检索结果-内蒙古大学图书馆

24th International Congress on Acoustics, ICA 2022

作者： Park, Kyeong Wan Lee, Geon Woo Kim, Hong Kook School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Korea Republic of

This paper proposes a neural network-based end-to-end multi-channel speech enhancement model that operates in time domain. To this end, a triple-path transformer network (TPTN) is proposed to extract clean speech features by replacing the attentive recurrent neural networks (RNNs) with transformers in the triple-path attentive recurrent network (TPARN) framework. The proposed TPTN is composed of an intra-chunk transformer, an inter-chunk transformer, and an inter-channel transformer. Thus, a series of TPTNs are applied to the speech features converted from multi-channel speech signals so that extracted features are represented with local and global temporal dependencies as well as spatial dependencies. The performance of the proposed TPTN-based multi-channel speech enhancement model was evaluated on the CHiME3 dataset by measuring the short-time objective intelligibility (STOI) score and perceptual evaluation of speech quality (PESQ) score. It was shown from the experiment that the proposed TPTN-based model achieved similar STOI score to and higher PESQ score by 0.15 than the TPARN-based model, while the number of parameters of the proposed model was smaller than that of the TPARN-based model. © ICA *** rights reserved

关键词： Deep Learning End-to-end model Multi-channel Speech enhancement Transformer

来源：评论

学校读者我要写书评

暂无评论

Analysis of Factors Influencing Decisions to Purchase Airline Tickets Online during the Covid-19 Pandemic

Analysis of Factors Influencing Decisions to Purchase Airlin...

引用

2023 International Conference on computer science, Information technology and Engineering, ICCoSITE 2023

作者： Lie, Yulius Perbangsa, Anzaludin Samsinga Pardamean, Bens Bina Nusantara University School of Information Systems Information System Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

The background of this research is the condition of the covid-19 pandemic which has an impact on online ticket sales. Meanwhile, when future of covid-19 pandemic is starting to become clearer, we are going to have a lot more infections but hopefully a lot fewer hospitalizations, people began to travel long distances that had been delayed by implementing health protocols. Airfare competition can influence the decision to buy airline tickets. Various things have been done to attract the attention of buyers. This research is a non-experimental quantitative research. Population in this research was people who have purchased plane tickets online during the covid-19 pandemic, and the sample were 113 respondents age between 15 and 64. Sampling technique used was simple random sampling. Analysis of the data used in this study using multicollinearity, heteroscedasticity, multiple linear, T-test, F-test, and coefficient of determination test. It was concluded that price, promotion, and lifestyle variables can influence online purchasing decisions. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Multi-task RetinaNet for Mitosis Detection 25th

Multi-task RetinaNet for Mitosis Detection

引用

25th International Conference on Medical Image Computing and computer-Assisted Intervention , MICCAI 2022

作者： Wang, Ziyue Chen, Yang Fang, Zijie Bian, Hao Zhang, Yongbing Department of Computer Science Harbin Institute of Technology Harbin China Shenzhen International Graduate School Tsinghua University Beijing China

ISBN: (纸本)9783031336577

The count of mitotic cells is a key feature in tumor diagnosis. However, due to the variability of mitotic cell morphology, detecting mitotic cells in tumor tissues is a highly challenging task. At the same time, the performance of the trained models often declines when there is a vast difference between the source domain and the target domain. (i.e., the different tumor types and scanners). Therefore, it is necessary to develop algorithms for detecting mitotic cells with robustness in domain shift scenarios. Our work proposes a foreground detection and tumor classification task based on the baseline (Retinanet) and utilizes data augmentation to improve our model’s detection ability and domain generalization performance. We achieve excellent performance on the challenging preliminary test dataset (F1 score: 0.5809) and the Final test dataset (F1:0.6300). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

ACO with Reinforcement Learning Applied to Rescues Operations on Urban Forests 13

ACO with Reinforcement Learning Applied to Rescues Operation...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Alves, Cláudio Mendonça, Israel De Almeida Guimarães, Vanessa González, Pedro Henrique System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan Coppead Graduate Business School Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9798350308365

In the context of smart cities where green infras-tructure is incentived, besides important benefits like regulating temperatures and absorbing pollutants among others, tour by urban forests is a way to experience closer contact with nature near of big urban centers. Eventually, visitors get lost, and helping these people with velocity is important to avoid severe incidents. Normally, rescue operations mobilize firefighters, ex-pensive equipment like helicopters and public resources. Following that idea of reducing search time in rescue operations, this paper considers the Data Mule Routing Problem with Limited Autonomy (DMRP-wLA). To find high-quality solutions, this paper proposes an Ant Colony Optimization algorithm enhanced with Reinforcement Learning to create an adaptive decision-making algorithm. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Correlating the Ambient Conditions and Performance Indicators of the LoRaWAN via Surrogate Gaussian Process-Based Bidirectional LSTM Stacked Autoencoder

引用

IEEE Transactions on Network and Service Management 2023年第3期20卷 3413-3427页

作者： Bhat, Showkat Ahmad Huang, Nen-Fu Hussain, Imtiyaz Sajjad, Uzair National Tsing Hua University College of Electrical and Computer Science Hsinchu1300044 Taiwan National Tsing Hua University Department of Computer Science Hsinchu1300044 Taiwan National Taipei University of Technology Graduate Program in Energy and Opto-Electronic Materials Taipei10608 Taiwan National Taipei University of Technology Department of Energy and Refrigerating Airconditioning Engineering Taipei10608 Taiwan

LoRa's biggest advantage is its flexibility, which is the ability to increase or decrease data rate and range while decreasing or increasing sensitivity. Whenever propagation conditions change frequently, this function allows the spreading factor to be modified accordingly. Despite their efficiency and scalability, adaptive data rate algorithms ignore and fail to factor in the complex correlation between ambient weather parameters influencing the communication channel design. In this research, a Bayesian surrogate Gaussian process-based bidirectional LSTM stacked autoencoder model (BSGP-BLSTM-SAE) is proposed to estimate the channel performance indicators such as received signal strength indicator (RSSI) and signal-to-noise ratio (SNR) and to determine the correlation between the ambient weather conditions and performance indicators for the LoRaWAN network. Bayesian optimization algorithm has been used to optimize the hyper-parameters of the developed model. A LoRaWAN experimental multivariate time series dataset has been used for the evaluation of the developed model, which upon testing and validation produces high accuracy in predicting the channel performance indicators and ambient conditions of the experimental LoRaWAN network. The mean absolute error of the developed model was around 0.45. Thus, the proposed model can predict the link performance indicators and thereby assist in real-time optimization of the transmission parameters to enhance the network performance in LoRaWAN-based systems at different ambient conditions. © 2004-2012 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第8期34卷 5122-5132页

作者： Huang, Shih-Chia Hoang, Quoc-Viet Le, Trung-Hieu National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology International Graduate Program in Electrical Engineering and Computer Science Taipei10608 Taiwan Hung Yen University of Technology and Education Faculty of Information Technology Hungyen 17000 Viet Nam

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Adoption of Artificial Intelligence technology in Parking Security System 7th

The Adoption of Artificial Intelligence Technology in Parkin...

引用

7th International Conference on Inventive Systems and Control, ICISC 2023

作者： Alhafizh, Muhammad Rifqi Adriawan, Albertus Baskara Yunandito Fernaldy, Darryl Gaol, Ford Lumban Matsuo, Tokuro Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program—Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Advanced Institute of Industrial Technology Tokyo Japan

ISBN: (纸本)9789819916238

Artificial intelligence (AI) refers to human-like intelligence exhibited by computers, robots, or other machines. In popular use, artificial intelligence refers to the ability of a computer or machine to mimic the ability of the human mind to learn from examples and experiences, recognize objects, understand and respond to language, make decisions, solve problems, and combine these and other abilities to perform functions that humans might perform. Artificial intelligence requires experience and data to smarten up the technology. The most important things in making artificial intelligence are learning, reasoning, and self-correction. At the learning stage, AI gives machines the ability to learn tasks without requiring a defined programming language. Then, the reasoning stage is the stage where the reason AI is applied in a technology. The self-correction stage is the stage where the AI is refining itself from and learning from experience in order to minimize errors or problems that exist. Then, this matter is concerned with the parking lot to be discussed. Parking can be interpreted as public facilities available in agencies or offices that serve to store vehicles. Vehicles entering the parking area become tens or even thousands, because it requires a parking system and management area. Such arrangements are capable of parking procedures and even other support systems such as adequate parking facilities and infrastructure, and another function is to create and develop parking systems in general to provide safety and comfort. The methodology obtained from this problem is checking the research model to check and find out the comparison of vehicle user’s Parking System Security between cars or motorcycles, as well as the usual parking lots visited. Then, we created a questionnaire. This study used questionnaires with the aim to get respondents’ results about the Parking Security System. Our sampling method is based on respondents aged 17–20 years. Questionnaires are su

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Explorations of using a convolutional neural network to understand brain activations during movie watching

引用

Psychoradiology 2024年第1期4卷 187-195页

作者： Wonbum Sohn Xin Di Zhen Liang Zhiguo Zhang Bharat B.Biswal Department of Biomedical Engineering New Jersey Institute of TechnologyNewarkNJ 07102USA Rutgers Biomedical and Health Sciences Rutgers School of Graduate StudiesNewarkNJ 07039USA School of Biomedical Engineering Health Science CenterShenzhen UniversityShenzhen51806China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518060China

Background Naturalistic stimuli,such as videos,can elicit complex brain ***,the intricate nature of these stimuli makes it challenging to attribute specific brain functions to the resulting activations,particularly for higher-level processes such as social *** We hypothesized that activations in different layers of a convolutional neural network(VGG-16)would correspond to varying levels of brain activation,reflecting the brain's visual processing ***,we aimed to explore which brain regions would be linked to the deeper layers of the *** This study analyzed functional MRI data from participants watching a cartoon *** a pre-trained VGG-16 convolutional neural network,we mapped hierarchical features of the video to different levels of brain *** maps from various kernels and layers were extracted from video frames,and the time series of average activation patterns for each kernel were used in a voxel-wise model to examine brain *** Lower layers of the network were primarily associated with activations in lower visual regions,although some kernels also unexpectedly showed associations with the posterior cingulate *** layers were linked to more anterior and lateral regions of the visual cortex,as well as the supramarginal *** This analysis demonstrated both the potential and limitations of using convolutional neural networks to connect video content with brain functions,providing valuable insights into how different brain regions respond to varying levels of visual processing.

关键词： convolutional neural network deep learning default mode network lateral occipital complex naturalistic condition supramarginal gyrus visual cortex

来源：评论

学校读者我要写书评

暂无评论

Enhancing Incremental Learning of CNN model using Filtered New Added Samples Assisted with XAI

Enhancing Incremental Learning of CNN model using Filtered N...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Chang, Kuei-Chung Kuo, Chun-Yu National Yunlin University of Science and Technology International Graduate School of Artificial Intelligence Taiwan Feng Chia University Dept. of Information Engineering and Computer Science Taiwan

ISBN: (纸本)9798350324174

In the incremental learning technique, the accuracy of the model is improved by increasing the number of training samples. However, there are some problems when making this training mode. First, it is not known whether the newly added training samples will affect the learning effect of the model. Second, we know the result of the model identification, but we don't know what features are used to identify this object. In this paper, we propose a training dataset curation approach to improve model accuracy with incremental learning. To select the most appropriate explainable AI (XAI) method, we use the intersection over union (IOU) metric to measure the range calculation of real objects and model features to know the rationality of the model explanation. As we know that increase suitable training samples can improve the accuracy of the model, we added the XAI method to filter out new samples that are not suitable for the training set. We use the crack identification dataset in our method, and the accuracy can be improved from 0.895 to 0.93. © 2023 IEEE.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Development of a Model for Discriminating Electroencephalograms of Patients with Mild Cognitive Impairment and Healthy Individuals Using a Support Vector Machine 13

Development of a Model for Discriminating Electroencephalogr...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Tanabe, Akifumi Nakatani, Kyosuke Harachi, Kento Yamamoto, Yusuke Muramatsu, Ayumi Nagahara, Hajime Takemura, Noriko Shimojo, Shinji Furihata, Daisuke Mizuno-Matsumoto, Yuko Kamae-Shigenobu, Kazue Shinosaki, Kazuhiro Graduate School of Information Science University of Hyogo Kobe Japan School of Life Science and Technology Tokyo Institute of Technology Yokohama Japan Aino University Department of Medical Engineering Ibaraki Japan Institute for Datability Science Osaka University Suita Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Aomori University Faculty of Software and Information Technology Aomori Japan Osaka University Cyber Media Center Suita Japan Asakayama General Hospital Sakai Japan

ISBN: (纸本)9798350373332

We performed machine learning using spectrum analysis and power spectra of electroencephalograms (EEGs) of patients with mild cognitive impairment (MCI). Spectrum analysis was performed on the EEGs of MCI patients and healthy individuals, and the power spectrum values of the two groups were calculated and compared. Based on the power spectrum values of the theta and alpha bands, models for discriminating MCI patients were created using a support vector machine (SVM), and their accuracies were compared. In the spectrum analysis, the theta band showed significantly higher power spectrum values in the MCI group. In the comparison of the accuracies of SVM models, the model using the theta band showed higher values in parameters, such as accuracy rate. These results suggested that the power spectrum values of the theta band are useful for discriminating MCI patients. © 2024 IEEE.

关键词： Electroencephalography

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：