检索结果-内蒙古大学图书馆

IEEE International Conference on Big Knowledge (ICBK)

作者： Qiang Chen Haining Meng Yihao Bao Mingsong Yang Xinyu Tong Qin Zhao Muhammad Bilal Khan Xinhong Hei School of Computer Science and Engineering Xi’an University of Technology Xi’an China School of Computer Science and Engineering Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an University of Technology Xi’an China School of Civil Engineering and Architecture Xi’an University of Technology Xi’an China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

Event extraction in rail transit plays a vital role in all stages of design, construction, and final acceptance. Event extraction is a key part of building event logic graph (ELG). However, the difficulty in obtaining semantic features and event local dependencies poses a challenge to accurate event extraction, which hinders the informatization and intelligent development of rail transit projects. To address these challenges, we proposes an event extraction method that fuses semantic and local dependency features. The study initially preprocesses the rail transit design codes dataset and performs sequence labeling. Then, the event trigger words are mined by combining the term frequency-inverse document frequency (TF-IDF) and minimum edit distance (MED) algorithms. Based on the semantic similarity measurement method and the trigger word mining results, the features representation of event semantic information is enhanced by using the Bidirectional Encoder Representations from Transformers (BERT) model and Bi-directional Long Short-Term Memory (BiLSTM) model. At the same time, event arguments are mined and a local dependency graph is generated based on their mining results, and then the enhanced local dependency features are obtained by using the graph convolutional network (GCN). Finally, the event semantic features and local dependency features are fused, and the conditional random field (CRF) is used to predict the labels to obtain the event extraction results. Through the comparison with five baseline methods on the datasets of rail transit design codes, it is found that the Precision, Recall, and F1 score of the proposed method are improved, with an average improvement of 9.604% on Precision, 9.342% on Recall, and 9.730% on F1 score, respectively. The contribution of the sub-modules to the overall performance is further evaluated through ablation experiments, which confirms the effectiveness and feasibility of the proposed method.

关键词： Rails Codes Semantics Bidirectional control Knowledge graphs Feature extraction Transformers Conditional random fields Logic Labeling

来源：评论

学校读者我要写书评

暂无评论

Efficiently improving the Wi-Fi-based human activity recognition, using auditory features, autoencoders, and fine-tuning

引用

Computers in Biology and Medicine 2024年 172卷 108232-108232页

作者： Rahdar, Amir Chahoushi, Mahnaz Ghorashi, Seyed Ali AIFA Dotin *** Tehran Iran Department of Computer Science & Digital Technologies School of Architecture Computing and Engineering University of East London LondonE16 2RD United Kingdom

Human activity recognition (HAR) based on Wi-Fi signals has attracted significant attention due to its convenience and the availability of infrastructures and sensors. Channel State Information (CSI) measures how Wi-Fi signals propagate through the environment. However, many scenarios and applications have insufficient training data due to constraints such as cost, time, or resources. This poses a challenge for achieving high accuracy levels with machine learning techniques. In this study, multiple deep learning models for HAR were employed to achieve acceptable accuracy levels with much less training data than other methods. A pretrained encoder trained from a Multi-Input Multi-Output Autoencoder (MIMO AE) on Mel Frequency Cepstral Coefficients (MFCC) from a small subset of data samples was used for feature extraction. Then, fine-tuning was applied by adding the encoder as a fixed layer in the classifier, which was trained on a small fraction of the remaining data. The evaluation results (K-fold cross-validation and K = 5) showed that using only 30% of the training and validation data (equivalent to 24% of the total data), the accuracy was improved by 17.7% compared to the case where the encoder was not used (with an accuracy of 79.3% for the designed classifier, and an accuracy of 90.3% for the classifier with the fixed encoder). While by considering more calculational cost, achieving higher accuracy using the pretrained encoder as a trainable layer is possible (up to 2.4% improvement), this small gap demonstrated the effectiveness and efficiency of the proposed method for HAR using Wi-Fi signals. © 2024 The Authors

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Cognitive computing Applications in Real-Time Financial Risk Management

Cognitive Computing Applications in Real-Time Financial Risk...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： Hari Prasad Josyula Sunil Rajaram Landge Piyush Ranjan Kishan D. Gajjar P. Anand Kumar Mohammad Jamal Bdair Management Sciences (BBA Information System) PSG College of Arts & Science Civil Aerodrome Post Sitra Coimbatore School of Architecture Computing and Engineering University of East London

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

The incorporation of cognitive computing into realtime financial threat operations, to highlight the revolutionary potential of this technology for the financial sector. Cognitive computing, which is a combination of artificial intelligence, machine literacy, and natural language processing, improves the capability to reuse enormous quantities of financial data quickly and directly. The purpose of this study is to investigate how cognitive systems can recognise, evaluate, and mitigate financial risks in real-time. These systems offer greater prophetic analytics and decision-making support in comparison to traditional methods. Cognitive computing makes it possible to conduct more accurate threat assessments, detect implicit dangers earlier, and improve nonsupervisory compliance. This is accomplished through the use of sophisticated algorithms and data analytics. Case studies illustrate the practical applications of these technologies through the use of colourful financial scripts, demonstrating how beneficial they are in improving threat operating methods. In the final section of the study, the author discusses the counterarguments that cognitive computing poses for the future of fiscal threat operation, as well as the implicit issues that are associated with its widespread abandonment.

关键词： Threat modeling Technological innovation Prevention and mitigation Decision making Real-time systems Natural language processing Stability analysis Regulation Cognitive systems Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Photovoltaic Panel Efficiency through a Dual-Sided Water Spray Cooling System

Enhancing Photovoltaic Panel Efficiency through a Dual-Sided...

引用

International Conference on Computer engineering, Network and Intelligent Multimedia (CENIM)

作者： Marvin S. Silva Ariel M. Lorenzo Gamaliel I. Soliven Alfredo M. Gumaru Leslie C. Soriano Christian M. Taguiam School of Architecture Computing and Engineering Department University of Saint Louis Tuguegarao City Cagayan Philippines University of Saint Louis University Research and Innovation Tuguegarao City Philippines

ISBN: (数字)9798350368802

ISBN: (纸本)9798350368819

Solar panels experience efficiency losses due to high temperatures, which can decrease power output by 0.3%-0.5% per degree above 25°C, with extreme heat causing up to 25% efficiency loss, as prolonged exposure and heat absorption negatively affect the performance of photovoltaic cells. The study investigates the effectiveness of a water spray cooling method to enhance the electrical efficiency ofphotovoltaic (PV) panels under peak solar irradiation conditions. By cooling both sides of the PV panel simultaneously, the researchers aimed to mitigate the adverse effects of high temperatures on panel performance. Experimental results demonstrated that the water-cooling method reduced the panel temperature to approximately 40. 73°C, leading to a remarkable total increase of 68.67% in electric power output and a total increase of 67.86% in electrical efficiency, equating to an effective improvement of 27.63 %. These findings indicate that the proposed cooling technique significantly enhances the operational efficiency of PV systems, making it a viable solution for improving energy output in high-temperature environments. Implementing such cooling strategies can not only optimize the performance of solar panels but also contribute to the long-term sustainability of solar energy systems, particularly in regions experiencing high solar radiation.

关键词： Radiation effects Temperature Cooling Solar energy Power systems Solar panels Solar radiation Sustainable development Solar heating System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Flexible ConvNext Block Based Multi-task Learning Framework for Liver MRI Images Analysis

Flexible ConvNext Block Based Multi-task Learning Framework ...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Sui, Dong Liu, Weifeng Guo, Maozu Li, Yang Zhang, Lei Luo, Gongning Wang, Kuanquan Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Beijing China University of Maryland Diagnostic Radiology and Nuclear Medicine BaltimoreMD United States Bio-Computing Research Center Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665468190

Liver cancer is the second leading cause of death all over the world in the 2020s', and the incidence rate has been growing on a global scale and become a serious threat to human life. Early diagnosis of liver cancer from medical images can allow the patients to receive better treatment and achieve good outcomes. Although medical imaging approaches have made significant progress over the past decades, there are still great demands to reconstruct the network structure for the adaptation to downstream tasks. It remains a great challenge for liver tumor identification from MRI images. Recently, self-attention mechanism based transformer models can capture long-range dependencies, which make them perform well on many medical image analysis tasks. Such as Segformer and TransUNet, since lacking the translation in-variance and inductive bias of CNNs, they are still needed large-scale training to fill the gap, especially in the field of medical image analysis domain. In this study, we incorporate a novel flexible Condeathblock as a feature extractor to perform liver images analysis and propose a new analytical framework CXNet to extract discriminative multi-scale visual representations. The experiments results demonstrated our framework outperforms the state-of the-art models on three datasets, including a publicly available liver segmentation dataset as well as two in-house liver tumor classification/segmentation datasets. On the 3DIRCADb dataset, our CXNet outperforms the UNet model by 2.82%, 2.73%, and 4.46% in terms of the Jaccard similarity coefficient, Dice coefficient, and accuracy, and outperforms the TransUNet model by 8.49%, 5.35%,which 3.62%, respectively. Code is available at https://***/SPECTRELWF/CXNet © 2022 IEEE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

aBLE: A Bluetooth Low Energy Hotel Asset Tracker

aBLE: A Bluetooth Low Energy Hotel Asset Tracker

引用

Aerospace Electrical engineering and Informatics (ICAAEEI), International Conference of Adisutjipto on

作者： Ariel Lorenzo Jenirose Matias Michael Angelo Abrogena Christopher Eleeson Capili Eize Jared Maramag George Benson Salvador Center for Engineering Research and Innovation Technology University of Saint Louis - Tuguegarao Tuguegarao City Cagayan Philippines School of Architecture Computing and Engineering University of Saint Louis - Tuguegarao Tuguegarao City Cagayan Philippines

ISBN: (数字)9798331507930

ISBN: (纸本)9798331507947

This study presents a Bluetooth Low Energy (BLE) Hotel Asset Tracker designed to transform asset management in hotel environments. Despite the underutilization of asset tracking solutions in the hospitality industry, this research develops a tailored, efficient system using BLE technology and beacon transmitters. The system provides real-time tracking of essential hotel room assets, such as luggage racks, blankets, remotes, and other amenities. Evaluation results show an impressive 98% accuracy rate in room identification and high user satisfaction. The mean SEQ rating, based on feedback from 23 participants, is approximately 6.26 out of 7, indicating that users found the system very easy to use, with most rating their experience as “Very Easy” or “Easy.” While feedback highlights the need for improvements, such as clearer instructions and smaller tag sizes, the system demonstrates its potential to improve operational efficiency and guest satisfaction. This research marks a significant advance in utilizing technology to address persistent challenges in the hospitality sector.

关键词： Accuracy Transmitters System performance Layout Transforms Real-time systems Asset management Reliability Bluetooth Low Energy Remote control

来源：评论

学校读者我要写书评

暂无评论

The Role of Artificial Intelligence in Asset Management of Enterprise Systems

The Role of Artificial Intelligence in Asset Management of E...

引用

2022 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2022

作者： Adebayo, Abimbola Sharif, Mhd Saeed Elmedany, Wael School of Architecture Computing and Engineering Computer Science and Dt Uel University way LondonE16 2RD United Kingdom University of Bahrain College of Information Technology Sakhir Bahrain

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

Initially, when artificial intelligence is mentioned in conjunction with the phrase 'asset management', what springs to mind is how AI is used for investment assets and financial portfolios. However, even more than the management of investment portfolios is the use of AI in asset management. Information asset management plays a key role in cyber security and AI can also aid in the efficient running of this sub-process. The aim of this paper is to highlight the various ways in which AI can help with the management of information assets and contribute to the strengthening of security postures of enterprise systems. It also proposes a method for the identification of rogue assets in an asset list using the isolation forest algorithm. Results of the research showed that in the detection of outlier assets based on chosen attributes, with an accuracy of 90%, the algorithm accurately identified assets with anomalies indicating its usefulness in identifying rogue assets in the asset management process. © 2022 IEEE.

关键词： Asset management

来源：评论

学校读者我要写书评

暂无评论

Thermal and Optical Performance of Semi-Transparent BIPV Windows in High-Rise Office Buildings: A Case Study in the UK 1st

Thermal and Optical Performance of Semi-Transparent BIPV Win...

引用

1st International Conference of Urban Climate, Sustainability, and Urban Design, UCSUD 2023

作者： Scibetta, Joseph Shi, Shaohang Du, Hu He, Bao-Jie Yang, Siliang School of Built Environment Engineering and Computing Leeds Beckett University LeedsLS2 8AG United Kingdom School of Architecture Tsinghua University Beijing100080 China School of Civil Engineering and Built Environment Liverpool John Moores University LiverpoolL3 3AF United Kingdom School of Architecture and Urban Planning Ministry of Education Chongqing University Chongqing400045 China Key Laboratory of New Technology for Construction of Cities in Mountain Area Ministry of Education Chongqing University Chongqing400045 China CMA Key Open Laboratory of Transforming Climate Resources to Economy Chongqing401147 China Mott MacDonald LeedsLS12 1BE United Kingdom

ISBN: (纸本)9789819784004

Semi-transparent building-integrated photovoltaic (BIPV) windows replace the external building glazing, allowing power to be generated as part of the existing building envelope. Due to the replacing of the BIPV windows, both thermal and optical performance of a building are worth exploring. This paper presents the results of a simulation study investigating the effects of applying BIPV windows to an existing office building within the UK, with a view to assessing the thermal performance, daylighting condition and BIPV electrical production capacity. It was considered on a typical floor of the office building, consisting of an open plan office space, two meeting rooms and a kitchen suite. A baseline scenario without BIPV window was modelled for comparison, giving recommendations to the viability of the BIPV window in terms of the overall performance. Basically, the use of the BIPV window resulted an annual cooling load reduction of 16.3% compared to the baseline. Heating loads were also reduced but only by 1.89%, while lighting energy usage was slightly increased due to a significantly worse performance in daylighting condition in the open plan office when applying the BIPV window. Specifically, daylight factor dropped over 50% in the office area, which, however, was already poor to begin with. The annual electricity generation of the BIPV window was little with only 902 kWh. This study can be a reference for future research on thermal and optical performance of high-rise office buildings using semi-transparent BIPV windows. © The Author(s) 2025.

关键词： Daylighting

来源：评论

学校读者我要写书评

暂无评论

Impurity explicit optimal Machine learning and statistical perfect construction for air quality prediction 2

Impurity explicit optimal Machine learning and statistical p...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Nareshkumar, R. Shalinikumari, R. Kowsalya, S. Sri Nandhini Vijay Anand, P. Mohamed, Ajmal Gayathri, S. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Networking and Communications Tamilnadu Kattankulathur India Bharath Institute of Higher Education and Research Selaiyur Department of Architecture Tamilnadu Chennai India Veltech Multitech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Information Technology Tamilnadu Chennai India CMR Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India Saveetha School of Engineering Department of Computer Science and Engineering Chennai India K. Ramakrishnan College of Technology Department of Computer Science and Engineering Tamilnadu Trichy India

ISBN: (纸本)9798350365269

The air quality index (AQI) is a metric used to report air quality levels. There has been a substantial rise in the level of air pollution in Indian cities. Multiple methodologies exist for formulating a mathematical equation to ascertain the air quality index. Multiple studies have established a correlation between exposure to air pollution and negative health effects in the general population. The objective of this study is to determine the optimal approach for predicting AQI in order to aid in climate regulation. Nine separate Machine learning (ML) algorithms have been employed in the suggested study to ascertain the AQI. The use of the SMOTE algorithm in the datasets in ML resulted in improved accuracy when comparing the outcomes. Furthermore, all of the implementations have been thoroughly documented using graphs and metrics, which clearly illustrate the differences in outcomes and aid in identifying the specific factors that led to the improvement in accuracy. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

High Quality Global Routing Algorithm Based on Multi-Stage Optimization

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2024年第4期36卷 607-614页

作者： Genggeng, Liu Zhenyu, Pei Ning, Xu College of Computer and Data Science Fuzhou University Fuzhou350116 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Information Engineering Wuhan University of Technology Wuhan430070 China

Global routing is a crucial step in VLSI physical design. To address the problems that the low utilization rate of capacity and easy to fall into local optimum in the existing global routing algorithms, a high-quality global routing algorithm based on multi-stage optimization is proposed. First, the virtual capacity dynamic adjustment strategy is introduced in the pre-connection stage and the routing reorganization stage to improve the utilization rate of capacity. Then, in the routing reorganization stage, the routing subarea adaptive expansion strategy is proposed to narrow the search space and improve the routing efficiency. Finally, the A* algorithm heuristic search is combined with the global search capability of the particle swarm algorithm to avoid the algorithm to choose the shortest path in the routing process, and thus avoid the algorithm to fall into the local optimum. Experimental results comparing with existing global routing algorithms on ISPD benchmark circuits show that the routing results of proposed algorithm reduce the wirelength by 6.0% to 22.8%. © 2024 Institute of computing Technology. All rights reserved.

关键词： Routing algorithms

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：