检索结果-内蒙古大学图书馆

14th International Conference on Measurement, MEASUREMENT 2023

作者： Ghosh, Anupam Bhattacharjee, Madhurima Kathpalia, Aditi Brunovsky, Martin Palus, Milan Institute of Computer Science of the Czech Academy of Sciences Department of Complex Systems Prague Czech Republic National Institute of Mental Health Clinical Research Programme Klecany Czech Republic

ISBN: (纸本)9788097262976

In this paper, we infer the direction of information transfer between interacting subsystems using a cross-dependence index derived from the phase dynamics of coupled subsystems. First, we apply this method to unidirectionally coupled Rössler oscillators. This index always has a higher value along the direction of coupling than that opposite to the coupling. Finally, we employ this method in analysis of EEG signals. The aim of this analysis is to identify the direction of information transfer in the brain in patients suffering from depression and quantify its changes during the treatment process. © 2023 Institute of Measurement science, Slovak Academy o.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Pattern Discovery in an EEG Database of Depression Patients: Preliminary Results 14

Pattern Discovery in an EEG Database of Depression Patients:...

引用

14th International Conference on Measurement, MEASUREMENT 2023

作者： Hlavackova-Schindler, Katerina Pacher, Christina Plant, Claudia Lazarenko, Mykola Palus, Milan Hlinka, Jaroslav Kathpalia, Aditi Brunovsky, Martin University of Vienna Data Mining and Machine Learning Research Group Faculty of Computer Science Vienna Austria Czech Academy of Sciences Institute of Computer Science Department of Complex Systems Prague Czech Republic National Institute of Mental Health Clinical Research Programme Klecany Czech Republic

ISBN: (纸本)9788097262976

The ability to predict response to medication treatment of depressed patients, either early in the course of therapy or before treatment even begins can avoid trials of ineffective therapy and save patients from prolonged intervals of suffering. Symptom alleviation requires 4-6 weeks after starting current antidepressive medication. Based on the data basis of the patients and their EEG before and on the 7th day of treatment we apply data mining, causal discovery and machine learning approaches to discover interactive patterns between patient's brain regions to separate the treatment responders from non-responders. In this paper we report the preliminary results of our international project "Learning Synchronization Patterns in Multivariate Neural Signals for Prediction of Response to Antidepressants"ongoing at the University of Vienna, the Czech Academy of sciences and the National Institute of Mental Health in the Czech Republic. © 2023 Institute of Measurement science, Slovak Academy o.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Newton-2EGSOR Method for Unconstrained Optimization Problems with a Block Diagonal Hessian

引用

SN computer science 2020年第1期1卷 1-11页

作者： Ghazali, Khadizah Sulaiman, Jumat Dasril, Yosza Gabda, Darmesah Faculty of Science and Natural Resources Mathematics with Economics Programme Universiti Malaysia Sabah Kota Kinabalu Sabah 88400 Malaysia Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka Melaka 76100 Malaysia

We find that finding the unconstrained optimizer for large-scale problems with the Newton method can be very expensive. Therefore, in this paper, we developed a new efficient method for solving large-scale unconstrained optimization problems with block diagonal Hessian matrices to reduce the cost of computing Newton’s direction. This method is a combination of the Newton method and the 2-point explicit group successive-over relaxation (2EGSOR) block iterative method. To calculate the performance of the developed method, we used a combination of the Newton method with Gauss–Seidel (Newton-GS) point iteration and the Newton method with successive-over relaxation (Newton-SOR) point iteration as reference methods. The numerical experiment has proven that the developed algorithms generate results that are more efficient compared to the reference methods with less execution time and fewer iterations. Through 90 test cases, we observe that the speedup ratio for our proposed method is up to 659.87 times faster compared to the Newton-SOR method and up to 1963.57 times more rapidly than the Newton-GS method. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Explicit group iterative method Large-scale unconstrained optimization problems Newton method

来源：评论

学校读者我要写书评

暂无评论

Tree paths: A new model for steering behaviors

Tree paths: A new model for steering behaviors

引用

9th International Conference on Intelligent Virtual Agents, IVA 2009

作者： Rodrigues, Rafael Araújo De Lima Bicho, Alessandro Paravisi, Marcelo Jung, Cláudio Rosito Magalhães, Léo Pini Musse, Soraia Raupp Graduate Programme in Computer Science PUCRS Building 32 Av. Ipiranga 6681 Porto Alegre RS Brazil Graduate Programme in Applied Computing UNISINOS Av. Unisinos 950 São Leopoldo RS Brazil School of Electrical and Computer Engineering UNICAMP Av. Albert Einstein 400 Campinas SP Brazil

ISBN: (纸本)3642043798

This paper describes a model for generating steering behaviors of groups of characters based on the biologically-motivated space colonization algorithm. This algorithm has been used in the past for generating leaf venation patterns and tree structures, simulating the competition for space between growing veins or branches. Adapted to character animation, this model is responsible for the motion control of characters providing robust and realistic group behaviors by adjusting just a few parameters. The main contributions are related with the robustness, flexibility and simplicity to control groups of characters. © 2009 Springer Berlin Heidelberg.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

The Response of EEG Signal on Brain Relaxation Meditation Using Different Type of Zikr

The Response of EEG Signal on Brain Relaxation Meditation Us...

引用

2021 International Conference on Biomedical Engineering, ICoBE 2021

作者： Razak, N.N. Abd Sidek, K.A. Alaa, K.Y.D. Nasir, N.F. Mohd Department of Electrical and Computer Engineering Kulliyyah of Engineering International Islamic University Malaysia Department of Computer Engineering College of Computer Science and Engineering University of Ha’il Saudi Arabia Biomedical Electronic Engineering Programme Faculty of Electronic Engineering Technology Universiti Malaysia Perlis Malaysia

Depression and stress are increasingly prevalent in today’s society, owing to people's hectic, competitive, and demanding lifestyles. These illnesses had become very common, particularly among young and middle-aged people, and suicidal ideation had been identified as one of the leading causes of death by the World Health Organization (WHO). Nature sound (sound of downpours or beach) has been linked to depression and anxiety in neurology research, and it has been shown to be an alternative to alleviate anxiety. The electroencephalogram (EEG) waveform has been discovered to possess the potential in identifying information from the brain signal as well as data from the past via Bluetooth communication. The waveform use in the study are the result of a few experiments. In this study, EEG data were collected from eight subjects, four males and four females, in between the age of 20 to 30 years old and in good health, using the BrainLink device. The participants were asked to listen to two playlists of zikr, Allah, Ya Allah, and SubhanAllah, during the experiments. To smooth the signal, the Butterworth filter was used. Later, the extracted features were Alpha, Beta, and Delta waves, which were segmented based on the filtered signal. To complete the decision-making stage, the average value of amplitude differences and the p-value test were performed in the final phase. Based on the results of the experiments, it is clear that zikr is dominant in Delta wave. In terms of data hypothesis analysis, the results of both experiment were differentiated to determine which brain signal was dominant, and p-value testing was performed. Furthermore, this research is an alternative to current methods because it suggest that zikr has the tendency to alter a person's brain state to be either in a relaxed or calm mode regardless of the type of zikr recitation. As an outcome, the study recommends the relationship of the reaction of EEG signal on brain relaxation with different types of zikr

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Procedural hair generation

Procedural hair generation

引用

8th Brazilian Symposium on Games and Digital Entertainment, SBGAMES2009

作者： Cassol, Vinícius Jurinic Marson, Fernando Pinho Musse, Soraia Raupp Graduate Programme in Computer Science Pontifícia Universidade Católica do Rio Grande do Sul - PUCRS Av. Ipiranga 6681 Porto Alegre RS Brazil

ISBN: (纸本)9780769539638

This paper presents a hair generation technique for cartoon and Anime characters. The main goal of this work is to provide a procedural generation technique, robust enough in order to create different types of hairs. We propose a parametric model that can produce diversity of obtained results through parameters variation. The model is organized in three steps: firstly, the strands generation, followed by positioning them in the head of the characters. Finally, the third step is responsible for providing cartoon rendering, including common characteristics in cartoon shading, as the black edges and solid colors. Visual inspection of obtained results indicate that generated hairs are coherent with expected in terms of visual aspects. © 2009 IEEE.

关键词： Cartoon Hair Hair Generation Procedural Modeling Hair procedural model Visual aspects Anime parameter variation

来源：评论

学校读者我要写书评

暂无评论

Demystifying networking: Teaching non-majors via analogical problem-solving

Demystifying networking: Teaching non-majors via analogical ...

引用

44th ACM Technical Symposium on computer science Education, SIGCSE 2013

作者： Iyer, Sridhar Murthy, Sahana Department of Computer Science and Engineering Indian Institute of Technology Bombay Powai Mumbai India Educational Technology Inter-Disciplinary Programme Indian Institute of Technology Bombay Powai Mumbai India

ISBN: (纸本)9781450320306

The goals of a typical Networking course for computer science majors include getting students to learn the relevant concepts, delving into details of various protocols, and using Networking utilities. Such focus on low-level details is unlikely to be interesting to non-majors. Also, there is a larger danger of students not understanding the basic concepts due to the perceived complexity in the details and technical jargon. We address both these issues by teaching Networking concepts through solving problems in analogical real-life scenarios. The main idea of our approach is: The instructor poses an analogy problem, students work in groups to devise solutions, followed by a class discussion to map the analogy problem as well as its solution to their corresponding technical details in Networking domain. Thus we emphasize the core concepts of Networking and demystify the specialized technical details. Across three offerings of this course, we have found that: (i) our students' performance on typical Networking questions is comparable or higher than traditionally taught students, (ii) students can solve unseen technical problems, (iii) students' confidence in tackling technical questions is high. Copyright © 2013 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Breast cancer classification using digital biopsy histopathology images through transfer learning 1

Breast cancer classification using digital biopsy histopatho...

引用

1st International Conference computer science and Engineering, IC2SE 2019

作者： Murtaza, Ghulam Shuib, Liyana Wahid Abdul Wahab, Ainuddin Mujtaba, Ghulam Raza, Ghulam Aniza Azmi, Nor Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Department of Computer Science Sukkur IBA University Sukkur Pakistan Department of Computer Science PAF-KIET Karachi Pakistan St. James's Hospital James's Street Ushers Dublin 8 Ireland Diagnostic Imaging and Radiotherapy Programme Faculty of Health Sciences Universiti Kebangsaan Malaysia Malaysia

Breast cancer (BC) infection, which is peculiar to women, brings about the high rate of deaths among women in every part of the world. The early investigation of BC has minimized the severe effects of cancer as compared to the last stage diagnosis. Doctors for diagnostic tests usually suggest the medical imaging modalities like mammograms or biopsy histopathology (Hp) images. However, Hp image analysis gives doctors more confidence to diagnose BC as compared to mammograms. Many studies used Hp images to develop BC classification models to assist doctors in early BC diagnosis. However, these models lack better and reliable results in terms of reporting multiple performance evaluation metrics. Therefore, the goal of this study is to create a reliable, more accurate model that consumes minimum resources by using transfer learning based convolution neural network model. The proposed model uses the trained model after fine tuning, hence requires less number of images and can show better results on minimum resources. BreakHis dataset, which is available publicly has been employed in overall experiments in this research. BreakHis dataset is separated into training, testing, and validation for the experimentation. In addition, the dataset for training was augmented followed by stain normalization. By using the concept of transfer learning (TL), AleNext was retained after fine-tuning the last layer for binary classification like benign and malignant. Afterward, preprocessed images are fed into the TL based model for training. The model training was performed many times by changing the hyper-parameters randomly until the minimum validation loss was achieved. Now the trained model was used for feature extraction. The extracted features were further evaluated by using six ML classifiers (i.e. softmax, Decision tree, Naïve Bayes, Linear discriminant analysis, Support vector machine, k-nearest neighbor) through five performance measures such as precision, F-measure, accuracy, spe

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Boosting Operating Theatre Utilisation Gains in Master Surgery Scheduling via Enhanced Genetic Algorithm with Naïve Seeds 18

Boosting Operating Theatre Utilisation Gains in Master Surge...

引用

18th IEEE International Conference on computer science and Information Technologies, CSIT 2023

作者： Dovhaniuk, Oleksii Reidy, Grace Dineen, Charlie Redmond, Paul Corrigan, Mark Tabirca, Sabin University College Cork School of Computer Science Cork Ireland South South West Hospital Group Ireland Transforming Theatre Programme Cork Ireland Royal College of Surgeons in Ireland Transforming Theatre Programme Dublin Ireland University College Cork Department of Surgery Cork Ireland

ISBN: (纸本)9798350360462

This paper starts a series of research works dedicated to developing a practical and robust scheduling system for hospitals with operating capacities. The current goal is to ensure that a genetic algorithm can generate valuable solutions for operating theatre scheduling problems and optimise simple-to-implement schedules. Operating theatre is the most costly resource in hospitals, requiring highly coordinated action from caregivers to satisfy patient's needs and, at the same time, minimise idle time and overruns. Therefore, any tool that helps organise and structure patient flow saves time, money and effort both for a healthcare recipient and hospital administration. The work overviews existing medical resource scheduling methods and emphasises the advantages and disadvantages of some of the approaches. Based on the existing methods, the genetic algorithm with some unique features and enhancing strategies is presented. The algorithm experiments and tuning are performed on real-hospital records. The results show the advantage of the proposed genetic algorithm over manual and naïve scheduling approaches, proving the value of the genetic algorithm for scheduling operating theatres. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Packaging Support System for Open Source Software

A Packaging Support System for Open Source Software

引用

2012 2nd International Conference on Information Communication and Management(ICICM 2012)

作者： Amnart Pohthong Supat Sriyanaluk Information and Communication Technology Programme Department of Computer Science Faculty of Science Prince of Songkla University

Open source software (OSS) has affected organizations and communities in many ways since it was introduced. OSS makes a significant impact on software development strategies and adoption in many organizations. OSS was used in software development in order to reduce cost, provide shorter time-to-market, and increase productivity. However, the documents needed in software engineering process for OSS development are often missing. Without these documents, software developers may have to take more time to modify available source code and it may increase the risk of misunderstandings. Therefore, the research reported here proposes a packaging support system for OSS in order to reduce these problems. The preliminary evaluation of system performance was conducted in our laboratory by the selected subjects acting as two groups of users: members and administrators. The results of system evaluation in term of users' satisfaction, using Likert scale, were rated as good quality (averaged 4.2) and very good quality (averaged 4.86) by members and administrators respectively.

关键词： open source software, packaging support system, software packaging

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：