检索结果-内蒙古大学图书馆

31st International Conference on Multimedia Modeling, MMM 2025

作者： Stroh, Michael Kloda, Vojtěch Verner, Benjamin Vopálková, Zuzana Buchmüller, Raphael Jäckl, Bastian Hajko, Jakub Lokoč, Jakub Visual Computing Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany SIRET Research Group Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic Data Analysis and Visualization Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany

ISBN: (纸本)9789819620739

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Human Evolutionary Optimization Algorithm for Optimal IoT Task Placement in Hybrid Cloud-Fog Networks

Human Evolutionary Optimization Algorithm for Optimal IoT Ta...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Baskar, R. Mohanraj, E. Jaisurya, K. Janani, S. Kesavan, M. K. S. Rangasamy College of Technology Department of Computer Science and Engineering Tiruchengode637 215 India K. S. Rangasamy College of Technology Department of Artificial Intelligence and Data Science Tiruchengode637 215 India K. S. Rangasamy College of Technology Computer Science and Engineering Tiruchengode637 215 India

ISBN: (纸本)9798331529833

The growing prevalence of Internet of Things (IoT) devices necessitates the strategic allocation of computational activities inside cloud-fog networks to achieve low latency, diminished energy consumption, and optimal resource utilisation. This study introduces a new Human Evolutionary Optimisation Algorithm (HEOA) designed for optimising IoT job placement inside hybrid cloud-fog environments. The suggested method emulates human decision-making to provide adaptive and intelligent job allocation, optimising computational load distribution between centralised cloud data centres and decentralised fog nodes. HEOA employs evolutionary processes, including selection, mutation, and crossover, to dynamically identify the ideal configuration for job offloading, therefore reducing response time and energy expenditures. Simulation studies indicate that HEOA surpasses conventional optimisation methods by attaining quicker convergence, enhanced resource efficiency, and superior scalability. The HEOA diminished energy usage by 12% and cut response time by 15%, rendering it highly compatible with contemporary IoT applications. This study enhances job scheduling frameworks in diverse cloud-fog settings, facilitating improved performance and sustainability in IoT ecosystems. © 2025 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning Approach for An Analysis of Real-estate Prices and Transactions

引用

IEEE Access 2025年 13卷 89248-89265页

作者： Yang, Cheng-Hong Lee, Borcy Lin, Yu-Da Tainan University of Technology Department of Information Management Tainan Taiwan National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung Taiwan Kaohsiung Medical University Ph.D. Program in Biomedical Engineering Kaohsiung Taiwan Kaohsiung Medical University School of Dentistry Kaohsiung Taiwan Kaohsiung Medical University Drug Development and Value Creation Research Center Kaohsiung Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

Research on the study of houses, condominiums and buildings in Taiwan’s metropolitan areas continues to be an important area of research. In real estate forecasting and analysis, methods such as statistical analysis and questionnaire data collection are widely used. However, when multidimensional data is considered, these methods are time-consuming and inadequate. This study aimed to build a real estate forecasting model that can adapt to a changing environment. data were collected from public government databases, the collected data were standardized for accurate clustering, an appropriate data clustering algorithm was applied to the standardized data, and cross-statistical analysis was performed to verify the adopted algorithm. We used a deep learning based on autoencoder algorithm to increase the accuracy of the clustering analysis. A double-bottom map particle swarm optimization (DBM-PSO) clustering algorithm was then used to determine the optimal clustering solution. Cluster analysis and deep learning were conducted on data collected from public websites to understand the factors that led to the sustained increase in housing prices in Taiwan over the past decade. The results of this study indicate that three key factors—the number of real estate transactions, the average unit price of real estate transactions, and the building material and construction index—significantly affected real estate prices in Taiwan. Our results could help researchers and governments to focus on specific aspects of real estate development without being influenced by other related factors. In addition, the relationships between real estate trends and the aforementioned three key factors were determined to obtain valuable information that can enable the Taiwanese government to regulate the property market and prevent excessive growth. The framework proposed in this paper allows researchers and governments to focus on specific aspects of real estate development without being influenced b

关键词： Houses

来源：评论

学校读者我要写书评

暂无评论

HPG-Tree: An Enhanced B+-Tree for Spatial Indexing

引用

IEEE Access 2025年 13卷 91312-91324页

作者： Amal Saif Alaa M. Altarazi Amer Al-Badarneh Mohammad J. Abdel-Rahman Computer Science Department Princess Sumaya University for Technology Amman Jordan Data Science Department Princess Sumaya University for Technology Amman Jordan

In modern applications such as geographic information systems, game development, and image processing, the demand for efficient two-dimensional spatial indexing is rising exponentially. Traditional approaches like R-tree can suffer from excessive overlap and fragmentation, while standard $B^{+}$ -trees are limited to one-dimensional data. Motivated by these gaps, we propose the hyperbolic paraboloid grid (HPG) tree, an enhanced $B^{+}$ -tree structure specifically tailored for two-dimensional datasets. First, we employ a grid-based strategy that maps two-dimensional points into one-dimensional values without resorting to hashing. By combining grid partitioning with the $B^{+}$ -tree’s efficient, self-balancing properties, the HPG-tree simultaneously addresses overlap, storage utilization, and query performance. Unlike purely one-dimensional indexes, this method preserves spatial locality and avoids excessive rebalancing. Further, the HPG-tree integrates a hyperbolic paraboloid-like framework in its node layout, allowing it to halve the number of index nodes in many cases. This optimization is key to reducing disk or memory scans, thereby accelerating point lookups, range queries, and updates. Our experiments demonstrate that the HPG-tree outperforms comparable state-of-the-art structures like $R^{*}$ -tree, achieving up to a 50% improvement in storage utilization and significant gains in query throughput. HPG-tree opens a promising avenue for modern spatial databases that require both high scalability and sub-second response, making it a robust and flexible option for today’s evolving data-intensive environments. These advantages make HPG-tree particularly well-suited to large-scale spatial databases requiring both high scalability and sub-second responsiveness. Following a detailed discussion of the shortcomings in existing methods, the paper presents the HPG-tree methodology, including its grid partitioning, node layout, and insertion procedures, illustrating why

关键词： Indexing Spatial databases Spatial indexes Memory management Standards Nearest neighbor methods Vegetation Taxonomy Partitioning algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for Precise Chronic Bronchitis Identification in X-Ray Modalities

引用

computers, Materials & Continua 2025年第4期83卷 381-405页

作者： Fahad Ahmad Saad Awadh Alanazi Kashaf Junaid Maryam Shabbir Asim Ali School of Computing Faculty of TechnologyUniversity of PortsmouthWinston Churchill Ave SouthseaPortsmouthPO12UPUK Portsmouth Artificial Intelligence and Data Science Center University of PortsmouthWinston Churchill AveSouthseaPortsmouthPO12UPUK Department of Computer Science College of Computer and Information SciencesJouf UniversitySakakaAljouf72341Saudi Arabia School of Biological and Behavioural Sciences Queen Mary University of LondonLondonE14NSUK Department of Computer Sciences Bahria UniversityLahorePunjab54700Pakistan

Image processing plays a vital role in various fields such as autonomous systems,healthcare,and cataloging,especially when integrated with deep learning(DL).It is crucial in medical diagnostics,including the early detection of diseases like chronic obstructive pulmonary disease(COPD),which claimed 3.2 million lives in ***,a life-threatening condition often caused by prolonged exposure to lung irritants and smoking,progresses through *** diagnosis through image processing can significantly improve survival *** encompasses chronic bronchitis(CB)and emphysema;CB particularly increases in smokers and generally affects individuals between 50 and 70 years *** damages the lungs’air sacs,reducing oxygen transport and causing symptoms like coughing and shortness of *** such as beta-agonists and inhaled steroids are used to manage symptoms and prolong lung ***,COVID-19 poses an additional risk to individuals with CB due to its impact on the respiratory *** proposed system utilizes convolutional neural networks(CNN)to diagnose *** this system,CNN extracts essential and significant features from X-ray modalities,which are then fed into the neural *** network undergoes training to recognize patterns and make accurate predictions based on the learned *** leveraging DL techniques,the system aims to enhance the precision and reliability of CB *** research specifically focuses on a subset of 189 lung disease images,carefully selected for model *** further refine the training process,various data augmentation and noise removal techniques are *** techniques significantly enhance the quality of the training data,improving the model’s robustness and *** a result,the diagnostic accuracy has improved from 98.6%to 99.2%.This advancement not only validates the efficacy of our proposed model but also represents a significant improvement over existing *** h

关键词： Deep learning chronic obstructive pulmonary disease chronic bronchitis convolutional neural network X-ray images

来源：评论

学校读者我要写书评

暂无评论

ENERGY-EFFICIENT ANT ROUTING ALGORITHM FOR OPTIMIZED PATH SELECTION NETWORK LONGEVITY IN WIRELESS SENSOR NETWORKS

引用

Telecommunications and Radio Engineering (English translation of Elektrosvyaz and Radiotekhnika) 2025年第2期84卷 21-42页

作者： Zelani, Shaik Khader Babu, D. Nagabhushana Surendra, Doddaga Rahman, Mohammad Zia Ur Department of Electronics and Communication Engineering Sri Vasavi Institute of Engineering and Technology-Autonomous Pedana India Department of Data Science Malla Reddy University Telangana Hyderabad India Department of Computer Science and Applications Koneru Lakshmaiah Education Foundation K L Deemed to be University Vaddeswaram Andhra Pradesh India Department of Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation K L Deemed to be University Vaddeswaram Andhra Pradesh India

The exponential growth of wireless sensor networks (WSNs) in various applications underscores the critical need for energy-efficient routing protocols to extend network lifespan. This paper introduces the Energy-Efficient Ant Routing Algorithm, a novel bioinspired routing strategy derived from ant colony optimization (ACO), which integrates traditional pheromone mechanisms with dynamic energy-aware adaptations to prioritize routes through nodes with higher residual energy levels, thereby balancing load and prolonging network functionality. The model’s adaptive pheromone updating mechanism, which considers both the cumulative path energy cost and the minimum residual energy of nodes along the path, encourages the use of energy-efficient routes and mitigates rapid energy depletion in critical network areas. This approach not only extends operational network lifetime but also supports higher data reliability and throughput in challenging WSN scenarios. The results of the proposed model demonstrated significant improvements over traditional ACO and other common energy-aware routing protocols. The network lifespan is extended by ~ 25% compared to standard ACO and by 15% compared to the best-performing conventional energy-aware routing protocol under the same conditions. Furthermore, EEARA achieved a 20% reduction in average energy consumption per node and enhanced the data delivery ratio by 10% due to more stable routing paths. The results underline the model’s potential as a scalable, efficient routing solution for energy-limited networks, promising substantial improvements in sustainable network operations. © 2025 by Begell House, Inc.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

FedNorm: Optimised Federated Learning Strategy Using Hybrid Regularisation Norm 12th

FedNorm: Optimised Federated Learning Strategy Using Hybrid ...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： John, Binu Menon, Varun Adhikari, Mainak Department of Computer Science and Engineering SCMS School of Engineering and Technology Kerala Ernakulam683576 India APJ Abdul Kalam Technological University Kerala Thiruvananthapuram695016 India School of Data Science Indian Institute of Science Education and Research Vithura Kerala Thiruvananthapuram695551 India

ISBN: (纸本)9783031818202

Federated Learning (FL) has emerged as a game-changing method for training machine learning (ML) models on decentralized data sources without centralizing the data itself. Conventional FL algorithms frequently exhibit performance instability and inefficiency, especially when working with non-Independent and Identically Distributed (non-IID) data distributions. To overcome these difficulties, we present FedNorm, a new FL method that uses hybrid regularisation approach to improve model stability and accuracy by balancing sparsity and smoothness, to increase generalization across varied data distributions. Our experimental setup uses the MNIST dataset to train models in both Independent and Identically Distributed (IID) and non-IID situations. The findings show that FedNorm routinely outperforms classic algorithms like FedAvg, FedSGD, FedNova and FedSAM, with minimal test loss and high accuracy. FedNorm has an exceptional accuracy rating of 0.98 on both IID and non-IID data. FedNorm addresses the constraints of conventional FL algorithms, resulting in a strong and dependable solution for FL in diverse situations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Rule-Based Dialect of Tulang Bawang Stemmer

Rule-Based Dialect of Tulang Bawang Stemmer

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Abidin, Zaenal Junaidi, Akmal Wamiliana Lumbanraja, Favorisen Rosyking Kurniasari, Dian Borman, Rohmat Indra Doctoral Program of Mathematics and Natural Sciences Universitas Lampung Bandar Lampung Indonesia Universitas Lampung Department of Computer Science Bandar Lampung Indonesia Universitas Lampung Department of Mathematics Bandar Lampung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandar Lampung Indonesia

ISBN: (纸本)9798331513320

Stemming, an essential procedure in natural language processing (NLP), diminishes words to their base forms, facilitating tasks such as information retrieval and sentiment analysis. Although stemming techniques for highresource languages are well-developed, numerous low-resource languages, including dialect of Tulang Bawang, suffer from inadequate solutions owing to a scarcity of linguistic data and resources. Existing systems, including rule-based stemmers, have demonstrated efficacy in processing low-resource languages such as Indonesian and Javanese by utilizing established morphological rules. Nonetheless, these methods encounter considerable obstacles, such as restricted adaptability, inability to accommodate unusual root structures, and excessive dependence on fixed rules that might result in over- or understemming. Rule-based methodologies frequently misidentify roots when faced with intricate affixes or unconventional word forms. We introduce an improved rule-based Tulang Bawang Stemmer aimed at overcoming these constraints by enhancing current linguistic rules and integrating new patterns specific to the language's morphology. Assessed on 500 test samples and 200 independent test samples, our improved stemmer attained gold standard evaluation metrics of 96.2% and 94%, respectively, surpassing prior implementations in both precision and generalization. The findings demonstrate the potential of enhanced rule-based techniques to improving NLP for lowresource languages. Improved stemming performance enables better downstream applications, promotes more efficient text analysis, and advances research in underrepresented languages. © 2025 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Piccolo: Large-Scale Graph Processing with Fine-Grained in-Memory Scatter-Gather 31

Piccolo: Large-Scale Graph Processing with Fine-Grained in-M...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Shin, Changmin Song, Jaeyong Jang, Hongsun Kim, Dogeun Sung, Jun Kwon, Taehee Ju, Jae Hyung Liu, Frank Choi, Yeonkyu Lee, Jinho Seoul National University Department of Electrical and Computer Engineering Korea Republic of Old Dominion Univeristy School of Data Science United States Samsung Electronics Korea Republic of

ISBN: (纸本)9798331506476

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound application. Because of this, existing graph processing accelerators typically employ a graph tiling-based or processing-in-memory (PIM) approach to relieve the memory bottleneck. In the tiling-based approach, a graph is split into chunks that fit within the on-chip cache to maximize data reuse. In the PIM approach, arithmetic units are placed within memory to perform operations such as reduction or atomic addition. However, both approaches have several limitations, especially when implemented on current memory standards (i.e., DDR). Because the access granularity provided by DDR is much larger than that of the graph vertex property data, much of the bandwidth and cache capacity are wasted. PIM is meant to alleviate such issues, but it is difficult to use in conjunction with the tiling-based approach, resulting in a significant disadvantage. Furthermore, placing arithmetic units inside a memory chip is expensive, thereby supporting multiple types of operation is thought to be impractical. To address the above limitations, we present Piccolo, an end-to-end efficient graph processing accelerator with fine-grained in-memory random scatter-gather. Instead of placing expensive arithmetic units in off-chip memory, Piccolo focuses on reducing the off-chip traffic with non-arithmetic function-in-memory of random scatter-gather. To fully benefit from in-memory scatter-gather, Piccolo redesigns the cache and miss-handling architecture (MHA) of the accelerator such that it can enjoy both the advantage of tiling and in-memory operations. Piccolo achieves a maximum speedup of 3.28 × and a geometric mean speedup of 1.62 ×, along with up to 59.7% reduction in energy consumption across various and extensive benchmarks. © 2025 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Scaling Rich Style-Prompted Text-to-Speech datasets

arXiv

引用

arXiv 2025年

作者： Diwan, Anuj Zheng, Zhisheng Harwath, David Choi, Eunsol Department of Computer Science The University of Texas Austin United States Department of Computer Science and Data Science New York University United States

We introduce Paralinguistic Speech Captions (ParaSpeechCaps), a large-scale dataset that annotates speech utterances with rich style captions. While rich abstract tags (e.g. guttural, nasal, pained) have been explored in small-scale human-annotated datasets, existing large-scale datasets only cover basic tags (e.g. low-pitched, slow, loud). We combine off-the-shelf text and speech embedders, classifiers and an audio language model to automatically scale rich tag annotations for the first time. ParaSpeechCaps covers a total of 59 style tags, including both speaker-level intrinsic tags and utterance-level situational tags. It consists of 342 hours of human-labelled data (PSC-Base) and 2427 hours of automatically annotated data (PSC-Scaled). We finetune Parler-TTS, an open-source style-prompted TTS model, on ParaSpeechCaps, and achieve improved style consistency (+7.9% Consistency MOS) and speech quality (+15.5% Naturalness MOS) over the best performing baseline that combines existing rich style tag datasets. We ablate several of our dataset design choices to lay the foundation for future work in this space. Our dataset, models and code are released at https://***/ajd12342/paraspeechcaps. Copyright © 2025, The Authors. All rights reserved.

关键词： Open systems

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：