检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kungurtsev, Vyacheslav Moore, Leonardo Christov Šír, Gustav Krutský, Martin Department of Computer Science Czech Technical University in Prague Czech Republic Institute of Advanced Consciousness Studies Los AngelesCA United States

Causal Learning has emerged as a major theme of research in statistics and machine learning in recent years, promising specific computational techniques to apply to datasets that reveal the true nature of cause and effect in a number of important domains. In this paper we consider the epistemology of recognizing true cause and effect phenomena. We apply the Ordinary Language method of engaging in thought exercises on the customary use of the word "cause", especially in scientific domains, to investigate valid semantics of reasoning about cause and effect. We recognize that the grammars of cause and effect are fundamentally distinct in form across scientific domains, yet they maintain a consistent and central function within every scientific paradigm. This function can best be described as the mechanism underlying fundamental forces of influence as considered prominent in the respective scientific domain. We demarcate 1) physics and engineering as domains wherein mathematical models are sufficient to comprehensively describe causality, 2) biology as introducing challenges of emergence while providing opportunities for showing consistent mechanisms across scale, and 3) the social sciences as introducing grander difficulties for establishing models of low prediction error but providing, through Hermeneutics, the potential for findings that are instrumentally useful, even if not predictively precise. We posit that definitive causal claims regarding a given phenomenon (writ large) can only come through an agglomeration of consistent evidence across multiple domains, such as statistical population-level observations, physiological and biochemical descriptions of underlying dynamics, etc. This presents important scientific and methodological questions as far as harmonizing between language games and emergence across scales. We highlight the role of epistemic hubris in the contemporary crisis of credibility in the sciences, for which causal learning as it is framed today se

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Algorithm-Driven News Use and Citizens’ Political Information Engagement

SSRN

引用

SSRN 2023年

作者： Bae, Soo Young Chin, Hyojin Cha, Meeyoung Department of Communication Studies University of Massachusetts Amherst United States Postdoctoral Researcher School of Computing Korea Advanced Institute of Science and Technology Korea Republic of School of Computing Korea Advanced Institute of Science and Technology Korea Republic of

While algorithm-based platforms such as social networking sites continue to grow as a primary source for news and public affairs information, their political impact on individuals remains unclear. In this paper, we explore the political outcomes of the algorithm-driven news environment, with a focus on its impact on citizens’ political learning. We highlight the differences between two types of algorithms – user-driven and socially-driven – and further compare their outcomes with news that has not been algorithmically processed. We explore these relationships in the context of the #MeToo movement in South Korea. Our study provides a nuanced understanding of the implications of algorithms in shaping citizens’ information exposure and draws attention to the need to examine the nature of information exposure with greater granularity in the current media environment. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Web Scraping Technique for Prediction of Air Quality through Comparative Analysis of Machine Learning and Deep Learning Algorithm

Web Scraping Technique for Prediction of Air Quality through...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： G. Kalaivani S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India

ISBN: (纸本)9781665489638

Air contamination has turned into a significant and difficult issue all over the planet and its direct impact with human well-being has drawn a lot of consideration from numerous analysts. Individuals are turning out to be known better ways of checking air quality data which are essential to safeguard human wellbeing from the genuine medical conditions brought about via air contamination. Numerous specialists are working on current air quality observation and expectations to carry out different government arrangements connected with the climate or air contamination and give precise outcomes to assist with settling on significant choices. This paper employs a machine learning method to implement predictive analytics and create a more accurate prediction model. These models are created by analysing trends and patterns using historical time series data and then creating a prediction model to forecast future values. These prediction models will be used to execute our suggested approach, the Air Quality Prediction Model (AQPM). This model yields a prediction model that accurately predicts the Air Quality Index (AQI) through the data collected. The information will be scraped from the Central Pollution Control Board (CPCB) website using the web scraping technique. The comparative analysis of ML and DL suggests that Long Short-Term Memory (LSTM) is the best fit model to measure air quality using three different accuracy metrics. Finally, the data are analysed using the predicted AQI in the LSTM model.

关键词： Analytical models Atmospheric modeling Time series analysis Predictive models Air quality Turning Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Emotion and Gesture Recognition System for Humans and Animals Using computer Vision and Deep Learning

Multi-Modal Emotion and Gesture Recognition System for Human...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Rekha R Nair Tina Babu Kishore S Smitha Shivaswamy Aruna S Manchikalapudi Bhargavi Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Application Nitte Institute of Professional Education Nitte(Deemed to be University) Mangaluru Karnataka India Department of Computer Applications Acharya Institute of Technology Bengaluru India School of Science and Computer studies CMR University Bangalore India Department of Computer Science and Engineering(AIML) Malla Reddy College of Engineering and Technology Hyderabad India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Emotion recognition through facial expressions and gesture analysis has emerged as a key area of research in computer vision and human-computer interaction. The ability to automatically detect and classify human emotions has wide-ranging applications, from enhancing user experiences to improving mental health monitoring and surveillance systems. This project builds on this background to develop a comprehensive system for recognizing emotions and gestures in both humans and animals. The system integrates facial emotion recognition, hand gesture interpretation, and animal emotion detection into a single platform. Using advanced deep learning models and computer vision libraries, the system classifies facial expressions into categories such as happiness, sadness, anger, fear, surprise, and neutral. The gesture recognition component interprets hand signals to convey messages like “need help” or “need water.” An innovative aspect of this work is the extension of emotion recognition to animals, particularly focusing on species like dogs and monkeys. Implemented primarily in Python, the system leverages libraries such as OpenCV and DeepFace. By combining these different modalities of nonverbal communication analysis, the project presents a versatile solution with potential applications in human-computer interaction, mental health monitoring, security, and animal welfare.

关键词： Hands Human computer interaction Emotion recognition computer vision Accuracy Animals Face recognition Computational modeling Gesture recognition Mental health

来源：评论

学校读者我要写书评

暂无评论

Harvesting Knowledge: An Innovative Ontology Framework for Agricultural Advancement using NPL methodologies

Harvesting Knowledge: An Innovative Ontology Framework for A...

引用

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： Deepa R Manisha Das Thilakavathy P Bennet Prabhu A Surendran R Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chennai India Department of CSE(AI&ML) GMR Institute of Technology Rajam Andhrapradesh India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India KONE Elevator India Technology & Engineering Centre Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

This paper introduces Agricultural Advancement using NLP (AA-NLP) techniques as a strategy to overcome the limitations of traditional agricultural management information systems. There is a lot of unstructured data available but this situation makes agricultural research inefficient because of its knowledge extraction and usage failure. This problem is addressed by combining an ontology framework developed for agricultural information management with Natural Language Processing (NLP) methods. The solution, AA-NLP, utilizes modern NLP algorithms which extract, classify and evaluate agricultural information from many textual sources that include research papers, reports and online repositories. AA-NLP achieves effective information retrieval and exploitation through named entity identification, sentiment analysis and semantic similarity as well as other techniques to convert unstructured input into structured ontological representations. Applying AA-NLP has several benefits such as increased discoverability of relevant agricultural information, automatic classification of scientific findings, and generation of actionable insights for decision making in farming practices, crop management and formulation of agricultural policies. The effectiveness of AA-NLP was analyzed in this paper by measuring the precision associated with knowledge extraction and ontology creation through various performance metrics including accuracy, sustainability farming practices, agricultural productivity and precision.

关键词： Productivity Sentiment analysis Semantics Ontologies Information retrieval Information management Data mining Stakeholders Sustainable development Farming

来源：评论

学校读者我要写书评

暂无评论

Event Causality Identification - Shared Task 3, CASE 2023 6

Event Causality Identification - Shared Task 3, CASE 2023

引用

6th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2023

作者： Tan, Fiona Anting Hettiarachchi, Hansi Hürriyetoğlu, Ali Oostdijk, Nelleke Uca, Onur Thapa, Surendrabikram Liza, Farhana Ferdousi Institute of Data Science National University of Singapore Singapore School of Computing and Digital Technology Birmingham City University United Kingdom KNAW Humanities Cluster DHLab Netherlands Centre for Language Studies Radboud University Netherlands Department of Sociology Mersin University Turkey Department of Computer Science Virginia Tech United States School of Computing Sciences University of East Anglia United Kingdom

ISBN: (纸本)9789544520892

The Event Causality Identification Shared Task of CASE 2023 is the second iteration of a shared task centered around the Causal News Corpus. Two subtasks were involved: In Subtask 1, participants were challenged to predict if a sentence contains a causal relation or not. In Subtask 2, participants were challenged to identify the Cause, Effect, and Signal spans given an input causal sentence. For both subtasks, participants uploaded their predictions for a held-out test set, and ranking was done based on binary F1 and macro F1 scores for Subtask 1 and 2, respectively. This paper includes an overview of the work of the ten teams that submitted their results to our competition and the six system description papers that were received. The highest F1 scores achieved for Subtask 1 and 2 were 84.66% and 72.79%, respectively. © CASE 2023 - Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, associated with 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Correction to: Yantramanav: a humanoid to spread literacy among rural children through eGurukul education system

引用

CSI Transactions on ICT 2022年第3期10卷 235-236页

作者： Rohini, A. Kalaivani, K. Karthika, R. A. Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India

来源：评论

学校读者我要写书评

暂无评论

Gender and Age Detection Techniques for Blind People using Principal Component Analysis

Gender and Age Detection Techniques for Blind People using P...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： J. Meenakshi G. Thailambal Department of Computer Science Vels Institute of Science and Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India

Predicting someone's gender and age-based solely on appearance is challenging for an AI model, as it requires recognizing and understanding complex patterns in images and videos. This kind of prediction is particularly used for blind people. Different kinds of techniques are applied to analyze and predict gender and age classification with the help of images. In the previous methods, accuracy and live prediction have different challenges such as accuracy and prediction rates. This work proposes a hybrid model to predict and analyze gender and age classification. This work consists of Haar Cascade, Histogram of Oriented Gradients, Hessian Filter and Principal Component Analysis. The Haar Cascade algorithm finds the face from the video images with constant speed and time. The Histogram-orientation extracts the features from the images, and the Hessian Filter finds the wrinkles and, based on that, finds the age. Principal Component Analysis is used to visualize and find the patterns from the images. This proposed hybrid work is implemented using 10137 images, and based on that, training and testing are performed. The proposed work is evaluated using recall, f1-score and precision. The proposed work achieved 87.30%. and 86.9% precision for gender classification and age classification respectively. This, compared to the previous work, produced effective results for gender and age detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-Heuristic with Machine Learning-Based Smart e-Health System for Ambient Air Quality Monitoring 4th

Meta-Heuristic with Machine Learning-Based Smart e-Health Sy...

引用

4th International Conference on Recent Innovations in computing, ICRIC 2021

作者： Rahi, Pankaj Sood, Sanjay P. Bajaj, Rohit University Institute of Computing Chandigarh University Punjab Gharuan Mohali India Health Informatics Division Centre for Development of Advanced Computing Punjab Mohali India Department of Computer Science and Engineering Chandigarh University Punjab Gharuan Mohali India

ISBN: (纸本)9789811688911

Health issues caused by air pollution are the primary concern nowadays. The air quality monitoring system aids in monitoring the level of air pollutants by measuring the concentration of a particular pollutant in the environment. A systematic study of the existing systems has been done to analyze the limitations in the current scenario of these systems. This paper proposes a smart e-health air quality monitoring system that utilizes a meta-heuristic Firefly algorithm as well as a Cat Swarm Optimization algorithm to efficiently optimize the selected features to give better results in the feature selection process. Further, these features are classified by using a Support Vector Machine which predicts the index level of the air quality and gives better precision and recall. The combination of all these algorithms has true positive and false positive rates as 99% and 88.4%, respectively while the recall rate is 89.6%. Also, the proposed work predicts a high air quality index based on the input dataset. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Evolution of Artificial Intelligence and Machine Learning in Betterment of Healthcare Services 1

Evolution of Artificial Intelligence and Machine Learning in...

引用

1st International Conference on Healthcare Innovations, Software and Engineering Technologies, HISET 2024

作者： Abu Eid, Aws Ismail Maula, Shabana Wagh, Aparna Vyas, Vibha Patil, Prakash Sridhar, P. Arab Open University Faculty of Computing Studies Amman Jordan Jaywant College of Engineering and Polytechnic Department of Computer Science Engineering Karad India Jaywant College of Management Karad India College of Engineering Pune Department of Electronics and Telecommunication Pune India Department of Radio-Diagnosis Karad India Institute of Aeronautical Engineering Department of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798350360707

Artificial Intelligence usually comprises a system that is composed of hardware and software. Machine learning is a subset of artificial intelligence (AI). The study discovered that the environment and contemporary technology on the current healthcare services have created new demands, which has led to the formation of these five categories of research. By matching eligible patients with clinical trials, AI technologies in the healthcare industry may also be beneficial for medical research. There are numerous other fascinating uses for AI in the biomedical field. It is evident that AI is becoming more and more relevant in the field of biomedicine. AI technologies may be able to assist in addressing significant health issues, but its potential may be constrained by the caliber of the health data that is now available and by the fact that AI cannot exhibit certain human traits, like empathy. Numerous ethical and societal concerns are brought up by the use of AI, many of which are also brought up by the use of data and healthcare technologies more generally. © 2024 IEEE.

关键词： Adversarial machine 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：