检索结果-内蒙古大学图书馆

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Design of a High Voltage Common Mode Resilient FlexRay Receiver in 180nm/5V CMOS Process 6

Design of a High Voltage Common Mode Resilient FlexRay Recei...

引用

6th Iranian International Conference on Microelectronics, IICM 2024

作者： Mansoury, Hamid Sadat Saeedi, Saeed Atarodi, Mojtaba Sharif University of Technology Dept. of Electrical Engineering Tehran Iran Tarbiat Modares University Dept. of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9798331511371

A FlexRay receiver that is capable of operating within [-60V, 60V] common mode range using a common mode cancellation method is presented in this paper. The receiver uses 5V MOSFET transistors and incorporates a digital block to reduce the required number of comparators to 2, potentially leading to lower power consumption and die area. Extensive simulations have been conducted to ensure the receiver's functionality within a temperature range of [-40°C, 150°C], which is particularly crucial for automotive applications. Furthermore, corner and mismatch simulations have been performed to ensure the circuit's process tolerance and suitability for mass production. Additionally, Electromagnetic Immunity simulations have been performed to ensure that the receiver, intended for automotive applications, meets the necessary standards. The layout of the receiver occupies an area of 153.6 × 128.7 μm2.. © 2024 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent H-Learning Based Cooperative Spectrum Sensing for Cognitive Radio Networks 32

Multi-Agent H-Learning Based Cooperative Spectrum Sensing fo...

引用

32nd International Conference on Electrical engineering, ICEE 2024

作者： Fard, E. Karimpour Nouri, M. Behroozi, H. Sobhi-Givi, S. Sharif University of Technology Dept. of Electrical Engineering Tehran Iran University of Mohaghegh Ardabili Dept. of Electrical and Computer Engineering Ardabil Iran

ISBN: (纸本)9798350376340

Fast and accurate methods for spectrum sensing (SS) are the key elements in cognitive radio networks (CRNs) that achieve high SS. This paper proposes a reinforcement learning (RL) scheme for secondary users (SUs) in a massive multiple-input multiple-output (MIMO) CRN to determine occupation and emptiness of scanned wideband channels. In the proposed H-learning method, the clustered neighboring SUs collect data to check the status of channels that improve reliability of measured sensing. Then, they share information about different frequency channels with other clusters and the status of channel occupation is determined for all SUs. This model-based learning method increases finding free channels and enhances spectral efficiency (SE) in presence of large probability of missing detection. Furthermore, each SU learns the presence pattern of primary user (PU) and gather a dynamic scan priority list to decrease scan overhead and access delays. Simulation results demonstrate the multi-agent reinforcement modified H-learning (MH-learning) method can achieve better performance in terms of PU usage percent, number of attempts, call block rate, and probability of detection in comparison to H-learning and some state-of-art learning methods. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Assessment of the seismic behavior of self-centering eccentrically braced frames with vertical link-beam

引用

STRUCTURES 2023年 48卷 1285-1305页

作者： Rofooei, Fayaz R. Soleimani, Mona Dept. of Civil Engineering Sharif University of Technology Azadi Ave. Tehran Iran

Conventional eccentric braced frames often sustain large residual deformations and significant damages after strong earthquakes which may lead to heavy damages or even destruction of the structure. This paper proposes a self-centering, Y-inverted, eccentrically braced frame (SC-YEBF) which combines the lateral load resisting benefits of YEBF including strength, stiffness and energy dissipation capacity with the re-centering capacity of posttensioned (PT) high strength steel strands used at beam-to-column connections. A design procedure is presented assuming that all the seismic input energy is dissipated through inherent damping and plastic deformations of the link-beams. Thus, in the presented design procedure, only the link-beams yield under the design earthquake and any other structural failure is prevented under the maximum considered earthquake (MCE). The feasibility of the proposed idea is checked first by cyclic loading analysis of a one-bay, one-story, SC-YEBF system using finite element models. Then, a simplified numerical approach for modeling such a system is presented. A series of nonlinear dynamic analyses are performed for a four-story steel frame equipped with SC-YEBF system under seven ground motions recorded on site classes C and D according to ASCE 7-16. The results indicate that the proposed system achieves the desired performance goals and sustains very small residual displacements. Also, the post-earthquake structural damage of main members including floor-beams, columns, and braces remains negligible.

关键词： Self-centering systems Post-tensioned cables Vertical link-beam Nonlinear analysis Residual deformation

来源：评论

学校读者我要写书评

暂无评论

Multi-objective stochastic optimization of a greenhouse energy system using an integrated demand-supply model 9

Multi-objective stochastic optimization of a greenhouse ener...

引用

9th International Conference on technology and Energy Management, ICTEM 2024

作者： Ghadertootoonchi, Alireza Solaimanian, Armaghan Khajehpour, Hossein Sharif University of technology dept. Energy Engineering Tehran Iran

ISBN: (纸本)9798350329797

With the growth in the population, the demand for food and agricultural products is increasing. Greenhouses are a promising option to meet such a growing demand as they can provide a controlled environment for the plant to grow. As a result, their performance highly depends on energy consumption. One of the main factors that affect the energy demand of a greenhouse is the weather. This study aims to investigate the effects of weather uncertainty on the planning and scheduling of a greenhouse energy system. To achieve this purpose, a two-objective (cost and temperature stability) stochastic linear model is developed and solved using historical data for the past 20 years of Tehran. The findings reveal that the deterministic approach underestimates the capital and operational costs of the system by more than 700$ during the lifetime of the greenhouse (20 years), and the underestimation rises with a growth in the importance of temperature stability. © 2024 IEEE.

关键词： Greenhouse energy demand Greenhouse energy system integrated energy model multi-objective optimization Stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Internal Short Circuit Diagnosis of Lithium-Ion Batteries Using an Equivalent Circuit Model and Machine Learning algorithms 9

Enhanced Internal Short Circuit Diagnosis of Lithium-Ion Bat...

引用

9th International Conference on technology and Energy Management, ICTEM 2024

作者： Noori, Fateme Moeini-Aghtaie, Moein Sharif University of Technology dept. Energy Engineering Tehran Iran

ISBN: (纸本)9798350329797

Diagnosing and detecting internal short circuits in lithium-ion batteries is a key issue to prevent thermal runaway failures and ensure overall safety. This study focuses on utilizing an Equivalent Circuit Model (ECM) and machine learning techniques to detect ISC faults in lithium-ion batteries. The impact of battery aging is considered by adjusting capacity and resistance values in the battery simulation. First, an ECM of a lithium-ion battery pack is developed in the MATLAB/SIMULINK platform, incorporating faulty and normal battery cells with varying aging levels. Subsequently, the output data from the simulated model is utilized as input for the Random Forest (RF) model under different operational scenarios. Classification results of the proposed model demonstrate an impressive accuracy rate of 96%. Moreover, by comparing the performance of the RF model with two other machine learning techniques, based on various matrices, a comprehensive analysis has been conducted. The RF algorithm outperformed other methods in battery fault detection, resulting in enhanced safety and reliability in energy storage systems. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Optimizing relay node placement and routing in WBANs using free search krill herd and harmony search algorithm

引用

Multimedia Tools and Applications 2025年第10期84卷 7257-7295页

作者： Patra, Sushree Chinmayee Samal, Tusharkanta Kabat, Manas Ranjan Mishra, Manas Ranjan Barik, Ram Chandra Dept. of Computer Sc. & Engineering Veer Surendra Sai University of Technology Odisha Sambalpur India Dept. of Computer Sc. & Engineering DRIEMS University Odisha Cuttack India Dept. of Computer Sc. & Engineering C.V. Raman Global University Odisha Bhubaneswar India

Wireless Body Area Network (WBAN) plays an important role in healthcare applications like in medical, non-medical and psychological sector for remote monitoring of health conditions of patients. Since the biosensors in WBAN are energy constrained in nature, the architecture of energy efficient and cost sensitive WBAN has attracted the researchers during the last decade. In this paper, a mathematical model for optimization of relay node placement in WBAN using Free Search Krill Herd (FSKH) algorithm because of its diversified phases of searching has been proposed. Furthermore, a routing protocol for energy efficient and reliable for data transmission over WBAN by using Harmony Search (HS) algorithm has been designed. The proposed algorithm has less 11.02%, 6.8% energy consumption in standing position, 5.6% and 11.02% in siting position and 12.5% and 18.75% siting on chair than its counterparts EAWD and Modified EAWD. Throughput has increased significantly by approximately 4–5 times as compare to iM-SIMPLE and *** proposed methodology has also shown greater improvement as its first node is completely exhausted after 28,545 rounds of data transmission while its existing counterpart’s iM-SIMPLE and Co-LAEEBA first node dies at 5100 rounds and 6800 rounds of transmission respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

40Hz Auditory Entrainment Promotes Synchronization Between Frontal and Parietal Regions of the Brain 31

40Hz Auditory Entrainment Promotes Synchronization Between F...

引用

31st International Conference on Electrical engineering, ICEE 2023

作者： Lahijanian, Mojtaba Aghajan, Hamid Sharif University of Technology Dept. of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350312560

Gamma oscillations are known to play a critical role in memory and cognition tasks. The quality of neural activity in this oscillatory band is impaired due to Alzheimer's disease (AD) dementia. Recently, promoting gamma oscillations through sensory stimulation has shown promising therapeutic results in reducing structural and cognitive symptoms of AD. Further analysis on the effects of sensory entrainment on the brain's oscillatory activity could help better understand the mechanisms underlying the observed improvements and optimize the stimulation protocols for achieving better outcome. In this study, we investigate the effects of 40Hz auditory brain stimulation on synchronizing frontoparietal neural activity based on electroencephalogram data recorded from a cohort of elderly participants with memory complaints. We observed that the entrained gamma band activity encompasses the entire scalp with most responsive regions in the frontal and parietal lobes. In addition, the neural activity of frontoparietal regions are synchronized due to entrainment and the quality of synchronization is correlated with the strength of entrainment. In other word, participants with highly responsive entrained sites in the frontal and parietal cortices present the most synchronized activity between these two regions. Long distance synchronization across the brain can help improve functional connectivity and improve the disrupted network-level coordination of sensory and frontal regions responsible for high-level cognitive operations. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Effect of PV roof coverage on the lighting availability, heating, and cooling demands for a Venlo greenhouse in Tehran 8

Effect of PV roof coverage on the lighting availability, hea...

引用

8th International Conference on technology and Energy Management, ICTEM 2023

作者： Solaimanian, Armaghan Roshandel, Ramin Sharif University of Technology Dept. Energy Engineering Tehran Iran

ISBN: (纸本)9781665452854

Despite of the fact that yield and water efficiency are higher than open-field cultivation in greenhouses, these structures are highly energy intensive. This is because the inside environmental parameters should be maintained in the proper range so that the plants can grow appropriately. To provide this energy sustainably, different renewable energy sources can be integrated in the greenhouse. Photovoltaic panels can be implemented in agricultural greenhouse to achieve clean vegetable production. However, due to shading effect installing the panels on the greenhouse roof affects the thermal energy demand and light availability inside the structure. This study aims to provide a simulation framework for evaluating the effect of covering the greenhouse roof with conventional solar panels on heating, cooling and natural lighting in greenhouses. The result shows that by 50% coverage of southern roof area, a 13.3% increase in yearly heating demand, a 42% decrease in yearly cooling demand, and a 29.6% natural lighting decrease are obtained. © 2023 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Control for a Building Heating System 11

Data-Driven Control for a Building Heating System

引用

11th RSI International Conference on Robotics and Mechatronics, ICRoM 2023

作者： Afsharardekani, Fatemeh Rezaeizadeh, Amin Sharif University of Technology Dept. of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350308105

One of the crucial ways to reduce the energy costs of buildings is to improve the energy efficiency of HVAC systems. Heating, Ventilation, and Air Conditioning (HVAC) systems are used to regulate the heating and cooling within a building. Controlling these systems is of great importance due to their significant energy consumption. Various control methods have demonstrated the potential for substantial savings in building operation costs. In this paper, we apply a Model Predictive Controller (MPC) to optimize control actions. MPC offers numerous opportunities to enhance energy efficiency in HVAC system operation, as it can consider constraints, predict disturbances, and balance multiple conflicting objectives, such as reducing building energy consumption while maintaining indoor thermal comfort. To implement MPC effectively, an appropriate model is required, and data-driven approaches have proven to be more practical and computationally efficient for modeling. In this study, we utilize Multiple Linear Regression (MLR) as a subset of the data-driven approach for system modeling. When compared to Rule-Based controllers (RBC), our proposed method demonstrates a significant reduction in energy consumption, with savings of up to 17%. © 2023 IEEE.

关键词： Multiple linear regression

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：