检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shibuya, Tatsukichi Inoue, Nakamasa Kawakami, Rei Sato, Ikuro Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (纸本)9798350368741

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in finetuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of Electrocardiogram Classification Using Dipper Throated Algorithm and Differential Evolution

引用

computers, Materials & Continua 2023年第2期74卷 2379-2395页

作者： Doaa Sami Khafaga El-Sayed M.El-kenawy Faten Khalid Karim Sameer Alshetewi Abdelhameed Ibrahim Abdelaziz A.Abdelhamid D.L.Elsheweikh Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt General Information Technology Department Ministry of DefenseThe Executive AffairsExcellence Services DirectorateRiyadh11564Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Specific EducationMansoura UniversityEgypt

Electrocardiogram(ECG)signal is a measure of the heart’s electrical ***,ECG detection and classification have benefited from the use of computer-aided systems by *** goal of this paper is to improve the accuracy of ECG classification by combining the Dipper Throated Optimization(DTO)and Differential Evolution Algorithm(DEA)into a unified algorithm to optimize the hyperparameters of neural network(NN)for boosting the ECG classification *** addition,we proposed a new feature selection method for selecting the significant feature that can improve the overall *** prove the superiority of the proposed approach,several experimentswere conducted to compare the results achieved by the proposed approach and other competing ***,statistical analysis is performed to study the significance and stability of the proposed approach using Wilcoxon and ANOVA *** results confirmed the superiority and effectiveness of the proposed *** classification accuracy achieved by the proposed approach is(99.98%).

关键词： Electrocardiogram differential evolution algorithm dipper throated optimization neural networks

来源：评论

学校读者我要写书评

暂无评论

Extracting Facial Features to Detect Deepfake Videos Using Machine Learning

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 834-842页

作者： Aslam, Ayesha Mir, Jamaluddin Zaman, Gohar Rahman, Atta Salam, Asiya Abdus Ali, Farhan Alhiyafi, Jamal Bakry, Aghiad Gul, Mustafa Jamal Gollapalli, Mohammed Mahmud, Maqsood Department of Computer Science Abbottabad University of Science and Technology Havelian Pakistan Department of Computer Science College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam31441 Saudi Arabia Department of Computer Information Systems College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam31441 Saudi Arabia College of Electronics and Information Engineering Shenzhen University Shenzhen China Department of Computer Science Kettering University FlintMI United States Department of Business Administration University of York York YO10 5DD Heslington United Kingdom Department of Information Technology & Engineering Sydney Met SydneyNSW2000 Australia School of Computing Ulster University Northern Ireland Belfast United Kingdom

Generative adversarial networks (GANs) have gained popularity for their ability to synthesize images from random inputs in deep learning models. One of the notable applications of this technology is the creation of realistic videos known as deepfakes, which have been misused on social media platforms. The difficulty lies in distinguishing these fake videos from real ones with the naked eye, leading to significant concerns. This study proposes a supervised machine learning approach to effectively differentiate between real and counterfeit videos by detecting visual artifacts. To achieve this, two facial features are extracted: eye blinking and nose position, utilizing landmark detection techniques. Both features were trained on supervised machine learning classifiers and evaluated using the publicly available UADFV and Celeb-DF deepfake datasets. The experiments successfully demonstrate that the proposed method achieves a promising and superior performance, with an area under the curve (AUC) of 97% for deepfake detection in contrast to state-of-the-art methods investigating the same datasets. © (2025), (science and Information Organization). All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Monitoring of Individual Household Electrical Appliances and Prediction of Energy Consumption Using Machine Learning 5

Monitoring of Individual Household Electrical Appliances and...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Selvam, N. Seenivasan, D. Naveen, G. Sudahar, R. Janagan, P. Dhanushmathi, S. M.Kumarasamy College of Engineering Department of Electrical and Electronics Engineering Karur India M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India

ISBN: (纸本)9798350385649

The study suggests a scalable method for estimating residential power usage. To increase the forecasting accuracy, an SVM (support vector machine) based technique combines many machine learning models, such as random forests, decision trees, and linear regression. Real-world data from Dutch families were used in the study, and the findings demonstrate that the suggested strategy performs better than conventional single-model techniques and attains higher accuracy in predicting energy use. The method is suited for usage in real-world applications since it is scalable and applies to huge datasets. An approach for machine learning used in load forecasting is called SVM (Support Vector Machine). Applications for long-term individual household forecasting include calculating advance payments to customers. However, there is a dearth of research on this type of forecasting;most techniques either concentrate on long-term predictions at the aggregate level or on individual family-level short-term projections. In order to close this distance, we provide a technique that uses only a few months' worth of current year's consumption data to anticipate each monthly consumption throughout the next year. Even with little data, utility suppliers may use this technique to predict any customer's consumption for the upcoming year. Data power use in the future may be predicted using linear regression. The linear regression process is used to forecast data in the future. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Building an Adaptive Cooperative Transmission Mechanism for Multimedia Convergence System

引用

Wireless Personal Communications 2023年第4期133卷 2227-2266页

作者： Su, Ming-Kai Lin, Jia-Yi Horng, Gwo-Jiun Aripriharta, Aripriharta Chen, Chao-Chun Department of Computer Science and Information Engineering Southern Taiwan University of Science and Technology Tainan Taiwan Institute of Manufacturing Information and Systems National Cheng Kung University Tainan Taiwan Malang Indonesia

In people's daily lives, electronic mail, audio-visual media platforms, and communication software all have the need for file transmission. This article proposes a digital aggregation system with an adaptive collaborative transmission mechanism. By using traditional UDP and TCP transmission protocols, the file transmission method is adaptively adjusted based on the file type, file size, and network conditions of the device. Through these selection parameters, the file has the most suitable and optimized transmission and upload mode during the transmission process. This article proposes a transmission mode that combines transmission speed and file integrity, systematically examining the existing transmission environment and improving traditional transmission protocols. The communication protocol method proposed through this method is 2.5% faster than traditional transmission protocols for image file transmission. Compared to traditional transmission protocols, the transmission speed of audio files is 1.07% faster. Compared to traditional transmission protocols, video file transmission speed is 1.21% faster. This study adopts a collaborative communication transmission mechanism, which accelerates the transmission speed of multiple clients obtaining files from the server by 1.2% compared to a non-collaborative communication transmission mechanism. The client can still connect to the server at a slower time. This mechanism can accelerate download speed and make it easier to obtain files. Combining with the transmission platform, examining the environmental conditions of the device can be applied to optimize the transmission between servers and clients. As users grow, cooperative communication can be used to accelerate the speed of file acquisition. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Artificial Intelligence and Automatic Morse Code Based Communication Recognition with Eye Tracking

引用

Journal of Mobile Multimedia 2023年第6期19卷 1439-1461页

作者： Medichalam, Krishnakanth Vijayarajan, V. Kumar, V. Vinoth Iyer, I. Manimozhi Vanukuri, Yaswanth Kumar Prasath, V.B. Surya Swapna, B. School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore 632014 India Department of Computer Science and Engineering East Point College of Engineering and Technology India Department of Electrical Engineering and Computer Science University of Cincinnati 45221 OH United States Department of ECE Dr MGR Educational and Research Institute Chennai 95 India

Morse code is one of the oldest communication techniques and used in telecommunication systems. Morse code can be transmitted as a visual signal by using reflections or with the help of flashlights, but it can also be used as a non-detectable form of communication by using the tapping of fingers or even blinking of eyes. In this paper, we develop a computer vision based approach that automatically characterizes the characters conveyed wherein a person can communicate to system or another person through Morse code with eye gestures. We can decode this visual eye tracking based language with the help of our automatic computer vision driven method. Our approach uses a normal webcam to detect the gestures made by the eyes and are interpreted as dots and dashes. These dots and dashes are used to represent the Morse code-based words. Image processing techniques-based blink and pupil detectors are employed. Blink detector helps us to detect a blink and the time that took for each blink. A blink that takes 2 to 4 seconds is acknowledged as a dot whereas a blink that takes more than 4 seconds is represented as a dash. The pupil detector helps us to detect the movement of the pupils, and if pupils move towards right with respect to a person then it is acknowledged as next letter and if the pupils are moved towards left with respect to a person then it is acknowledged as next word. In this way, we decode the Morse code which will be communicated using eyes and establish a non-detectable communication between a person and an automatic system. Our experimental results on an unconstrained visual scene with preliminary greeting words indicate the promise of an automatic eye tracking based system with success rate of 98.25% that can be of use in non-verbal communications. © 2023 River Publishers.

关键词： blinks communication eye detection face detection gestures image processing Morse code

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Detection Using Classification and Prediction Models

Heart Disease Detection Using Classification and Prediction ...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Shanthi, P.A. Padmapriea, S. Sachet, K. Livinesh, L. Tharun, A.K. Sri Sai Ram Engineering College Department Of Mathematics Chennai India Sri Sai Ram Engineering College Department Of Computer Science And Business Systems Chennai India

ISBN: (纸本)9798350352689

Cardiovascular diseases persist as a prominent global cause of mortality, emphasizing the importance of precise prediction techniques for timely identification and intervention. This research explores the efficacy of three machine learning models - Logistic Regression, K-Nearest Neighbor (KNN) Classifier, and Gaussian Naive Bayes (Gaussian NB) - in predicting heart disease using datasets of varying sizes and test proportions. Leveraging demographic, clinical, and physiological variables such as age, gender, blood pressure, cholesterol levels, fasting blood sugar levels, electrocardiogram results, and maximum heart rate, predictive models were trained and evaluated. Across all dataset with different sizes and test proportions, Gaussian NB consistently demonstrated superior performance, characterized by high accuracy, precision, recall, and F1-score. Logistic Regression also exhibited commendable performance, particularly in terms of simplicity and interpretability, slightly lower than Gaussian NB. In contrast, KNN Classifier displayed varied performance across datasets with different sizes and test proportions, indicating sensitivity to these factors. These findings underscore the potential of machine learning models, particularly Gaussian NB and Logistic Regression, in enhancing heart disease prediction accuracy, thus enabling targeted interventions and personalized treatment strategies for improved patient outcomes. Further optimization and consideration of dataset characteristics are warranted to enhance the performance of KNN Classifier in heart disease prediction tasks. © 2024 IEEE.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading in NTN-empowered MEC using Multi-Agent Distributed Deep Reinforcement Learning

Computation Offloading in NTN-empowered MEC using Multi-Agen...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Fatima, Nida Saxena, Paresh Giambene, Giovanni Bits Pilani Department of Computer Science and Information Systems Hyderabad India University of Siena Department of Information Engineering and Mathematical Sciences Siena Italy

ISBN: (纸本)9798350351255

In this paper, we investigate Non-Terrestrial Network (NTN)-empowered Multi-access Edge Computing (MEC) systems for emerging applications like telemedicine, industrial automation, and augmented reality, which demand significant computational resources from User Equipments (UEs). To address these issues, we consider that UEs can either process tasks locally or offload them to edge servers deployed on Unmanned Aerial Vehicles (UAVs) and Low Earth Orbit (LEO) satellites. The efficacy of such systems crucially depends on formulating an efficient computation offloading policy. We propose a multi-agent distributed deep reinforcement learning (MADDRL) approach for computation offloading in NTN-empowered MEC systems. Our approach utilizes two distributed DRL frameworks: Centralized Training and Decentralized Execution (CTDE), where training occurs on a central controller, and Independent Learners (IL), where training is performed locally on the UEs. In both frameworks, policies are executed by UEs in a decentralized manner. Simulation results show that the CTDE framework reduces the average cost, defined as the weighted sum of delay and energy consumption experienced by the UEs, by 11%, 42%, and 66% compared to IL, local, and random policies, respectively. © 2024 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Hybrid Dipper Throated and Grey Wolf Optimization for Feature Selection Applied to Life Benchmark Datasets

引用

computers, Materials & Continua 2023年第2期74卷 4531-4545页

作者： Doaa Sami Khafaga El-Sayed M.El-kenawy Faten Khalid Karim Mostafa Abotaleb Abdelhameed Ibrahim Abdelaziz A.Abdelhamid D.L.Elsheweikh Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of System Programming South Ural State UniversityChelyabinsk454080Russia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Specific EducationMansoura UniversityEgypt

Selecting the most relevant subset of features from a dataset is a vital step in data mining and machine *** feature in a dataset has 2n possible subsets,making it challenging to select the optimum collection of features using typical *** a result,a new metaheuristicsbased feature selection method based on the dipper-throated and grey-wolf optimization(DTO-GW)algorithms has been developed in this *** can result when the selection of features is subject to metaheuristics,which can lead to a wide range of ***,we adopted hybrid optimization in our method of optimizing,which allowed us to better balance exploration and harvesting chores more *** propose utilizing the binary DTO-GW search approach we previously devised for selecting the optimal subset of *** the proposed method,the number of features selected is minimized,while classification accuracy is *** test the proposed method’s performance against eleven other state-of-theart approaches,eight datasets from the UCI repository were used,such as binary grey wolf search(bGWO),binary hybrid grey wolf,and particle swarm optimization(bGWO-PSO),bPSO,binary stochastic fractal search(bSFS),binary whale optimization algorithm(bWOA),binary modified grey wolf optimization(bMGWO),binary multiverse optimization(bMVO),binary bowerbird optimization(bSBO),binary hysteresis optimization(bHy),and binary hysteresis optimization(bHWO).The suggested method is superior 4532 CMC,2023,vol.74,no.2 and successful in handling the problem of feature selection,according to the results of the experiments.

关键词： Metaheuristics dipper throated optimization grey wolf optimization binary optimizer feature selection

来源：评论

学校读者我要写书评

暂无评论

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF 41

Principled Penalty-based Methods for Bilevel Reinforcement L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shen, Han Yang, Zhuoran Chen, Tianyi Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Department of Statistics and Data Science Yale University United States

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions. To tackle this new class of bilevel problems, we introduce the first principled algorithmic framework for solving bilevel RL problems through the lens of penalty formulation. We provide theoretical studies of the problem landscape and its penalty-based (policy) gradient algorithms. We demonstrate the effectiveness of our algorithms via simulations in the Stackelberg game and RLHF. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

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：