检索结果-内蒙古大学图书馆

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Raad, Rabei Zearah, Sajad Ali Saleem, Munqith. Al-Tahee, Ali Mustafa Qasim Abbas, Saad Kadhim, Mohammed National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Iraq Al-Ayen University Scientific Research Center Thi-Qar Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Al-Farahidi University Medical Instruments Engineering Techniques Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

The purpose of a Corporate Protection System (CPS) is to prevent unauthorized individuals from gaining access to a company's facilities and/or data. Based on the nature of the company being secured, particular characteristics and functionalities of a safety measure may need to be tailored to meet their needs. Genetic linkage, selection, recombination rates, mutation rates, genetic drift, mating systems, and population structure influence linkage heterogeneity. Security in business is a technique for protecting business data against unauthorized access and risks that protects company data stored in the system from malicious intent and defends against host-based attacks. Information security suggests that all attempts to safeguard an organization's information are driven by creating resources that might improve the organization's performance. The article proposed an Information Security in Business based Advanced Protection (ISB-AP) technique to safeguard a corporate company's property and resources from intruders. To defend against threats, physical assets, information systems, and other assets are covered by various security procedures based on Artificial Intelligence (AI) technology. The conceptual model of software used in the study incorporates conscientiousness and agreement. Although conscientiousness and agreeableness diminished this link, the behavioural purpose was related to attitude constructs' perceived usefulness and ease of use. The proposed method yields the following results: time in-device ratio of 75.67%, security requirements ratio of 90.955%, transmission bytes in attack ratio of 87.05%, challenges in supply chain ratio of 85.45%, annual occurrence ratio of 89.88%, and overall percentage performance ratio of 91.87%. © 2023 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Internet of Things and wearable device-basedtracking of an elderly person's physical activity 1

Internet of Things and wearable device-basedtracking of an e...

引用

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Ali Zearah, Sajad Mohammed Abed, Ansam Hussian, Ahmed Ali Ettyem, Sajjad Hussam, Ragheed Matti, Imad Alayen University Scientific Research Center Thi-Qar Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Technologies National University of Science and Technology Department of Medical Devices Engineering Nasiriyah Dhi Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

The potential for real-time activity tracking (R- TAT) to shed light on the health and habits of the elderly is a major reason why it should be widely adopted. This strategy allows for the unobtrusive collecting and analysis of data connected to a person's day-to-day physical activities by deploying wearable devices equipped with sensors and leveraging the connectivity of IoT. These details can be crucial in the early diagnosis of health problems, allowing for prompt interventions and individualized healthcare plans. Ethical constraints, data privacy, and the requirement for userfriendly gadgets offer considerable challenges to mainstream adoption. To facilitate real-time monitoring while giving top priority to data integrity and confidentiality, a new algorithm called the IoT-Enabled Data Transmission Privacy Recognition Algorithm (IoT-DTPRA) has been suggested in the present research. Provides fine-grained control over data sharing options and uses strong measures like encryption and anonymization to preserve the privacy of senior citizens' personal information. Caretakers, healthcare professionals, and family members all benefit from the actionable information provided by IoT-DTPRA since it provides a comprehensive and privacy-conscious way to monitoring the physical activity of the elderly. The suggested methodology is verified using simulation analysis, which use actual situations and synthetic datasets to assess the IoT-DTPRA system's performance in a range of environments. The methodology's reliability and robustness across a wide range of physical activities and environmental circumstances have been verified by this thorough validation. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Target Detection in Complex Environments using UAV and Deep Learning-based Focal Pruning Method 1

Target Detection in Complex Environments using UAV and Deep ...

引用

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Thejeel, Sara H. Hussian, Ahmed Hussian, Ahmed Ahmed, Wasan Saad Ali Zearah, Sajad Ali, Mohsin National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq AlTurath University College Computer Technologies Engineering Baghdad Iraq Al-Ayen University Scientific Research Center Thi-Qar Iraq Computer Technology Engineering Al-Maamoun University College Baghdad Iraq

ISBN: (纸本)9798350359756

Applications from computer vision that use deep learning for target detection have become incredibly popular recently. The requirement for future applications includes monitoring, visual navigation, object identification, and sensor-based preventative planning, together with the growing UAV industry advances, which hold great potential for deep learning. Deep learning techniques for object detection have swiftly evolved into a rendering tool for photos taken by flying drones. This paper's primary goal is to present a comprehensive overview of contemporary deep learning-based object recognition algorithms and to explore their most recent contributions to UAV low-altitude datasets. As opposed to standard or remote-sensor datasets, which comprise a smaller percentage of the literature, low-level UAV datasets are the focus of the research. To conduct real-time bridge crack diagnosis with Unmanned Aerial Vehicles (UAV), a deep learning system dubbed the You Only Look Once version-4 Focal Pruning Method (YOLOv4-FPM) is suggested based on the YOLOv4 model. For YOLOv4-FPM, focal loss architecture is utilized to streamline the loss feature, improve accuracy and colour transmission, and solve issues with dynamic context. A pruning method is used to speed up detection and facilitate the network. The outcomes show that the model can successfully handle the difficulty given by various backdrops, and the detection velocity is 97.2% effective enough for the real-time detection mission. The YOLOv4-FPM of deep learning technology guarantees 96.3% detection accuracy compared to current drone detection methods. © 2023 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

TTSlow: Slow Down Text-to-Speech With Efficiency Robustness Evaluations

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 693-704页

作者： Xiaoxue Gao Yiming Chen Xianghu Yue Yu Tsao Nancy F. Chen Institute for Infocomm Research Agency for Science Technology and Research (A*STAR) Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Department of Electrical Engineering Chung Yuan Christian University Taoyuan City Taiwan

Text-to-speech (TTS) has been extensively studied for generating high-quality speech with textual inputs, playing a crucial role in various real-time applications. For real-world deployment, ensuring stable and timely generation in TTS models against minor input perturbations is of paramount importance. Therefore, evaluating the robustness of TTS models against such perturbations, commonly known as adversarial attacks, is highly desirable. In this paper, we propose TTSlow, a novel adversarial approach specifically tailored to slow down the speech generation process in TTS systems. To induce long TTS waiting time, we design novel efficiency-oriented adversarial loss to encourage endless generation process. TTSlow encompasses two attack strategies targeting both text inputs and speaker embedding. Specifically, we propose TTSlow-text, which utilizes a combination of homoglyphs-based and swap-based perturbations, along with TTSlow-spk, which employs a gradient optimization attack approach for speaker embedding. TTSlow serves as the first attack approach targeting a wide range of TTS models, including autoregressive and non-autoregressive TTS ones, thereby advancing exploration in audio security. Extensive experiments are conducted to evaluate the inference efficiency of TTS models, and in-depth analysis of generated speech intelligibility is performed using Gemini. The results demonstrate that TTSlow can effectively slow down two TTS models across three publicly available datasets.

关键词： Perturbation methods Speech processing Robustness Computational modeling Security Optimization Text to speech Speech recognition Predictive models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Seamless Distributed Power Management of DC Microgrid under Cyber Attacks with Bidirectional Power Flow

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Tran, Dat Thanh Kim, Kyeong-Hwa Lai, Jih-Sheng Seoul National University of Science and Technology Research Center for Electrical and Information Technology Department of Electrical and Information Engineering Seoul01811 Korea Republic of Department of Electrical and Computer Engineering BlacksburgVA24061 United States

A seamless distributed power management for the dc microgrid (DCMG) with bidirectional power flow is presented in this paper to achieve the overall system stabilization even under severe cyber attacks. First, a distributed secondary control (DSC) based on the V*-P droop curves is presented to ensure the power and voltage regulation for the DCMG system consisting of the electric vehicle (EV), wind turbine, battery, load, and utility grid agents under uncertain conditions. The proposed scheme automatically adjusts the utility grid droop curve to minimize electricity expenditure under electricity price change. To eliminate the negative effect of severe cyber attacks such as false data injection (FDI) and denial-of-service (DoS) in the distributed DCMG system, a resilient DSC based on the compensation term is utilized in the proposed scheme. In addition, by modifying the DSC structure of each power agent, the proposed scheme reduces the overshoot of the dc bus voltage even in the presence of the electricity price change, agent power variation, sudden utility grid disconnection, or critical state-of-charge (SOC) levels. Furthermore, the proposed distributed DCMG system utilizes only the unidirectional digital communication links (DCLs) to cut down the system cost and communication burden, which greatly simplifies communication structure. The efficiency and feasibility of the proposed distributed power management are validated by simulation and experimental results under various conditions. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Aided Optimization Approach for Sustainable Energy Systems 1

Machine Learning-Aided Optimization Approach for Sustainable...

引用

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Hussian, Ahmed Ali Ettyem, Sajjad Ali Zearah, Sajad Ahmed, Ibrahem Ismail, Laith S. Ibrahem, Marwa Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq National University of Science and Technology Dhi Qar Department of Medical Devices Engineering Technologies Nasiriyah Iraq Al-Ayen University Thi-Qar Scientific Research Center Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

Energy derived from renewable sources is expanding quickly. Renewable energy systems meet off-grid and on-grid load requirements, often connected to conventional sources. Geothermal, solar, wind, and other renewable energy sources can be harnessed economically at the current rate of technological development. Renewable-based electricity production is an alternative form of green power generation that reduces issues with energy consumption. Though this raises numerous uncertainties and difficulties, it may jeopardize potential economic, technological, and environmental gains. Consequently, a Machine Learning aided Optimization Approach (MLOA) for sustainable energy systems has been suggested in this study. The Enhanced Long Short-Term Memory (E-LSTM) model of recurrent neural networks trained by Adam optimizer is employed in MLOA due to its ability to predict solar and wind generation to provide optimal energy consumption control. The numerical outcomes demonstrate that the suggested MLOA method improves prediction and accuracy rates by 98.22% compared to other current approaches. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Smart City Application based on Internet-of-Things and Artificial Intelligence for Energy Management Dynamic Memory Modelling 1

Smart City Application based on Internet-of-Things and Artif...

引用

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Zearah, Sajad Ali Al-Tahee, Mustafa Mohammed, Aymen Shnawa, Ammar H. Harith Jameel Mahdi, Hasan Majeed, Zainab Al-Ayen University Scientific Research Center Thi-Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

By and by, the world ingests a lot of energy, including power, machine protection energies, water-driven energy, etc. Since power stays huge, considering world development, a few researchers have endeavored to deliver power from environmentally friendly power sources from intelligent gadget sensor's point of interaction to address family and modern energy deficiencies. To address the energy management problem during information processing on the Internet of Things (IoT) platform, an Artificial Intelligence Assisted Dynamic Memory Modelling on Internet-of-Things (AIADMM) has been designed and developed with mathematical modeling with multiple information processing sensors for domestic and industrial applications. However, These Particular gadgets, for example, the piezoelectric module, electric structure intensity to the electrical converter, and sun-powered board approach, are utilized to associate the energy stockpiling framework for power age in the standard techniques without streamlined calculations, prompting appeal in energy enhancement research. Thus, the whole energy age by environmentally friendly power sources is improved by two models planned in this exploration: the Artificial Neural Network (ANN) and the Artificial Intelligence Assisted Dynamic Memory Modelling on Internet-of-Things (AIADMM). Test results at the lab scale have been broken down in light of Factual constraints, such as Root Mean Square Error (RMSE). The R2 relationship coefficient, dependability factor, energy then, at that point, network clog, and time delay on the IoT stage shows promising outcomes. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Triethyleneglycol C60 Mono-adduct Derivative for Efficient Electron Transport in Inverted Perovskite Solar Cells

引用

Chinese Journal of Chemistry 2023年第4期41卷 431-442页

作者： Azhar Fakharuddin Konstantina-Kalliopi Armadorou Leandros P.Zorba Marinos Tountas Tobias Seewald Anastasia Soultati Polychronis Tsipas Emilia R.Schütz Nikolaos Tzoganakis Stylianos Panagiotakis Konstantina Yannakopoulou Athanasios Dimoulas Vassilis Psycharis Emmanuel Kymakis Abd Rashid bin Mohd Yusoff Konstantinos Aidinis Lukas Schmidt-Mende Georgios C.Vougioukalakis Mohammad Khaja Nazeeruddin Maria Vasilopoulou Department of Physics University of Konstanz78457 KonstanzGermany Institute of Nanoscience and Nanotechnology National Center for Scientific Research DemokritosAgia Paraskevi15341 AthensGreece Department of Chemistry National and Kapodistrian University of Athens15771 AthensGreece Department of Electrical&Computer Engineering Hellenic Mediterranean UniversityEstavromenosHeraklionGR-71410 CreteGreece Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)PohangGyeongbuk37673 Republic of Korea Department of Electrical and Computer Engineering Ajman UniversityP.O.Box 346AjmanUnited Arab Emirates Center of Medical and Bio-allied Health Sciences Research AjmanUnited Arab Emirates Institute of Chemical Sciences and Engineering École Polytechnique Fédérale de Lausanne(EPFL)Rue de l'Industrie 17CH-1951 SionSwitzerland

Inverted perovskite solar cells(PSCs)have attracted increasing attention in recent years owing to their low-temperature fabrication proces ***,they suffer from a limited number of electron transport materials available with[6,6]-phenyl C61 butyric acid methyl ester(PCBM)to be the most widely studied based on its appropriate energy levels and high electron *** low relative permittivity and aggregation tendency upon illumination of PCBM,however,compromises the solar cell efficiency whereas its modest hydrophobicity negatively impacts on the device *** electron transport materials with desired properties and appropriate degree of hydrophobicity are thus desirable for further developments in inverted ***,we synthesize a triethyleneglycol C60 mono-adduct derivative(termed as EPF03)and test it as a novel electron transport material to replace PCBM in inverted PSCs based on a quadruple cation(RbCsMAFA)*** also compare this derivative with two novel fullerenes decorated with two(EPF01)or one dodecyl(EPF02)long side *** latter two fail to perform efficiently in inverted PSCs whereas the former enabled a power conversion efficiency of 18.43%,which represents a 9%improvement compared to the reference device using PCBM(17.21%).The enhanced performance mainly stems from improved electron extraction and reduced recombination enabled by the insertion of the large relative permittivity amongst other properties of ***,our results indicate that triethylene glycol side chains can also passivate perovskite trap states,suppress ion migration and enhance photostability and long-term stability of EPF03 based perovskite solar cells.

关键词： Electron transport layer Defect passivation Biexponential trap flling Charge transfer Fullerenes

来源：评论

学校读者我要写书评

暂无评论

Human-computer Interaction Assisted Economic Growth and Financial Status of Urban Cities using Artificial Intelligence 1

Human-Computer Interaction Assisted Economic Growth and Fina...

引用

1st IEEE International Conference on Emerging research in Computational Science, ICERCS 2023

作者： Dawood, Mustafa Nazar Brayyich, Mohammed Majed, Safa Zearah, Sajad Ali Ali, Aqeel Ali, Ahmed Al-Turath University College Computer Technologies Engineering Baghdad Iraq National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Al-Ayen University Scientific Research Center Thi-Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

The rate of population increase in an urban region is an important Economic Growth and Financial factor (EGF). Urbanization helps a nation's economy develop and flourish. Urbanization refers to the spread of a city or suburb into its environs. The growth of cities indicates a country's economic well-being since cities are major financial hubs. Employment opportunities increase, and the local economy benefits as a metropolitan area expands. Demand for products and services rises due to urbanization, prompting a reallocation of resources (land, labor, and capital) from agriculture to other sectors of the economy. Cities have increasing needs, exacerbated by poor air and water quality, limited water supply, waste-disposal worries, and excessive energy usage. Economic expansion is impossible without technological progress, which makes it possible to mass-produce better goods at reduced prices. Effective city planning will be crucial for addressing these, and other challenges as the world's urban centers grow. Artificial Intelligence (AI) has already had a wide-ranging impact on our culture, and its influence on our daily lives and the economy is only growing. The research suggests that an AI-EGF might be a valuable tool for increasing the prosperity of urban areas. Some people believe that AI can help the economy develop and increase productivity. Analysis of large data sets may be performed effectively to raise productivity and standard of living. When a new product, market, or industry is created, consumer demand increases and new revenue opportunities arise. Recent years have seen a rise in the urgency of concerns about the impact of AI on organizations and consumers. The result of artificial intelligence (AI) on businesses and workers' financial security is a topic of intense interest. The experiments show that the suggested strategy is 37% more efficient on average. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Unsupervised optical flow estimation with dynamic timing representation for spike camera 23

Unsupervised optical flow estimation with dynamic timing rep...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Lujie Xia Ziluo Ding Rui Zhao Jiyuan Zhang Lei Ma Zhaofei Yu Tiejun Huang Ruiqin Xiong School of Computer Science Peking University and National Engineering Research Center of Visual Technology (NERCVT) National Engineering Research Center of Visual Technology (NERCVT) and Beijing Academy of Artificial Intelligence National Biomedical Imaging Center College of Future Technology Peking University School of Computer Science Peking University and National Engineering Research Center of Visual Technology (NERCVT) and Institute for Artificial Intelligence Peking University

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers architecture, it applies dilated convolutions on temporal dimension to extract features on multi-temporal scales with few parameters. And we design layer attention to dynamically fuse these features. Moreover, we propose an unsupervised learning method for optical flow estimation in a spike-based manner to break the dependence on labeled data. In addition, to verify the robustness, we also build a spike-based synthetic validation dataset for extreme scenarios in autonomous driving, denoted as SSES dataset. It consists of various corner cases. Experiments show that our method can predict optical flow from spike streams in different high-speed scenes, including real scenes. For instance, our method achieves 15% and 19% error reduction on PHM dataset compared to the best spike-based work, SCFlow, in Δt = 10 and Δt = 20 respectively, using the same settings as in previous works. The source code and dataset are available at https://***/Bosserhead/USFlow.

关键词：

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：