检索结果-内蒙古大学图书馆

Asian Conference on Affective Computing and intelligent Interaction (ACII Asia)

作者： Ming-Hsiang Su Chung-Hsien Wu Kun-Yi Huang Qian-Bei Hong Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan

ISBN: (纸本)9781538653128

This study proposes a long-short term memory (LSTM)-based approach to text emotion recognition based on semantic word vector and emotional word vector of the input text. For each word in an input text, the semantic word vector is extracted from the word 2vec model. Besides, each lexical word is projected to all the emotional words defined in an affective lexicon to derive an emotional word vector. An autoencoder is then adopted to obtain the bottleneck features from the emotional word vector for dimensionality reduction. The autoencoder bottleneck features are then concatenated with the features in the semantic word vector to form the final textual features for emotion recognition. Finally, given the textual feature sequence of the entire sentence, the LSTM is used for emotion recognition by modeling the contextual emotion evolution of the input text. For evaluation, the NLPCC-MHMC-TE database containing seven emotion categories: anger, boredom, disgust, anxiety, happiness, sadness, and surprise was constructed and used. Five-fold cross-validation was employed to evaluate the performance of the proposed method. Experimental results show that the proposed LSTM-based method achieved a recognition accuracy of 70.66%, improving 5.33% compared with the CNN-based method. Besides, the proposed method based on integration of the semantic word vector and emotional word vector of the input text outperformed that using the individual feature vector.

关键词： Emotion recognition Databases Logic gates Feature extraction Semantics Speech recognition computer science

来源：评论

学校读者我要写书评

暂无评论

Achieving reliable communication between Kafka and ROS through bridge codes

Achieving reliable communication between Kafka and ROS throu...

引用

International Conference on Advanced Robotics (ICAR)

作者： Luan Lucas Lourenço George Oliveira Patricia Della Méa Plentz Juha Röning Robotizando UFSC JoinvilleBrazil Graduate Program in Computer Science Federal University of Santa Catarina Florianópolis Brazil Biomimetics and Intelligent Systems Group - BISG University of Oulu Oulu Finland

ISBN: (纸本)9781665436854

The number of smart warehouses has increased in the last few years, mainly because of the enormous sales volume in e-commerce systems. Such physical environments are fully equipped with robots that solve the orders that arrive there. Most research in the literature presents results just about the path planning and allocation tasks as the main problems related to this area. However, it is also essential to consider how robotic platforms, such as ROS (Robot Operating System), deal with integrating with streaming platforms that manage the orders that arrive into the smart warehouses. This paper presents a simple way to integrate ROS with Kafka, a streaming platform highly used in e-commerce systems. We develop a bridge code to glue these two platforms and test it within three realist simulation scenarios. As we will show, the use of the QoS profiles provided by the ROS Data Distribution Service (DDS) allows us to achieve a higher level of reliability.

关键词： Bridges Codes Operating systems Quality of service Path planning Reliability Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Exploring Macroscopic Fluctuation of Facial Expression for Mood Disorder Classification

Exploring Macroscopic Fluctuation of Facial Expression for M...

引用

Asian Conference on Affective Computing and intelligent Interaction (ACII Asia)

作者： Qian-Bei Hong Chung-Hsien Wu Ming-Hsiang Su Kun-Yi Huang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781538653128

In clinical diagnosis of mood disorder, a large portion of bipolar disorder patients (BDs) are misdiagnosed as unipolar depression (UDs). Clinicians have confirmed that BDs generally show "reduced affect'' during clinical treatment. Thus, it is expected to build an objective and one-time diagnosis system for diagnosis assistance by using machine-learning techniques. In this study, facial expressions of BD, UD and control group (C) elicited by emotional video clips are collected for exploring temporal fluctuation characteristics of intensities of facial muscles expression among the three groups. The differences of facial expressions among mood disorders are investigated by observing macroscopic fluctuations. To deal with these problems, the corresponding methods for feature extraction and modeling are proposed. From the viewpoint of macroscopic facial expression, action unit (AU) is applied for describing the temporal transformation of muscles. Then, modulation spectrum is used for extracting short-term variation of AU. The multilayer perceptron (MLP)-based disorder prediction model is then applied to obtain the prediction results. For evaluation of the proposed method, 12 subjects for three group are included in the K-fold (K=12) cross validation experiments. The experiment results reached 61.1% classification accuracy, and outperformed the other baseline methods.

关键词： Mood Gold Fluctuations Databases Feature extraction Modulation Predictive models

来源：评论

学校读者我要写书评

暂无评论

Syncgan: Synchronize the Latent Spaces of Cross-Modal Generative Adversarial Networks

Syncgan: Synchronize the Latent Spaces of Cross-Modal Genera...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wen-Cheng Chen Chien-Wen Chen Min-Chun Hu Dept. of Computer Science and Information Engineering National Cheng Kung University Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of conditional based cross-modal GANs adopt the strategy of one-directional transfer and have achieved preliminary success on text-to-image transfer. Instead of learning the transfer between different modalities, we aim to learn a synchronous latent space representing the cross-modal common concept. A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs. Our GAN model, named as SyncGAN, can successfully generate synchronous data (e.g., a pair of image and sound) from identical random noise. For transforming data from one modality to another, we recover the latent code by inverting the mappings of a generator and use it to generate data of different modality. In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications.

关键词： Synchronization Gallium nitride Generators Data models Training Generative adversarial networks Training data

来源：评论

学校读者我要写书评

暂无评论

Multimodal Temporal Modeling of Emotion using Physiological Signals

TechRxiv

引用

TechRxiv 2023年

作者： Hinduja, Saurabh Bilalpur, Maneesh Jivnani, Liza Vimalkumar Canavan, Shaun Dept. of Psychology University of Pittsburgh United States Dept. of Intelligent Systems Program University of Pittsburgh United States Dept. of Computer Science University of South Florida United States

Modeling of human emotion is a challenging problem that can require multiple signals types, as well as contextual information that has been obtained over time. Considering this, in this paper we present our approach, based on physiological signals, to the Emotion Physiology and Experience Collaboration (EPIC) challenge at Affective Computing & intelligent Interaction (ACII), 2023. In total there are four scenarios that we model: 1) across time;2) across subjects;3) across elicitor;and 4) across version. To tackle this challenge, we propose to use a physiological fusion-based approach to solve each scenario. Along with this, we give a detailed analysis of the evaluated physiological signals and personalized predictions for each subject are shown. Our proposed approach shows encouraging results with the lowest root mean square error achieved for scenario 4 (across version) for both valence and arousal on the challenge test set. © 2023, CC BY.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

Scalable and efficient neural speech coding: A hybrid design

arXiv

引用

arXiv 2021年

作者： Zhen, Kai Sung, Jongmo Lee, Mi Suk Beack, Seungkwon Kim, Minje Department of Computer Science and Cognitive Science Program Indiana University BloomingtonIN47408 United States Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Dept. of Intelligent Systems Engineering Indiana University United States

We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine. The proposed NWC also defines quantization and entropy coding as a trainable module, so the coding artifacts and bitrate control are handled during the optimization process. We achieve efficiency by introducing compact model components to NWC, such as gated residual networks and depthwise separable convolution. Furthermore, the proposed models are with a scalable architecture, cross-module residual learning (CMRL), to cover a wide range of bitrates. To this end, we employ the residual coding concept to concatenate multiple NWC autoencoding modules, where each NWC module performs residual coding to restore any reconstruction loss that its preceding modules have created. CMRL can scale down to cover lower bitrates as well, for which it employs linear predictive coding (LPC) module as its first autoencoder. The hybrid design integrates LPC and NWC by redefining LPC’s quantization as a differentiable process, making the system training an end-to-end manner. The decoder of proposed system is with either one NWC (0.12 million parameters) in low to medium bitrate ranges (12 to 20 kbps) or two NWCs in the high bitrate (32 kbps). Although the decoding complexity is not yet as low as that of conventional speech codecs, it is significantly reduced from that of other neural speech coders, such as a WaveNet-based vocoder. For wide-band speech coding quality, our system yields comparable or superior performance to AMR-WB and Opus on TIMIT test utterances at low and medium bitrates. The proposed system can scale up to higher bitrates to achieve near transparent performance. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

eVision: Forecasting the spread of Tuberculosis in India with Deep Learning

eVision: Forecasting the spread of Tuberculosis in India wit...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Juan Zuluaga Michael Castillo Divya Syal Andres Calle Navid Shaghaghi Department of Bioengineering (BIOE) Computer Science & Engineering (CSEN) Ethical Pragmatic & Intelligent Computing (EPIC) Laboratory in collaboration with the Healthcare Innovation & Design (HID) Program Information Systems & Analytics (ISA) and Mathematics & Computer Science (MCS) Santa Clara University Santa Clara California USA

Humanity has battled tuberculosis for all of recorded history. Some studies estimate that Mycobacterium tuberculosis may have been around as long as 3 million years but it was only in 1834 when Johann Schonlein officially presented the characteristics of it. Even though the TB epidemic has touched all corners of the world, Africa and Asia are the regions that currently suffer the worst consequences. The purpose of this study is to construct a model within the eVision forecasting environment, capable of forecasting the trend of Tuberculosis cases in India, as India is the country that accounts for the largest percentage of TB cases and deaths worldwide. And being able to make predictions for India may also lead to successful results for other regions in Asia and Africa. In order to do so, this study presents different test cases that show the effectiveness of the model, varying the number of steps for each one of the data sets created. It's important to note, that these data sets are combinations of data gathered from the states with the most TB cases in India in the last years, as well as the total data for India, and supplemental data from Google Trends, as a way to facilitate the machine learning model. Even though the final results were respectable compared to past research done on India and other countries, the model nevertheless has a limitation on the number of weeks ahead which the predictions are still considered to be good; with 7 weeks being the optimal result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Psychoacoustic calibration of loss functions for efficient end-to-end neural audio coding

arXiv

引用

arXiv 2020年

作者： Zhen, Kai Lee, Mi Suk Sung, Jongmo Beack, Seungkwon Kim, Minje Department of Computer Science and Cognitive Science Program Indiana University BloomingtonIN47408 United States Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Dept. of Intelligent Systems Engineering Indiana University United States

Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the objective nature of the loss function usually leads to suboptimal sound quality as well as high run-time complexity due to the large model size. In this work, we present a psychoacoustic calibration scheme to re-define the loss functions of neural audio coding systems so that it can decode signals more perceptually similar to the reference, yet with a much lower model complexity. The proposed loss function incorporates the global masking threshold, allowing the reconstruction error that corresponds to inaudible artifacts. Experimental results show that the proposed model outperforms the baseline neural codec twice as large and consuming 23.4% more bits per second. With the proposed method, a lightweight neural codec, with only 0.9 million parameters, performs near-transparent audio coding comparable with the commercial MPEG-1 Audio Layer III codec at 112 kbps. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-domain learning by meta-learning: Taking optimal steps in multi-domain loss landscapes by inner-loop learning

arXiv

引用

arXiv 2021年

作者： Sicilia, Anthony Zhao, Xingchen Minhas, Davneet S. O’Connor, Erin E. Aizenstein, Howard J. Klunk, William E. Tudorascu, Dana L. Hwang, Seong Jae Intelligent Systems Program University of Pittsburgh United States Department of Computer Science Radiology Psychiatry - University of Pittsburgh United States Department of Diagnostic Radiology & Nuclear Medicine University of Maryland Baltimore United States

We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications. Many existing MDL techniques are model-dependent solutions which explicitly require nontrivial architectural changes to construct domain-specific modules. Thus, properly applying these MDL techniques for new problems with well-established models, e.g. U-Net for semantic segmentation, may demand various low-level implementation efforts. In this paper, given emerging multi-modal data (e.g., various structural neuroimaging modalities), we aim to enable MDL purely algorithmically so that widely used neural networks can trivially achieve MDL in a model-independent manner. To this end, we consider a weighted loss function and extend it to an effective procedure by employing techniques from the recently active area of learning-to-learn (meta-learning). Specifically, we take inner-loop gradient steps to dynamically estimate posterior distributions over the hyperparameters of our loss function. Thus, our method is model-agnostic, requiring no additional model parameters and no network architecture changes;instead, only a few efficient algorithmic modifications are needed to improve performance in MDL. We demonstrate our solution to a fitting problem in medical imaging, specifically, in the automatic segmentation of white matter hyperintensity (WMH). We look at two neuroimaging modalities (T1-MR and FLAIR) with complementary information fitting for our problem. © 2021, CC BY.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

AAAI 2008 workshop reports

AAAI 2008 workshop reports

引用

作者： Anand, Sarabjot Singh Bunescu, Razvan Carvcdho, Vitor Chomicki, Jan Conitzer, Vincent Cox, Michael T. Dignum, Virginia Dodds, Zachary Dredze, Mark Furcy, David Gabrilovich, Evgeniy Göker, Mehmet H. Guesgen, Hans Hirsh, Haym Jannach, Dietmar Junker, Ulrich Ketter, Wolfgang Kobsa, Alfred Koenig, Sven Lau, Tessa Lewis, Lundy Matson, Eric Metzler, Ted Mihalcea, Rada Mobasher, Bamshad Pineau, Joelle Poupart, Pascal Raja, Anita Ruml, Wheeler Sadeh, Norman Shani, Guy Shapiro, Daniel Smith, Trey Taylor, Matthew E. Wagstaff, Kiri Walsh, William Zhou, Rong Department of Computer Science University of Warwick United Kingdom School of Electrical Engineering and Computer Science Ohio University United States Microsoft Live Labs United States computer science and engineering University at Buffalo United States Computer science and economics Duke University United States Intelligent Computing group of BBN Technologies Utrecht University Netherlands Department of Computer science Harvey Mudd College United States University of Pennsylvania United States University of Wisconsin United States Yahoo Research PricewaterhouseCoopers Center for Advanced Research United States Department of Computer science School of Engineering and Advanced Technology Massey University New Zealand Departent of Computer science Rutgers University United States Department of Computer Science Dortmund University of Technology. Germany ILOG Rotterdam School of Management Erasmus University Netherlands Donald Bren School of Information and Computer Sciences University of California Irvine United States Depatrment of Computer science University of Southern California United States IBM Almaden Research Center United States Department of Computer Information Technology Southern New Hampshire University United States Computer and Information Technology Program College of Technology Purdue University United States Hughes Program for Religion and Science Dialogue Oklahoma City University United States Department of Computer Science and Engineering University of North Texas United States School of Computing DePaul University United States Department of Computer Science McGill University Canada School of Computer Science University of Waterloo Canada Department of Software and Information Systems University of North Carolina Charlotte United States University of New Hampshire United States Microsoft Research Institute for the Study of Learning and Expertise Applied Reactivity Inc. United States NASA Ames Research Center Carnegie Mellon University West

AAAI was pleased to present the AAAI-08 Workshop program, held Sunday and Monday, July 13-14, in Chicago, Illinois, USA. The program included the following 15 workshops: Advancements in POMDP Solvers;AI Education Workshop Colloquium;Coordination, Organizations, Institutions, and Norms in Agent systems, Enhanced Messaging;Human Implications of Human-Robot Interaction;intelligent Techniques for Web Personalization and Recommender systems;Metareasoning: Thinking about Thinking;Multidisciplinary Workshop on Advances in Preference Handling;Search in Artificial Intelligence and Robotics;Spatial and Temporal Reasoning;Trading Agent Design and Analysis;Transfer Learning for Complex Tasks;What Went Wrong and Why: Lessons from AI Research and Applications;and Wikipedia and Artificial Intelligence: An Evolving Synergy. Copyright © 2009, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Human robot interaction

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：