检索结果-内蒙古大学图书馆

Journal of Energy Systems 2025年第1期9卷 132-158页

作者： Elbaş, Hakan Bilgin, Turgay Tugay Bursa Technical University Graduate School Department of Intelligent Systems Engineering Bursa Turkey Bursa Technical University Faculty of Engineering and Natural Sciences Department of Computer Engineering Bursa Turkey

This review examines the methods, determinants, and forecasting horizons used in electricity demand forecasting in Türkiye. The study investigates how Türkiye's electricity demand is influenced by economic, climatic, socio-demographic, and technological factors, and explores the evolving landscape of forecasting techniques, from traditional statistical models to advanced machine learning and hybrid approaches. The research addresses three key questions: The significant determinants of electricity demand in Türkiye, the most effective forecasting methods, and the application of these insights to improve energy planning and policy development. Through a systematic analysis of peer-reviewed literature, official reports, and case studies, the study reveals the complex interplay of factors affecting electricity demand and the increasing sophistication of forecasting methodologies. Economic growth, industrial production, climate change, urbanization, and technological advancements emerge as primary drivers of demand, while artificial neural networks and hybrid models demonstrate superior forecasting capabilities. The study highlights the importance of integrated modeling approaches, sector-specific strategies, and the incorporation of climate projections in long-term planning. It also emphasizes the need for aligning energy policies with broader economic and environmental objectives. This review provides valuable insights for researchers, policymakers, and industry stakeholders, offering a comprehensive framework for understanding and improving electricity demand forecasting. © 2025 Erol Kurt. All rights reserved.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Fuzzy conceptualization of the search queries

引用

International Journal of Information Technology (Singapore) 2024年第2期16卷 957-965页

作者： Sijin, P. Champa, H.N. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India

Deciding the context of the search query based on its representation over a concept network using fuzzy methods provides a better thrust to the overall search process. The existing context based search diversification methods emphasize the importance of the numerical representation of the query over a data repository and derive a query peace which is conceptually measured. The search operation can use these semantically meaningful segments as a confident segment in the conceptual network. The proposed Fuzzy Conceptual Search Model (FCM) derives a query string which is contextually measured by means of valid segmentation, Pairwise Type Detection and concept labeling on its Concept Network. The approach measures the semantic coherence among segments in the search query and prepares a valid query piece. The Maximal Clique Cycle Count (MCCC) algorithm is used in valid segmentation process. The novel randomized MCCC algorithm improved the quality of query segmentation process and considered shared segments and conceptual ring count to improvise the efficiency of the search. The segmented query paths are processed with proper instances to pinpoint the context of the search at an earlier phase. The instance ambiguity is removed by conducting a threshold pair wise modeling of typed terms followed by a weighted voting approach called Concept labeling. The proposed FCM shows good results in terms of precision for both query and tweet data sets with varying impact lexical feature indication values. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Concept labeling Concept network Conceptual ring Maximal clique Singleton score

来源：评论

学校读者我要写书评

暂无评论

EARLY PREDICTION OF ALZHEIMER'S DISEASE USING MAGNETIC RESONANCE IMAGES (MRI) IN LEVERAGING DEEP LEARNING MODELS 2

EARLY PREDICTION OF ALZHEIMER'S DISEASE USING MAGNETIC RESON...

引用

2nd International Conference on computer Vision and Internet of Things, ICCVIoT 2024

作者： Kalpana, T. ThamilSelvan, R. Chitra, K. Rojaa, K.M. Santhiya, M. Sowmiyavarshan, A.D. Department of Computer Applications Kongu Engineering College Erode India Department of Computer Science and Engineering Kongu Engineering College Erode India

ISBN: (纸本)9781837242672

Alzheimer's disease is a well-known illness characterized by memory loss and cognitive decline. Since current treatments work best in the early stages, early detection is vital for effective management. The Magnetic Resonance Imaging (MRI) plays a key role in diagnosing Alzheimer's by providing detailed images of brain structures. Advances in deep learning have further improved MRI-based diagnosis through automated image ***2 and MobileNetV3 are lightweight convolutional neural networks (CNNs) known for their high performance and speed, making them ideal for resource-limited and real-time ***3 is a widely used CNN, known for its strong performance in image classification tasks. By training these deep learning models on complete MRI datasets, they offer the potential to aid doctors in making accurate and timely diagnoses. This approach couldlead to better outcomes and improved quality of life for *** research aims to enhance early detection and treatment methods for Alzheimer's disease, contributing to advancements in deep learning models. © The Institution of engineering & Technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Protein data in the identification and stage prediction of bronchopulmonary dysplasia on preterm infants: a machine learning study

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 387-392页

作者： Jeyananthan, Pratheeba Bandara, K.M.D.D. Nayanajith, Y.G.A. Department of Computer Engineering Faculty of Engineering University of Jaffna Jaffna Sri Lanka

Bronchopulmonary Dysplasia (BPD) is a chronic lung disease mostly affecting the premature newborns who are in the need for oxygen therapy. Main reason for this disease is underdeveloped lungs which need the help of ventilator to expand and breath. This is a very serious disease without a specific test for diagnosis. As treatment is very important for this disease in order to improve the lung function of the baby, on time diagnosis is crucial. Hence, this study checks the potential of protein data in the diagnosis of BPD, and also in the prediction of BPD stage. Mutual information is used in the selection of relevant features of each study. Selected set of features are used with different machine learning algorithms and the accuracies among the models are compared. By this comparison, this study reveals the best number of features in each of the prediction along with the best machine learning algorithm. The highest accuracy value obtained in the diagnosis model shows that it can be used in practice to improve the diagnosis accuracy. However, it seems that prediction of the disease stage is a far complex problem which needs further improvement in its accuracy. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Bronchopulmonary dysplasia (BPD) Feature selection GO analysis Machine learning models Performance comparison Protein data

来源：评论

学校读者我要写书评

暂无评论

An improved method for classifying depth-based human actions using self-adaptive evolutionary technique

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 157-173页

作者： Pareek, Preksha Thakkar, Ankit Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India

Automatic Human Action Recognition (HAR) using RGB-D (Red, Green, Blue, and Depth) videos captivated a lot of attention in the pattern classification field due to low-cost depth cameras. Feature extraction in action recognition is an important aspect. As compared to Depth Motion Maps (DMM), Depth Motion Maps–Local Binary Pattern (DMM–LBP) provides compact representation of features. After extracting features using DMM–LBP, Principal Component Analysis (PCA) is used for dimensionality reduction. For classification task, randomly generated input weights of Extreme Learning Machine (ELM) can lead to non-optimal results. Therefore, in this paper, we have used an improved learning algorithm named Self-adaptive Differential Evolution (SaDE) ELM for action classification. In the proposed approach, DMM–LBP is used for feature extraction and SaDE–ELM is used for action classification. To evaluate strength of the proposed approach, experiments are performed on four public datasets, namely, MSRAction3D, MSRDaily Activity3D, UTD–MHAD, and MSRGesture3D. The proposed approach gives better accuracy compared to existing approaches Kernel ELM (KELM), l2-Collaborative Representation Classifier (l2-CRC), and Probabilistic CRC (ProCRC) methods. We have also presented statistical significance of results in the paper. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Rice spikelet’s disease detection using hybrid optimization model and optimized CNN

引用

Soft Computing 2024年第21期28卷 12787-12806页

作者： Patel, Bharati Department of Computer Science and Engineering Faculty of Science and Technology ICFAI University Raipur India

Rice fields all across the world are affected by spikelet sterility, often known as rice spikelet's disease. It is characterized by the improper development of spikelet’s, which lowers grain output and quality. For optimal management and the avoidance of yield losses, this disease must be discovered early. In this study, a deep learning-based approach utilizing optimization techniques was proposed for accurate segmentation and disease detection in rice crops. The research aimed to address the vulnerability of rice crops to disease attacks from seed germination to mature spikelets. The proposed model consisted of three major phases: pre-processing, segmentation, feature extraction and disease detection. Gaussian filtering was employed to preprocess the raw rice crop images, while a new hybrid Whale Customized Gravitational Optimization Algorithm was utilized for segmentation. Disease detection was performed using a hybrid deep learning model called HybridNet, which combines convolutional neural networks (CNN) with an optimized recurrent neural network (RNN) model. The dataset intended for this proposed project is sourced from the CABI PlantwisePlus Knowledge Bank. The proposed model for rice spikelet disease detection achieved high accuracy with Sensitivity (0.9269), Specificity (0.9756), and Accuracy (0.9634). This indicates that the model effectively identifies and detects diseases in rice spikelets, demonstrating its reliable performance in disease management and crop protection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

HeRo: Heuristic-Based Routing in Payment Channel Networks

IEEE Networking Letters

引用

IEEE Networking Letters 2025年第1期7卷 56-60页

作者： Mishra, Shruti Aggarwal, Virat Pal, Sujata Agarwal, Vidushi Indian Institute of Technology Ropar Department of Computer Science and Engineering Rupnagar140001 India

Payment channels support off-chain transactions by enhancing transaction speed and reducing fees in the main blockchain. However, the costs and complexity of the network increase as we increase the size of the network. To address these challenges, we propose Heuristic-Based Routing with Scheduling (HeRo) combining heuristic-based routing and scheduling techniques in Payment Channel Networks (PCNs). HeRo achieves a cost reduction of 32.71% and 73.08% compared with multi-charge PCN (MPCN-RP) and Dijkstra algorithms, respectively. © 2019 IEEE.

关键词： Network routing

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-Commerce Text Classification: A GRU-Based Approach for Improved Product Understanding 5th

Enhancing E-Commerce Text Classification: A GRU-Based Approa...

引用

5th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Nazmul Abdal, Md. Shaown, Shahanaz Islam Islam, Khairum Aman, Rutba Department of Computer Science and Engineering University of Liberal Arts Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Uttara University Dhaka Bangladesh Department of Computer Science and Engineering University of Dhaka Dhaka Bangladesh

ISBN: (纸本)9789819791118

In the burgeoning landscape of e-commerce, the ability to accurately classify product texts is paramount for enhancing user experience and driving business success. Traditional approaches to text classification often struggle with the nuances and complexities inherent in e-commerce product descriptions. In this paper, we propose a novel approach utilizing Gated Recurrent Unit (GRU) to address these challenges and improve product understanding in e-commerce text classification tasks. Our model leverages the inherent sequential nature of product descriptions, effectively capturing long-range dependencies and semantic relationships within the text. We use a standard dataset in extended trials to demonstrate the superiority of our GRU-based approach over conventional methods in terms of classification accuracy and robustness across diverse product categories. Furthermore, we conduct comprehensive analyses to gain insights into the inner workings of our model and its ability to learn meaningful representations of e-commerce text data. The performance of the model is compared using several cutting-edge techniques, including Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM) in order to show that our model is superior at correctly classifying e-commerce texts. The experimental findings show that the suggested model performs competitively in classifying e-commerce texts, surpassing other approaches with an accuracy of 98.35%. Our findings underscore the potential of GRU-based approaches for advancing the state-of-the-art in e-commerce text classification, offering promising avenues for future research and practical applications in the domain. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Minimizing model size of CNN-based Vehicle Make Recognition for Frontal Vehicle Images

引用

IEEE Access 2025年 13卷 97409-97420页

作者： Puisamlee, Wiput Chawuthai, Rathachai King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Electrical Engineering Bangkok Thailand King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Computer Engineering Bangkok Thailand

Vehicle Make Model Recognition (VMMR) is generally considered in any Intelligent Transport Systems (ITS), free flow image-based toll systems, and enforcement systems. These systems need to analyze and process any images of the front of vehicles as evidence of use. Currently, Convolutional Neural Networks (CNN) are well-known techniques for image classification research and they applied to solve problems in the VMMR domain. Increasing the accuracy of classification with a large number of classes requires more complex model structures and a greater number of internal parameters. It resulted in the issues larger models and potentially longer processing times. This work aims to study and develop a smaller CNN model that is suitable for devices with limited resources, such as embedded computers and embedded computer cameras, for recognizing vehicle makes from frontal images. The experimental datasets were collected from actual free-flow toll systems, and a CNN model was developed that achieved 99% accuracy in recognizing vehicle makes. The developed model is smaller than state-of-the-art CNN models tested (VGG16, InceptionV3, Yolo11m-cls, and ResNet50) and achieves over 90% accuracy. It was able to develop the CTv1 model to achieve an F1 score approximately 2.06% higher than the best one, which is InceptionV3, while reducing the number of parameters by 69.95%. The model was tested on a Raspberry Pi 3 Model B, where it processed images at the average speed of 1 second per image and a power consumption of 25 milliwatts-hour (mWh). Our study also reduces the CNN model size using Depth-wise Separable Convolutional and 1x1 Convolutional Dimension Reduction (Bottleneck) methods, as well as adjusting the Padding and Stride of the Convolutional Layer to test the accuracy, training time, processing time, and model size for vehicle make recognition. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploration, Collaboration, and Applications in Multi-Agent Reinforcement Learning

引用

Performance Evaluation Review 2025年第3期52卷 31-34页

作者： Chen, Jingdi Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States

In recent years, the field of humancentric decision-making has emerged as a critical area of research, driven by its potential to fundamentally reshape how decisions are made across a variety of complex systems. Human-centric decision-making is characterized by considerable variability, which can be both advantageous and problematic. Variability is beneficial in contexts like brainstorming or problem-solving, where diverse perspectives lead to innovation. However, in situations where consistency is crucial- such as public health, safety, and fairness-this variability can have negative consequences. For instance, when radiologists interpret the same mammogram differently, it can result in unnecessary medical procedures. Similarly, in military operations, inconsistent judgments by sonar technicians regarding potential threats can jeopardize both crew safety and mission success. This highlights the critical need for a deeper understanding of decisions where the stakes are high. Thus, it is important to deepen our understanding of the decision-making process in completed and dynamic scenarios that involve multiple decisionmakers. This should guide the creation of validated methods to identify, measure, model, and adjust variability in judgments to improve decision-making in multi-agent environments. © 2025 Copyright is held by the owner/author(s).

关键词： Reinforcement learning

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：