检索结果-内蒙古大学图书馆

3rd International conference on Language processing and Knowledge Management, LPKM 2024

作者： Chamekh, Ameni Mahfoudh, Mariem Boukadi, Khouloud MIRACL Laboratory Sfax Tunisia Faculty of Economics and Management of Sfax Sfax Tunisia Higher Institute of Computer Science and Multimedia of Sfax Sakiet Ezzit Tunisia

ISBN: (纸本)9783031850660

This paper focuses on creating a dataset in an agricultural domain to understand and analyze sentiments related to pesticides, pests and crop disease. Collecting data allows us to gain insights into the opinions, attitudes, and experiences of farmers, agricultural experts, and consumers. Therefore, we collected data from social media and online platforms based on a list of keywords extracted from the AGROVOC multilingual controlled thesaurus. We have obtained two datasets: the first comprises 1617 tweets regarding pests and crop diseases from Twitter, while the second consists of 10 181 reviews on pesticide products from Amazon. Aspect extraction has been employed, identifying and extracting specific features or aspects discussed in reviews or tweets. This process enables a more granular and detailed data analysis by allowing us to go deeper into the data and understand the sentiment associated with each aspect rather than the overall sentiment. We identified eight aspects within the Amazon dataset, including "price", "package", "toxicity", etc. Similarly, we extracted relevant aspects from our Twitter dataset, resulting in five aspects such as: "pests", "safety", "toxicity", etc. Then, the data will be pre-annotated in collaboration with agricultural domain experts from INAT. This data will be used for future analyses and will inform the purchasing decisions of various decision-makers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

5th International conference on Computing and Network Communications, CoCoNet 2023

5th International Conference on Computing and Network Commun...

引用

5th International conference on Computing and Network Communications, CoCoNet 2023

ISBN: (纸本)9789819747108

The proceedings contain 44 papers. The special focus in this conference is on Computing and Network Communications. The topics include: Maximizing Efficiency: Unveiling the Potential of Kubernetes Metrics;resource-Aware Learning Automata for Low-Latency Task Scheduling in Fog Computing;Design of High Gain Wideband Petal-Shaped Magneto-Electric Dipole Metal Antenna for 5G Sub-6 GHz and Wi-Fi Applications;A Novel Billhook-Shaped 2-Element MIMO Array for Sub-6 GHz Millimeter Wave Application;energy-Efficient Transmission in Wireless Sensor Network Using Compressive Sensing;smart City Solutions for Traffic Management;an IoT-Assisted Real-Time Urban Air Pollution data Collection System;real-Time Stock Price Prediction Using Apache Kafka;RSS-Based Localization Using GRU and BiGRU Deep Learning Models in LoRaWAN-IoT Networks;locating and Routing for IoT-Based Fire Evacuation System;an Energy-Efficient data Management Approach Using Sparse Compression in Future-Ready IoT Networks;a Framework for Developing IoT and Edge Computing-Based Smart Transportation Applications;a Mathematical Model for data Traffic Management in Next-Generation IoT Networks;crowdsourced Mobile Applications for Disaster Relief: A Case Study of Landslide Tracker and Amrita Kripa App Deployments in Sikkim Schools;design and modeling of Modular Wheelchair for Therapeutic Exercises;analyzing data Traffic in IoT Networks: A Novel Graph-Based Architecture;A Lightweight Privacy-Preserving and Authentication Model (LiPAM-FSG) for Fog-Based Smart Grids;time Series analysis and Rule Mining for Detecting Industrial control System data Injection Attacks;Radius-Based Authentication: UFrames’ Novel Approach to Prevent Account Sharing;deep Neural Network-Based Secure Energy-Efficient Power Allocation in an Interference Network;An Adaptive Time Quantum-Based Efficient Round-Robin Algorithm for CPU Scheduling;low-Cost Advanced Undetectable Hardware-Based Malicious Keyboard;constructing a Blind Digital Signature Scheme

关键词：

来源：评论

学校读者我要写书评

暂无评论

Role of Artificial Intelligence in Facilitating Open Innovation in VAT Management 5th

Role of Artificial Intelligence in Facilitating Open Innovat...

引用

5th 5th Olympus - International conference on Supply Chain

作者： Yordanova, Zornitsa Univ Natl & World Econ Sofia Bulgaria

ISBN: (纸本)9783031693434;9783031693441

In the dynamic landscape of fiscal policy and tax administration, the integration of Artificial Intelligence (AI) within Value-Added Tax (VAT) management systems offers transformative opportunities to enhance efficiency, compliance, and transparency. Amidst a complex global economic environment characterized by intricate transactions and international trade, there is a critical need for innovative approaches to VAT collection and compliance. This study embarks on an exploratory analysis of AI's role in revolutionizing VAT management practices through the prism of open innovation-a paradigm that advocates leveraging external knowledge and technological advancements to drive internal innovation. Utilizing a qualitative research methodology, inclusive of a literature review and case studies, this paper examines the current and potential impacts of AI on VAT management practices. It delves into the application of AI in automating the processing of tax regulations, facilitating data modeling, and enhancing decision-making processes within VAT systems. Furthermore, this research evaluates the contributions of open innovation strategies, such as collaboration with external partners and engagement with user communities, to the development and continuous improvement of AI-enhanced VAT management tools. Drawing insights from interviews with development teams and tax professionals, alongside an examination of documentary evidence, this study presents a novel framework for understanding and advancing AI applications in VAT administration. It highlights the synergistic effects of AI and open innovation in creating more resilient, efficient, and transparent VAT systems. The results show that AI technologies and open innovation practices have a lot of potential to bring VAT management up to date, as long as problems like data privacy, engaging stakeholders, and the fact that tax laws are always changing are properly dealt with. This research contributes to the burgeoning discourse

关键词： Artificial Intelligence Open Innovation Value-added tax Digital Transformation process automation ERP data Analytics Business Intelligence

来源：评论

学校读者我要写书评

暂无评论

5th International conference on Computing and Network Communications, CoCoNet 2023

5th International Conference on Computing and Network Commun...

引用

5th International conference on Computing and Network Communications, CoCoNet 2023

ISBN: (纸本)9789819745395

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-Criteria Decision Making Based on Greedy Algorithm and Genetic Algorithm

Research on Multi-Criteria Decision Making Based on Greedy A...

引用

Electronics, Energy Systems and Power Engineering (EESPE), IEEE International conference on

作者： Zhengrong Deng Yilin Wu Wenjuan Jiang Jiao Huang Xiangtan University Xiangtan China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

The purpose of this paper is to explore how to construct a multi-criteria decision-making model using greedy algorithm and genetic algorithm to optimize the decision-making problem in the production process of enterprises. For the assembly process of parts in actual production, this paper proposes an optimization strategy based on multi-criteria decision-making, which combines the greedy algorithm and genetic algorithm to solve the decision-making problem at each stage. First, for the problem of multi-process production process, the complex multi-process problem is transformed into multiple single-process sub-problems for step-by-step solution. Then, in each stage, the maximum profit value of each process is calculated by greedy algorithm and the optimal solution is obtained by loop iteration. In addition, the results of the greedy algorithm are further optimized by combining the genetic algorithm, and the consistency and feasibility of the two algorithms in the decision-making results are verified. Finally, the paper optimizes the decision-making model and proposes the optimal strategy through multiple simulations and normality tests [1], which further improves the overall efficiency of the production system. The mathematical problem of multi-process quality inspection explored in this paper is inherently complex, involving multiple influences and correlations between processes, making it difficult to trace the root cause of quality. The modeling process is challenged by the variety and volume of data and the need to iteratively adjust the model and capture correlations between processes. The complexity and resource consumption of dealing with large amounts of data, as well as the uncertainty and risk factors involved in computational analysis, make it difficult to optimize and control, requiring a balance between quality, cost, and efficiency. The research employs a variety of technological tools and methods to cope with these difficulties, such as data mining, ma

关键词： Greedy algorithms Solid modeling Decision making Production Prediction algorithms Mathematical models data models MCDM Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Graphic 3D modeling Technology Based on Neural Network in Intelligent Construction System

Research on Graphic 3D Modeling Technology Based on Neural N...

引用

Electronics, Energy Systems and Power Engineering (EESPE), IEEE International conference on

作者： Jiwen Zhang Changchun University of Architecture and Civil Engineering Changchun China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper mainly discusses the innovative application of neural network in 3D graphic modeling and designs an efficient 3D modeling algorithm. The algorithm takes deep learning as the core and realizes high-precision modeling of building structures by extracting multi-level features of graphic data. CNN is used to process multi-dimensional images to generate 3D models with rich details, which greatly improves the modeling efficiency and accuracy. In addition, this paper introduces the simulation technology of the model in the intelligent construction system, and verifies the stability and robustness of the algorithm through experiments under different parameters. The experimental results show that the proposed modeling algorithm achieves higher accuracy than traditional algorithms in complex structure recognition and saves nearly $\mathbf{3 0 \%}$ in computing time. data analysis further confirms the adaptability and effectiveness of the neural network model in complex building environments, and provides data support and algorithm basis for in-depth research on future intelligent construction systems.

关键词： Graphics Solid modeling Three-dimensional displays Accuracy Computational modeling Buildings Neural networks Feature extraction data models Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Taxonomy for Enhancing Metacognitive Adaptivity and Personalization in Serious Games Using Multimodal Trace data 10th

A Taxonomy for Enhancing Metacognitive Adaptivity and Person...

引用

10th Joint International conference on Serious Games

作者： Azevedo, Roger Dever, Daryn Wiedbusch, Megan Brosnihan, Annamarie Delgado, Tara Marano, Cameron Patel, Milouni Smith, Kevin Univ Cent Florida Sch Modeling Simulat & Training Orlando FL 32826 USA Univ Florida Inst Adv Learning Technol Sch Teaching & Learning Coll Educ Gainesville FL 32611 USA

ISBN: (纸本)9783031741371;9783031741388

This paper presents a theoretically-driven and empirically-based preliminary taxonomy for optimizing metacognitive adaptivity and personalization in serious games by leveraging multimodal trace data. By integrating diverse sources of multimodal trace data, such as eye tracking, log files, concurrent verbalizations, facial expressions of emotions, physiological sensors, and screen recordings, the taxonomy aims to capture nuanced insights into learners' metacognitive processes during gameplay. Our taxonomy focuses on six specific metacognitive processes, including judgments of learning (JOLs), feelings of knowing (FOKs), content evaluations (CEs), monitoring progress towards goals (MPTG), and monitoring use of strategies (MUS), and self-questioning (SQ). These metacognitive processes are critical in learning, reasoning, and problem solving across several learning technologies, including serious games. We provide operational definitions and examples of how each process can be captured by each multimodal data channel during gameplay. More specifically, the taxonomy facilitates the development of serious games that dynamically adjust difficulty levels, provide personalized feedback, and offer tailored scaffolding to enhance metacognitive development using advanced machine learning techniques, including generative AI, for real-time multimodal analysis. Through this taxonomy, researchers and developers can design and evaluate adaptive serious games that optimize metacognitive awareness, monitoring, regulation, and reflection, contributing to advancing the science of learning with serious games. Lastly, future research needs to empirically test these recommendations, andwe expect further refinements based on such testing with different serious games across various learners, tasks, domains, and educational contexts.

关键词： Serious games Metacognition Adaptivity Personalization Multimodal data Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Research on Robust Passenger Flow control Model of Metro Under a Short-Turning Operation Pattern

Research on Robust Passenger Flow Control Model of Metro Und...

引用

International conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Xue, Hongjiao Jia, Limin Peng, Fei Sun, Xuan Wang, Hongyan Li, Ying School of Automotive Engineering Beijing Polytechnic Beijing100176 China Beijing Automation Engineering School Beijing100101 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789819639564

Passenger flow control is the most direct and effective way to solve the problem of metro line congestion. To solve the problem that the random arrival characteristics of passenger flow affect the reliability of the passenger flow control strategy, this paper provides a robust passenger flow control strategy for a metro line under a short-turning operation pattern in peak hours according to the dynamic, time-varying and random characteristics of passenger flow. Firstly, a short-turning operation pattern environment is constructed, and the arrival rate of historical inbound passenger flow is obtained by statistical analysis. Poisson process is used as a parameter to generate multi-scene random arrival passenger flow data. Secondly, a robust passenger flow control and ride strategy is proposed considering the passenger flow OD of the stations inside and outside the short-turning sections. Combining with the strategy, a robust passenger flow collaborative control model is constructed with multi-scene random arrival passenger flow data as input. Finally, an empirical study was carried out on the Beijing Fangshan metro line. The results show that the robust passenger flow control strategy is applicable to the three passenger flow scenarios, and can ensure the passengers’ safety in the three passenger flow scenarios. Moreover, compared with the separate passenger flow control in a single passenger flow scenario, the passenger waiting time under the robust passenger flow control strategy only increases by 1.19%, 4.47% and 4.42% respectively, which basically ensures the travel efficiency of passengers. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

A Variational Quantum Soft Actor-Critic Algorithm for Continuous control Tasks 4th

A Variational Quantum Soft Actor-Critic Algorithm for Conti...

引用

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

作者： Policicchio, Antonio Acuto, Alberto Barillà, Paola Bozzolo, Ludovico Conterno, Matteo NTT DATA Italia S.p.A. Via Ernesto Calindri 4 Milan20143 Italy

ISBN: (纸本)9783031812460

Quantum Computing promises the availability of computational resources and generalization capabilities well beyond the possibilities of classical computers. An interesting approach for leveraging the near-term, Noisy Intermediate-Scale Quantum Computers, is the hybrid training of Parameterized Quantum Circuits (PQCs), i.e. the optimization of a parameterized quantum algorithms as a function approximation with classical optimization techniques. When PQCs are used in Machine Learning models, they may offer some advantages over classical models in terms of memory consumption and sample complexity for classical data analysis. In this work we explore and assess the advantages of the application of Parametric Quantum Circuits to one of the state-of-art Reinforcement Learning algorithm for continuous control - namely Soft Actor-Critic. We investigate its performance on the control of a virtual robotic arm by means of digital simulations of quantum circuits. A quantum advantage over the classical algorithm has been found in terms of a significant decrease in the amount of required parameters for satisfactory model training, paving the way for further developments and studies. A quantum advantage over the classical algorithm has been found in terms of a significant decrease in the amount of required parameters for satisfactory model training, paving the way for further developments and studies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Advancing Infiltration Rate Prediction in Algeria’s Mitidja Plain: A Machine Learning and Empirical Model Comparison

引用

Earth Systems and Environment 2025年 1-22页

作者： Mazighi, Amina Meddi, Mohamed Meddi, Hind Abdi, Ishak Boucefiane, Abdelkader Tariq, Aqil Higher National School of Hydraulics of Blida Blida LGEE Blida 09000 Algeria Department of Civil Engineering and Hydraulics University of Jijel Jijel 18000 Algeria Earth Sciences Department Faculty of Natural and Life Sciences and Earth Sciences Djilali BOUNAAMA University of Khemis Miliana Ain Defla 44001 Algeria Department of Wildlife Fisheries and Aquaculture College of Forest Resources Mississippi State University Starkville 39762-9690 MS United States

Accurate modeling of soil infiltration rates is essential for sustainable water management, flood mitigation, and erosion control. However, traditional empirical models often fall short in capturing the complexity and variability of infiltration processes across diverse soil and climatic conditions. This study addresses this limitation by evaluating the performance of empirical models (Kostiakov, Modified Kostiakov, Horton, Philip, SCS, and a Novel model) and machine learning models (GPR, GBR, XGBoost, CATBoost, LightGBM, RF) using infiltration data from 70 sites in the Mitidja Plain, north of Algeria. Model performance was assessed using RMSE, NRMSE, r, NSE, and KGE. The Novel model outperformed all other empirical models (NSE = 0.921, KGE = 0.843, NRMSE = 0.089), Machine learning models, particularly GPR, demonstrated superior predictive capability (NSE = 0.938, KGE = 0.938, NRMSE = 0.065). Sensitivity analysis identified cumulative time as the most influential factor in infiltration prediction, followed by soil texture and initial water content. These findings highlight the potential of machine learning to capture complex infiltration dynamics more reliably than traditional empirical approaches. The results offer valuable insights for improving hydrological modeling, optimizing water resource management, and supporting sustainable agricultural practices in the Mitidja Plain and similar environments. © King Abdulaziz University and Springer Nature Switzerland AG 2025.

关键词： Empirical models Gaussian process regression (GPR) Infiltration models Machine learning Mitidja Plain Predictive accuracy

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：