检索结果-内蒙古大学图书馆

Emerging technology (INCET), International Conference for

作者： Samundiswary Srinivsan R Sathya Bama Krishna Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai SIES Graduate School of Technology Navi Mumbai

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Deep Learning has been widely applied in all application domains namely Healthcare, Entertainment, Banking & finance, Agriculture, Aerospace & defence etc. Due to stupendous achievement of deep learning as a data processing technique has fascinated in all research areas. Handling of Deep learning in Banking and Financial sector is pervasive. Advancement of Information extraction especially because of different formats of information such as text, image, sound, video can be extracted simultaneously by the usage of deep learning techniques. This study reviews and analyses multimodal information extraction based on deep learning techniques especially on banking and financial sector. It aims to enhance the efficiency of document-intensive business tasks in the financial sector. Deep review analysis will be carried out to understand subtasks of Information extraction and techniques involved in Banking domain. Finally, how multimodal information extraction using deep learning enhances the efficiency than unimodal and its use cases in current AI based automation world will be highlighted.

关键词： Deep learning Surveys Systematics Reviews Semantics Finance Banking

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Sampling: A Framework for Imbalanced Classification With Overlapped Classes

Two-Stage Sampling: A Framework for Imbalanced Classificatio...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Firdausanti, Neni Alya Fatyanosa, Tirana Noor Data, Mahendra Mendonca, Israel Aritsugi, Masayoshi Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Computer Science Brawijaya University Malang Indonesia Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (纸本)9781665480451

Class imbalance and overlapping instances problems have long been recognized as one of the major causes of the performance deterioration of the classification model. Moreover, the majority class may have an irrelevant and noisy instance that shifts the decision boundary of the classification far away from the ideal one. We propose a framework for balancing the class distribution and mitigating the class overlap problem in a dataset. The key feature of our framework is its ability to detect the overlapping instances between classes and then remove the problematic instances from the majority class. Thus, it will have more precise information for the oversampling method to generate the synthetic minority instances. We evaluated the proposed framework using the Lending club and ten other datasets from the KEEL repository. We demonstrate the implementations of our framework using Tomek and Edited Nearest Neighbor for removing the overlapping instances from the majority class and SWIM-MD for generating the synthetic minority instances. Also, we used eight well-known classifiers to show that our proposed framework can improve the performance of various classifiers. Lastly, we present a detailed analysis of the experimental result that shows the superiority of our proposed framework. Our proposed framework outperformed the state-of-the-art methods in terms of geometry mean classification performance metric. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction

arXiv

引用

arXiv 2024年

作者： Bae, Inhwan Lee, Junoh Jeon, Hae-Gon AI Graduate School School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju Korea Republic of

Language models have demonstrated impressive ability in context understanding and generative performance. Inspired by the recent success of language foundation models, in this paper, we propose LMTraj (Language-based Multimodal Trajectory predictor), which recasts the trajectory prediction task into a sort of question-answering problem. Departing from traditional numerical regression models, which treat the trajectory coordinate sequence as continuous signals, we consider them as discrete signals like text prompts. Specially, we first transform an input space for the trajectory coordinate into the natural language space. Here, the entire time-series trajectories of pedestrians are converted into a text prompt, and scene images are described as text information through image captioning. The transformed numerical and image data are then wrapped into the question-answering template for use in a language model. Next, to guide the language model in understanding and reasoning high-level knowledge, such as scene context and social relationships between pedestrians, we introduce an auxiliary multi-task question and answering. We then train a numerical tokenizer with the prompt data. We encourage the tokenizer to separate the integer and decimal parts well, and leverage it to capture correlations between the consecutive numbers in the language model. Lastly, we train the language model using the numerical tokenizer and all of the question-answer prompts. Here, we propose a beam-search-based most-likely prediction and a temperature-based multimodal prediction to implement both deterministic and stochastic inferences. Applying our LMTraj, we show that the language-based model can be a powerful pedestrian trajectory predictor, and outperforms existing numerical-based predictor methods. Extensive experiments show that our LMTraj can successfully understand social relationships and accurately extrapolate the multimodal futures on the public pedestrian trajectory prediction bench

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Segmenting vegetation from UAV images via spectral reconstruction in complex field environments

引用

植物表型组学（英文） 2025年第1期7卷 212-224页

作者： Zhixun Pei Xingcai Wu Xue Wu Yuanyuan Xiao Peijia Yu Zhenran Gao Qi Wang Wei Guo State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China State Key Laboratory of Green Pesticide Guizhou UniversityGuiyang 550025China New Rural Development Research Institute Guizhou UniversityGuiyang550025China Graduate School of Agricultural and Life Sciences The University of TokyoTokyo188-0002Japan

Segmentation of vegetation remote sensing images can minimize the interference of background,thus achieving efficient monitoring and analysis for vegetation *** segmentation of vegetation poses a significant challenge due to the inherently complex environmental ***,there is a growing trend of using spectral sensing combined with deep learning for field vegetation segmentation to cope with complex ***,two major constraints remain:the high cost of equipment required for field spectral data collection;the availability of field datasets is limited and data annotation is time-consuming and *** address these challenges,we propose a weakly supervised approach for field vegetation segmentation by using spectral reconstruction(SR)techniques as the foundation and drawing on the theory of vegetation index(Ⅵ).Specifically,to reduce the cost of data acquisition,we propose SRCNet and SRANet based on convolution and attention structure to reconstruct multispectral images of fields,***,borrowing from the Ⅵprinciple,we aggregate the reconstructed data to establish the connection of spectral bands,obtaining more salient vegetation ***,we employ the adaptation strategy to segment the fused feature map using a weakly supervised method,which does not require manual labeling to obtain a field vegetation segmentation *** segmentation method can achieve a Mean Intersection over Union(MIoU)of 0.853 on real field datasets,which outperforms the existing *** addition,we have open-sourced a dataset of unmanned aerial vehicle(UAV)RGB-multispectral images,comprising 2358 pairs of samples,to improve the richness of remote sensing agricultural *** code and data are available at egment_SR,and .

关键词： Segmentation Spectral reconstruction UAV field images

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Network-based Models as Bahasa Indonesia-Sundanese Language Neural Machine Translator

Recurrent Neural Network-based Models as Bahasa Indonesia-Su...

引用

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

作者： Wijanarko, Bambang Dwi Heryadi, Yaya Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Online Learning Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Sequential data are available in many domains including weather observation data, stock price, gene sequence, and many others. Sequential data processing is very instrumental as a solution to a variety of downstream tasks in Natural Language Processing such as language translation. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, language translation is not an easy computation task when there is a language-resource gap. This paper presents some empirical results from the exploration of the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU), the Long Short-term Memory (LSTM), and the Bidirectional Long Short-term Memory (Bi-LSTM) models as machine translation models from Bahasa Indonesia to the Sundanese language. These empirical results show that the Bi-LSTM achieved the highest performance (0.95 average training accuracy and 0.92 average testings BLEU score) compared to the RNN (0.93 average training accuracy and 0.91 average testings BLEU score), the GRU (0.88 average training accuracy and 0.89 average testings BLEU score), and the LSTM (0.92 average training accuracy and 0.91 average testings BLEU score) models. These results validate some previously reported studies that claim the Bi-LSTM model potentially outperforms the other recurrent neural network-based models when it is used to process sequence datasets. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Positioning Control for Voice Coil Motor Using Unbalanced Multilevel Inverter Topology

Positioning Control for Voice Coil Motor Using Unbalanced Mu...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Takei, Gaku Obara, Hidemine Haneda, Ryo Nozaki, Takahiro Graduate School of Science and Technology Keio University Yokohama Japan Yokohama National University Department of Physics Electrical and Computer Engineering Yokohama Japan Keio University Department of System Design Engineering Yokohama Japan

ISBN: (纸本)9798331533892

This article proposes a new multi-level inverter (MLI) based on flying capacitor inverter (FCI), with focused on high-precision positioning control for a voice coil motor (VCM). Multi-level inverters (MLIs) have the characteristic that increasing the number of output voltage levels reduces the output voltage error. However, as the number of levels increases, the number of circuit elements increases, and the circuit becomes more complex. In addition, the output voltage amplitude for each level is constant in conventional inverters. As a result, such as high-precision positioning control of VCM, designing an appropriate inverter for a reference wave that contains a large amount of low-voltage components increases the number of circuit elements. Therefore, this paper proposes a MLI with two unbalanced dc-input voltages, referred to as unbalanced MLIs (UMLIs) hereinafter. This topology uses two different dc-input voltages, and it is possible to reduce the output voltage level in extremely low-voltage range compared to other voltage levels. Simulation results when the high-precision positioning control of the VCM confirm that the proposed UMLIs improves the control performance compared to the conventional FCIs with equal number of output voltage levels and uniform level widths. © 2025 IEEE.

关键词： motion control Multi-level inverter voice coil motor

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Nerve Injury Classification in Brachial Plexopathies Using Magnetic Resonance Neurography with Modified Hiking Optimization Algorithm

引用

Academic Radiology 2025年第7期32卷 3824-3840页

作者： Dahou, Abdelghani Elaziz, Mohamed Abd Khattap, Mohamed G. Hassan, Hend Galal Eldeen Mohamed Ali School of Computer Science and Technology Zhejiang Normal University Jinhua 321004 China Mathematics and Computer Science department University of Ahmed DRAIA Adrar 01000 Algeria Department of Mathematics Faculty of Science Zagazig University Zagazig 44519 Egypt Faculty of Computer Science and Engineering Galala University Suez 435611 Egypt Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Diagnostic Interventional Radiology and Molecular Imaging Faculty of Medicine Ain Shams University Cairo 11591 Egypt Technology of Radiology and Medical Imaging Program Faculty of Applied Health Sciences Technology Galala University Suez 435611 Egypt

Rationale and Objectives: Brachial plexopathies (BPs) encompass a complex spectrum of nerve injuries affecting motor and sensory function in the upper extremities. Diagnosis is challenging due to the intricate anatomy and symptom overlap with other neuropathies. Magnetic Resonance Neurography (MRN) provides advanced imaging but requires specialized interpretation. This study proposes an AI-based framework that combines deep learning (DL) with the modified Hiking Optimization Algorithm (MHOA) enhanced by a Comprehensive Learning (CL) technique to improve the classification of nerve injuries (neuropraxia, axonotmesis, neurotmesis) using MRN data. Materials and Methods: The framework utilizes MobileNetV4 for feature extraction and MHOA for optimized feature selection across different MRI sequences (STIR, T2, T1, and DWI). A dataset of 39 patients diagnosed with BP was used. The framework classifies injuries based on Seddon's criteria, distinguishing between normal and abnormal conditions as well as injury severity. Results: The model achieved excellent performance, with 1.0000 accuracy in distinguishing normal from abnormal conditions using STIR and T2 sequences. For injury severity classification, accuracy was 0.9820 in STIR, outperforming the original HOA and other metaheuristic algorithms. Additionally, high classification accuracy (0.9667) was observed in DWI. The proposed framework outperformed traditional methods and demonstrated high sensitivity and specificity. Conclusion: The proposed AI-based framework significantly improves the diagnosis of BP by accurately classifying nerve injury types. By integrating DL and optimization techniques, it reduces diagnostic variability, making it a valuable tool for clinical settings with limited specialized neuroimaging expertise. This framework has the potential to enhance clinical decision-making and optimize patient outcomes through precise and timely diagnoses. © 2025 The Association of University Radiologists

关键词： Brachial Plexopathy (BP) Comprehensive Learning (CL) Deep Learning (DL) Feature Selection (FS) Hiking Optimization Algorithm (HOA) Magnetic Resonance Neurography (MRN) MobileNetV4

来源：评论

学校读者我要写书评

暂无评论

An Incremental Learning Algorithm on Imbalanced Data for Network Intrusion Detection Systems 22

An Incremental Learning Algorithm on Imbalanced Data for Net...

引用

10th International Conference on computer and Communications Management, ICCCM 2022

作者： Data, Mahendra Aritsugi, Masayoshi Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Computer Science Brawijaya University Malang Indonesia Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (纸本)9781450396349

Incremental learning is a promising algorithm for creating an adaptive network intrusion detection system (IDS) model. In contrast with batch learning models, incremental learning models can be retrained easily when new network intrusion data emerge. Moreover, some incremental learning models, such as the Hoeffding Tree model, can be retrained only using latest training data. This advantage is appealing because computer networks produce enormous amounts of data every day. Using incremental learning models for detecting the ever-growing network intrusions can save computational resources while preserving the performance of the models. However, network data suffer from the imbalanced data problem where the data distribution of the classes in the training data is often severely disproportional. This imbalanced data problem is affecting the performance of incremental learning algorithms. To mitigate this problem, we propose an incremental learning algorithm for network IDSs that can learn from imbalanced data. Our proposed method is an ensemble incremental learning algorithm composed of the Hoeffding Tree, incremental Adaptive Boosting (AdaBoost), and Hard Sampling algorithms. The experimental results show that our proposed model has superior performance compared to the other incremental learning models tested in this study. Moreover, our proposed method increases the robustness of the incremental learning model against the imbalanced data problem. © 2022 ACM.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Application of Generalized Extreme Value Model Based on Bayesian Parameter Estimation in Extreme High Temperature Weather Analysis

Application of Generalized Extreme Value Model Based on Baye...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： Luo Jiaheng Luo Yinqi Li Jianping School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan Graduate School of University of Electronic Science and Technology of China Chengdu Sichuan

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

In order to analyze the distribution characteristics of extreme high temperature, this paper takes the maximum temperature data from 1960 to 2022 in Cengong County as the research object, and constructs a generalized extreme value model. Firstly, a preliminary statistical analysis of the maximum temperature data in Cengong County was carried out, revealing that although the distribution of maximum temperature and the normal distribution can indicate that there are fewer years of extreme high temperature, and the distribution trend is more consistent, there are obvious differences in the tail characteristics of the two parts. Modeling the sample data with a normal distribution can lead to underestimation of what will happen in extreme heat. Secondly, the Metropolis-Hastings sampling algorithm is used to simulate the MCMC of posterior distributed random samples, and the three-parameter simulation value of the generalized extreme value model is obtained, and the mean value is used as the parameter estimation value. Finally, the reproducibility levels under the 20-, 50-, and 100-year return periods were calculated by using the three-parameter simulation values of the posterior period. The results show that the Bayesian method can overcome the problem that the asymptotic normality of the maximum likelihood estimation is not necessarily true, and the parameters calculated based on the Bayesian method have a better effect on model fitting. At the same time, the generalized extreme model has good prediction ability, and the longer the prediction period, the more uncertain the future.

关键词： Analytical models Temperature distribution Maximum likelihood estimation Parameter estimation Computational modeling Fitting Predictive models Gaussian distribution Bayes methods Meteorology

来源：评论

学校读者我要写书评

暂无评论

Analysing Relaxation Effects Through Natural Experiences Using Natural Sounds and VR Devices

Analysing Relaxation Effects Through Natural Experiences Usi...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Yukizi Suzuki Yusuke Sekine Kiichi Tago Graduate School of Information and Computer Science Chiba Institute of Technology Narashino Japan

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

In recent years, studies have been conducted on virtual reality (VR) relaxation using VR devices to reduce stress. Our previous study suggested that VR relaxation using a virtual world, a 360-degree image, and a 360-degree video could produce comparable relaxation effects. However, in our study, the 360-degree image had no sound. The addition of natural sounds to the image may potentially enhance the relaxation effect. Therefore, this study aims to investigate the impact of incorporating natural sounds into the 360-degree image for relaxation. We employ five evaluation metrics to measure the relaxation effect: electroencephalography (EEG), heart rate, salivary amylase, State-Trait Anxiety Inventory (STAI), and a subjective stress questionnaire. These metrics are used to calculate the relaxation scores. The experimental results revealed a significant difference in relaxation scores derived from the EEG data. It suggests that adding natural sounds to 360-degree images can enhance the relaxation effect of VR relaxation.

关键词： Measurement Heart rate Anxiety disorders Virtual reality Human factors Forestry Medical services Electroencephalography Information technology Stress measurement

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：