检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Ferigo, Andrea Iacca, Giovanni Medvet, Eric Nadizar, Giorgia Department of Information Engineering and Computer Science University of Trento Italy Department of Engineering and Architecture University of Trieste Italy Department of Mathematics and Geosciences University of Trieste Italy Department of Information and Communication Technology

Multi-cellular organisms typically originate from a single cell, the zygote, that then develops into a multitude of structurally and functionally specialized cells. The potential of generating all the specialized cells that make up an organism is referred to as cellular "totipotency", a concept introduced by the German plant physiologist Haberlandt in the early 1900s. In an attempt to reproduce this mechanism in synthetic organisms, we present a model based on a kind of modular robot called Voxel-based Soft Robots (VSRs), where both the body, i.e., the arrangement of voxels, and the brain, i.e., the Artificial Neural Network (ANN) controlling each module, are subject to an evolutionary process aimed at optimizing the locomotion capabilities of the robot. In an analogy between totipotent cells and totipotent ANN-controlled modules, we then include in our model an additional level of adaptation provided by Hebbian learning, which allows the ANNs to adapt their weights during the execution of the locomotion task. Our in silico experiments reveal two main findings. Firstly, we confirm the common intuition that Hebbian plasticity effectively allows better performance and adaptation. Secondly and more importantly, we verify for the first time that the performance improvements yielded by plasticity are in essence due to a form of specialization at the level of single modules (and their associated ANNs): thanks to plasticity, modules specialize to react in different ways to the same set of stimuli, i.e., they become functionally and behaviorally different even though their ANNs are initialized in the same way. This mechanism, which can be seen as a form of totipotency at the level of ANNs, can have, in our view, profound implications in various areas of AI and applications thereof, such as modular robotics and multi-agent systems. © 2024, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Pedestrian Social Distancing Risk Alert System for COVID-19

引用

computer Systems Science & Engineering 2023年第10期47卷 937-954页

作者： Zhihan Liu Xiang Li Siqi Liu Wei Li Xiangxu Meng Jing Jia College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Department of Clinical Laboratory Harbin Medical University Cancer HospitalHarbinHeilongjiang150081China Faculty of Arts Design and ArchitectureSchool of Built EnvironmentThe University of New South WalesSydneyNSW 2052Australia

The COVID-19 virus is usually spread by small droplets when talking,coughing and sneezing,so maintaining physical distance between people is necessary to slow the spread of the *** World Health Organization(WHO)recommends maintaining a social distance of at least six *** this paper,we developed a real-time pedestrian social distance risk alert system for COVID-19,whichmonitors the distance between people in real-time via video streaming and provides risk alerts to the person in charge,thus avoiding the problem of too close social distance between pedestrians in public *** design a lightweight convolutional neural network architecture to detect the distance between people more *** addition,due to the limitation of camera placement,the previous algorithm based on flat view is not applicable to the social distance calculation for cameras,so we designed and developed a perspective conversion module to reduce the image in the video to a bird’s eye view,which can avoid the error caused by the elevation view and thus provide accurate risk indication to the *** selected images containing only person labels in theCOCO2017 dataset to train our *** experimental results show that our network model achieves 82.3%detection accuracy and performs significantly better than other mainstream network architectures in the three metrics of Recall,Precision and mAP,proving the effectiveness of our system and the efficiency of our technology.

关键词： Convolutional neural network pedestrian detection social distancing COVID-19

来源：评论

学校读者我要写书评

暂无评论

Global scale solar energy harnessing: An advanced intra-hourly diffuse solar irradiance predicting framework for solar energy projects

引用

Neural Computing and Applications 2024年第18期36卷 10585-10598页

作者： El-kenawy, El-Sayed M. Bailek, Nadjem Bouchouicha, Kada Zerouali, Bilel Hassan, Muhammed A. Kuriqi, Alban Jamil, Basharat Colak, Ilhami Khalil, Adel Ibrahim, Abdelhameed Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura35111 Egypt Laboratory of Mathematics Modeling and Applications Department of Mathematics and Computer Science Faculty of Sciences and Technology Ahmed Draia University of Adrar Adrar01000 Algeria Energies and Materials Research Laboratory Faculty of Sciences and Technology University of Tamanghasset Tamanrasset10034 Algeria MEU Research Unit Middle East University Amman Jordan Adrar01000 Algeria Vegetal Chemistry-Water-Energy Laboratory Faculty of Civil Engineering and Architecture Department of Hydraulic Hassiba Benbouali University of Chlef Ouled Fares Chlef02180 Algeria Mechanical Power Engineering Department Faculty of Engineering Cairo University Giza12613 Egypt School of Architecture University of Waterloo 7 Melville St S CambridgeONN1S 2H4 Canada CERIS Instituto Superior Tecnico Universidade de Lisboa Lisbon Portugal Civil Engineering Department University for Business and Technology PristinaKosovo10000 High Temperature Processes Unit IMDEA Energy Institute Av. Ramón de La Sagra 3 Móstoles Madrid28935 Spain Faculty of Engineering and Architectures Nisantasi University Istanbul Turkey Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

Diffuse horizontal irradiance (DHI) forecasts are critical for adopting solar photovoltaic technology. Yet, they can lack reliability given the limited and uncertain meteorological data available for desert areas. This research develops a new sine cosine dipper throated optimization (SCDTO) technique, targeting DHI prediction even given such data constraints. SCDTO uniquely hybridizes sine cosine metaheuristics, adept at exploration, with dipper throat optimization, providing focused exploitation. This hybridization aims to create a robust ensemble model capable of delivering reliable DHI predictions despite climatic uncertainty. The ensemble model, employing various input combinations, was rigorously evaluated across multiple meteorological stations. The SCDTO algorithm exhibited remarkable performance improvements, yielding substantial reductions exceeding 93% in root mean squared error and 98% in mean absolute error at key stations in Morocco, including Tan-Tan, Zagora, Erfoud, and Oujda. Comparative analyses against established optimization algorithms consistently underscored the superior predictive capabilities of SCDTO. Visualizations, including box plots and histograms, demonstrated SCDTO’s efficacy in minimizing prediction errors, particularly for Tan-Tan, Zagora, and Erfoud stations. Also, statistical validation through one-way analysis of variance (ANOVA) further affirmed the significance of the proposed SCDTO method. Therefore, this hybrid metaheuristic optimization enables more accurate DHI predictions from limited meteorological data. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Cell Phone Image-Based Persian Rice Detection and Classification Using Deep Learning Techniques

arXiv

引用

arXiv 2024年

作者： Kelishami, Mahmood Saeedi Kelishami, Amin Saeidi Kelishami, Sajjad Saeedi Department of Mathematics Rasht Branch Islamic Azad University Iran Department of Computer Engineering Sharif University of Technology Iran Department of Architecture Rasht Branch Islamic Azad University Iran

This study introduces an innovative approach to classifying various types of Persian rice using image-based deep learning techniques, highlighting the practical application of everyday technology in food categorization. Recognizing the diversity of Persian rice and its culinary significance, we leveraged the capabilities of convolutional neural networks (CNNs), specifically by fine-tuning a ResNet model for accurate identification of different rice varieties and employing a U-Net architecture for precise segmentation of rice grains in bulk images. This dual-methodology framework allows for both individual grain classification and comprehensive analysis of bulk rice samples, addressing two crucial aspects of rice quality assessment. Utilizing images captured with consumer-grade cell phones reflects a realistic scenario in which individuals can leverage this technology for assistance with grocery shopping and meal preparation. The dataset, comprising various rice types photographed under natural conditions without professional lighting or equipment, presents a challenging yet practical classification problem. Our findings demonstrate the feasibility of using non-professional images for food classification and the potential of deep learning models, like ResNet and U-Net, to adapt to the nuances of everyday objects and textures. This study contributes to the field by providing insights into the applicability of image-based deep learning in daily life, specifically for enhancing consumer experiences and knowledge in food selection. Furthermore, it opens avenues for extending this approach to other food categories and practical applications, emphasizing the role of accessible technology in bridging the gap between sophisticated computational methods and everyday tasks. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Use of WebAssembly in HPC

arXiv

引用

arXiv 2023年

作者： Chadha, Mohak Krueger, Nils John, Jophin Jindal, Anshul Gerndt, Michael Benedict, Shajulin Chair of Computer Architecture and Parallel Systems Technische Universität München Germany Department of Computer Science and Engg. Indian Institute of Information Technology Kerala Kottayam India

Containerization approaches based on namespaces offered by the Linux kernel have seen an increasing popularity in the HPC community both as a means to isolate applications and as a format to package and distribute them. However, their adoption and usage in HPC systems faces several challenges. These include difficulties in unprivileged running and building of scientific application container images directly on HPC resources, increasing heterogeneity of HPC architectures, and access to specialized networking libraries available only on HPC systems. These challenges of container-based HPC application development closely align with the several advantages that a new universal intermediate binary format called WebAssembly (Wasm) has to offer. These include a lightweight userspace isolation mechanism and portability across operating systems and processor architectures. In this paper, we explore the usage of Wasm as a distribution format for MPI-based HPC applications. To this end, we present MPIWasm, a novel Wasm embedder for MPI-based HPC applications that enables high-performance execution of Wasm code, has low-overhead for MPI calls, and supports high-performance networking interconnects present on HPC systems. We evaluate the performance and overhead of MPIWasm on a production HPC system and AWS Graviton2 nodes using standardized HPC benchmarks. Results from our experiments demonstrate that MPIWasm delivers competitive native application performance across all scenarios. Moreover, we observe that Wasm binaries are 139.5x smaller on average as compared to the statically-linked binaries for the different standardized benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Anomaly Localization at High-Density Crowd Using Motion Shape Image (MSI) 1st

Anomaly Localization at High-Density Crowd Using Motion Shap...

引用

1st International Conference on Artificial Intelligence for Smart Community, AISC 2020

作者： Farooq, M.U. Mohamad Saad, M.N. Daud Khan, S. Saleh, Y. Universiti Teknologi PETRONAS Tronoh Malaysia Department of Computer Science National University of Technology Islamabad Pakistan Electrical Engineering Department Faculty of Engineering and Islamic Architecture Umm Al-Qura University Makkah Saudi Arabia

ISBN: (纸本)9789811621826

Anomaly localization plays a critical role if a disaster occurs in a high-density crowd to efficiently rescue the crowd from the right location. This paper enriches anomaly localization by introducing new localization features, in addition to the ‘only’ localization feature of source/start point detection existing literature offers. New features introduced include crowd density estimation in localized regions and direction/angle of a localized region. A motion shape image (MSI) based approach is introduced for localization and features detection and experimentation is performed on benchmark and our proposed high-density crowd datasets. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Identification Using CNN

Crop Yield Identification Using CNN

引用

Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF), International Conference on

作者： G. Yogapriya R. Shalini Kumari S. Suganthi K. Agalya T. Elangovan D. Selva Pandian School of Environment Architecture and Design SRM Institute of Science and Technology Ramapuram Chennai Department of Architecture Periyar Maniammai Institute of science and Technology Thanjavuri Tamilnadu Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Department of Computer Science and Engineering Karpagam Academy of Higher Education Eachanari Coimbatore

The number of people living in the world is continuously rising, which means that there must be an increase in crop production. The estimation of agricultural yields as well as the monitoring of the growth of crops are very significant for the overall economic development of a nation. The prediction of crop production is highly difficult since it is dependent on a wide variety of factors, including the genotype of the crop, environmental factors, management strategies, and the relationships between these elements. Deep learning is gaining relevance in environmental monitoring, crop type segmentation, and crop yield estimation applications as a result of recent advancements in image classification achieved by the utilization of deep Convolutional Neural Networks. Convolutional neural networks, or CNNs, are a type of deep learning approach that has shown remarkable performance in picture classification tasks. In this study, CNNs are utilized to construct a model for crop production prediction.

关键词： Deep learning Training Neural networks Crops Production Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Divergence Behavior Detection at High Density Crowd 1st

Deep Learning Approach for Divergence Behavior Detection at ...

引用

1st International Conference on Artificial Intelligence for Smart Community, AISC 2020

作者： Farooq, M.U. Mohamad Saad, M.N. Saleh, Y. Daud Khan, S. Universiti Teknologi PETRONAS Tronoh Malaysia Electrical Engineering Department Faculty of Engineering and Islamic Architecture Umm Al-Qura University Makkah Saudi Arabia Department of Computer Science National University of Technology Islamabad Pakistan

ISBN: (纸本)9789811621826

At high-density crowd gatherings, people naturally escape from the region where any unexpected event happens. Escape in high-density crowds appears as a divergence pattern in the scene and timely detecting divergence patterns can save many human lives. In this paper, we propose to physically capture crowd normal and divergence motion patterns (or motion shapes) in form of images and train a shallow convolution neural network (CNN) on motion shape images for divergence behavior detection. Crowd motion pattern shape is obtained by extracting ridges of Lagrangian Coherent Structure (LCS) from the Finite-Time Lyapunov Exponent (FTLE) field and convert ridges into the grey-scale image. We also propose a divergence localization algorithm to pinpoint anomaly location(s). Experimentation is carried out on synthetic crowd datasets simulating normal and divergence behaviors at the high-density crowd. Comparison with state-of-the-art methods shows our method can obtain better accuracy for both divergence behavior detection and localization problems. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A review of Federated Learning in Intrusion Detection Systems for IoT

arXiv

引用

arXiv 2022年

作者： Belenguer, Aitor Navaridas, Javier Pascual, Jose A. Department of Computer Architecture and Technology University of the Basque Country UPV/EHU Spain

Intrusion detection systems are evolving into intelligent systems that perform data analysis while searching for anomalies in their environment. The development of deep learning technologies paved the way to build more complex and effective threat detection models. However, training those models may be computationally infeasible in most Internet of Things devices. Current approaches rely on powerful centralized servers that receive data from all their parties – violating basic privacy constraints and substantially affecting response times and operational costs due to the huge communication overheads. To mitigate these issues, Federated Learning emerged as a promising approach, where different agents collaboratively train a shared model, without exposing training data to others or requiring a compute-intensive centralized infrastructure. This paper focuses on the application of Federated Learning approaches in the field of Intrusion Detection. Both technologies are described in detail and current scientific progress is reviewed and categorized. Finally, the paper highlights the limitations present in recent works and presents some future directions for this technology. © 2022, CC BY-NC-SA.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Using Swarm Intelligence Algorithms for Optimization in IoT Applications 10

Using Swarm Intelligence Algorithms for Optimization in IoT ...

引用

10th IEEE Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems, ICCC 2022

作者： Roshanzamir, Mohamad Nematollahi, Mohammad Ali Darbandy, Mohammad Tayarani Roshanzamir, Mahdi Alizadehsani, Roohallah Shoeibi, Afshin Ahmadian, Davood Fasa University Faculty of Engineering Department of Computer Engineering Fasa74617-81189 Iran Fasa University Faculty of Science Department of Computer Sciences Fasa74617-81189 Iran Islamic Azad University Taft School of Architecture Taft*** Iran University of Tabriz Department of Electrical and Computer Engineering Tabriz Iran Victoria Australia K. N. Toosi University of Technology FPGA Laboratory Faculty of Electrical Engineering Tehran Iran University of Tabriz Faculty of Mathematics Statistics and Computer Sciences Tabriz Iran

ISBN: (数字)9781665481779

ISBN: (纸本)9781665481779

Internet of Things (IoT) is considered as the next industrial revolution in the years ahead. Many devices will have been connected to the Internet and more and more devices were added to them. The number of these types of devices is increased rapidly. So, management of them needs advanced technologies. Optimization of different problems in IoT is an essential subject of many researches and Swarm Intelligence algorithms (SI) are one of the most successful methods in this field. They were inspired by the collective behavior of simple creatures which communicate directly and indirectly with each other. Although they are considered as simple agents, their collective behavior is smart. They can overcome most problems in their life using collective behavior. In this research, we investigated some of the most common optimization problems in IoT and the SI algorithms which are used to solve them. © 2022 IEEE.

关键词： Internet of things

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

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

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：