检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lyu, Zhijin Jin, Yutong Das, Sneha Dept. Electrical and Photonics Engineering Technical University of Denmark Lyngby Denmark Dept. Engineering King’s College London London United Kingdom Dept. Applied Mathematics and Computer Science Technical University of Denmark Lyngby Denmark

Determining the robustness of deep learning models is an established and ongoing challenge within automated decision-making systems. With the advent and success of techniques that enable advanced deep learning (DL), these models are being used in widespread applications, including high-stake ones like healthcare, education, border-control. Therefore, it is critical to understand the limitations of these models and predict their regions of failures, in order to create the necessary guardrails for their successful and safe deployment. In this work, we revisit robustness, specifically investigating the sufficiency of robust accuracy (RA), within the context of deepfake detection. We present robust ratio (RR) as a complementary metric, that can quantify the changes to the normalized or probability outcomes under input perturbation. We present a comparison of RA and RR and demonstrate that despite similar RA between models, the models show varying RR under different tolerance (perturbation) levels. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Cryptocurrency Price Prediction: Incorporating Time-Reversed ARIMA and BVIC 19

Advanced Cryptocurrency Price Prediction: Incorporating Time...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Luc, Minh Tuan Senkerik, Roman Dang, Tran Khanh Dept. of Computer Science Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava Ostrava-Poruba Czech Republic Center for Applied Information Technology Ton Duc Thang University Ho Chi Minh city Viet Nam Institute for Experiential Technology Van Lang University Ho Chi Minh city Viet Nam Faculty of Information Technology School of Technology Van Lang University Ho Chi Minh city Viet Nam

ISBN: (纸本)9798331507817

The highly volatile nature of cryptocurrencies, particularly Bitcoin, exhibits extreme price volatility, making accurate price prediction a challenging task for traditional forecasting models. This paper proposes an enhanced ARIMA model, called ARIMA_T, which incorporates time-reversed data and optimizes model selection using the Backward Validated Information Criterion (BVIC). The ARIMA_T model aims to improve forecasting accuracy by capturing both linear and non-linear patterns in the data that standard ARIMA models often overlook. We apply this model to predict Bitcoin prices over short and medium-term horizons, specifically 1-day, 7-days, and 30-days ahead predictions. The dataset spans from April 2013 to February 2024. Experimental results demonstrate that ARIMA_T consistently outperforms the traditional ARIMA model across all forecast horizons, as evidenced by lower Root Mean Square Error (RMSE) values. The ARIMA_T model provides more accurate and robust predictions, particularly for short-term forecasting, making it a valuable tool for navigating the volatile cryptocurrency market. This study also discusses the limitations of both models in handling longer-term predictions and suggests future work in integrating ARIMA_T with machine learning techniques for further improvements. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Impact on mental health due to COVID-19 pandemic: A cross-sectional study in Bangladesh

引用

Clinical eHealth 2023年第1期6卷 42-52页

作者： Pathan, Refat Khan Biswas, Munmun Yasmin, Suraiya Uddin, Mohammad Amaz Das, Anindya Khandaker, Mayeen Uddin Faruque, M.R.I. Sarker, Moniruzzaman Dept. of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Bandar Sunway 47500 Malaysia Dept. of Computer Science and Engineering BGC Trust University Bangladesh Chittagong 4381 Bangladesh Department of Computer and Information Science Tokyo University of Agriculture and Technology Koganei - 184-0012 Tokyo Japan Dept. of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong 4349 Bangladesh Dept. of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chittagong 4349 Bangladesh Center for Applied Physics and Radiation Technologies School of Engineering and Technology Sunway University Selangor Bandar Sunway 47500 Malaysia Space Science Centre Universiti Kebangsaan Malaysia 43600 UKM Selangor Bangi Malaysia Department of Marketing Sunway University Business School Sunway University Selangor Bandar Sunway 47500 Malaysia Faculty of Graduate Studies Daffodil International University Daffodil Smart City Birulia Savar Dhaka – 1216 Bangladesh

The government of Bangladesh has implemented the “Stay Home” policy following the WHO recommendation to resist the community transmission of Covid-19. As a result, the routine activities of all government, semi-government establishments, including educational institutions, are severely affected, and the country's economic growth becomes slowed down. To overcome such a situation, the relevant authorities have introduced the “Work from Home” policy for the employees and “Remote Education” for students. However, due to the persistence of multi-dimensional socio-economic problems, many employees and students face big challenges in performing their regular jobs while adopting such a policy. Consequently, enormous psychological anxiety has been developed for all people, including students, parents, employees, etc., and concurrently created severe changes in their behavior. This study aims to analyze the reasons for the behavioral changes of the employees, students, academic staff, and family members of different ages due to psychological anxiety, stress, or physical issues. A comprehensive online-based survey has been carried out on people working in various sectors in Bangladesh. A modified Apriori Algorithm has been used to sort out the associations between the causes and types of behavioral changes. Analyzed data revealed a massive human behavioral change in most participants. This finding indicates that the negligence of those significant human behavioral changes may cause a higher risk of creating psychological imbalance. Therefore, there is a need to have a solid understanding of the reasons for the behavioral changes and set up standard guidelines to maintain “Work from Home” in this Covid-19 situation to avoid psychological imbalance. Based on this study, some suggestions have been given for implementation by the government on an urgent basis. © 2023

关键词： Apriori algorithm Behavioral changes Covid-19 outbreak Family crisis Work from home

来源：评论

学校读者我要写书评

暂无评论

Spectrum converting nanocomposites for sensitive detectors of short-wavelength radiation 20

Spectrum converting nanocomposites for sensitive detectors o...

引用

Optical Components and Materials XX 2023

作者： Patel, Darayas N. Sarkisov, Sergey S. Darwish, Abdalla M. Whyte, Kelly Collins, Sabrina Smith, Crystal Math and Computer Science Dept. Oakwood University 7000 Adventist Blvd HuntsvilleAL35896 United States SSS optical Technologies 515 Sparkman Drive HuntsvilleAL35816-3417 United States Physics and Pre-Engineering Dept. Dillard University 2601 Gentilly Blvd New OrleansLA70122 United States

ISBN: (纸本)9781510659391

Existing UV sensors often use vacuum photo-multiplying tubes (PMTs). Solid state photodetectors are either blind to UV (use silicon) or have low sensitivity (use wide bandgap semiconductors). We report on our efforts to develop polymer nanocomposites made of the nanoparticles (NPs) of perovskites CsPbX3 (X stands for Cl, Br, and I) and lanthanide doped compounds that captured UV photons and efficiently converted their energy into visible and near-infrared (NIR) photons. The wavelength of these low-energy photons matches the spectral response of silicon avalanche photo diodes (APDs) with an electronic gain of > 106. For instance, NPs of perovskite CsPbBr3 with a diameter of 16 nm produced strong visible radiation at 512 nm being excited with a 372-nm UV laser while the NPs of La2O3: Eu3+ demonstrated strong photoluminescence in red region (between 600 and 650 nm) with a quantum yield of 60%. The nanocomposites were integrated with silicon APDs. The proposed combination worked as a UV detection system with two orders of magnitude improved sensitivity. Such a photodetector is particularly useful for the non-line-of-sight (NLOS) free space optical communication (FSO) in the solar-blind spectral region 100-280 nm where the background noise from solar UV radiation is eliminated due to absorption by ozone layer in the upper atmosphere. © 2023 SPIE.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer-based Classification for Lung and Colon Cancer using Histopathology Images

Vision Transformer-based Classification for Lung and Colon C...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Munjur Hasan Md Saifur Rahman Sabrina Islam Tanvir Ahmed Nafiz Rifat Mostofa Ahsan Rahul Gomes Md. Chowdhury Dept. of Computer Science and Engineering Gono Bishwabidyalay Savar Dhaka Bangladesh Dept. of Math Science and Technology University of Minnesota Crookston Crookston MN USA Dept. of Biological Sciences Florida Atlantic University Boca Raton FL USA Dept. of Computer Science North Dakota State University Fargo ND USA Dept. of Computer Science University of Wisconsin-Eau Claire Eau Claire WI USA Dept. of Computer Science East Stroudsburg University East Stroudsburg PA USA

In this day and age, a considerable number of fatalities are caused by colon and lung cancer. Although their appearance simultaneously is rare, the likelihood of cancer cells spreading between these two organs in the absence of early diagnosis is relatively significant. The second highest cause of death worldwide is cancer. Colon and lung cancers are the most typical and lethal malignancies among the many different forms. Historically, physicians had to go through a lengthy and time-consuming process to evaluate histopathological images and identify cancer cases; however, current technology options make it possible to complete this process more quickly. This study classified the histopathological imagery LC25000 gathered at the Tampa, Florida-based James A. Haley Veterans Hospital of Lung and Colon Cancers using several Convolutional Neural Network (CNN) variants as well as the more recent vision transformer architecture. Based on the outcomes of this study, it has been observed that using the Vision Transformer provides exceptional performance outperforming deep learning CNN, VGG19, and Resnet 50 algorithms with 100% accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Automaton Induced Brain-Actuated Takagi-Sugeno Speed Modulation for Position Control of a Rehabilitative Robot Arm

Learning Automaton Induced Brain-Actuated Takagi-Sugeno Spee...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Baishali De Anwesa Mondal Amit Konar Anuradha Saha Atulya K Nagar ETCE Dept. Artificial Intelligence Lab Jadavpur University Kolkata Electrical Engineering Dept. Jadavpur University Kolkata Netaji Subhas Engineering College Kolkata Dept. of Math and Computer Science Liverpool Hope University UK

ISBN: (数字)9798350319545

ISBN: (纸本)9798350319552

The paper introduces a novel 2-loop architecture of brain-actuated position control system of a robot arm, realized with a Takagi-Sugeno type fuzzy speed modulator placed in the outer loop and a traditional speed-controller placed in the inner loop. The Takagi-Sugeno type speed modulator modulates the speed based on the degree of fuzziness of positional error and its time-derivative. Reinforcement Learning is employed here to autonomously determine the parameters involved in the Takagi-Sugeno type speed modulator, so as to minimize the steady-state positional error of the robot arm. The proposed Reinforcement Learning is synthesized by a Learning Automaton (matrix), whose row indices correspond to antecedents of Takagi-Sugeno fuzzy rules and columns designate possible choice of a pair of parameters. The learning in the automaton is initialized with randomly selected probabilities, so that each row-sum is unity. The automaton generates trial actions when a specific row condition is instantiated by measurement. At the end of the learning epoch, the steady-state error is measured. If it is below a user-defined threshold, the selected actions are reinforced, by increasing probabilities for the selected action, and decreasing probabilities of the non-selected actions, so that row-sum remains unity. If the steady-state error after a learning epoch is above the threshold, the selected actions are penalized. After the Learning Automaton converges, it is used for parameter selection of the Takagi-Sugeno speed-modulator based on the highest probability in each row. The complete robot arm was tested on healthy and neuro-motor patients, and the experimental results are encouraging.

关键词： Learning automata Modulation Position control Reinforcement learning Arms Manipulators Takagi-Sugeno model

来源：评论

学校读者我要写书评

暂无评论

Optimization Approach to Modification of Characteristics of Bragg Structure Based on Parametric Weighting

Optimization Approach to Modification of Characteristics of ...

引用

International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED)

作者： M. V. Andreev O. O. Drobakhin Computer Science & Information Technology Dept. Oles Honchar Dnipro National University Dnipro Ukraine Applied Radiophysics Electronics and Nanomaterials Dept. Oles Honchar Dnipro National University Dnipro Ukraine

ISBN: (数字)9798331506087

ISBN: (纸本)9798331506094

Weight processing of the values of reflection coefficients from the interfaces of layers of a Bragg-type structure reducing the side lobe level in the passband of the reflection frequency response is considered. To ensure a reduction of the level of side lobes in the Bragg structure at a fixed width of the Bragg reflection, a technology based on optimization of the objective function containing samples of the frequency response in the passband has been developed. The conditions for the dielectric constant values exceeding unity and not decreasing the reflection level in the reflection frequency band are shown. The results of using the Taylor window, which has found application in modern radar and antenna technology, are presented.

关键词： Measurement Dielectric constant Radar antennas Linear programming Reflection Frequency response Reflection coefficient Radar applications Passband Optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Local Interpretable Model-Agnostic Explanations for Speech Emotion Recognition with Distribution-Shift

Exploring Local Interpretable Model-Agnostic Explanations fo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Maja J. Hjuler Line H. Clemmensen Sneha Das CNRS Grenoble INP LIG University Grenoble Alpes Grenoble France School of Computer Science Queensland University of Technology Brisbane QLD Australia Dept. of Applied Mathematics and Computer Science Technical University of Denmark Lyngby Denmark

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We introduce EmoLIME 1 , a version of local interpretable model-agnostic explanations (LIME) for black-box Speech Emotion Recognition (SER) models. To the best of our knowledge, this is the first attempt to apply LIME in SER. EmoLIME generates high-level interpretable explanations and identifies which specific frequency ranges are most influential in determining emotional states. The approach aids in interpreting complex, high-dimensional embeddings such as those generated by end-to-end speech models. We evaluate EmoLIME, qualitatively, quantitatively, and statistically, across three emotional speech datasets, using classifiers trained on both hand-crafted acoustic features and Wav2Vec 2.0 embeddings. We find that EmoLIME exhibits stronger robustness across different models than across datasets with distribution shifts, highlighting its potential for more consistent explanations in SER tasks within a dataset.

关键词： Emotion recognition Explainable AI Closed box Speech recognition Signal processing Predictive models Acoustics Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Reliability Analysis of a Monitoring System for Extraterrestrial Habitats

Reliability Analysis of a Monitoring System for Extraterrest...

引用

IEEE International Conference on Wireless and Mobile Computing, Networking And Communications (WiMob)

作者： Saurabh Band Florian Stechmann Malavika Unnikrishnan Shadi Attarha Christiane Heinicke Andreas Willig Anna Foerster dept. Sustainable Communication Networks University of Bremen Germany Center of Applied Space Technology and Microgravity University of Bremen Germany Dept. of Computer Science and Software Engineering University of Canterbury New Zealand

ISBN: (数字)9798350387445

ISBN: (纸本)9798350387452

This paper presents a robust and dependable monitoring system designed for space missions where reliability is critical. Theoretically, we use the Markov chain model to evaluate the availability of the system, considering multiple instances of backup devices. The results indicate a substantial improvement in system availability with the inclusion of backup devices. The findings highlight the significance of redundancy in enhancing system dependability while considering practical constraints. Based on this insight, we design an algorithm to deploy backup devices in the system that would improve the system's availability without putting strain on the resources (e.g., channel congestion). It uses backup devices at the sensor node and gateway levels. The algorithm involves backup devices that actively monitor and take over in case of failures, enhancing the system's ability to recover lost or faulty data. We test the system in three failure scenarios: hard failures, sensor failures, and gateway failures. We perform the experiments on our hardware prototypes. Experimental results demonstrate that using backup devices significantly improves the Packet Reception Ratio (PRR) in failure scenarios. We observed an improvement of 30 - 34% in packet reception for different failure scenarios.

关键词： Wireless communication Wireless sensor networks Space missions Redundancy Prototypes Logic gates Reliability theory Reliability engineering Monitoring Strain

来源：评论

学校读者我要写书评

暂无评论

Managing the Fall Risk in Smart Homes Using Monocular Cameras, Ambient Sensors and an Interactive Social Robot

Managing the Fall Risk in Smart Homes Using Monocular Camera...

引用

2022 IEEE International Conference on Blockchain, Smart Healthcare and Emerging Technologies, SmartBlock4Health 2022

作者： Lachaux, Killian Maitre, Julien Bouchard, Kevin Lussier, Maxime Bottari, Carolina Couture, Melanie Bier, Nathalie Giroux, Sylvain Gaboury, Sebastien Universite du Quebec À Chicoutimi Dept. of Math. and Computer Science Chicoutimi Canada Universite de Montreal Dept. of Medicine Montreal Canada School of Rehabilitation Universite de Montreal Montreal Canada Center for Research and Expertise in Social Gerontology CIUSSS West-Central Montreal Côte Saint-Luc Canada Universite de Sherbrooke Dept. of Computer Science Sherbrooke Canada

ISBN: (纸本)9781665460149

One of the biggest challenges faced by older adults is the risk of falling. Falls and the fear of falling cause serious physical and mental health issues. They are also a very impacting factor on the independence of the individual. This paper approaches the problem through the view of a population afflicted by the self-neglect syndrome. Therefore, we propose the NAOREA system, using monocular cameras, various ambient sensors and a humanoid social robot, to manage the risk of falling through a step-by-step process. This system achieved up to 100% detection rates of obstacles for proactive fall control in a real-home setting, as well as a 87% detection rates of falls after they happened. © 2022 IEEE.

关键词： Fall detection

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：