检索结果-内蒙古大学图书馆

Forecasting Directional Movement of Stock Prices using Deep Learning

Annals of Data Science 2023年第5期10卷 1361-1378页

作者： Chandola, Deeksha Mehta, Akshit Singh, Shikha Tikkiwal, Vinay Anand Agrawal, Himanshu Department of Electrical Engineering and Computer Science York University Toronto Canada Hebert Werthim College of Engineering University of Florida Gainesville Gainesville United States Department of Electronics and Communication Engineering Jaypee Institute of Information Technology Noida India Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Stock market’s volatile and complex nature makes it difficult to predict the market situation. Deep Learning is capable of simulating and analyzing complex patterns in unstructured data. Deep learning models have applications in image recognition, speech recognition, natural language processing (NLP), and many more. Its application in stock market prediction is gaining attention because of its capacity to handle large datasets and data mapping with accurate prediction. However, most methods ignore the impact of mass media on the company’s stock and investors’ behaviours. This work proposes a hybrid deep learning model combining Word2Vec and long short-term memory (LSTM) algorithms. The main objective is to design an intelligent tool to forecast the directional movement of stock market prices based on financial time series and news headlines as inputs. The binary predicted output obtained using the proposed model would aid investors in making better decisions. The effectiveness of the proposed model is assessed in terms of accuracy of the prediction of directional movement of stock prices of five companies from different sectors of operation. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Methods for Enhancing Parkinson's Disease Early Detection 4

Hybrid Deep Learning Methods for Enhancing Parkinson's Disea...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Devi, S. Vijaya Amala Vijayalakshmi, K. Krishnan, R. Santhana Raj, J. Relin Francis Umesh, R. Soundiraraj, N. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Velammal College of Engineering and Technology Department of Information Technology Madurai India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India

ISBN: (纸本)9798331523923

Parkinson's Disease (PD) is a progressive neurodegenerative disorder that significantly impacts motor function. Early detection is critical for effective intervention, yet traditional diagnostic methods often face limitations in accuracy and timeliness. This paper proposes a hybrid deep learning model combining EfficientNet, BiLSTM, and GANs to improve PD detection accuracy using medical images and sequential data. EfficientNet is employed for extracting features from MRI scans, while BiLSTM is used to analyze temporal data, such as gait and speech patterns, to capture the progressive changes associated with PD. Additionally, GANs are utilized to augment the dataset, addressing the challenges of data scarcity and imbalance. The fusion of spatial and temporal features enables a more comprehensive understanding of PD, improving diagnostic performance. Bayesian optimization is applied for hyperparameter tuning, and K-fold cross-validation ensures robust model evaluation. The results demonstrate that the hybrid model outperforms single-modal approaches in both classification and regression tasks, offering enhanced accuracy in detecting PD and predicting disease severity. Furthermore, interpretability techniques like Grad-CAM and attention mechanisms are incorporated to provide insights into the model's decision-making process. This work presents a promising approach for automating PD diagnosis and lays the groundwork for further research in multi-modal deep learning for disease detection. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Federated Multiarmed Bandits Under Byzantine Attacks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1488-1501页

作者： Saday, Artun Demirel, Ilker Yildirim, Yigit Tekin, Cem Bilkent University Department of Electrical and Electronics Engineering Ankara06800 Turkey Massachusetts Institute of Technology Computer Science & Artificial Intelligence Laboratory CambridgeMA02139 United States

Multiarmed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multiarmed bandits (FMAB) is an emerging framework where a cohort of learners with heterogeneous local models play an MAB game and communicate their aggregated feedback to a server to learn a globally optimal arm. Two key hurdles in FMAB are communication-efficient learning and resilience to adversarial attacks. To address these issues, we study the FMAB problem in the presence of Byzantine clients who can send false model updates threatening the learning process. We analyze the sample complexity and the regret of β-optimal arm identification. We borrow tools from robust statistics and propose a median-of-means (MoM)-based online algorithm, Fed-MoM-UCB, to cope with Byzantine clients. In particular, we show that if the Byzantine clients constitute less than half of the cohort, the cumulative regret with respect to \beta-optimal arms is bounded over time with high probability, showcasing both communication efficiency and Byzantine resilience. We analyze the interplay between the algorithm parameters, a discernibility margin, regret, communication cost, and the arms’ suboptimality gaps. We demonstrate Fed-MoM-UCB's effectiveness against the baselines in the presence of Byzantine attacks via experiments. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Convolutional Neural Network with Pose Estimation for Human Activity Recognition

引用

computer Systems Science & engineering 2023年第2期44卷 1719-1733页

作者： S.Nandagopal G.Karthy A.Sheryl Oliver M.Subha Department of Computer Science and Engineering Nandha College of TechnologyErode638052TamilnaduIndia Department of Electronics and Communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126TamilnaduIndia Department of Computer Science and Engineering St.Joseph's College of EngineeringChennai600119TamilnaduIndia Department of Electronics and Communication Engineering University College of Engineering NagercoilNagercoil629004TamilnaduIndia

Human Action Recognition(HAR)and pose estimation from videos have gained signiﬁcant attention among research communities due to its applica-tion in several areas namely intelligent surveillance,human robot interaction,robot vision,*** considerable improvements have been made in recent days,design of an effective and accurate action recognition model is yet a difﬁcult process owing to the existence of different obstacles such as variations in camera angle,occlusion,background,movement speed,and so *** the literature,it is observed that hard to deal with the temporal dimension in the action recognition *** neural network(CNN)models could be used widely to solve *** this motivation,this study designs a novel key point extraction with deep convolutional neural networks based pose estimation(KPE-DCNN)model for activity *** KPE-DCNN technique initially converts the input video into a sequence of frames followed by a three stage process namely key point extraction,hyperparameter tuning,and pose *** the keypoint extraction process an OpenPose model is designed to compute the accurate key-points in the human ***,an optimal DCNN model is developed to classify the human activities label based on the extracted key *** improving the training process of the DCNN technique,RMSProp optimizer is used to optimally adjust the hyperparameters such as learning rate,batch size,and epoch *** experimental results tested using benchmark dataset like UCF sports dataset showed that KPE-DCNN technique is able to achieve good results compared with benchmark algorithms like CNN,DBN,SVM,STAL,T-CNN and so on.

关键词： Human activity recognition pose estimation key point extraction classiﬁcation deep learning RMSProp

来源：评论

学校读者我要写书评

暂无评论

Suppression of over voltage in SiC-based inverter fed induction motor

引用

Australian Journal of Electrical and electronics engineering 2024年第1期21卷 11-28页

作者： Salau, Ayodeji Olalekan Kanchana, Kadirvel Anoop, Kuttichakku Johny Markus, Elisha Didam Braide, Sepiribo Lucky Department of Electrical/Electronics and Computer Engineering Afe Babalola University Ado-Ekiti Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electrical Electronics Engineering Saveetha Engineering College Chennai India Department of Electrical and Electronics Engineering VISAT Engineering College Kerala Ernakulam India Department of Electrical/Electronic and Computer Engineering Central University of Technology Free State Bloemfontein South Africa Department of Electrical/Electronic Engineering University of Port Harcourt Rivers State Choba Nigeria

Silicon carbide (SiC) based inverters are widely used due to their fast switching and ability to withstand high temperatures and Voltage. This helps to increase efficiency and reduces switching losses compared to the silicon-based inverter. However, this fast-switching device causes an increase in the Voltage at the junction of the cable and motor due to the reflected wave. The main causes of overvoltage are cable/motor impedance mismatch, fast-switching inverter devices (IGBT), and inverter-motor separation. To extend the induction motor lifespan, overvoltage reduction is necessary. Passive and active filters solve the problem, but passive filters are bulky and have high power loss. This paper presents a shunt active filter approach for an inverter-fed induction motor to reduce overvoltage. To show the effectiveness of the proposed approach, the findings were compared to the topology of the clamp-type active filter already in use. The shunt active filter used Proportional Integral (PI) and fuzzy controllers to generate reference current according to the Synchronous Reference Frame (SRF) theory. Harmonics in the power system were removed using the SRF theory. The unique aspect of this work is how the reference current is produced in the shunt active filter using the SRF theory. The proposed shunt active filter with a fuzzy controller was added to the hardware implementation to achieve better results than previous active filters. ©, Engineers Australia.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Low-power test pattern generator using modified LFSR

引用

Aerospace Systems 2024年第1期7卷 67-74页

作者： Govindaraj, V. Dhanasekar, S. Martinsagayam, K. Pandey, Digvijay Pandey, Binay Kumar Nassa, Vinay Kumar Department of Electronics and Communication Engineering Dr NGP Institute of Technology Coimbatore641048 India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore641202 India Department of Electronics and Communication Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India Department of Technical Education Uttar Pradesh Kanpur India Department of Information Technology College of Technology Govind Ballabh Pant University of Agriculture and Technology Pantnagar Udham Singh Nagar Uttarakhand India Computer Science Engineering Department Rajarambapu Institute of Technology Rajaramnagar Sakharale Tel Walwa Dist Sangli Maharashtra Islampur415414 India

Low-power designs are getting increased significance in numerous applications like high-performance computing and wireless communication due to the rise in power dissipation. Power dissipation of VLSI (very large scale integration) circuits in test mode is much higher than in the normal operation mode due to the high frequency of applied test patterns. Product lifetime, yield, reduced performance, and circuit damage will result from this additional power consumption in testing. Therefore, the main objective of today’s test applications is to minimize power dissipation by increasing the correlation of applied successive test vectors. Low-power test pattern generator (TPG) using LFSR (linear feedback shift register) and binary to the excess-4 converter and binary ripple counter is proposed. The test vectors generated by the TPG have a high correlation between successive test vectors, which leads to minimum switching. During the testing of benchmark circuits, the proposed method shows a significant reduction in dynamic power consumption concerning its peer works. © Shanghai Jiao Tong University 2023.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Noise Estimation from Degraded Speech

Noise Estimation from Degraded Speech

引用

International Conference on 6G Communications Networking and Signal Processing, SGCNSP 2023

作者： Thorbole, Shubham Raj, Rahul Upadhyay, Navneet Department of Electronics and Communication Engineering The LNM Institute of Information Technology Jaipur India Department of Computer and Communication Engineering The LNM Institute of Information Technology Jaipur India

ISBN: (纸本)9789819778751

In real-world scenarios, speech signals are often corrupted by various types of noise, which can significantly degrade the intelligibility and quality of the speech. Noise in such environments is highly non-stationary, changing rapidly and unpredictably. A new algorithm has been created to estimate noise in speech signals affected by rapidly changing and unpredictable non-stationary noise. This algorithm aims to enhance speech quality and intelligibility in challenging acoustic settings. It determines signal presence by comparing the power spectrum of noisy speech to a continually updated local minimum, calculated from past noisy speech power spectra with a look-ahead factor. Its standout feature is its rapid adaptability to swiftly respond to new noise patterns, crucial for maintaining speech clarity and quality in dynamic noise environments. Formal experiments validated its effectiveness compared to other noise-estimation methods when integrated into speech enhancement systems, using metrics like mean squared error (MSE) and signal to noise ratio (SNR). This algorithm significantly contributes to noise estimation and voice enhancement, offering effectiveness in handling highly non-stationary noise and being adaptable and versatile for various applications. This algorithm stands as a substantial advancement in the domains of noise estimation and voice enhancement overall. Its utility extends across diverse applications owing to its proficiency in handling highly non-stationary noise conditions, coupled with its adaptability and versatility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Techniques in Intrusion Detection System-Internet of Vehicles: A State-of-the-Art Review

引用

computers, Materials & Continua 2024年第8期80卷 2785-2813页

作者： Wufei Wu Javad Hassannataj Joloudari Senthil Kumar Jagatheesaperumal Kandala N.V.P.SRajesh Silvia Gaftandzhieva Sadiq Hussain Rahimullah Rabih Najibullah Haqjoo Mobeen Nazar Hamed Vahdat-Nejad Rositsa Doneva School of Information Engineering Nanchang UniversityNanchang330031China Department of Computer Engineering Technical and Vocational University(TVU)Tehran***Iran Department of Computer Engineering University of BirjandBirjand***Iran Department of Computer Engineering Babol BranchIslamic Azad UniversityBabol***Iran Department of Electronics&Communication Engineering Mepco Schlenk Engineering CollegeSivakasi626005India School of Electronics Engineering VIT-AP UniversityNear Vijayawada522237India Faculty of Mathematics and Informatics University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria Examination Branch Dibrugarh UniversityDibrugarh786004India Department of Computer Engineering Faculty of EngineeringUniversity of BirjandBirjand***Iran Faculty of Electrical and Computer Engineering University of BirjandBirjand***Iran Malaysian Institute of Information Technology Universiti Kuala LumpurKuala Lumpur50250Malaysia Faculty of Physics and Technology University of Plovdiv Paisii HilendarskiPlovdiv4000Bulgaria

The high performance of IoT technology in transportation networks has led to the increasing adoption of Internet of Vehicles(IoV)*** functional advantages of IoV include online communication services,accident prevention,cost reduction,and enhanced traffic *** these benefits,IoV technology is susceptible to cyber-attacks,which can exploit vulnerabilities in the vehicle network,leading to perturbations,disturbances,non-recognition of traffic signs,accidents,and vehicle *** paper reviews the state-of-the-art achievements and developments in applying Deep Transfer Learning(DTL)models for Intrusion Detection Systems in the Internet of Vehicles(IDS-IoV)based on anomaly ***-IoV leverages anomaly detection through machine learning and DTL techniques to mitigate the risks posed by *** systems can autonomously create specific models based on network data to differentiate between regular traffic and *** these techniques,transfer learning models are particularly promising due to their efficacy with tagged data,reduced training time,lower memory usage,and decreased computational *** evaluate DTL models against criteria including the ability to transfer knowledge,detection rate,accurate analysis of complex data,and *** review highlights the significant progress made in the field,showcasing how DTL models enhance the performance and reliability of IDS-IoV *** examining recent advancements,we provide insights into how DTL can effectively address cyber-attack challenges in IoV environments,ensuring safer and more efficient transportation networks.

关键词： Cyber-attacks internet of things internet of vehicles intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Enhanced Electric Power Adaptability Using Hybrid Pumped-Hydro technology with Wind and Photovoltaic Integration

引用

Energy engineering 2023年第9期120卷 1939-1961页

作者： Uwem O.Ikitde Abayomi A.Adebiyi Innocent E.Davidson Ayodeji S.Akinyemi Department of Electrical Power Engineering Durban University of TechnologyDurban4001South Africa Department of Electrical Electronics and Computer EngineeringCape Peninsula University of TechnologyBellville7535South Africa

The integration of solar and wind energy into the electrical grid has received global research attention due to their unpredictable *** wind energy varies across all timescales of utility activity,renewable energy generation should be supplemented and enhanced,from real-time,minute-to-minute variations to annual alterations influencing *** energy generation does not only fluctuate but is also challenging to accurately forecast the timeframes of significance to electricity decision makers;day-ahead and long-term making plans of framework sufficiency such as meeting the network peak load annually.A utility that integrates wind and solar energy into its electricity mix would understand how to adapt to uncertainty and variability in operations while sustaining grid *** to hydropower’s adaptability,a system using hydropower as one of its generating resources could be precisely adapted to absorb the variability of wind and solar *** objective of this research study is to create a hybrid system comprising hydro-wind and solar(Hybrid-HWS)integration for power balancing in an isolated electrical network in Klipkop village,Pretoria region,South *** desirability of designing and building goaf storage tank in regard to capability,the fullness of line throughoutwater pumping,dispensing,storage tank spillage,and pressure difference throughout liquid flow within the storage tanks were preliminary assessed using geotechnical and weather forecasting data from a distinctive area of Klipkop town in Pretoria,South *** facility hours premised on daylight accessibility are scheduled to balance maximum load at early and late ***,in the scenario of electrical power,time shift requiring storage for extended periods of time,such as in terms of hours,Hybrid-HWS has been found to have a crucial *** results of simulations showed a coordinated process design for Hybrid-HWS Energy Storage(ES)to determine ev

关键词： Pumped hydro storage(PHS) hybrid hydro-wind-solar technique abandoned coal mine power balancing

来源：评论

学校读者我要写书评

暂无评论

Feature-enhanced deep learning technique with soft attention for MRI-based brain tumor classification

引用

International Journal of Information technology (Singapore) 2024年第3期16卷 1617-1626页

作者： Mohanty, Bipin Ch. Subudhi, P.K. Dash, Ratnakar Mohanty, Bidyadhar Department of Electronics and Communication Engineering BPUT Odisha Rourkela 769015 India Department of Electronics and Communication Engineering Nalanda Institute of Technology Odisha Bhubaneshwar 754005 India Department of Computer Science and Engineering National Institute of Technology Odisha Rourkela 769008 India

Brain tumor classification using Magnetic Resonance Imaging (MRI) is a pivotal area in medical diagnostics, with the potential to influence early detection and subsequent treatment strategies. Over the years, various machine learning and deep learning models have been proposed to enhance the accuracy of MRI-based tumor detection. In this evolving landscape, this paper introduces a distinctive deep-learning model that harnesses the power of a soft attention mechanism. We employ a meticulously designed Convolutional Neural Network (CNN) comprising four convolution layers. One of the significant innovations in our approach is the method of feature extraction. Instead of extracting features solely from the final layer, as is common in many models, our approach aggregates and combines features from all layers. This ensures that the vital characteristics intrinsic to each layer are not lost but rather amalgamated into a robust and comprehensive feature vector. The incorporation of a soft attention mechanism at the terminal stages ensures that the most salient and clinically relevant features are emphasized, enhancing classification accuracy. To validate the efficacy of our proposed model, we employed standard datasets for training and testing. A comparative analysis with existing state-of-the-art models affirms the superiority and potential of our approach in the realm of MRI-based brain tumor classification. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Brain tumor CNN Deep learning MRI Soft-attention

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：