检索结果-内蒙古大学图书馆

Hypernasality severity analysis using spectral and residual features 10

Hypernasality severity analysis using spectral and residual ...

10th International Conference on Internet of Everything, Microwave engineering, communication and Networks, IEMECON 2021

作者： Kumar Dubey, Akhilesh Kumar Singh, Deepak Tiwari, B.B. Dept. of computer science and engineering AP Guntur India VSB Purvanchal University Dept. of electronics and communication engineering UP Jaunpur India

ISBN: (纸本)9781665426862

In this work, spectral and linear prediction residual characteristics of normal, mild, and moderate-severe hypernasal /i/ vowel are analyzed for finding their nature in these three levels of hypernasality severity. The nasal tract and the oral tract coupling during vowel sound production by the children with cleft palate introduces additional nasal pole-zero pairs in these vowels. So the spectral characteristics of these vowels deviate compared to normal vowels. Further, the inappropriate modeling of this deviated spectrum by the LP model, due to the presence of zeros, gives the deviated residual characteristic also. The spectral and residual analysis is done using vocal tract constriction (VTC) evidence, power spectral entropy (PSE) and peak to side-lobe ratio (PSR) features. The first two features capture the spectral deviation in terms of low-frequency dominance and spectral flatness in the hypernasal vowel spectrum respectively whereas the third feature capture the residual deviation in terms of the presence of undesirable signal components in the residual signal. The analysis result reveals that the value of VTC evidence increases whereas the value of PSE and PSR features decreases as the severity of hypernasality increases. © 2021 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Automated Boundary Identification for Machine Learning Classifiers

Automated Boundary Identification for Machine Learning Class...

引用

Search-Based and Fuzz Testing (SBFT), IEEE/ACM International Workshop on

作者： Felix Dobslaw Robert Feldt Dept. of Quality Mngmt Communication and Inf. Systems Mid Sweden University Östersund Sweden Dept. of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798400705625

ISBN: (纸本)9798350376012

AI and Machine Learning (ML) models are increasingly used as (critical) components in software systems, even safety-critical ones. This puts new demands on the degree to which we need to test them and requires new and expanded testing methods. Recent boundary-value identification methods have been developed and shown to automatically find boundary candidates for traditional, non-ML software: pairs of nearby inputs that result in (highly) differing outputs. These can be shown to developers and testers, who can judge if the boundary is where it is supposed to ***, we explore how this method can identify decision boundaries of ML classification models. The resulting ML Boundary Spanning Algorithm (ML-BSA) is a search-based method extending previous work in two main ways. We empirically evaluate ML-BSA on seven ML datasets and show that it better spans and thus better identifies the entire classification boundary(ies). The diversity objective helps spread out the boundary pairs more broadly and evenly. This, we argue, can help testers and developers better judge where a classification boundary actually is, compare to expectations, and then focus further testing, validation, and even further training and model refinement on parts of the boundary where behaviour is not ideal.

关键词： Training Conferences Machine learning Fuzzing Software systems Classification algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Building Collaborative Learning: Exploring Social Annotation in Introductory Programming

Building Collaborative Learning: Exploring Social Annotation...

引用

Software engineering: Software engineering Education and Training (ICSE-SEET), IEEE/ACM International Conference on

作者： Francisco Gomes De Oliveira Neto Felix Dobslaw Dept. of Computer Science and Engineering Chalmers and the University of Gothenburg Gothenburg Sweden Dept. of Quality Mngmt Communication and Inf. Systems Mid Sweden University Östersund Sweden

ISBN: (数字)9798400704987

ISBN: (纸本)9798350352115

The increasing demand for software engineering education presents learning challenges in courses due to the diverse range of topics that require practical applications, such as programming or software design, all of which are supported by group work and interaction. Social Annotation (SA) is an approach to teaching that can enhance collaborative learning among students. In SA, both students and teachers utilize platforms like Feedback Fruits, Perusall, and Diigo to collaboratively annotate and discuss course materials. This approach encourages students to share their thoughts and answers with their peers, fostering a more interactive learning environment. We share our experience of implementing social annotation via Perusall as a preparatory tool for lectures in an introductory programming course aimed at undergraduate students in Software engineering. We report the impact of Perusall on the examination results of 112 students. Our results show that 81% of students engaged in meaningful social annotation successfully passed the course. Notably, the proportion of students passing the exam tends to rise as they complete more Perusall assignments. In contrast, only 56% of students who did not participate in Perusall discussions managed to pass the exam. We did not enforce mandatory Perusall participation in the course. Yet, the feedback from our course evaluation questionnaire reveals that most students ranked Perusall among their favorite components of the course and that their interest in the subject has increased.

关键词： Training Software design Annotations Federated learning Buildings Programming profession Software engineering

来源：评论

学校读者我要写书评

暂无评论

RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers

arXiv

引用

arXiv 2023年

作者： Seth, Pratinav Goel, Rashi Mathur, Komal Vemulapalli, Swetha Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Data Science & Computer Applications Dept. of Computer Science & Engineering Dept. of Information and Communication Technology India

This paper describes our approach to submissions made at Shared Task 2 at BLP Workshop - Sentiment Analysis of Bangla Social Media Posts(Hasan et al., 2023a;Islam et al., 2021;Hasan et al., 2023b). Sentiment Analysis is an action research area in the digital age. With the rapid and constant growth of online social media sites and services and the increasing amount of textual data, the application of automatic Sentiment Analysis is on the rise. However, most of the research in this domain is based on the English language. Despite being the world's sixth most widely spoken language, little work has been done in Bangla. This task aims to promote work on Bangla Sentiment Analysis while identifying the polarity of social media content by determining whether the sentiment expressed in the text is Positive, Negative, or Neutral. Our approach consists of experimenting and finetuning various multilingual and pre-trained BERT-based models on our downstream tasks and using a Majority Voting and Weighted ensemble model that outperforms individual baseline model scores. Our system scored 0.711 for the multiclass classification task and scored 10th place among the participants on the leaderboard for the shared task. Our code is available at https://***/ptnv-s/RSM-NLP-BLP-Task2. Copyright © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Study of Fiber Optic Sensor for Various Biomedical Applications

Study of Fiber Optic Sensor for Various Biomedical Applicati...

引用

IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)

作者： Joyline Germine D’Sa Poojith Kumar Ullal Srajana Srajana Sushanth Maroli Nikhil Shetty Dept. of Computer Science and Engineering Sahyadri College of Engineering & Management Adyar Mangalore India Dept. of Electronics and Communication Engineering Sahyadri College of Engineering & Management Adyar Mangalore India

Fiber optic sensors have been widely used in various biomedical applications due to their high sensitivity, reliability, and non-invasiveness. In this paper, we propose a novel approach to designing an optical sensor for detecting impurities in a mixture. The proposed sensor utilizes a flexible polymer layer and an optical fiber cable to detect variations in the power of the adulterated mixture. The polymer layer is made of PDMS, which swells or shrinks in response to the level of adulteration present in the mixture. As a result, the intensity of the output spectra changes, which can be used to detect impurities. The sensor's results will be compared with those obtained from the pure mixture to evaluate its accuracy. In conclusion, the proposed sensor has several advantages, such as low cost, easy to handle, ease of fabrication, and high sensitivity, making it a promising candidate for detecting impurities in various mixtures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Art of Rare Pattern Discovery Techniques in Data Mining

Art of Rare Pattern Discovery Techniques in Data Mining

引用

Information Technologies and communications (GCITC), Global Conference on

作者： Mahendra M Adarsha S P Anant Saraswat D Nagaraju Dept. Of Computer Science and Engineering Sanskrithi School of Engineering Puttaparthi Andhra Pradesh India Dept. Of Electronics and Communication Engineering Sanskrithi School of Engineering Puttaparthi Andhra Pradesh India

In the current era, data analysis has become an integral part of decision-making processes. Data is collected from various sources, such as cloud warehouses, for decision-making and subjected to different classifications and data mining algorithms. One of the most crucial tasks in data mining is rare item set mining, which employs different association-based techniques and threshold values to uncover hidden data in the form of patterns. The research paper provides a comprehensive overview of the latest rare pattern mining techniques and their applications, which can be highly beneficial in achieving efficient and effective decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Four-element MIMO Antenna Array for 5G Smartwatches

A Four-element MIMO Antenna Array for 5G Smartwatches

引用

Asia-Pacific Conference on Microwave

作者： Hsin-Lung Su Jun-Yi Jiang Hong-Zhan Huang Dept. Computer and Communication National Pingtung University Pingtung City Taiwan Dept. Computer Science and Information Engineering National Pingtung University Pingtung City Taiwan

This paper presents a simple structure four-element multiple-input multiple-output (MIMO) antenna array for 5G smartwatch applications. Each antenna is a simple F-shaped microstrip line structure. The neutralization line is loaded between two antennas to improve the isolation. The operating bandwidth of the single antenna covers the 5G new radio (NR) bands n77 and n78 with 6-dB impedance bandwidth. The isolation is higher than 10 dB. Furthermore, the proposed MIMO smartwatch antenna array is fabricated and measured.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Bengali abusive text classification: Using Deep Learning Techniques

Automated Bengali abusive text classification: Using Deep Le...

引用

Advances in Electronics, communication, Computing and Intelligent Information systems (ICAECIS), International Conference on

作者： Showni Rudra Titli Shimul Paul Dept. Electronics and Communication Engineering National Institute of Technology Calicut India Dept. Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh

In recent years, the breakdown of most human causes that hampers a large number of people is verbal abuse. The most noticeable fact is that most of the verbal abuse is made online by people behind the screen. While this problem has occurred with growing modern technologies, a modern solution is needed to solve the drawback. The growing rate of abusive comments and hate speech online is rapidly increasing on a large scale, and manual reports and corrections cannot help this critical situation. This proposed model introduces automation of the hate speech filtering process through deep learning. This work uses only Bengali datasets to find the real classification, as many Bengali and English mixed research works are available in this field. Using the intelligent automated classification of text comments in a limited resource-constrained language (example: Bengali) is critical for several reasons. This proposed system classifies 'Personal Offensive Text', 'Geographical Offensive Text', 'Religious Offensive text', 'Crime Offensive Text', 'Entertainment, Sports, Meme Tiktok, and others'. By combining two large datasets for this research and employing Bengali BERT, the best feasible outcome has been *** paper indicates the complete results of the combined two different datasets and classified into nine segments, while the proposed Bengali BERT models achieved the highest accuracy of 0.706 and a weighted f1 score of 0.705 in the identification and classification tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Change Bit-dept. Procedure for Data Measured Preprocessing before Compression

Change Bit-Depth Procedure for Data Measured Preprocessing b...

引用

2022 IEEE International Multi-Conference on engineering, computer and Information Sciences, SIBIRCON 2022

作者： Levenets, Alexey V. Bondarenko, Vladislav V. Bahenov, Ruslan I. Belozerov, Oleg I. Belozerova, Svetlana I. Bogatenkov, Sergey A. Pacific National University Dept. Automation and System Engineering Khabarovsk Russia Sholom-Aleichem Priamursky State University Dept. Information Systems and Mathematics Birobidzhan Russia Far Eastern State Transport University Dept. Computer Technology and Computer Graphics Khabarovsk Russia South Ural State University Dept. Information Technology in Economics Chelyabinsk Russia

ISBN: (纸本)9781665464802

The paper proposes to change the bit-dept. of the original data sequence as a preprocessing of the measuring data, which is carried out before the compression procedure. In this case the digit capacity conversion is performed without accounting for the primary data sample boundaries. The simulation was carried out in the Matlab software environment. The findings of the authors' research are presented. They prove to be a promising approach for some types of the studied data at least and several digit capacity values. The analysis of autocorrelation function values showing the data correlation revealed by the conversion is used as an assessment of perspective of the active conversion. In this article the authors review the values of secondary maximums of autocorrelation function. Their occurrence shows the demonstration of the implied correlative correspondence. Such correlations can potentially allow the converted data to be compressed more effectively than the original data using the known compression methods. © 2022 IEEE.

关键词： Data compression

来源：评论

学校读者我要写书评

暂无评论

A New Proposed Data Security Model in Cloud Computing Environment

A New Proposed Data Security Model in Cloud Computing Enviro...

引用

computer, Electronics & Electrical engineering & their Applications (IC2E3), International Conference on

作者： Pallab Banerjee Vishal Prasad Kanika Thakur Probal Banerjee Dept. of Computer Science Engineering Amity University Jharkhand Ranchi India Dept. of Electronics and Communication Engineering Govt. Polytechnic Ranchi Jharkhand India

Advancement in the environment of cloud computing has rapidly increases over the past years. In cloud computing protection of data utilizing centralized resources has arisen because of a growing number of businesses storing their data int the cloud helps them easily to access their data easily. The major issues faced by users nowadays, the safety and fetching of user cloud data is arisen rapidly. In this proposed algorithm, the user's data is encrypted using the advanced encryption standards algorithm, and the encrypted data is then performed with some xor operations in cypher block chaining mode using a secret key known only to the data owner to increase confidentiality and security level. If the user does not provide a secret key, the system can generate one on its own.

关键词：

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：