检索结果-内蒙古大学图书馆

Annals of Data Science 2023年第3期10卷 619-635页

作者： Zehtab-Salmasi, Aidin Feizi-Derakhshi, Ali-Reza Nikzad-Khasmakhi, Narjes Asgari-Chenaghlu, Meysam Nabipour, Saeideh Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran Department Computer and Electrical Engineering University of Mohaghegh Ardabili Ardabil Iran

Price prediction is one of the examples related to forecasting tasks and is a project based on data science. Price prediction analyzes data and predicts the cost of new products. The goal of this research is to achieve an arrangement to predict the price of a cellphone based on its specifications. So, five deep learning models are proposed to predict the price range of a cellphone, one unimodal and four multimodal approaches. The multimodal methods predict the prices based on the graphical and non-graphical features of cellphones that have an important effect on their valorizations. Also, to evaluate the efficiency of the proposed methods, a cellphone dataset has been gathered from GSMArena. The experimental results show 88.3% F1-score, which confirms that multimodal learning leads to more accurate predictions than state-of-the-art techniques. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Price prediction Multimodal learning Convolutional neural network Inception Classification Prediction Multimodal Price Deep learning Data science Mobile phone

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Model for Segmentation of the Skin Lesion Based on Residual Attention U-Net

引用

computers, Materials & Continua 2023年第6期75卷 5177-5192页

作者： Saleh Naif Almuayqil Reham Arnous Noha Sakr Magdy M.Fadel Department of Information Systems College of Computer and Information SciencesJouf UniversitySakakaSaudi Arabia Department of Communications and Electronics Delta Higher Institute for Engineering and Technology(DHIET)MansouraEgypt Computers Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt

Skin segmentation participates significantly in various biomedical applications,such as skin cancer identification and skin lesion *** paper presents a novel framework for segmenting the *** framework contains two main stages:The first stage is for removing different types of noises from the dermoscopic images,such as hair,speckle,and impulse noise,and the second stage is for segmentation of the dermoscopic images using an attention residual U-shaped Network(U-Net).The framework uses variational Autoencoders(VAEs)for removing the hair noises,the Generative Adversarial Denoising Network(DGAN-Net),the Denoising U-shaped U-Net(D-U-NET),and Batch Renormalization U-Net(Br-U-NET)for remov-ing the speckle noise,and the Laplacian Vector Median Filter(MLVMF)for removing the impulse *** the second main stage,the residual attention u-net was used for *** framework achieves(35.11,31.26,27.01,and 26.16),(36.34,33.23,31.32,and 28.65),and(36.33,32.21,28.54,and 27.11)for removing hair,speckle,and impulse noise,respectively,based on Peak Signal Noise Ratio(PSNR)at the level of(0.1,0.25,0.5,and 0.75)of *** framework also achieves an accuracy of nearly 94.26 in the dice score in the process of segmentation before removing noise and 95.22 after removing different types of *** experiments have shown the efficiency of the used model in removing noise according to the structural similarity index measure(SSIM)and PSNR and in the segmentation process as well.

关键词： Skin tumor speckle noise impulse noise hair noise deep learning segmentation

来源：评论

学校读者我要写书评

暂无评论

Gradient Optimizer Algorithm with Hybrid Deep Learning Based Failure Detection and Classification in the Industrial Environment

引用

computer Modeling in engineering & Sciences 2024年第2期138卷 1341-1364页

作者： Mohamed Zarouan Ibrahim M.Mehedi Shaikh Abdul Latif Md.Masud Rana Department of Electrical and Computer Engineering(ECE) King Abdulaziz UniversityJeddah21589Saudi Arabia Center of Excellence in Intelligent Engineering Systems(CEIES) King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Nuclear Engineering King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical and Electronic Engineering Rajshahi University of Engineering and TechnologyRajshahiBangladesh

Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Industry ***, various modernized industrial processes have been equipped with quite a few sensors to collectprocess-based data to find faults arising or prevailing in processes along with monitoring the status of *** diagnosis of rotating machines serves a main role in the engineering field and industrial production. Dueto the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experienceand human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’sinterest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDLFDC)in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelettransform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residualnetwork (ResNet18) model was exploited for the extraction of features from the vibration signals which are thenfed into theHDLmodel for automated fault detection. Finally, theGOA-based hyperparameter tuning is performedtoadjust the parameter valuesof theHDLmodel *** experimental result analysis of the GOAHDL-FD Calgorithm takes place using a series of simulations and the experimentation outcomes highlight the better resultsof the GOAHDL-FDC technique under different aspects.

关键词： Fault detection Industry 4.0 gradient optimizer algorithm deep learning rotating machineries artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Abnormal Activity Detection and Classification of Bus Passengers with In-Vehicle Image Sensing

引用

IEEE Access 2024年 12卷 23057-23065页

作者： Lin, Huei-Yung Tseng, Chun-Han National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106 Taiwan National Chung Cheng University Department of Electrical Engineering Chiayi621 Taiwan

As the self-driving technology is getting mature for public transportation applications, the safety concern of onboard passengers has become an important issue. It is essential to identify inappropriate or hazardous behaviors of passengers for the vehicles without human operators. In this work, we propose a technique to detect and classify the abnormal activities of passengers in a bus environment. Different from the existing human activity classification algorithms, our approach reduces the occlusion and increases the recognition rate by acquiring images from an overhead vision system. To overcome the increased complexity on feature extraction and classification, an action recognition network for top-view images are proposed by incorporating both spatial and temporal information. An image dataset, BUS-HAR, is generated for practical application scenarios with bus passengers. Experiments using real-world scene images have demonstrated the feasibility of our technique compared to existing approaches. The codes and image dataset are made available publicly at https://***/richardkuo1999/passenger-action-recognition. © 2013 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Disparity Computation With Low Intensity Quantization on Stereo Image Pairs

IEEE Transactions on Computational Imaging

引用

IEEE Transactions on Computational Imaging 2024年 10卷 318-328页

作者： Lin, Huei-Yung Hsu, Tsai-Yu National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan National Chung Cheng University Department of Electrical Engineering Minhsiung621301 Taiwan

From variate bit-rate stereo matching, it is observed that the image pair with a low intensity quantization level is still capable of providing good disparity maps. In this article, a mathematical model representing the level of disparity discontinuity is proposed to formulate the mismatching prediction based on the intensity quantization. It is used to derive the minimum quantization level for quality-assured stereo matching. Due to the high computational cost of stereo processing, the reduction of image data usage will benefit both network training and real-time inference. The formulation presented in this work is investigated extensively for various types of scenes for disparity computation. In the experiments, the feasibility of our approach is validated with Middlebury, KITTI 2015, and synthetic Scene Flow datasets. © 2015 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Secure speaker identification in open and closed environments modeled with symmetric comb filters

引用

Multimedia Tools and Applications 2025年第18期84卷 19147-19189页

作者： Shafik, Amira Monir, Mohamad El-Shafai, Walid Khalaf, Ashraf A. M. Nassar, M.M. El-Fishawy, Adel S. El-Din, M. A. Zein Dessouky, Moawad I. El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Minia University Minia61519 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Speech is a fundamental means of human interaction. Speaker Identification (SI) plays a crucial role in various applications, such as authentication systems, forensic investigation, and personal voice assistance. However, achieving robust and secure SI in both open and closed environments remains challenging. To address this issue, researchers have explored new techniques that enable computers to better understand and interact with humans. Smart systems leverage Artificial Neural Networks (ANNs) to mimic the human brain in identifying speakers. However, speech signals often suffer from interference, leading to signal degradation. The performance of a Speaker Identification System (SIS) is influenced by various environmental factors, such as noise and reverberation in open and closed environments, respectively. This research paper is concerned with the investigation of SI using Mel-Frequency Cepstral Coefficients (MFCCs) and polynomial coefficients, with an ANN serving as the classifier. To tackle the challenges posed by environmental interference, we propose a novel approach that depends on symmetric comb filters for modeling. In closed environments, we study the effect of reverberation on speech signals, as it occurs due to multiple reflections. To address this issue, we model the reverberation effect with comb filters. We explore different domains, including time, Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Discrete Sine Transform (DST) domains for feature extraction to determine the best combination for SI in case of reverberation environments. Simulation results reveal that DWT outperforms other transforms, leading to a recognition rate of 93.75% at a Signal-to-Noise Ratio (SNR) of 15 dB. Additionally, we investigate the concept of cancelable SI to ensure user privacy, while maintaining high recognition rates. Our simulation results show a recognition rate of 97.5% at 0 dB using features extracted from speech signals and their DCTs. Fo

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing

引用

Multimedia Tools and Applications 2025年第17期84卷 18071-18093页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. T

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A novel deep dual self-attention and Bi-LSTM fusion framework for Parkinson’s disease prediction using freezing of gait: a biometric application

引用

Multimedia Tools and Applications 2024年第33期83卷 80179-80200页

作者： Habib, Zeeshan Mughal, Muhammad Ali Khan, Muhammad Attique Hamza, Ameer Alturki, Nazik Jamel, Leila Department of Electrical Engineering HITEC University Taxila Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia

Parkinson’s disease (PD) disorder is caused by the imbalance of inhibitory dopamine and excitatory acetylcholine neurotransmitters, which causes hindrance in locomotion. Freezing of gait (FOG), tremors, and bradykinesia are the most debilitating and disconcerting symptoms of Parkinson’s Disease (PD). FOG episodes occur due to neurological control disorder and motorized impairments, which sternly hinder voluntary movement and forward locomotion. The computational intelligence techniques can effectively predict PD from the sensor data. To detect the FOG episodes often experienced by PD patients, this paper utilizes a 5G spectrum that operates at 4.8 GHz. The main idea of the proposed system is to extract the wireless channel characteristics information (containing amplitude variances) that can be integrated into a 5G communication system. This system collects data through wireless devices such as dipole antennas, network interface cards, and RF signal generators. Five human activities were performed: fast walking, slow walking, sitting on a chair, FOG episodes, and voluntary stopping. We proposed a novel deep dual self-attention and Bi-LSTM fusion architecture for PD prediction to train the collected dataset. Two architectures have been proposed, namely Deep Dual Attention Neural Network (D2ANN) and BiLSTM Neural Network (BNN), for the classification of PD using Chanel State information (CSI) data. After that, the most prominent information is extracted using self-attention activation. A newly informed weighted fusion approach is proposed, and tree growth optimization is employed for the best feature selection. Finally, the selected features are classified using a multilayer full SoftMax neural network. The experimental process was conducted on FOG wireless sensor network data and obtained the highest accuracy of 98.66%. Compared to the results with state-of-the-art techniques, the proposed framework shows improved accuracy, recall, and precision rates. © The Author(s

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

FA-FENet: A Feature Attention Front-End Network Based on a Lightweight CNN Architecture for Recognizing Abnormal Underwater Illegal Fishing Behavior

引用

IEEE Access 2025年 13卷 87753-87776页

作者： Huang, Xiang-Rui Chen, Liang-Bi National Penghu University of Science and Technology Department of Electrical Engineering Penghu880011 Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu880011 Taiwan

In the past decade, studies on illegal fishing have neglected to consider illegal underwater fishing. Traditionally, supervisor-based methods have been used to manually interpret underwater behavior;however, existing artificial intelligence (AI) and Internet of Things (IoT) methods are not applicable to illegal underwater fishing. Therefore, in this study, we used a computer vision AI method to perform the challenging task of illegal underwater fishing image recognition. Illegal underwater fishing images have unclear features and high feature similarity. In this study, we define normal underwater travel as wearing diving clothing. Abnormal underwater behavior includes underwater personnel with illegal fishing equipment. Herein, we propose a feature attention front-end network (FA-FENet), a novel end-to-end convolutional neural network (CNN) architecture that differs from previous methods in that it allows flexible integration with various backbone networks. The front end of the backbone network can be directly replaced to improve the learning efficiency and performance of the proposed network. The convolutional layers in our proposed FA-FENet include dilated convolutions, group convolutions, padded convolutions, pooling layers, and activation functions. We also comprehensively review the performance of the proposed FA-FENet. A series of ablation studies demonstrate that the proposed FA-FENet can be applied in shallow backbone networks. In addition, FA-FENet has potential in emerging networks with good performance in illegal underwater fishing identification tasks. Finally, we conducted experiments with an underwater fishing behavior dataset. The experimental results demonstrate that our proposed method outperforms recently reported methods with attention mechanisms. Specifically, FA-FENet-RegNet achieves an accuracy of 88.81%, FA-FENet-ResNet18 reaches 78.32%, and FA-FENet-ShuffleNetV2 attains 80.41%. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reducing Barriers in Analyzing Eye Tracking Data: The Development of a GUI to Preprocess Eye Tracking Data

Reducing Barriers in Analyzing Eye Tracking Data: The Develo...

引用

2024 systems and information engineering Design Symposium, SIEDS 2024

作者： Atweh, Jad A. Tabbara, Ihab Nasrallah, Ghady Riggs, Sara L. University of Virginia Department of Systems and Information Engineering CharlottesvilleVA United States American University of Beirut Department of Electrical and Computer Engineering Beirut Lebanon

ISBN: (纸本)9798350385144

By capturing gaze points and eye movement patterns, eye tracking technology enables researchers to gain insights into visual attention, cognitive processes, and human behavior. Raw eye tracking data is inherently noisy, containing coordinates with occasional invalid entries. Researchers commonly face the challenge of cleaning and refining this data before proceeding to calculate essential eye tracking metrics. Critical preprocessing steps involve filtering out noise, detecting events such as fixations and saccades, and deriving metrics such as fixation duration, saccade amplitude, and more. This paper introduces a tool that provides users with the ability to preprocess data from both Gazepoint and FOVIO eye trackers. The methodology adopted for this line of work is based on Nyström and Holmqvist's (2010) data and velocity-driven algorithm. Preliminary results show the methodology developed as part of this line of work is promising in terms of improved accuracy and reliability in detecting fixations and saccades. Furthermore, this code and its versatile Graphical User Interface (GUI) has been successfully employed in multiple studies. Finally, we present supplementary code for calculating various eye tracking metrics and percent gaze overlap, extending the utility of our tool for in-depth analysis of visual attention and collaborative gaze behavior. © 2024 IEEE.

关键词： Eye tracking

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：