issues, such as experiences with trauma or abuse in life, work-life stress, relationship difficulties, etc. Help is available for many of the mental health issues that are identified within a person. The proposed solution is implementing a friendly chatbot that is capable of capturing human emotional states (happy, angry, sad, etc.) and mental health states (depression, anxiety, stress, etc.) using human computer interaction and health record management. The proposed solution has been developed by considering both regular users and mental health practitioners. The user can communicate with the proposed assistant using text or voice to identify their emotions and mental health based on keywords, particular characteristics of voice and facial recognition used during the conversation. Once the mental health and emotion statuses are analyzed the electronic health records will be readily available on the blockchain as blockchain tokens, this could be shared with the practitioners securely.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Detection and Classification of Melanoma Based on Android MobileNet V2 Convolutional Neural Network

Early Detection and Classification of Melanoma Based on Andr...

引用

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Prabandari, Jasmine Iswarini Dyah Sari, Christy Atika Rachmawanto, Eko Hari Irawan, Candra Altamer, Bilal R. Alkhafaji, Mohamed Ayad University of Dian Nuswantoro Study Program in Informatics Engineering Semarang Indonesia University of Dian Nuswantoro Study Program in Information Systems Semarang Indonesia Mosul University Presidency University of Mosul Mosul Iraq National University of Science and Technology Department of Computer Science DhiQar Iraq

ISBN: (纸本)9798350339215

Melanoma is a malignant form of cancer that affects the skin and has a particularly high mortality rate, so it requires early detection to increase the level of safety for users. Diagnosis and detection of skin cancer are usually done through manual screening and visual inspection. This process requires a long time, has high complexity, is subjective, and is prone to errors. CNN is one of the algorithms with advantages in accurate classification. In this research, early detection and classification of melanoma cancer were carried out based on two classes, namely benign and malignant using the Convolutional Neural Network method. Our proposed method yields an accuracy of 81.11% for the validation data. The accuracy results obtained can be improved by using more datasets and increasing the number of layers used. This study uses the CNN method using MobileNet V2 architecture to detect melanoma skin cancer. The class used is benign and malignant. © 2023 IEEE.

关键词： Convolutional neural networks

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：