检索结果-内蒙古大学图书馆

3rd international conference on pattern recognition and Artificial Intelligence, ICPRAI 2022

作者： Likforman-Sulem, Laurence Cordasco, Gennaro Esposito, Anna Telecom Paris/Institut Polytechnique de Paris Palaiseau France Department of Psychology Università degli Studi della Campania "L. Vanvitelli" Caserta Italy Vietri sul Mare Italy

ISBN: (纸本)9783031090363

Handwriting is an everyday life human activity. It can be collected off-line by scanning sheets of paper. The resulting images can then be processed by a computer-based system. Thanks to digitizing tablets, handwriting can also be collected on-line. From the collected raw signals (pen position, pressure over time), the dynamics of the writing can be recovered. Since handwriting is unique for each individual, it can be considered as a biometric modality. Biometric systems predicting gender from off-line handwriting, have thus been recently proposed. However we observe that, in contrast to other modalities such as speech, it is not straightforward for a human being (even expert) to predict gender. In this study we explore the limits of automatic gender prediction from on-line handwriting collected from a young adults population, homogeneous in terms of age and education. Statistical analysis of on-line dynamic features can highlight differences between male and female groups [6]. In the present study, we focus on a sentence copying task, and provide statistically significant features to a classifier, based on a machine learning approach (SVMs). Since the dataset is relatively small (240 subjects), several evaluation frameworks are explored: cross validation (CV), bootstrap, and fixed train/test partitions. Accuracies obtained from fixed partitions range from 37% to 79%, while those estimated by CV and bootstrap are around 65%. This shows to our opinion the limits of the gender recognition task for our young adult population dataset. © 2022, Springer Nature Switzerland AG.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

Balancing Security and Privacy-Preserving Counterterrorism

Balancing Security and Privacy-Preserving Counterterrorism

引用

Automation, Computing and Renewable Systems (ICACRS), international conference on

作者： R.Tamilkodi L.Venkateswara Kiran K.Sai Soudamini P.Pratibha P.Ramu M.Praneeth Dept of CSE(AIML&CS) Godavari Global University Rajahmundry AP Dept of MCA Godavari Global University Rajahmundry AP Dept of CSE(AIML) Godavari Institute of Engineering & Technology (A) Rajahmundry AP

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Through speeches, films, and controversial websites, the internet has emerged as a key channel for the spread of *** groups use social media to indoctrinate people and spread their message, recruiting those who are most likely to join them. An effective web data mining method is suggested in this project to automatically identify and highlight such web properties for human assessment. Text, photos, videos, and audio are all mixed together on web pages, which are made with HTML (Hypertext Markup Language). We can extract textual information from these online pages and find trends by using data mining and web mining tools. Additionally, our system integrates an email filtering mechanism to detect and redirect unwanted messages that may be linked to terrorism directly to the recipient's spam folder users are protected from potentially harmful content. Our approach leverages advanced data mining algorithms to automatically flag suspicious emails and web content for further examination, enhancing digital security and countering the spread of terrorist propaganda online.

关键词： machine learning algorithms Social networking (online) Law enforcement Terrorism Unsolicited e-mail Semantics Web pages Web mining Market research Videos

来源：评论

学校读者我要写书评

暂无评论

Advanced machine learning Frameworks for Multimodal Image and Speech Signal Processing

Advanced Machine Learning Frameworks for Multimodal Image an...

引用

Advancement in Technology (ICONAT), international conference for

作者： P Ramesh Naidu Saurabh Shandilya Srividya C N Shantanu Sudhir Gujar Supriya Devi Dankan Gowda V Department OF Computer Science and Engineering Nitte Meenakshi Institute of Technology Bangalore Karnataka India Department of Advance Computing Poornima College of Engineering Jaipur Rajasthan India Dept. of ECE Faculty of Engineering Management & Technology BGSIT Adichunchanagiri University B G Nagara India Department of CyberSecurity Golisano College of Computing and Information Sciences Rochester Institute of Technology Rochester NY Department of Mathematics Alliance University Bangalore Karnataka India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

Multimodal data processing, especially the fusion of image and speech modality, is important for future human computer interface, medical applications and security surveillance. This research proposes the new machine learning approach for the efficient handling of multimodal data in which feature extraction from images and from the speech signal is obtained by employing CNN and LSTM networks, respectively. These features are combined by a hybrid fusion approach so that the resulting algorithm would be both accurate and fast. CIFAR-10 and LibriSpeech were used to assess the framework; the highest accuracy was 92% whilst the conventional methods like MDNN and EFMS could only reach 86%. Moreover, the analysis showed that the proposed method can take a processing time of 0.15 seconds to taxonomy and 0.45 seconds for speech data, thus making it preferable for real time data. These results illustrate the framework’s efficiency in predicting the multimodal input and demonstrate superiority over the prior methods.

关键词： Accuracy Surveillance Taxonomy Speech recognition machine learning Speech enhancement Signal processing Feature extraction data processing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Question-Aware Deep learning Model for Arabic machine Reading Comprehension 3rd

Question-Aware Deep Learning Model for Arabic Machine Readi...

引用

3rd international conference on Intelligent Systems and pattern recognition, ISPR 2023

作者： Al-Harbi, Marwa Obeidat, Rasha Al-Ayyoub, Mahmoud Alawneh, Luay Department of Computer Science Jordan University of Science Irbid Jordan Department of Information Technology Ajman University Ajman United Arab Emirates Department of Software Engineering Jordan University of Science Irbid Jordan

ISBN: (纸本)9783031463372

machine reading comprehension is one of the most long-standing challenges in artificial intelligence. It is a subtask question-answering system that aims to find a text span in a reading context that answers a question. It is the core of several applications, such as customer service systems and chatbots. However, However, few studies have targeted machine reading comprehension of Arabic text. Besides, The existing models generate a context representation independently from the question. As an analogy to some people’s comprehension styles who believe that by reading the question, they gain a better understanding of the reading passage, we present a question-aware neural machine reading comprehension model for Arabic. Our model extracts a representation of the context by incorporating the question using several bidirectional attention units to achieve various levels of question-centered context understanding. Our experimental evaluation shows that our model outperforms strong machine reading comprehension baselines, including DrQA and QaNET models applied to Arabic, by a significant margin with an F1 score of 59.6%. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

IoT-based Car Driver Assistance System using Computer Vision and machine learning

IoT-based Car Driver Assistance System using Computer Vision...

引用

Artificial Intelligence For Internet of Things (AIIoT), international conference on

作者： Kumar Shubham Kumar Satyam Pranav Kapisway Raghav Memani Aniket Anand C Sathiya Kumar VIT Vellore India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

This paper presents an innovative approach for improving driver convenience and safety by combining Artificial Intelligence (AI) and Internet of Things (IoT) with computer vision techniques like OpenCV. By using intelligent automation, the suggested system, termed the IoT-based Car Driver Assistance System using Computer Vision and machine learning, seeks to both enhance and reduce potential driving-related risks. A camera and sensor suite are installed on the dashboard of the vehicle as part of the system design to enable real-time data collection and processing. By utilizing face recognition algorithms, the system begins by confirming the driver’s identification prior to vehicle activation, which improves security. The system always keeps a watch on the driver’s condition, looking for indications of drowsiness while operating and sending out alerts in a timely manner to help avoid collisions. The technology improves situational awareness by detecting and alerting the driver to approaching obstacles on the road, helping the driver avoid potentially dangerous situations. The technology also facilitates hands-free driving by utilizing hand gesture detection to provide seamless control over in-car audio operations such as track selection and volume adjustment. Call management is integrated with gesture recognition, enabling drivers to use hand gestures to accept or reject incoming calls. The system aims to improve the driving experience by utilizing facial recognition and mood detection to identify the driver’s emotional state and provide tailored Spotify music choices. By recognising traffic signals and lane changes, the technology helps drivers maintain lane discipline, which improves road safety and encourages adherence to traffic laws. In order to lessen the difficulties of parking in crowded areas, the system also offers intelligent parking assistance. With a full feature set that gives drivers more control, awareness, and efficiency while driving, the proposed I

关键词： Computer vision machine learning algorithms Mood Face recognition Vehicle safety machine learning Automobiles

来源：评论

学校读者我要写书评

暂无评论

3rd international conference on Smart and Intelligent learning for Information Optimization, CONSILIO 2021

3rd International Conference on Smart and Intelligent Learni...

引用

3rd international conference on Smart and Intelligent learning for Information Optimization, CONSILIO 2021

The proceedings contain 37 papers. The topics discussed include: wavelet tree ensembles with machine learning and its classification;energy efficient NoC design through supervised machine learning;design and development of novel ensemble classifier for visual sentiment analysis;applying SWOT for B2B decisions, extension to larger data with machine learning regression;realization of low cost footwear integrated step-counting device for health monitoring system;assessment of optimizers impact on image recognition with convolutional neural network to adversarial datasets;efficient construction of successive cancellation decoding of polar codes using logistic regression algorithm;prediction accuracy model aiming to improve prediction accuracy in congenital heart anomaly detection using hybrid feature selection with modified particle swarm optimization approach;and mutual information-based optimum metrics identification in symmetry-based brain abnormality detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Short-Term Wind Power Prediction Framework Based on Singular Spectrum Analysis and Deep Belief Network Utilized Improved Adaptive Genetic Algorithm 3

A Novel Hybrid Short-Term Wind Power Prediction Framework Ba...

引用

3rd international conference on Industrial Artificial Intelligence, IAI 2021

作者： Yuan, Weiru Tang, Zhenhao Bu, Bing Cao, Shengxian Northeast Electric Power University School of Automation Engineering Jilin132012 China Guodian Hefeng Wind Power Development Co. Ltd. Shenyang110000 China

ISBN: (纸本)9781665435178

A machine learning based framework involving data-mining method was proposed in this paper. To begin with, a powerful signal decomposition technique (singular spectrum analysis, SSA) was used to divide the original wind sequence into several sub-series to form a potential feature set. Then, the optimal sub-series is screened as the input feature set based on a novel swarm intelligence optimization algorithm (adaptive genetic algorithm based on improved harmony search algorithm, IAGA). Finally, a more appropriate sub-feature set together with the corresponding machine learning model (deep belief network, DBN) were established. A series of simulations is conducted by utilizing actual dataset to validate the proposed method. Comparison results represent that the proposed SSA-IAGA-DBN method achieves high prediction accuracy and robustness in short term wind power prediction tasks. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Modelling and predicting the spread of COVID-19 cases depending on restriction policy based on mined recommendation rules

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2021年第3期18卷 2789-2812页

作者： Yakovyna, Vitaliy Shakhovska, Natalya Univ Warmia & Mazury Olsztyn Poland Lviv Polytech Natl Univ Lvov Ukraine

This paper is an extended and supplemented version of the paper "Recommendation Rules mining for Reducing the Spread of COVID-19 Cases", presented by the authors at the 3rd international conference on Informatics & data-Driven Medicine in November 2020. The paper examines the impact of government restrictive measures on the spread and effects of COVID-19. The work is devoted to the improvement of recommendation rules based on novel ensemble of machine learning methods such as regression tree and clustering. The dynamics of migration between countries in clusters, and their relationship with the number of confirmed cases and the percentage of deaths caused by COVID-19, were studied on the example of Poland, Italy and Germany. It is shown that there is a clear relationship between the cluster number and the number of new cases of diseases and death. It has also been shown that different countries' policies to prevent the disease, in particular the timing of restrictive measures, correlate with the dynamics of the spread of COVID-19 and the consequences of the disease. For example, the results show a clear proactive tactic of restrictive measures by example of Germany, and catching up on the spread of the disease by example of Italy. A regression tree and guidelines about influence of features on the spreading of COVID-19 and mortality due to this infection have been constructed. The paper predicts the number of deaths due to COVID-19 on a 21 day interval using the obtained guidelines on the example of Sweden. Such forecasting was carried out for two potential government action options: with existing precautionary actions and the same precautionary actions, if they had been taken 20 days earlier (following the example of Germany). The RMSE of the mortality forecast does not exceed 4.2, which shows a good prognostic ability of the developed model. At the same time, the simulation based on the strategy of anticipatory introduction of restrictions gives 2-6% lower values

关键词： clustering classification COVID-19 prognostic data machine learning

来源：评论

学校读者我要写书评

暂无评论

Tagging Units in the Text and the Bayes Algorithm

Tagging Units in the Text and the Bayes Algorithm

引用

Informatics, Electronics, and Radio Engineering (PIERE), international conference Problems of

作者： Elov Botir Boltayevich Bekmuradova Iroda Zokir qizi Israilova Saodat Turapovna Toirova Guli Ibragimovna Department of Computer Linguistics and Digital Technology Alisher Navo 'i Tashkent State University of Uzbek Language and Literature Tashkent Uzbekistan Department of computer linguistics and digital technologies Master student of Tashkent state university of Uzbek language and literature Tashkent Uzbekistan Senior teacher of UzNU candidate of philological sciences name of organization Uzbekistan National University Tashkent Uzbekistan Professor of the Department of Uzbek Linguistics and Journalism Doctor of Philology Bukhara State University Bukhara Uzbekistan

ISBN: (数字)9798331516321

ISBN: (纸本)9798331516338

This article presents an analysis of the methods employed for the tagging of units within textual data. The stages of automatic tagging of language units, in particular slangs, are covered in detail based on the working theory of the Bayesian algorithm. The factors that contribute to an increased accuracy of the calculated probability are outlined. And also this article analyzes the advantages and disadvantages of the Bayesian algorithm for text unit tagging. The steps of the algorithm are elucidated with the aid of illustrative examples. Describes the characteristics of the Bayesian algorithm as a computational method for estimating the probability of an object, its characteristics, and the group to which it belongs. This method has been shown to provide accurate results in data analysis using machine learning methods for automatic tagging of jargon, the necessity of distinguishing and automatic classification of lexical units in the language corpus, its importance in solving the problems related to the confusion in the analysis of the text containing such units.

关键词： machine learning algorithms Accuracy Translation Software algorithms machine learning Tagging Prediction algorithms Bayes methods Classification algorithms Object recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of Hearing-Impaired Children's Kannada Speech with Limited Vocabulary

Automatic Recognition of Hearing-Impaired Children's Kannada...

引用

Smart Systems for applications in Electrical Sciences (ICSSES), international conference on

作者： Chandrashekar H M Anushree T R Chaitra T P Meghana K Monisha T U N Sreedevi Dept. Electronics and Telecommunication Siddaganga Institute of Technology Tumakuru India All India Institute Of Speech and Hearing Mysore India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Hearing is essential in our daily lives, helping us to understand language through sound and contributing to proper speech development. Hearing loss affects many people worldwide, and children account for a large part which can hinder their communication and development skills. Hearing impairment can influence the progression of children's participation in activities suitable for their age, as well as their functional speech communication abilities and language proficiency. Kannada database developed in collaboration with the All India Institute of Speech and Hearing (AIISH), Mysore, is used for hearing-impaired (HI) children. The main aim of this work is to build an automatic speech recognizer (ASR) system with a limited vocabulary dataset using Raspberry Pi. data augmentation is used since the dataset is limited in number of words and number of children. Shorttime Fourier transform (STFT) spectrograms are extracted by varying frame sizes by incorporating augmentation to build an ASR model. A convolutional neural network (CNN) classifier is used to build an ASR model. The speech recognition accuracies for HI speech are compared with and without data augmentation. Improved recognition accuracy is obtained with data augmentation. Finally, real-time implementation for ASR is also carried out and it is observed that there is a scope for improvement of the developed ASR system.

关键词： Vocabulary Accuracy Working environment noise Speech recognition Auditory system machine learning data augmentation Real-time systems Convolutional neural networks Spectrogram

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：