检索结果-内蒙古大学图书馆

3rd Novel Intelligent and Leading Emerging sciences Conference, NILES 2021

作者： Hefny, Abdelrahman H. Dafoulas, Georgios A. Ismail, Manal A. National Egyptian E-Learning University Faculty of Computers Information Technology Giza Egypt Middlesex University Faculty of Science and Technology Computer Science Department London United Kingdom Helwan University Faculty of Engineering Computer Engineering and Systems Department Cairo Egypt

ISBN: (纸本)9781665421577

This work presents a prototype and preliminary evaluation experiments of a management conversational assistant for software engineering teams. Such teams commonly rely on text chat for communications using specialized collaboration platforms such as Slack or Microsoft Teams. A conversational assistant integrated into these platforms can help in several tasks related to project and team management, thus benefiting both managers and software developers. The proposed design of the conversational assistant is described in terms of its architectural design and interaction design, and the important design decisions are explained. Preliminary evaluation shows that the proposed chatbot can be used effectively to interact with users reactively and proactively over public and private channels. However, for better results, a specific intent classifier should be used for each combination of user roles and channel types. In addition, interacting to messages with unspecified target over public channels is affected by the relatively limited intent classifier accuracy and still requires improvement. © 2021 IEEE.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Enhancing Rehabilitation Outcomes: A Hybrid Cognitive-Machine Learning Approach

Enhancing Rehabilitation Outcomes: A Hybrid Cognitive-Machin...

引用

International Conference on Communication and Electronics systems (ICCES)

作者： Vijaya Chandra Jadala S. Hrushikesava Raju S. Adinarayna Nabanita Choudhury Shaik Jumlesha U. Sesadri School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Guntur Department of Computer Science and Systems Engineering College of Engineering Andhra University Visakhapatnam Faculty of Computer Technology Assam down town University Guwahati Assam Department of CSE Annamacharya Institute of Technology and Science AP Department of CSE Vardhaman College of Engineering Hyderabad Telangana

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Traditional rehabilitation methods often focus on a single impairment, leading to challenges such as low motivation and inadequate responses to the diverse needs of patients, time taken for appointments, and lack of personal monitoring of health status. To address these issues, The model employs meta-cognitive strategies, dynamic adaptive training, and modified Convolutional Neural Networks (CNN) within an ensemble framework, targeting multiple impairments while tailoring interventions to individual patient requirements. A hybrid model proposed would integrate cognitive and machine learning methodologies to enhance personalized rehabilitation. By selectively employing meta-cognitive strategies, dynamic adaptive training, and modified Convolutional Neural Networks (CNN) within an ensemble framework, the proposed system aims to bridge existing gaps in rehabilitation practices. The hybrid system is designed to efficiently manage patient data, reduce the complexity of rehabilitation tasks, and optimize computational resources. The use of stacking as an ensemble method further mitigates biases and uncertainties associated with individual models, thereby improving the reliability of the rehabilitation framework. Preliminary outcomes indicate that this hybrid approach achieves superior accuracy and efficiency compared to traditional methods, ultimately enhancing adaptability to the varied needs and preferences of patients.

关键词： Training Adaptation models Accuracy Adaptive systems Uncertainty Computational modeling Stacking Convolutional neural networks Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

RLStop: A Reinforcement Learning Stopping Method for TAR

arXiv

引用

arXiv 2024年

作者： R., Bin-Hezam M., Stevenson Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science Faculty of Engineering University of Sheffield Sheffield United Kingdom

We present RLStop, a novel Technology Assisted Review (TAR) stopping rule based on reinforcement learning that helps minimise the number of documents that need to be manually reviewed within TAR applications. RLStop is trained on example rankings using a reward function to identify the optimal point to stop examining documents. Experiments at a range of target recall levels on multiple benchmark datasets (CLEF e-Health, TREC Total Recall, and Reuters RCV1) demonstrated that RLStop substantially reduces the workload required to screen a document collection for relevance. RLStop outperforms a wide range of alternative approaches, achieving performance close to the maximum possible for the task under some circumstances. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Influence of Sentiments in Digital Currency Prediction Using Hybrid Sentiment-based Support Vector Machine with Whale Optimization Algorithm (SVMWOA)

The Influence of Sentiments in Digital Currency Prediction U...

引用

2021 International Congress of Advanced Technology and engineering, ICOTEN 2021

作者： Hitam, Nor Azizah Ismail, Amelia Ritahani Samsudin, Ruhaidah Ameerbakhsh, Omair Department of Computer Science Kuala Lumpur Malaysia Universiti Teknologi Malaysia Faculty of Computing Department of Information Systems Johor Skudai Malaysia Taibah University College of Computer Science and Engineering Department of Information Systems

ISBN: (纸本)9781665412247

Getting an accurate prediction of a digital currency, also known as a cryptocurrency price index, becomes a significant factor in helping investors make the right decision. Failure to predict the movement of the crypto market gives a huge impact on profit loss. The difficult part is that market is dynamic in a way that is driven by many factors including inflation rate, economics, and natural calamities. This creates a chaos in the price of index so does the sentiment of the investor. This study proposes a machine learning model that applies a combination of sentiment-based support vector machine that is optimized by the whale optimization algorithm for predicting the daily price of a digital currency. Support Vector Machine (SVM) technique is used with the Whale Optimization Algorithm (WOA) which is inspired by the swarm optimization algorithms. The proposed Hybrid Sentiment-based Support Vector Machine with a Whale Optimization Algorithm (SVMWOA). will be evaluated and compared based on performance measures. The proposed method is compared with Support Vector Machine Optimized by Genetic Algorithm (SVMGA) and the Support Vector Machine Optimized by Harmony Search (SVMHS). The proposed model is found robust to be used in other fields of study. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Low-power High-gain Inverter Stacking Amplifier with Rail-to-Rail Output 3

A Low-power High-gain Inverter Stacking Amplifier with Rail-...

引用

3rd IEEE International Conference on Design and Test of Integrated Micro and Nano-systems, DTS 2021

作者： Shad, Erwin H. T. Moeinfard, Tania Molinas, Marta Ytterdal, Trond Faculty of Information Technology and Electrical Engineering Engineering Cybernetics Trondheim Norway York University Faculty of Electrical Engineering and Computer Science Toronto Canada Faculty of Information Technology and Electrical Engineering Electronic Systems Trondheim Norway

ISBN: (纸本)9780738132631

In this article, a rail-to-rail low-power amplifier is presented based on stacking inverter-based amplifiers. The output voltages of each inverter-based amplifier are converted to a current and then mirrored to the output so that a rail-to-rail output is achieved. Besides, extensive simulations have been carried out to show the effect of drain-source voltage on the intrinsic gain of a transistor. Based on these simulations, a minimum supply voltage is chosen to achieve high open-loop gain and low closed-loop gain error. All the simulations are carried out in a commercially available 0.18 μm CMOS technology. The proposed amplifier achieves 88 dB open-loop gain. It is exploited in a capacitively-coupled amplifier structure. The closed-loop gain is 40 dB in the bandwidth of 0.1 Hz to 10 kHz when the power consumption is 0.54 μW at a 1.2 V supply voltage. The total input-referred noise is 4.7 μVrms in the whole bandwidth. The proposed neural amplifier achieved 0.02 SEF in the bandwidth from 200 Hz to 10 kHz. The proposed amplifier achieved a rail-to-rail output swing while the SEF is among the best reported SEF in the literature. Besides, to show the robustness of the proposed structure in the presence of process and mismatch variation, 500 Monte Carlo simulations are carried out. The PSRR and CMRR mean values are 89 dB and 68 dB, respectively. Finally, the proposed neural amplifier area consumption is 0.03 mm2 without pads. © 2021 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Embedded Acoustic Noise Cancellation (ANC) Performances Analysis for Voice Communications using Linear Adaptive Approaches 23

Embedded Acoustic Noise Cancellation (ANC) Performances Anal...

引用

6th International Conference on Networking, Intelligent systems and Security, NISS 2023

作者： Wahbi, Azeddine Ouchatti, Abderrahmane Elghayyaty, Mohamed El Habti El Idrissi, Anas Roukhe, Ahmed Bensassi, Bahloul Hlou, Laamari Lab. of Elec. and Industrial Engineering Information Processing Computer Sciences and Logistic Faculty of Sciences Ain Chock Casablanca Hassan Ii University Maarif Casablanca Morocco Laboratory of Electronic Systems Information Processing and Energetics Faculty of Sciences Ibn Tofail University Kenitra Morocco Laboratory of Atomic Mechanical Photonics and Energy Faculty of Science University Moulay Ismail Meknes Morocco

ISBN: (纸本)9798400700194

ANC systems have emerged as the most widely adopted technologies in voice communications. This paper purpose a comparison between the adaptive approaches in time and frequency domain, which is used to model, design and implement these systems. All designs are developed by creating new embedded blocks using Simulink environment. Furthermore, the performance of the proposed embedded designs based adaptive algorithm is analyzed and evaluated on the basis of Signal to Noise Ratio (SNR) and computational complexity improvement, where these designs are applied on ANC to compensate linear distortion in the noise path. Moreover, the produced results showed that using embedded blocks based adaptive algorithm in frequency domain gives the best result than the rest of the other embedded designs. © 2023 ACM.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Improved Archimedes Optimization Algorithm with Deep Learning Empowered Fall Detection System

引用

computers, Materials & Continua 2022年第8期72卷 2713-2727页

作者： Ala Saleh Alluhaidan Masoud Alajmi Fahd N.Al-Wesabi Anwer Mustafa Hilal Manar Ahmed Hamza Abdelwahed Motwakel Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science College of Science&Arts at MahayilKing Khalid UniversityMuhayel Aseer62529Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’a61101Yemen Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia

Human fall detection(FD)acts as an important part in creating sensor based alarm system,enabling physical therapists to minimize the effect of fall events and save human ***,elderly people suffer from several diseases,and fall action is a common situation which can occur at any *** this view,this paper presents an Improved Archimedes Optimization Algorithm with Deep Learning Empowered Fall Detection(IAOA-DLFD)model to identify the fall/non-fall *** proposed IAOA-DLFD technique comprises different levels of pre-processing to improve the input image ***,the IAOA with Capsule Network based feature extractor is derived to produce an optimal set of feature *** addition,the IAOA uses to significantly boost the overall FD performance by optimal choice of CapsNet ***,radial basis function(RBF)network is applied for determining the proper class labels of the test *** showcase the enhanced performance of the IAOA-DLFD technique,a wide range of experiments are executed and the outcomes stated the enhanced detection outcome of the IAOA-DLFD approach over the recent methods with the accuracy of 0.997.

关键词： Fall detection intelligent model deep learning archimedes optimization algorithm capsule network

来源：评论

学校读者我要写书评

暂无评论

Addressing Non-stationarity with Stochastic Trend in the Context of Limited Time Series Data: An Experimental Survey

Research Square

引用

Research Square 2025年

作者： Batoure Bamana, Apollinaire Sokdou Bila Lamou, Yannick Fotsa-Mbogne, David Jaures Shafiee Kamalabad, Mahdi Department of Computer Engineering University Institute of Technology The University of Ngaoundere Cameroon Department of Robotic and Industrial Computing School of Chemical Engineering and Mineral Industries The University of Ngaoundere Cameroon Department of Mathematics and Computer Science Faculty of Science The University of Ngaoundere Cameroon Laboratory of Mathematics Computer Science and Applications Department of Mathematics and Computer Science National Higher School of Agro-Industrial Sciences The University of Ngaoundéré Cameroon Laboratory of Mathematics and Computer Science Department of Mathematics Statistics and Computer Science Faculty of Science The University of Bertoua Cameroon Department of Methodology and Statistics Faculty of Social and Behavioural Sciences Utrecht University Utrecht Netherlands Centre for Complex Systems Studies Utrecht University Utrecht Netherlands

Stationarity in time series is a key property for practical data analysis, inferences, and predictions particularly in biosciences. Stationarity can be either deterministic or stochastic. If a time series data is not stationary, it can be rendered stationary through detrending or differentiation techniques. Differentiation can be performed in either an integer or fractional form. This paper investigates non-stationarity in time series data, focusing specifically on stochastic trends characterised by a unit root. It hypothesises that fractional differentiation can enhance forecast accuracy for datasets with limited volume. For experiments, 24 series corresponding to weekly Malaria and Typhoid Fever from Adamawa Region (Cameroon) are analysed and forecasted. Each series comprises 156 observations covering January 2021 to December 2023. After collecting, checking and classifying the data, four forecasting models, Auto Regressive Integrated Moving Average (ARIMA), Fractional ARIMA (ARFIMA), Long Short-Term Memory (LSTM), and the proposed Fractional Differencing and LSTM (FD-LSTM), are implemented. The models' performances are evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of determination (R2) metrics, which inform further analysis and recommendations. Results reveal that ARFIMA outperformed the ARIMA by 93% in training and 100% in testing. Similarly, FD-LSTM achieved a 100% improvement over LSTM in training and testing. These findings underscore the value of achieving stationarity through fractional differentiation, enhancing model performance and providing a robust framework for forecasting in datasets with limited observations. © 2025, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Novel Bendable Mnxca(0.90−X)Ni0.10fe2o4 Substrate Based Symmetrical Metamaterial Absorber for Rf Energy Harvesting Application to Achieve Sustainable Development Goals

SSRN

引用

SSRN 2024年

作者： Hasan, Mohammad Shakibul Islam, Mohammad Tariqul Ouda, Mohammad Alenezi, Abdulmajeed M. Soliman, Mohamed S. Samsuzzaman, Md. Department of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia Electrical Engineering Technology College of Engineering & Technology University of Doha for Science and Technology Doha24449 Qatar Department of Electrical Engineering Faculty of Engineering Islamic University of Madinah Madinah41411 Saudi Arabia Department of Electrical Engineering College of Engineering Taif University Taif21944 Saudi Arabia Department of Computer and Communication Engineering Faculty of Computer Science and Engineering Patuakhali Science and Technology University Bangladesh

This article presents a bendable substrate MnxCa(0.90−x)Ni0.10Fe2O4 based metamaterial absorber for RF energy harvesting from Wifi frequency of 5 GHz to the achievement of the Sustainable Development Goals. The bendable metamaterial absorber (BMMA) energy harvester unit cell constructed with the physical dimension of 21 × 21 *** proposed unit cell consist of cross sign shaped resonator surrounded by circular ring resonator is located middle portion and boundary split outer ring resonator. Based on the simulation findings, the proposed BMMA energy harvester provides maximum energy harvesting efficiency of 99.42% at 5 GHz. Due to the symmetrical design, the energy harvester unit cell shows excellent angle insensitive up to 90 degrees for incident angle and polarization angle. The proposed BMMA exhibits single negative properties, and it shows excellent harvesting efficiency for various bending conditions. The lightweight, flexibility of the structure indicate that MnxCa(0.90−x)Ni0.10Fe2O4 based bendable metamaterial absorber energy harvester have significant potential for RF energy harvesting application from wifi frequency of 5 GHz and it achieve Sustainable Development Goals (SDGs), specially alignment with SDG 7 (Affordable and Clean Energy), SDG 9 (Industry, Innovation, and Infrastructure), SDG 11 (Sustainable Cities and Communities),and SDG 13 (Climate Action). © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hermitian {P,k+1}-(anti-)reflexive solutions to a quaternion matrix equation

引用

Computational and Applied Mathematics 2025年第6期44卷

作者： Liu, Xin Li, Wanqi Yuan, Shifang Zhang, Yang Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa999078 China School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa999078 China School of Mathematics and Computational Science Wuyi University Jiangmen529020 China Department of Mathematics University of Manitoba WinnipegMBR3T 2N2 Canada

In this paper, we consider the Hermitian {P,k+1}-(anti-)reflexive solutions to the quaternion matrix equation AXB+CXD=E and AX=E, respectively. We use the complex representation method to obtain the necessary and sufficient conditions for the existence of the Hermitian {P,k+1}-reflexive solution (resp. Hermitian {P,k+1}-anti-reflexive solution), respectively, and derive their solutions when the matrix equations have the Hermitian {P,k+1}-reflexive solution (resp. Hermitian {P,k+1}-anti-reflexive solution). Finally, two examples are provided to verify the effectiveness of our method. © The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional 2025.

关键词： Polynomials

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：