检索结果-内蒙古大学图书馆

7th international conference on machine learning and soft computing, icmlsc 2023

ISBN: (纸本)9781450398633

the proceedings contain 31 papers. the topics discussed include: research on location problem based on fuzzy multi-criteria decision method;decision model of ship intelligent collision avoidance based on automatic information system data and generic adversary imitation learning-deep deterministic policy gradient;research on energy consumption prediction based on fast attribute reduction of weighted neighborhood rough set with moving horizon;solving multimodal multi-objective problems with local pareto front using a population clustering mechanism;validated computation of Lipschitz constant of recurrent neural networks;neural network optimization objective vector representation based on genetic algorithm and its multi-objective optimization method;improved multilayer perceptron neural networks weights and biases based on the grasshopper optimization algorithm to predict student performance on ambient learning;and spatio-temporal deep fusion graph convolutional networks for crime prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cultivating Quadrupedal Robotic Agility: Unveiling Reinforcement learning Dynamics with the Boosted Tree Motif Classifier

引用

international JOURNAL OF SEMANTIC computing 2025年

作者： Allred, Christopher Pusey, Jason Harper, Mario Utah State Univ USU Dept Comp Sci Logan UT 84322 USA Army Res Lab ARL Adelphi MD USA

this study examines the Boosted Tree Motif Classifier (BTMC), which leverages gradient boosting for the precise classification of intricate motion patterns in quadrupedal robots, with a particular emphasis on dynamic actions like jumping. Building upon our previous conference paper [C. Allred, J. Pusey and M. Harper, Detecting ballistic motions in quadruped robots: A BTMC for understanding reinforcement learning, in 7th IEEE Int. Conf. Robotic computing (IEEE, 2023)], this journal extension expands the study by incorporating multivariate motif analysis, additional machine learning models, and a more comprehensive evaluation of reinforcement learning dynamics. BTMC achieves 96% precision, effectively identifying complex motion patterns during training. through experiments at multiple levels of from individual motors to full robotic actuation, BTMC consistently outperforms traditional techniques in accuracy. this study lays the foundation for future research on whole-body reward development, providing clearer insights into the intricate relationship between rewards and learned skills.

关键词： Reward Modeling Boosted Tree Motif Classifier Quadruped Robots

来源：评论

学校读者我要写书评

暂无评论

Prediction of Soil Pollution Using machine learning Methods in Absheron Peninsula 16th

Prediction of Soil Pollution Using Machine Learning Methods ...

引用

16th international conference on Application of Fuzzy Systems, soft computing and Artificial Intelligence Tools, ICAFS 2023

作者： Abdullayeva, Maya Babayeva, Tunzala Dadashova, Shebnem Azerbaijan State Oil and Industry University Azadlig 16/21 Baku Azerbaijan

ISBN: (纸本)9783031725050

this paper presents a comprehensive study contributing to soil pollution research by applying machine learning techniques. the research explores predicting soil heavy metals and pollution indices, identifying, and classifying potentially polluting enterprises, and reviewing machine learning models for soil pollution prediction. the study employs various machine learning algorithms, including linear regression, decision tree regressor, and k nearest neighbor, to predict soil pollution at depths not physically investigated. this approach proves instrumental in reducing the time, staff, and resources required for pollution measurement in the Absheron Peninsula. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Use of machine learning Methods for Analysis of Factors Affecting ICT Contribution to Different Countries Development 16th

Use of Machine Learning Methods for Analysis of Factors Affe...

引用

16th international conference on Application of Fuzzy Systems, soft computing and Artificial Intelligence Tools, ICAFS 2023

作者： Aliev, Araz R. Ismayilova, Nigar T. Ismayilov, Elviz A. Azerbaijan State Oil and Industry University Azadlig Ave. 20 Baku Azerbaijan Center for Mathematics and Its Applications Institute of Mathematics and Mechanics Khazar University Baku Azerbaijan

ISBN: (纸本)9783031725050

Investigating the development of ICT in different countries, particularly in developing nations, holds significant importance. the advent of machine learning has opened new avenues for analysis in diverse industries, including economics. In this study, machine learning methods are applied to extract factors influencing ICT development using data obtained from the World Bank. the data is processed using LASSO regression and XGBoost regression methods to predict the "Computer, communications, and other services (% of commercial service exports)" parameter and identify the most significant factors impacting the target parameter. the XGBoost model's capability to yield accurate results with only a limited number of parameters allows for substantial data reduction while retaining the economic advantages of identifying the most informative features. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

machine learning Approaches for the Early Diagnosis of Autism Spectrum Disorder: A Systematic Framework 15th

Machine Learning Approaches for the Early Diagnosis of Autis...

引用

15th international conference on soft computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2023

作者： Narayanan, Neethu Remya, K.R. Varghese, Bindiya M. Department of Computer Science Rajagiri College of Social Sciences (Autonomous) Kerala Kochi India

ISBN: (纸本)9783031810824

this study uses machine learning to address the urgent need for early detection and intervention in autism spectrum disorder (ASD). Autism Spectrum Disorder (ASD), a disorder of neural development affecting cognition and social interaction, necessitates customized interventions. Our research uses various screening assessments in early infancy as datasets to train for neural network algorithms, with the objective of identifying patterns associated with ASD. the suggested methodology utilizes predictive machine learning techniques to assess the ASD spectrum, accounting for its diverse pitches. Utilizing sophisticated screening instruments and an innovative methodology, we seek to establish a dependable system for the early detection of ASD. Ethical considerations, data privacy, and algorithmic openness are essential. the studies seek to foster collaboration among experts in neurodevelopment, psychological science, and data science to build precise tools for earlier identification of ASD. the use of machine learning, an effective tool, enhances the knowledge of healthcare workers. the research results underscore technology's capacity to transform initial measures, leading to enhanced outcomes for those on the autistic spectrum. It provides this assistance to enhance the dialogue at the gathering, thereby promoting interaction at the nexus of healthcare and digital technology. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Autism Spectrum Disorder (ASD) machine learning Neurological

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

Recognition of Respiratory Diseases from X-ray Images Based on machine learning Methods 16th

Recognition of Respiratory Diseases from X-ray Images Based ...

引用

16th international conference on Application of Fuzzy Systems, soft computing and Artificial Intelligence Tools, ICAFS 2023

作者： Shakhmametova, G.R. Bogdanova, D.R. Ziyazetdinova, L. Yu. Ufa University of Science and Technology Ufa Russia

ISBN: (纸本)9783031725050

the article analyzes the current state of research and existing solutions in the field of recognizing respiratory diseases from functional diagnostic images. the solution of the problem of recognizing respiratory diseases such as cardiomegaly, pleural thickening and pulmonary fibrosis from chest X-rays is presented. the end user of the proposed software is a medical professional - radiologist. the developed software application for recognizing respiratory diseases from X-ray images consists of two interacting parts: user interface and neural network. the information system uses a convolutional neural network to solve the recognition problem. the Python programming language is used to create the convolutional neural network using TensorFlow and Keras libraries. As a dataset for training and testing of the neural network, an open set from the Kaggle website is chosen. the performance analysis of the developed application showed an accuracy of 92% in recognizing respiratory diseases by the trained model. the maximum time of recognizing a chest X-ray image took 1 min and the minimum time 20 s, while a radiologist needs from 10 to 20 min to decipher one X-ray image. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Event Organization Efficiency through Intelligent Chatbot: A Study on Automated Assistance and Engagement 15th

Enhancing Event Organization Efficiency Through Intelligent ...

引用

15th international conference on soft computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2023

作者： Reddy, Avala Raji Bhavya, K.R. Srilekha, M. Mulugu, Narendhar Sandhya, K. Rao, B. Narendra Kumar CMR Technical Campus Telangana Hyderabad India REVA University Karnataka Bangalore India Malla Reddy Institute of Engineering and Technology (Autonomous) Telengana Hyderabad India Mohan Babu University Andhra Pradesh Tirupati India

ISBN: (纸本)9783031810855

Chatbot is a computer program that applies the Artificial Intelligence (AI) and Natural Language processing (NLP) that helps to communicate with the human beings. It provides the automated assistance to the user by answering to the user for specified information. Now days, in many of the website’s developers using Chatbots to answer their user queries. But many of them are not giving accurate answers to the users that makes users dissatisfaction. In this paper, we built an intelligent event Chatbot that majorly focuses on the event management in the organization. Also, here we used machine learning algorithms to improve the accuracy. Here, we did the experimentation on a university Chatbot where the university conducts many numbers of events in their institution through their technical association clubs. Obviously, it will be difficult to the event organizers to answer the queries of the users 24 × 7. In these kinds of the scenarios the intelligent event Chatbot helps the event organizers to clarify all the questions raised from the users. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Artificial Intelligence Deep learning Natural Language Processing Neural Network Pytorch Tkinter

来源：评论

学校读者我要写书评

暂无评论

Utilization of machine learning Algorithms to Monitor the Growth Path of Fishes in Marine Aquaculture 15th

Utilization of Machine Learning Algorithms to Monitor the Gr...

引用

15th international conference on soft computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2023

作者： Ajibade, Samuel-Soma M. Essah, Richard Tapales, Catherine P. Antecristo, Charmaine P. Cababat, Feliciana G. Oyebode, Oluwadare Joshua Akintoye, Kayode A. Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Malaysia Department of Computer and Information Sciences Sunway University Selangor Malaysia Department of Computer Science and Engineering Chandigarh University Punjab India College of Arts and Sciences Cebu Technological University Cebu Moalboal Philippines Cebu Technological University Cebu Moalboal Philippines College of Education Cebu Technological University Cebu Moalboal Philippines Department of Civil and Environmental Engineering ABUAD Ado Ekiti Nigeria Department of Computer Science The Federal Polytechnic Ekiti State Ado Ekiti Nigeria

ISBN: (纸本)9783031810855

Under a realistic cellular metabolic economic model of Nile tilapia, this work investigates Q-learning fish growth trajectory analysis. we offer two Q-learning data mining algorithms the best management policy using simulated data of optimum growth projections starting at the early growth stage and ending at appropriate market share. the early or primitive Q-learning technique learns optimum feed supplying regulatory regime for fish cultivation rate for the fished present the cages, whereas other one continuously adjusts appropriate nutrition controls the law for agricultural fish rate of increase in tanks together within ideal temperature pattern. the cumulative percentage weight of fishes through both vessels on land and afloat cages was tracked with relative dynamic model errors of 1.7% and 6.6%, respectively, using Q-learning control rules. Furthermore, contrasted to drifting cages where its water temp is controlled at 29.7 ℃, the eating and heat management policies minimise the proportional rate of feeding along with wastage of food in by 11%. Data, algorithms, and performance of DL approaches used in adaptive aquaculture farms are also examined. In a nutshell, our goal is to give scholars and clinicians a greater grasp of the latest advancements of deep learning in aquaculture, which will help them develop smart aquacultural applications. With improved machine - learning technologies, a video trying to track biological early warning has made significant progress. Artificial intelligence has helped researchers better understand behavioural reactions to pharmacological and environmental stress. We discuss pioneer efforts in exact monitoring of a gathering of individuals in 2d/3d space in this paper, which introduces the fundamentals of activity recognition. Video tracking's professional and operational difficulties are discussed. the toxicological study based on fish behavioral data is then summarized. © the Author(s), under exclusive license to Springer Nature

关键词： artificial intelligence cellular metabolic data mining algorithms pharma logical trajectory

来源：评论

学校读者我要写书评

暂无评论

OSOL: Open Linked Data Generation Using Semantics Oriented learning Paradigms 15th

OSOL: Open Linked Data Generation Using Semantics Oriented L...

引用

15th international conference on soft computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired computing, NaBIC 2023

作者： Aravind Krishnan, A. Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9783031889912

In the era of Web 3.0, there is an imminent need for a strategic framework for open linked data and meta tag generation for web pages as they would be useful in indexing which would serve as a roadmap for retrieval and also several other applications such as text summarization, text mining, etc. this paper proposes an open-linked data generation framework in which the XGBoost classifier classifies the web URL dataset. Category extraction and URL canonicalization are performed which helps in strategic maximal utilization of the term set. Strategic knowledge base repositories like CYC and NELL are used for entity enrichment in the model. the RBFNN classifies the web-based directories extracted from the current structure of the web using a focused crawler. Unlike most traditional frameworks, the OSOL uses Semantics-oriented reasoning, which is achieved through the SimRank measure with an empirically decided threshold. the Eagle optimization algorithm (a metaheuristic, nature-inspired algorithm) generates the optimal solution set. Shannon’s entropy helps in feature selection for classifying the dataset. this framework can achieve an overall mean precision percentage of 95.17%, a mean recall percentage of 96.75%, and an FDR value of 0.05, making it the best-in-class model for linked open data and meta-tag generation. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： entity enrichment linked open data meta tag generation retrieval web-based directories

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：