检索结果-内蒙古大学图书馆

AHHO: Arithmetic Harris Hawks Optimization algorithm for demand side management in smart grids

Discover Internet of Things 2023年第1期3卷 3页

作者： Manzoor, Awais Judge, Malik Ali Islam, Saif ul Neggaz, Nabil Abulaigh, Laith Ahmad, Ishfaq Department of Computer Science COMSATS University Islamabad Islamabad44550 Pakistan Department of Computer Sciences Institute of Space Technology Islamabad Pakistan Faculty of Mathematics and Computers University of Sciences and Technologies-USTO-MB Oran Algeria Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Faculty of Information Technology Middle East University Amman11831 Jordan Department of Computer Science and Engineering The University of Texas at Arlington Arlington United States

Energy management strategies are crucial to efficiently scheduling appliances and preventing peak generation due to increased energy demand. It is essential to manage the demand and supply of energy based on the consumer’s consumption patterns using various heuristic optimization techniques. Additionally, the end-user is more concerned with minimizing electricity costs and reducing peak-to-average ratios (PARs). This work proposes an arithmetic Harris hawks optimization (AHHO) as a new approach for improving the Harris hawks algorithm to optimize residential demand response (DR) load management in a smart grid. Our method employs arithmetic and lightweight flight operators based on the Lévy flight distribution to generate diverse design solutions and improve the HHO’s exploration capabilities. We consider 15 smart appliances and categorize them based on how much energy they use, computing the electricity price using real-time pricing (RTP) and critical peak pricing (CPP). While maintaining user satisfaction within operational and power limits, the objective is to decrease energy costs and PAR. We evaluate the effectiveness of our proposed AHHO approach against nine cutting-edge algorithms using both RTP and CPP schemes. The findings demonstrate that our suggested approach performs better than the other algorithms because it achieved cost savings of 42.10% and 30% under RTP and CPP schemes, respectively. Meanwhile, it also reduced PAR by 55.17% and 50% under RTP and CPP schemes, respectively. © The Author(s) 2023.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph-Based AU Relationship Learning for Facial Action Unit Detection

Spatial-Temporal Graph-Based AU Relationship Learning for Fa...

引用

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Zihan Song, Siyang Luo, Cheng Zhou, Yuzhi Wu, Shiling Xie, Weicheng Shen, Linlin Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology China University of Leicester School of Computing and Mathematical Sciences United Kingdom

ISBN: (纸本)9798350302493

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence;(ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation;and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5. © 2023 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Advancements in Object Detection for Accurate and Efficient Visual Recognition Using Machine Learning 2

Advancements in Object Detection for Accurate and Efficient ...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Fernandez, F. Mary Harin Ramachandran, A. Ganesh Saravanan, S.K. Bhanumathi, M. Sangeetha, M. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering SIMATS Tamil Nadu Chennai India Chennai India Computer Engineering Department University of Technology and Applied Sciences Nizwa Oman

ISBN: (纸本)9798350383867

Object detection in images and videos is a vital task in computer vision where its application goes beyond the automobile driving and surveillance, to healthcare. The paper introduces an object detection model which is specific and powerful, that is able to recognize visually with machine learning. The framework is constructed on the basis of the recent innovations in deep learning and attentive mechanisms, which not only lead to the best performance in object detection today but also guarantee the widest applicability. Using an extensive experiment which reveals the described model superiority over the current state-of-the-art algorithms by evaluating mAP indices, whereas the latter has a normal complexity. The ablation study uncovers the impact of core parameters including attention mechanisms and semi-supervised techniques, underlining their importance in the growth of detection precision. Moreover, the illustrative comparison of outcomes from detecting objects on the framework calls for attention to the capacity of the networks to objectify in different categories. Our outcome also suggest that although the proposed framework has a human-level performance in task of object detection there is still a scope to enhance their performance above the human level. Summarizing, this work concludes the conversation and can be considered in the progress of research developments of the object detection systems aimed at practical object meeting situations. © 2024 IEEE.

关键词： computer vision Deep Learning Machine Learning Object Detection Visual Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Intrusion Detection with Advanced Deep Features and Ensemble Classifier Techniques

引用

SN computer Science 2025年第4期6卷 1-17页

作者： Toralkar, Pawan Mainalli, Kavita Allagi, Shridhar Debnath, Sanjoy Kumar Bagchi, Susama Leong, Wai Yie Khan, Muhammad Numan Ali Department of Artificial Intelligence Madanapalle Institute of Technology and Science Andhra Pradesh Madanapalle India Department of Computer Science and Engineering KLEIT: KLE Institute of Technology Karnataka Hubballi India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India INTI International University and Colleges Negeri Sembilan Nilai Malaysia College of Computing and Applied Sciences University of Technology and Applied Sciences Shinas Oman

Intrusion detection is crucial for modern cyber-security, aiming to detect and mitigate unauthorized access and malicious activities within networks. Traditional systems often rely on linear models, which may fail to capture complex patterns in advanced threats. This study proposes a heuristic approach to select the best deep features through an ensemble framework consisting of Random Forest (RF) and Support Vector Machine (SVM) classifiers using soft voting. The novelty of this work is the deep feature extraction through Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Autoencoder for intrusion detection. These extracted features were fed separately for classification. In order to balance the explainability and accuracy, the ensemble classifier consisting of RF and SVM, uses feature importance ranking (RF) and unambiguous decision bounds (SVM) to provide partial interpretability. Evaluating the NSL-KDD and CICDDoS2019 datasets, our ensemble model with CNN features achieves near-perfect accuracy of 99.99% and 99.91% respectively. RNN and Autoencoder models also show high performance, each reaching 99.3% accuracy on the CICDDoS2019 dataset with Soft Voting classifiers. This work highlights the importance of the ensemble method with better feature selection in intrusion detection. The proposed system outperformed the standard methods by providing a robust, scalable solution for organizational security. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolution neural network (CNN) Intrusion detection Random forest (RF) Recurrent neural network (RNN) Voting classification (Voting)

来源：评论

学校读者我要写书评

暂无评论

Augmented Journeys: Interactive Points of Interest for In-Car Augmented Reality 25

Augmented Journeys: Interactive Points of Interest for In-Ca...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Schramm, Robin Connor Fedrizzi, Ginevra Sasalovici, Markus Freiwald, Jann Philipp Schwanecke, Ulrich Mercedes-Benz Tech Motion GmbH Baden-Württemberg Böblingen Germany Computer Vision and Mixed Reality Group RheinMain University of Applied Sciences Hessen Wiesbaden Germany Institute of Media Informatics Ulm University Ulm Germany

ISBN: (纸本)9798400713941

As passengers spend more time in vehicles, the demand for non-driving related tasks (NDRTs) increases. In-car Augmented Reality (AR) has the potential to enhance passenger experiences by enabling interaction with the environment through NDRTs using world-fixed Points of Interest (POIs). However, the effectiveness of existing interaction techniques and visualization methods for in-car AR remains unclear. Based on a survey (N=110) and a pre-study (N=10), we developed an interactive in-car AR system using a video see-through head-mounted display to engage with POIs via eye-gaze and pinch. Users could explore passed and upcoming POIs using three visualization techniques: List, Timeline, and Minimap. We evaluated the system's feasibility in a field study (N=21). Our findings indicate general acceptance of the system, with the List visualization being the preferred method for exploring POIs. Additionally, the study highlights limitations of current AR hardware, particularly the impact of vehicle movement on 3D interaction. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Augmented Reality Automotive User Interfaces In-Car Passenger Points of Interest Vehicle Visualization

来源：评论

学校读者我要写书评

暂无评论

Development and Analysis of a Versatile Dataset of Speech, Real and Synthesized, of Arabic Learners 3

Development and Analysis of a Versatile Dataset of Speech, R...

引用

3rd International Conference on Computing and Information Technology, ICCIT 2023

作者： Alsulaiman, Mansour Algabri, Mohammed Mathkour, Hassan Bencherif, Mohamed A. Muhammad, Ghulam Al-Gahtani, Saad Faisal, Mohammed Mekhtiche, Mohamed Amine Alfakih, Taha King Saud University College of Computer and Information Sciences Computer Engineering Department Riyadh Saudi Arabia AlMaarefa University College of Applied Sciences Computer Science and Information Systems Department Riyadh Saudi Arabia King Saud University College of Computer and Information Sciences Computer Science Department Riyadh Saudi Arabia Riyadh Saudi Arabia King Saud University Arabic Language Institute Saudi Arabia Center of Ai & Robotics Kuwait

ISBN: (纸本)9798350321487

computer-Aided Pronunciation Training (CAPT) systems are gaining popularity recently due to the advancements in deep neural networks (DNN) and machine learning and the availability of databases of speech of language learners. Unfortunately, research in Arabic CAPT systems suffer from the lack of CAPT datasets compared to other languages. In this paper, we present the details of and the ideas used in the development of a versatile dataset of speech, real and synthesized, of Arabic Learners. To develop the dataset, we utilized an existing Arabic speech corpus, King Saud University Speech Database (KSU-SD). KSU-SD's main application was a speaker recognition system, but it was designed to be useful in other applications such as CAPT systems. KSU-SD includes a large number of speakers from diverse nationalities (Saudis, Arabs, and Non-Arabs). KSU-SD contains the recording of about 60 non-native speakers from more than 20 nationalities, hence we selected it to build the non-native Arabic-CAPT corpus. The developed corpus consists of transcribed, segmented, and annotated speech, which makes it suitable for building Arabic CAPT systems. In addition to presenting the details of developing the dataset, we also present an analysis of the text and speech errors of the dataset. The dataset was verified by many CAPT systems. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Developing Real-World Applications with Algorithmic Intelligence in Reinforcement Learning for Robotics 2

Developing Real-World Applications with Algorithmic Intellig...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Bhanumathi, M. Sangeetha, M. Harin Fernandez, F. Mary Ganesh Ramachandran, A. Saravanan, S.K. Chennai India Department of Computer Engineering University of Technology and Applied Sciences Nizwa Oman Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering Simats Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

In the study, three leading reinforcement learning algorithms Deep Q-Network (DQN), Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor - Critic (A3Cc are applied in a number of real-world robotics tasks. The focus of our analysis is on performance indicators, computational efficiencies across multiple environments as well with respect to customer satisfaction rating. The DQN demonstrated good performance, with the success rate of up to 85% in object manipulation tasks and confirmed its reliability under controlled lab conditions where it made only a 5 percent error. PPO excelled in autonomous navigation (82%) and was the most energy-efficient option, requiring just 10 hours for training and using only twelve KWH of power. Compared with A3C, the method performed to a higher level of adaptability and robustness, especially in object manipulation (90% success rate) and dynamic environments (10% error rates applicable for outdoor variable weather conditions). But A3C was also the most automatable, which required 15 hours to train and consumed an astonishing amount of electricity - 18 kWh. Regarding customer satisfaction, PPO performs the best in end-user rating on user interface;A3C shows a preference with engineers due to its advanced features and flexibility. The focus of this study is significant trade-offs between performance, efficiency and user preference in real robotics applications that advocate for individual tailoring selections as well as deployments based on task specifics nature. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Malaria Cell Classification Using CNN: A Deep Learning Approach

Malaria Cell Classification Using CNN: A Deep Learning Appro...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Ali, Muhammad Qasim Kouatly, Rand Karunanithi, Meerah Hassan, Ahmed Rizvi, Syed Arslan Abbas Puthiyapurayil, Nafeesath Parappurath Gik Institute of Engg. Sciences & Tech Faculty of Computer Science & Engg Topi Pakistan University of Europe for Applied Sciences Department of Business Potsdam Germany Berlin School of Business and Innovation Department of Computer Science Berlin Germany Qilu Institute of Technology School of Int. Manu. & Cont. Engg Jinan City China

ISBN: (纸本)9798350353907

Plasmodium malaria is a parasitic protozoan that causes malaria in humans. computer-aided detection of Plasmodium is a research area attracting significant interest. In the current paper, the results of different machine learning, neural network, and deep learning approaches are speculated to evaluate their performance on cell images from digital microscopy concerning the identification of Plasmodium. A publicly available dataset containing 27,558 individual images is utilized, with half of these images containing Plasmodium and the remaining consisting of uninfected cells. The dataset is randomly split into 80-20% groups for training and testing. Color normalization is performed, and all images are spatially reshaped to a predefined size that matches the chosen architecture configurations. A fast CNN model is developed to classify cells in specific cell images. Additionally, classification and ranking of algorithms for transfer learning are conducted using existing networks such as AlexNet, ResNet, VGG-16, and DenseNet. Alongside the evaluation of the bag-of-features model performance, a Support Vector Machine is also employed for classification. A generalized probability trait of an image is assigned only after thoroughly evaluating the probability values given by each CNN model developed for this purpose in this paper. The algorithm achieves an overall accuracy of 96.7% on the test dataset. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Losing Human Identity: Current Threats and Challenges of Robotics and AI 6

Losing Human Identity: Current Threats and Challenges of Rob...

引用

6th Social Robots with AI: Prospects, Risks, and Responsible Methods Robophilosophy, RP 2024

作者： Yatsenko, Olena Sushchenko, Oleksandra Dégallier Rochat, Sarah Institute for Human-Centered Engineering School of Engineering and Computer Science Bern University of Applied Sciences Biel Switzerland Department of Art and Media School of ARTS Aalto University Espoo Finland Human Digital Transformation Strategic Thematic Field Bern University of Applied Sciences Bern Switzerland

ISBN: (纸本)9781643685670

The authors of the article examine the reasons for the pessimistic perspective, that envisions the possibility of catastrophe for humanity caused by the "singularity". We argue that the interaction between humans and machines is neither a matter of competition nor collaboration. Instead, a more realistic outcome of human-machine interactions is the erosion of the genuine foundations of human identity nature. This perspective is based on an analysis of the essential elements that constitute human identity, as well as the most significant ways in which robotics and artificial intelligence (AI) affect individual, social, and cultural life. Through this analysis, we aim to identify the threats and opportunities, as well as propose viable solutions for the preservation and sustainable development of humanity.. © 2025 IOS Press. All rights reserved.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

A Parallel High-Utility Itemset Mining Algorithm Based on Hadoop

引用

Complex System Modeling and Simulation 2023年第1期3卷 47-58页

作者： Zaihe Cheng Wei Shen Wei Fang Jerry Chun-Wei Lin School of Internet of Things Wuxi Institute of TechnologyWuxi 214121China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan UniversityWuxi 214122China Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergen 5020Norway

High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data ***,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this *** P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce *** the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset *** the Map phase,the P-EFIM algorithm divides the task into multiple independent *** uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure ***,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce *** are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.

关键词： pattern mining data mining Hadoop parallel high-utility itemset mining big data

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：