检索结果-内蒙古大学图书馆

Deep Learning Based Facial Emotion Recognition using Multiple Layers Model

Deep Learning Based Facial Emotion Recognition using Multipl...

2021 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2021

作者： Sandra, Lidia Heryadi, Yaya Lukas Suparta, Wayan Wibowo, Antoni Krida Wacana Christian University Psychology Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia Faculty of Engineering Jakarta12930 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665499699

A Facial Emotion Recognition (FER) system is an important tool to be implemented in any psychology academic field and beyond. This paper aims to show a system of Facial Emotion Recognition that can be done using the multiple layers model of ResN et50 which is an ANN. The dataset is an array that consists of 7 different emotions represented by the numbers 0-6. The emotion included in the dataset is 'anger', 'disgust', 'fear', 'happiness', 'sadness', 'shock', and 'neutrality'. This research found that the highest accuracy in the application of the model was recorded at 65% and the test was 60% to recognize facial emotion from a graphical input. © 2021 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI 41

Position: Bayesian Deep Learning is Needed in the Age of Lar...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural Network Analysis of Mt-Mst Pathways in Biological Motion Processing

SSRN

引用

SSRN 2024年

作者： Zhang, Yun Liu, Ying Feng, Tingting Zhang, Tao Qu, Hong Yi, Zhang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China State Key Laboratory of Brain and Cognitive Science Institute of Psychology Chinese Academy of Sciences Beijing100101 China Department of Psychology University of Chinese Academy of Sciences Beijing100049 China College of Computer Science Sichuan University Chengdu610065 China

Understanding the neural mechanisms underlying biological motion perception remains a significant challenge in neuroscience. To further explore this mechanism, we construct the BioMotion-SNN model using real bioneural data from the MT to MST regions in macaques. To characterize neuron activity within specific time windows, we propose the windows learning strategy, which employs windowed learning to extract crucial information related to specific events or stimuli. By analyzing the connectivity structure of the BioMotion-SNN model, we identify regular projection patterns from MT to MST, reflected in the varying response characteristics of MT neurons based on their projection strength to different MST neuron populations. This work not only verifies some biological properties of MST neurons, but also underscores the potential of neurodevelopmental SNN models, driven byreal electrophysiological data, in improving our understanding of neural processing. © 2024, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Cuisine Image Recognition and Recommender System using Convolutional Neural Network

Cuisine Image Recognition and Recommender System using Convo...

引用

IEEE Eurasia Conference on IOT, Communication and engineering (ECICE)

作者： Chin-Chih Chang Chi-Hung Wei Kuan-Yun Wu Hao-Xiang Kao Sean Hsiao Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Bachelor Program of Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu Taiwan

The fusion of technology and culinary exploration has allowed for the emergence of advanced online customer service systems. We developed a novel approach to enhance the dining experience. We used a Cuisine Image Recognition and Recommender System (CIRRS) powered by Convolutional Neural Network (CNN) to identify and suggest diverse cuisines based on visual inputs. CIRRS swiftly identified diverse cuisines from user-captured images, offering information on origin, ingredients, and variations by crawling websites. The system enhanced dining experiences by suggesting personalized menus based on individual preferences and past selections. Extensively tested across various culinary genres, CIRRS consistently demonstrated accuracy and adaptability. User feedback validated its potential to simplify dining choices and elevate satisfaction. This innovative system enriched dining experiences as a valuable tool for culinary enthusiasts, chefs, and restaurateurs, bridging the gap between technology and gastronomy, It also offers a unique way to explore Taiwanese cuisines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disclosure Privacy Information Social Media on TikTok 9

Disclosure Privacy Information Social Media on TikTok

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Syamsuar, Dedy Fahrezi, Fazri Favian, Ahnaf Irwansyah, Edy Irawan, Achmad Fakhri School of Information System Bina Nusantara University Faculty of Engineering Professional Engineer Program Dept. Information System Department Jakarta11480 Indonesia School of Information System Bina Nusantara University Information System Department Jakarta11480 Indonesia School of Information System Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

With the rapid development of technology, the use of social media by the public, especially among young people, is increasing. One of the social media platforms currently used by young people is the TikTok application. It is a video-based TikTok feature accompanied by music, writing, and pictures that are considered attractive, so teenagers like it to show their existence and self-disclosure. Therefore, this study aims to examine the intention of users to disclose their privacy. As the basis of the theory, this study deployed the privacy calculus theory, where the perceived benefits and perceived risks play crucial roles in the intention to disclose their privacy. The study successfully collected 369 responses. The empirical findings indicated that only the relationship between Perceived Personalization (PP) and Perceived Risk (PR) was not supported. However, all the remaining hypotheses were supported. These findings emphasize how several complicated variables influence social media users' intentions to disclose their privacy. When people feel in control of their privacy settings and see significant benefits, they are more likely to divulge personal information;nevertheless, perceived risks can greatly discourage users. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Genetic Algorithm to Optimize Cargo Stability in Container Transportation 11

A Genetic Algorithm to Optimize Cargo Stability in Container...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Hsieh, Chi-Jung Wu, Kuang-Sung Wu, Tin-Yu Tey, Fu Jie Chen, Yi-Kai Ho, Jye Yi National Ilan University Department of Computer Science and Information Engineering Ilan County Taiwan National Ilan University Master Program of E-Learning for Multimedia and Network Communications Yilan Taiwan National Pingtung University of Science and Technology Department of Management Information Systems Pingtung County Taiwan National Taiwan University of Science and Technology Department of Electrical Engineering Taipei Taiwan

ISBN: (纸本)9781665492324

In the era of the global village, frequent cross-border trade in goods has made container transportation a significant part in delivery of cargo. However, rollover accidents of container trucks often occur because of tall truck height, improper cargo stowage or crooked roads. Therefore, how to find the optimal center of gravity (CG) of the packed cargo remains an issue that the transportation industry should not neglect. To optimize cargo stability and reduce the incidence of rollovers, this paper proposes a genetic algorithm that scores the cargo stacking process to find the best CG of the cargo based on the CG of the vehicle. According to the deviation angle and the point closest to the best CG, we can Figure out the optimal cargo stacking method. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

From Pictures to Prompts: Analyzing and Reconstructing AI-Generated Images with BLIP2 and CLIP 24

From Pictures to Prompts: Analyzing and Reconstructing AI-Ge...

引用

8th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2024

作者： Kuo, Yi-Hsuan Chang, Hsien-Tsung Department of Computer Science and Information Engineering Chang Gung University Taoyuan China Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan China

ISBN: (纸本)9798400717383

This study presents a novel approach to analyzing and reconstructing AI-generated images using BLIP2 and CLIP models, focusing on a dataset of 268,000 Midjourney-generated images and prompts. We introduce a multi-level feature classification system encompassing 11 categories and 1,100 features, and employ BLIP2 for descriptive text generation and CLIP for feature similarity analysis. Our methodology involves image pre-processing, custom feature extraction, and image reconstruction under various conditions. The effectiveness of our approach is demonstrated through similarity scores between original and reconstructed images, ranging from 68.15 to 71.25 across different feature extraction conditions. This research contributes to the fields of natural language processing and information retrieval by offering insights into AI-generated image analysis, proposing new methods for feature extraction and reconstruction, and suggesting avenues for improving image generation models and multi-modal understanding. © 2024 Copyright held by the owner/author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing Task Execution in Robotic Swarms: Coordination Strategies for Enhanced Efficiency

Optimizing Task Execution in Robotic Swarms: Coordination St...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Vandna Bansla Inderjeet Kaur Rudramani Bhutia Girish Singh Bisht Khemraj Sharma Shivalik Engineering College Dehradun U.K India Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad U.P. India Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation A.P. India Department of Computer Science & Engineering Tula’s Institute Dehradun India Department of Business Administration Doctoral Program in Management Sciences NANHUA UNIVERSITY Dalin Chiayi R.O.C

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

The “swarm robotics” is a relatively recent field of study that investigates the ways in which several robot systems interact with one another throughout the course of time. The organization is able to accomplish its goals by delegating work to a large number of robots that are capable of doing activities that are beyond the capabilities of a single robot. This is accomplished via the use of a broad variety of different methods. It is possible to make use of optimization algorithms in robotic swarms in order to discover answers to difficult trans disciplinary challenges that are encountered in real-world environments. The fact that algorithms for swarm intelligence are able to adjust to changing circumstances makes the potential of this happening a reality. In order to achieve the highest possible level of performance, this study analyses a broad range of different swarm optimization algorithms that may be used to robotic swarm scenarios. This category contains a variety of methodologies, including PSO, GPSO, CSO, ACO, and GSO, among others. Within this section, a comprehensive analysis is provided for each of the strategies that came before it, and an inquiry into the potential future course of action for swarm optimization is furthermore carried out. The ramifications of these tactics are also discussed in this section, which is included in the overall debate.

关键词： Robot kinematics Swarm robotics Organizations Planning Particle swarm optimization Informatics Optimization

来源：评论

学校读者我要写书评

暂无评论

Adopting Centroid and Bandwidth to Shape Security Line

Adopting Centroid and Bandwidth to Shape Security Line

引用

International Conference of computer science and Information Technology

作者： Heni Ispur Pratiwi Iman Herwidiana Kartowisastro Benfano Soewito Widodo Budiharto Doctorate Program School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Doctorate Program of Computer Science Bina Nusantara University Jakarta Indonesia Computer Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia Computer Science BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

The voice patterns of gender and age have been used as speaker's identity and implied into sectors such as smart cards, healthcare, banking, and other security access controls. However, age, illness, and ambient noise factors exist challenging issues of voice changes in speech recognition systems to be resolved. This paper presents experiment results of observing those issues, and its goal was obtaining the elements of voice features to secure the speaker's identity. Mel-frequency Cepstral Coefficient (MFCC) was used to conduct observations on spectral centroid and bandwidth, it has effectively performed capturing features of individual speech signal. The experiment was conducted with data split into three groups: under 13, range 13 to 19, and above 19 years old for both male and female. The results showed that both gender under 13 have centroid voices reached to 98%, age of 13 to 19 remain with centroid reached 98% of bandwidth for male and passing over 100% for female, then above 19 for both genders speak lower with centroid 50% of bandwidth, and male above age of 19 remains to keep centroid about 50% and female changes to 95%. MFCC fits to expose the speech spectrum for the purpose of an analysis frame on specific local spectral properties of voices, and the finding is to form a security line or an individual profiling adoption.

关键词： computer science Smart cards Shape Bandwidth Speech recognition Medical services Banking

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Eye Movements Using Multi-way Autoregressive Model

Emotion Recognition from Eye Movements Using Multi-way Autor...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian-Fang Ma Xuan-Hao Liu Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The application of physiological signals in emotion recognition is a popular research topic in human-computer interactions. Eye movement, as an important physiological signal, plays an essential role in medicine, psychology, cognitive science, and other scientific research fields. Previous studies have successfully identified human emotions by combining various eye-related measurements, selecting features, and utilizing machine learning techniques. However, the exploration of eye movement signals in emotion recognition remains insufficient. In this study, we utilize eye tracking heatmap and eye movement trajectory data for emotion recognition for the first time. Based on the two types of eye movement data, we develop a multi-way autoregressive model capable of processing multi-view eye movement data. Compared to traditional deep learning baseline models, our model better adapts to the structure of eye movement data and significantly improves the classification performance. Furthermore, we integrate heatmap and trajectory data with commonly used eye-related measurement features, which further enhance the performance of emotion recognition beyond previous methods.

关键词： Heating systems Emotion recognition Adaptation models Accuracy Psychology Gaze tracking Biomedical measurement Data models Physiology Trajectory

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：