检索结果-内蒙古大学图书馆

Efficient Global Neural Architecture Search

SN computer Science 2025年第3期6卷 1-12页

作者： Siddiqui, Shahid Kyrkou, Christos Theocharides, Theocharis Electrical and Computer Engineering Department University of Cyprus Nicosia Cyprus KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

Neural architecture search (NAS) has shown promise towards automating neural network design for a given task, but it is computationally demanding due to training costs associated with evaluating a large number of architectures to find the optimal one. To speed up NAS, recent works limit the search to network building blocks (modular search) instead of searching the entire architecture (global search), approximate candidates’ performance evaluation in lieu of complete training, and use gradient descent rather than naturally suitable discrete optimization approaches. However, modular search does not determine network’s macro architecture i.e. depth and width, demanding manual trial and error post-search, hence lacking automation. In this work, we revisit NAS and design a navigable, yet architecturally diverse, macro-micro search space. In addition, to determine relative rankings of candidates, existing methods employ consistent approximations across entire search spaces, whereas different networks may not be fairly comparable under one training protocol. Hence, we propose an architecture-aware approximation with variable training schemes for different networks. Moreover, we develop an efficient search strategy by disjoining macro-micro network design that yields competitive architectures in terms of both accuracy and size. Our proposed framework achieves a new state-of-the-art on EMNIST and KMNIST, while being highly competitive on the CIFAR-10, CIFAR-100, and FashionMNIST datasets and being 2-4 times faster than the fastest global search methods. Lastly, we demonstrate the transferability of our framework to real-world computer vision problems by discovering competitive architectures for face recognition applications. © The Author(s) 2025.

关键词： AutoML Convolutional neural networks Deep learning Image classification Neural architecture search

来源：评论

学校读者我要写书评

暂无评论

A Holistic Assessment Framework for Evaluating Buildings' Green and Digital Readiness Level

A Holistic Assessment Framework for Evaluating Buildings' Gr...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Stylianides, Nearchos Hadjidemetriou, Lenos Charalambous, Charalambos Panayiotou, Christos University of Cyprus Kios Research and Innovation Center of Excellence Department of Electrical and Computer Engineering Nicosia Cyprus

ISBN: (纸本)9789531842976

Smart buildings assessment methodologies are important tools utilized across all stages of transitioning towards a greener, smarter, and energy-efficient building sector. Existing assessment methods either focus only on specific building aspects, or consider buildings with particular technical characteristics, or require explicit technical knowledge by the users to evaluate building performance. Consequently, this paper proposes a holistic and flexible assessment framework that encompasses all facets of a building, including green factor, energy efficiency, occupants' comfort, and digitization levels. The proposed framework does not require strong technical knowhow to perform the assessment and can be generally applied for evaluating different buildings by providing basic information about their main characteristics. The assessment framework was applied to a real commercial building, demonstrating its effective use in evaluating overall building performance and analyzing the score in each individual impact category or domain. In addition, two potential action plans were formulated by utilizing the proposed framework to explore different pathways for enhancing the building's performance. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Embedded and Real-Time Anomalous Command Classification in Unmanned Ground Vehicle Operations 32

Embedded and Real-Time Anomalous Command Classification in U...

引用

32nd IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2024

作者： Elia, Rafaella Theocharides, Theocharis Kios Research and Innovation Center of Excellence University of Cyprus Department of Electrical and Computer Engineering Nicosia Cyprus

ISBN: (纸本)9798331539672

Unmanned Ground Vehicles (UGVs) are increasingly used in safety-critical applications, typically controlled under challenging conditions that may cause stress and fatigue on the operator. This can potentially compromise the safety of the mission due to involuntary movements by the operator, resulting in abnormal commands issued on the remote controller of the vehicle. Such movements can be detected by evaluating the mental state of the operator, the operational context of the UGV, and of course real-time movement detection by the operator. To detect such anomalous commands, we propose a three-stage Machine Learning (ML) based approach, which is suitable for embedded implementation providing real-time classification. Firstly, we detect whether there is any movement on the controller and classify the type of the given movement. Next, we classify whether the operator is under incremental stress and finally discern, in relationship to the UGV's operational context extracted by the state of the UGV is considered normal or not. We use a dataset collected through real-world scenarios, to evaluate the proposed approach, and we evaluate the performance of the proposed approach on an embedded platform (Jetson Xavier NX), extracting relevant metrics such as processing time, energy consumption, and classification accuracy. Our findings demonstrate successful high classification rates for the mental state of the operator (96%) and the ground vehicle movements (74%), as well as the associated involuntary command recognition, with low energy (0.43mJ) and time (0.39s) requirements. © 2024 IEEE.

关键词： Remotely operated vehicles

来源：评论

学校读者我要写书评

暂无评论

Passivity Preserving Safety-Critical Control of Switched Systems 63

Passivity Preserving Safety-Critical Control of Switched Sys...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Meng, Qingkai Kasis, Andreas Polycarpou, Marios M. University of Cyprus Kios Research and Innovation Center of Excellence Department of Electrical and Computer Engineering Nicosia1678 Cyprus

ISBN: (纸本)9798350316339

System safety refers to the property of the state trajectories to remain within some predefined set at all times. Integrating safety and stability offers significant advantages, such as resilience to disturbances and enhanced reliability and predictability. This paper combines control barrier functions and passivity methodologies, in the context of switched systems, to simultaneously ensure stability and safety. We derive conditions under which the passivity of switched systems is preserved under control barrier function-based switched safety-critical control. This enables the construction of a suitable design framework for observer-based output feedback controllers and switching laws, that achieve simultaneous stability and safety guarantees, without imposing any assumption on the safety of individual subsystems. Furthermore, we show that the simultaneous passivity and safety of interconnected switched systems under feedback and parallel configurations can be guaranteed by applying the developed conditions on each local switched subsystem. The applicability of the developed theoretical results is validated through a planar moving body example. © 2024 IEEE.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Gradient Optimizer Algorithm with Hybrid Deep Learning Based Failure Detection and Classification in the Industrial Environment

引用

computer Modeling in engineering & Sciences 2024年第2期138卷 1341-1364页

作者： Mohamed Zarouan Ibrahim M.Mehedi Shaikh Abdul Latif Md.Masud Rana Department of Electrical and Computer Engineering(ECE) King Abdulaziz UniversityJeddah21589Saudi Arabia Center of Excellence in Intelligent Engineering Systems(CEIES) King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Nuclear Engineering King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical and Electronic Engineering Rajshahi University of Engineering and TechnologyRajshahiBangladesh

Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Industry ***, various modernized industrial processes have been equipped with quite a few sensors to collectprocess-based data to find faults arising or prevailing in processes along with monitoring the status of *** diagnosis of rotating machines serves a main role in the engineering field and industrial production. Dueto the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experienceand human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’sinterest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDLFDC)in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelettransform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residualnetwork (ResNet18) model was exploited for the extraction of features from the vibration signals which are thenfed into theHDLmodel for automated fault detection. Finally, theGOA-based hyperparameter tuning is performedtoadjust the parameter valuesof theHDLmodel *** experimental result analysis of the GOAHDL-FD Calgorithm takes place using a series of simulations and the experimentation outcomes highlight the better resultsof the GOAHDL-FDC technique under different aspects.

关键词： Fault detection Industry 4.0 gradient optimizer algorithm deep learning rotating machineries artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Passive Attack Detection for a Class of Stealthy Intermittent Integrity Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 898-915页

作者： Kangkang Zhang Christodoulos Keliris Thomas Parisini Bin Jiang Marios M.Polycarpou Department of Electrical and Electronic Engineering Imperial College LondonLondon SW72AZUKand also with the KIOS Research and Innovation Center of ExcellenceUniversity of CyprusNicosia 1678Cyprus KIOS Research and Innovation Center of Excellence and the Department of Electrical and Computer Engineering University of CyprusNicosia 1678Cyprus Department of Electrical and Electronic Engineering Imperial College LondonLondon SW72AZUK Department of Engineering and Architecture University of TriesteTrieste 34127Italy KIOS Research and Innovation Center of Excellence University of CyprusNicosia 1678Cyprus College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China

This paper proposes a passive methodology for detecting a class of stealthy intermittent integrity attacks in cyberphysical systems subject to process disturbances and measurement noise.A stealthy intermittent integrity attack strategy is first proposed by modifying a zero-dynamics attack *** stealthiness of the generated attacks is rigorously investigated under the condition that the adversary does not know precisely the system state *** order to help detect such attacks,a backward-in-time detection residual is proposed based on an equivalent quantity of the system state change,due to the attack,at a time prior to the attack occurrence time.A key characteristic of this residual is that its magnitude increases every time a new attack *** estimate this unknown residual,an optimal fixed-point smoother is proposed by minimizing a piece-wise linear quadratic cost function with a set of specifically designed weighting *** smoother design guarantees robustness with respect to process disturbances and measurement noise,and is also able to maintain sensitivity as time progresses to intermittent integrity attack by resetting the covariance matrix based on the weighting *** adaptive threshold is designed based on the estimated backward-in-time residual,and the attack detectability analysis is rigorously investigated to characterize quantitatively the class of attacks that can be detected by the proposed ***,a simulation example is used to demonstrate the effectiveness of the developed methodology.

关键词： Backward-in-time equivalent quantity fixed-point smoother intermittent integrity attacks

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface Direct Data Modulation With Adaptive Beam Steering Backscatter Communication

引用

IEEE Internet of Things Journal 2025年第11期12卷 15600-15619页

作者： Amri, Muhammad Miftahul Aziz, Arif Abdul Tran, Nguyen Minh Park, Je Hyeon Kim, Dong In Choi, Kae Won Sungkyunkwan University College of Information and Communication Engineering Department of Electrical and Computer Engineering Suwon16419 Korea Republic of Telkom University University Center of Excellence for Intelligent Sensing-IoT Bandung Indonesia Department of Wireless Communications Hanoi Viet Nam

Reconfigurable intelligent surface (RIS) has emerged as a promising technology for next-generation wireless communications due to its ability to manipulate electromagnetic (EM) waves. This work introduces a novel RIS direct modulation scheme based on the backscatter communication concept. In this work, the RIS acts as a sole information modulator. Unlike conventional RIS systems that relay incoming data-carrying waves, this work enables RIS to encode its own information into unmodulated waves without requiring any hardware modifications. We propose an adaptive algorithm that maximizes modulation order while meeting the quality of service (QoS) requirements by selecting appropriate constellation points to minimize error probability. The proposed scheme was validated through simulations and experiments using a passive 5.8 GHz RIS prototype. The validations demonstrate consistent performance in both distributed and co-located transmitter-receiver scenarios. These results highlight its feasibility as an alternative approach for RIS-assisted communications and contribute to further exploration of RIS-enabled symbiotic radio (SR) and over-the-air (OTA) modulation systems. © 2014 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach for automated grading of knee osteoarthritis severity

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Kaur, PrabSimran Kohli, Guneet Singh Bedi, Jatin Wasly, Saud Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Electrical and Computer Engineering Department King Abdulaziz University Jeddah22254 Saudi Arabia Center of Excellence in Intelligent Engineering Systems King Abdulaziz University Jeddah22254 Saudi Arabia

Knee Osteoarthritis (OA) is a prevalent musculoskeletal disorder that affects the knee joint that causes pain, stiffness, and reduced mobility. It is also known as "Degenerative Joint Disease" and is caused by the degeneration of cartilage in the knee joint, leading to bone-on-bone contact and further damage. Knee OA is prevalent in the population, affecting around 22% to 39% of people in India, and there is currently no treatment available that can halt the progression of the disease. Therefore, early diagnosis and management of symptoms are essential to reduce its impact on an individual’s quality of life. To address this issue, have introduced a framework that leverages ConvNeXt architecture, a modernization of ResNets (ResNet-50) architecture towards Hierarchical Transformers (Swin Transformers), to provide accurate identification and classification of knee osteoarthritis. The classification of knee osteoarthritis was done using the Kellgren and Lawrence (KL) graded X-ray images. These images of the damaged knees are preprocessed and augmented, creating a scaled, enhanced, and varied version of the features, thus making the data fitter and more significant for classification. The performance estimation of the proposed strategy is conducted on the Osteoarthritis Initiative (OAI), a research project focused on knee osteoarthritis that works in partnership with NIH and other private industries to develop a public domain dataset that can facilitate research and evaluation. It involves training the prepared data using various hyper-tuned versions of ConvNeXt. The different fine-tuned results of the ConvNeXt models on each KL Grade are evaluated against the other state-of-the-art models and vision transformers. The comparative assessment of widely used performance measures shows that the proposed approach outperforms the conventional models by generating the highest score for all the KL grades. Lastly, an approach is employed to statistically confirm the validity of t

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

School Start Time Selection for the Morning Commute Problem: A Regional Modeling and Optimization Approach 27

School Start Time Selection for the Morning Commute Problem:...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Georgantas, Antonios Timotheou, Stelios Panayiotou, Christos G. University of Cyprus 2109 Kios Research and Innovation Center of Excellence Department of Electrical and Computer Engineering Panepistimiou 1 Avenue Cyprus

ISBN: (纸本)9798331505929

Urban traffic congestion during morning rush hour is a source of severe discomfort for commuters. Some commuters must make an intermediate stop at a school to drop off their children before heading to their destination. On the other hand, a different portion of commuters utilize the same network infrastructure to arrive at their destination directly. The fact that schools start at the same time implies that the school-oriented commuters depart from their homes almost simultaneously, significantly contributing to congestion. To address this issue, we propose a feedback-based mechanism that in conjunction with different optimization solvers, staggers the start time of schools such that the peak demand is redistributed. The related problem is formulated as a bi-objective mixed integer nonlinear program that jointly minimizes i) the total time spent by all vehicles inside the network and ii) the overall change between the initial and the staggered start time of the schools. Simulation experiments verify that for the examined network architecture, the developed approach can pinpoint school start times that can completely eliminate congestion. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Gas Density Sensors Integration on Heterogeneous Mobile Robots 8

Gas Density Sensors Integration on Heterogeneous Mobile Robo...

引用

8th International Conference on Information Technology, Information Systems and electrical engineering, ICITISEE 2024

作者： Jotham, Adrian Ferdin Jimananda, Aulia Samudra Adhiwangsa, Fahmi Jati, Agung Nugroho Shiddieqy, Hasbi Ash School of Electrical Engineering Telkom University Department of Computer Engineering Indonesia The University Center of Excellence for Intelligent Sensing-IoT Telkom University Indonesia The University Center of Excellence Energy and Climate Change Telkom University Indonesia

ISBN: (纸本)9798350368970

Gas measurement to describe a gas dispersion throughout the indoor environment was developed using two heterogeneous mobile sensors. They were applied to two different heights of measurement. These heterogeneities are related to the sensor type and sensor's carrier. They affect the measurement results in terms of accuracy and accumulative information. Calibration and data synchronization were required to keep the overall results representative with error minimization. The experiment-based mobile measurements were conducted by utilizing a nano-UA V and a UGV in an indoor environment. The result indicates that the gas dispersion can be generated at each height. The variation of the measurement results was influenced by the wind direction, gas mass, sensor sensitivities, and even the UAV's turbulences. © 2024 IEEE.

关键词： Microrobots

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：