检索结果-内蒙古大学图书馆

28th Americas Conference on Information Systems, AMCIS 2022

作者： Lindström, Nataliya Berbyuk Asatiani, Aleksandre Staron, Miroslaw Söder, Ola Department of Applied Information Technology University of Gothenburg Sweden Department of Computer Science and Engineering Chalmers & University of Gothenburg Sweden Axis Communications Lund Sweden

ISBN: (纸本)9781958200001

While software metrics are indispensable for quality assurance, using metrics in practice is complicated. Quality, productivity, speed, and efficiency are important factors to be considered in software development (Holmstrom et al. 2006;Svensson 2005). Measuring correct metrics and using them in the right and transparent way contributes to pushing development in a desirable direction, leading to achieving projected goals and outcomes (Staron and Meding 2018). On the other hand, tracking the wrong metrics, and failing to interpret and communicate them properly results in a stressful work environment, conflicts, distrust, lower engagement, and decreased productivity (de Sá Leitão Júnior 2018;Ellis et al. 1991;Staron 2012). To ensure proper and effective use of metrics in organizations, successful communication around metrics is essential (Lindström et al. 2021;Post et al. 2002;Staron and Meding 2015). The purpose of this study is to understand and improve communication about metrics in contexts of contemporary software development practice in organizations. This is achieved by identifying the bottlenecks in the process of communication around metrics and how to overcome them in practice. Drawing on 38 semi-structured interviews and interactive workshops with metrics teams members and stakeholders from three organizations, we identify three interrelated challenges including limited knowledge about metrics and lack of terminology, uncoordinated use of multiple communication channels, and sensitivity of metrics, which influence workplace communication, trust, and performance. Our study shows the importance of developing metrics terminology to ensure the development of a shared understanding of metrics. Further, raising awareness about the affordances such channels as dashboards, email, MS Teams meetings/chat, stand up meetings, reports, etc., commonly used in software organizations, and how they can be combined to successfully transfer information about metrics is essent

关键词： Terminology

来源：评论

学校读者我要写书评

暂无评论

Comparison of Machine Learning Algorithm for Stock Price Prediction Using Sentiment Analysis

Comparison of Machine Learning Algorithm for Stock Price Pre...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Anuradha Yenkikar C. Narendra Babu Department of Computer Science and Engineering Ramaiah University of Applied Sciences Bangalore Karnataka India Pune Institute of Computer Technology Pune India

Forecasting companies' stock market prices are one the interesting topics for analysts and researchers. Although a company's stock price can be unpredictable, long-term forecasts can help but it is dependent on many factors such as the company's business model, change in leadership, and investors' mood. It has been found to be insufficient to predict stock values just on the basis of historical data or textual information. Previous research in sentiment analysis have shown a strong correlation between the movement of stock prices and the publication of news stories. At different levels, a number of sentiment analysis research have been attempted utilizing methods. In this paper, we made a comparison of various Machine Learning methods on five datasets of financial news related to the company and domains in which the company. Encouraging results are obtained using 13 models i.e., Linear Regression, Ridge Regression, Lasso Regression, Random Forest, Naive Bayes, Logistic Regression, LSTM, ARIMA, Logistic Regression, Support Vector Machines, Decision Tree, Boosted Tree, and ensemble method which depict polarity of news articles being positive or negative and the accuracies are 93.90%, 92.31 %, 92.27%, 85.44%, 84.65%, 84.65%, 94.73%, 90.13%, 82%, 83%, 72%, 70%, 95.11 % respectively.

关键词： Support vector machines Sentiment analysis Neural networks Companies Predictive models Prediction algorithms Stock markets

来源：评论

学校读者我要写书评

暂无评论

Transcription for Thai Traditional Medicine Texts with Wav2Vec2

Transcription for Thai Traditional Medicine Texts with Wav2V...

引用

International Electrical Engineering Congress (iEECON)

作者： Jettasic Popun Wilaiporn Lee Akara Prayote Kanabadee Srisomboon Luepol Pipanmekaporn Department of Computer and Information Science Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

Recently, Automatic Speech Recognition (ASR) technology is widely used for communication convenience in converting speech to text. Initial surveys reveal that existing studies on ASR, both in Thai and foreign languages, focus on contemporary language communication, lacking support for specialized vocabulary. Thai Traditional Medicine (TTM) contain ancient medical terminology recorded in various media such as palm leaves, parchment, notebooks, and inscriptions. Centuries of textual preservation have led to text degradation. Given the suitability of ASR study to accommodate medical terminology and ancient languages, it is proposed to apply it to convert original Thai Traditional Medicine texts into contemporary language, aiding experts in reading and interpreting them. ASR involves converting speech signals into text. In this paper, we propose an end-to-end speech recognition approach for Thai Traditional Medical texts leveraging self-supervised learning (SSL) to overcome the limitations of limited labeled data. We utilize a transformer-based model pre-trained (XLSR-Wav2Vec) on unlabeled TTM texts speech data using SSL techniques and fine-tune it with a small dataset of labeled TTM texts audio-text pairs. Due to the absence of a Thai Traditional Medicine vocabulary repository, a dataset comprising text and speech is developed, consisting of 1,800 training sentences and 200 test sentences randomly selected from recordings of 10 Thai Traditional Medicine experts. Offline evaluation methods are employed, resulting in improved accuracy rates. Future efforts will focus on expanding the speech dataset to enhance recognition accuracy further. This study lays the groundwork for efficiently extracting knowledge from Thai Traditional Medicine prescriptions, ensuring the preservation of this valuable heritage for future generations.

关键词： Training Surveys Vocabulary Accuracy Terminology Self-supervised learning Speech enhancement Transformers Automatic speech recognition Speech to text

来源：评论

学校读者我要写书评

暂无评论

A Comparison and Evaluation of Named Entity Recognition Methods in Thai Traditional Medicine Texts

A Comparison and Evaluation of Named Entity Recognition Meth...

引用

International Electrical Engineering Congress (iEECON)

作者： Warodom Phungjununt Wilaiporn Lee Akara Prayote Luepol Pipanmekaporn Kanabadee Srisomboon Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Computer and Information Science Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

The knowledge extraction and transliteration processes for the Thai traditional medicine documents requires experts to extract information from the textbook and spend a plenty of time. To reduce the complexity of these processes, the named entity recognition (NER) from the machine learning principle is applied to extract the key information from the document. In this work, three NER models including, CRFSuite, Bi-LSTM-CRF, and pre-trained model (WangchanBERTa) are considered the accuracy of each model of NER for the Thai traditional documents. After the testing process, the experimental results show that CRFSuite model is the most computationally efficient model and deliver high precision and recall. Moreover, CRFSuite model has the highest scores of each entity. While the accuracy of the WangchanBERTa model is the highest and faster convergence in the training process. Although the results from the Bi-LSTM-CRF model provide moderate accuracy, the Bi-LSTM-CRF can detect the common entities higher than other models.

关键词： Training Accuracy Computational modeling Named entity recognition Machine learning Real-time systems Computational efficiency Data mining Testing Convergence

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based UAVs Trajectory Optimization for Maximum Communication Coverage of Users 4

Deep Reinforcement Learning Based UAVs Trajectory Optimizati...

引用

4th International Conference on Advances in computer technology, Information science and Communications, CTISC 2022

作者： Zhao, Yueyue Sun, Xuemei Liu, Yanjing Yang, Qingyong Tiangong University School of Computer Science and Technology Tianjin China Tianjin Sino-German University of Applied Acience School of Software and Communication Tianjin China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

With its flexibility and easy deployment, UAV can timely provide communication for areas with damaged infrastructure. However, due to some constraints of the UAV itself, such as limited energy and limited communication range, designing reasonable trajectory for UAV to improve the system performance has been studied. Considering UAV energy and user movement, we propose a deep reinforcement learning-based method of maximizing the number of users covered and saving energy (MUSE) to control UAVs. By observing system state, then the UAVs perform the optimal actions to maximize service users and prolong this network lifetime by maximizing the system reward. Simulation experiments show that the algorithm is superior to Q-learning in maximizing service users, moreover, with increasing number of UVAs, the system energy consumption is stable, which achieves the purpose of saving energy. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Based Multi-Retinal Disease Diagnosis and Classification Framework

引用

computers, Materials & Continua 2022年第12期73卷 5543-5557页

作者： Thavavel Vaiyapuri S.Srinivasan Mohamed Yacin Sikkandar T.S.Balaji Seifedine Kadry Maytham N.Meqdad Yunyoung Nam College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Saveetha School of Engineering Saveetha Institute of Medical and Technical SciencesSaveetha NagarThandalamChennai602105India Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Saveetha School of Engineering Saveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering College of Engineering&TechnologySRM Institute of Science and TechnologyVadapalani CampusChennai600026India Department of Applied Data Science Noroff University CollegeKristiansand4608Norway Department of Computer Techniques Engineering Al-Mustaqbal University CollegeHillahBabil51001Iraq Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea

In past decades,retinal diseases have become more common and affect people of all age grounds over the *** examining retinal eye disease,an artificial intelligence(AI)based multilabel classification model is needed for automated *** analyze the retinal malady,the system proposes a multiclass and multi-label arrangement ***,the classification frameworks based on features are explicitly described by ophthalmologists under the application of domain knowledge,which tends to be time-consuming,vulnerable generalization ability,and unfeasible in massive ***,the automated diagnosis of multi-retinal diseases becomes essential,which can be solved by the deep learning(DL)*** this motivation,this paper presents an intelligent deep learningbased multi-retinal disease diagnosis(IDL-MRDD)framework using fundus *** proposed model aims to classify the color fundus images into different classes namely AMD,DR,Glaucoma,Hypertensive Retinopathy,Normal,Others,and Pathological ***,the artificial flora algorithm with Shannon’s function(AFA-SF)basedmulti-level thresholding technique is employed for image segmentation and thereby the infected regions can be properly *** addition,SqueezeNet based feature extractor is employed to generate a collection of feature ***,the stacked sparse Autoencoder(SSAE)model is applied as a classifier to distinguish the input images into distinct retinal *** efficacy of the IDL-MRDD technique is carried out on a benchmark multi-retinal disease dataset,comprising data instances from different *** experimental values pointed out the superior outcome over the existing techniques with the maximum accuracy of 0.963.

关键词： Multi-retinal disease computer aided diagnosis fundus images deep learning segmentation intelligent models

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Framwork for Classification and Detection of Anomaly Based Network Intrusion using NSL-KDD Dataset 3

An Efficient Deep Learning Framwork for Classification and D...

引用

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Mehrotra, Parth Dwivedi, Uttkarsh G.L. Bajaj Institute of Technology and Management Department of Computer Science and Enginnering Gr. Noida India G.L. Bajaj Institute of Technology and Management Department of Applied Computer Science and Enginnering Gr. Noida India

ISBN: (纸本)9798331519582

The past few years have seen unprecedented growth in the realms of technology and networking, as well as the proliferation of Internet services across all industries and regions. Because of rising instances of piracy and the compromise of several cutting-edge systems, it is crucial that we build information security tools capable of identifying emerging threats. An Intrusion Detection System (IDS) that use deep learning (DL) methods to identify network anomalies is a crucial piece of information security technology. The purpose of this study is to look at DL techniques and see if they can be used in an anomaly-based IDS. The purpose of this research is to employ a hybrid model Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), & and (Convolutional Neural Networks (CNN) to identify the unknown assault package in a state-of-the-art IDS with high network performance. Standard classification metrics were used to evaluate DL models trained on the NSL-KDD dataset. These metrics included recall, f1- score, precision, and accuracy of categorization. We used the NSL-KDD dataset to fit and assess the flow. The model's outstanding producing abilities and excellent incursion identification performance are made possible by these data characteristics. Attack detection in the NSL-KDD dataset may be accomplished in two ways: binary classification and multiclass classification. Positive outcomes have been seen when applying the suggested strategy to multiclass classification (98% accuracy) and binary classification (99.99 percent accuracy). IDS have shown encouraging results from experiments using deep IDS models. According on the results of the research, the proposed approach outperforms the competing methodologies. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Neural Network for Recognizing Exercise Activity Using Inertial Sensor and Motion Capture System 4

A Hybrid Deep Learning Neural Network for Recognizing Exerci...

引用

4th International Conference on Big Data Analytics and Practices, IBDAP 2023

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350300192

The recognition of human activities holds great significance in the fields of AI and human-computer interaction studies. Human activity recognition (HAR) finds extensive application, including in behavioral assessment, gesture identification, fall detection, and gait evaluation. Recent strides in wearable technology and AI have showcased the potential to accurately classify movement events for HAR, achieved by analyzing time-series data collected from wearable sensors. This study focuses on deep learning networks, particularly CNN and LSTM, to extract spatial and temporal features from wearable sensor data for efficient exercise activity classification. A comprehensive assessment compared two sensor data types: 3-axis linear acceleration from IMUs and 3D acceleration from MOCAP markers. Findings highlight comparable accuracy between IMUs and MOCAP in exercise identification. The hybrid CNN-LSTM demonstrated high efficacy, achieving remarkable F1-scores of 98.85% for IMU and 98.23% for MOCAP data. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Deep Learning Robustness for Sensor-based Human Activity Recognition 46

A Comparative Study of Deep Learning Robustness for Sensor-b...

引用

46th International Conference on Telecommunications and Signal Processing, TSP 2023

作者： Mekruksavanich, Sakorn Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350303964

Recognition of human activities has become a highly significant area of research in the current era of the Internet of Things and A.I. technologies. Human activity recognition (HAR) plays a crucial role in monitoring and analyzing human behaviors using various types of sensors. Such sensor-based HAR systems are being used in various industry domains, including healthcare, professional sports, and worker assessment in intelligent factories. The integration of micro electronics mechanical systems sensor technology in smart wearable devices has significantly improved the capabilities of HAR using machine learning and deep learning techniques. However, processing longtime dependent sequence samples with noisy data is still a significant challenge, affecting the classification time and accuracy. This study aimed to analyze noise-tolerant deep learning models for recognizing physical activities from noisy smartphone data. The study analyzed the recognition performances of the five most popular deep learning networks for HAR under different levels of Gaussian noise. The results indicated that the BiGRU network demonstrated outstanding robustness to Gaussian noise of different levels. © 2023 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Application of CRISP-DM and DMME to a Case Study of Condition Monitoring of Lens Coating Machines 6

Application of CRISP-DM and DMME to a Case Study of Conditio...

引用

6th IEEE International Workshop on Metrology for Industry 4.0 and IoT, MetroInd4.0 and IoT 2023

作者： Butt, Fatima Sajid Schafer, Jorg Wagner, Matthias F. Stegelmeyer, Dirk Oteiza, David Gomez-Ullate Frankfurt University of Applied Sciences Indas Faculty 2 of Computer Science and Engineering Germany Universidad de Cádiz Escuela Superior de Ingeniería Cádiz11001 Spain Ie University School of Science and Technology Madrid28006 Spain

ISBN: (纸本)9798350396577

Condition monitoring industrial machinery by using data mining in industrial projects has been extensively extended in the last few years. Applying data science to industrial processes should be straightforward in theory, but very few instances in the literature deal with the actual practical issues encountered while carrying out industrial data science projects. The case study discussed in this paper was pursued in accordance with the steps outlined in the standard CRISP-DM (CRoss-Industry Standard Process for Data Mining) including its latest holistic approach for engineering applications called DMME (Data Mining Methodology for Engineering Applications). The industrial data was acquired as part of industrial cooperation from multiple anti-reflective lens coating machines. Various deep learning (DL) models like long short-term memory (LSTM), and machine learning (ML) models like Decision Trees and Support Vector Machines (SVM) were used as proof of concept for confirming the domain understanding of the process experts. Our main contribution is the description of deficiencies and gaps of the standard process framework CRISP-DM based on the issues faced in implementing each phase of the process in a real world case study. In addition, we propose future research ideas to close these gaps. This complements findings in the literature on gaps in CRISP-DM and DMME. © 2023 IEEE.

关键词： Data mining

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：