scholarly journals A three-stage quality diagnosis platform for laser-based manufacturing processes

2020 ◽  
Vol 110 (11-12) ◽  
pp. 2991-3003
Author(s):  
Panagiotis Stavropoulos ◽  
Alexios Papacharalampopoulos ◽  
John Stavridis ◽  
Kyriakos Sampatakakis
Keyword(s):  
Technical Assistance ◽  
Image Data ◽  
Real Data ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Web Based ◽  
Learning Techniques ◽  
Weld Defect ◽  
Readiness Level ◽  
Quality Diagnosis

Abstract Diagnosis systems for laser processing are being integrated into industry. However, their readiness level is still questionable under the prism of the Industry’s 4.0 design principles for interoperability and intuitive technical assistance. This paper presents a novel multifunctional, web-based, real-time quality diagnosis platform, in the context of a laser welding application, fused with decision support, data visualization, storing, and post-processing functionalities. The platform’s core considers a quality assessment module, based upon a three-stage method which utilizes feature extraction and machine learning techniques for weld defect detection and quality prediction. A multisensorial configuration streams image data from the weld pool to the module in which a statistical and geometrical method is applied for selecting the input features for the classification model. A Hidden Markov Model is then used to fuse this information with earlier results for a decision to be made on the basis of maximum likelihood. The outcome is fed through web services in a tailored User Interface. The platform’s operation has been validated with real data.

Twitter sentiment analysis for the estimation of voting intention in the 2017 Chilean elections

2020 ◽  
Vol 24 (5) ◽  
pp. 1141-1160
Author(s):  
Tomás Alegre Sepúlveda ◽  
Brian Keith Norambuena
Keyword(s):  
Machine Learning ◽  
Support Vector Machines ◽  
Sentiment Analysis ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Traditional Methods ◽  
Actual Result ◽  
Learning Techniques ◽  
Vector Machines

In this paper, we apply sentiment analysis methods in the context of the first round of the 2017 Chilean elections. The purpose of this work is to estimate the voting intention associated with each candidate in order to contrast this with the results from classical methods (e.g., polls and surveys). The data are collected from Twitter, because of its high usage in Chile and in the sentiment analysis literature. We obtained tweets associated with the three main candidates: Sebastián Piñera (SP), Alejandro Guillier (AG) and Beatriz Sánchez (BS). For each candidate, we estimated the voting intention and compared it to the traditional methods. To do this, we first acquired the data and labeled the tweets as positive or negative. Afterward, we built a model using machine learning techniques. The classification model had an accuracy of 76.45% using support vector machines, which yielded the best model for our case. Finally, we use a formula to estimate the voting intention from the number of positive and negative tweets for each candidate. For the last period, we obtained a voting intention of 35.84% for SP, compared to a range of 34–44% according to traditional polls and 36% in the actual elections. For AG we obtained an estimate of 37%, compared with a range of 15.40% to 30.00% for traditional polls and 20.27% in the elections. For BS we obtained an estimate of 27.77%, compared with the range of 8.50% to 11.00% given by traditional polls and an actual result of 22.70% in the elections. These results are promising, in some cases providing an estimate closer to reality than traditional polls. Some differences can be explained due to the fact that some candidates have been omitted, even though they held a significant number of votes.

scholarly journals Detecting Suspicious Texts Using Machine Learning Techniques

2020 ◽  
Vol 10 (18) ◽  
pp. 6527 ◽  
Author(s):  
Omar Sharif ◽  
Mohammed Moshiul Hoque ◽  
A. S. M. Kayes ◽  
Raza Nowrozy ◽  
Iqbal H. Sarker
Keyword(s):  
Machine Learning ◽  
Instant Messaging ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Text Documents ◽  
Digital Platforms ◽  
Malicious Activity ◽  
Internet Users ◽  
Learning Techniques ◽  
The Web

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents has been growing enormously in recent years through instant messaging, social networking posts, blogs, online portals and other digital platforms. Unfortunately, the misapplication of technologies has increased with this rapid growth of online content, which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio, or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier ‘tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

scholarly journals A Study of University Website Content Classification Using Machine Learning

2021 ◽  
Vol 2129 (1) ◽  
pp. 012043
Author(s):  
H R Mohd Sharul ◽  
I Nor Azman ◽  
M Mohd Su Elya
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Web Pages ◽  
Web Content ◽  
Web Based ◽  
Content Classification ◽  
Learning Techniques ◽  
Information Products ◽  
Website Content ◽  
New Framework

Abstract A university website is a gateway to the institution’s information, products, and services. As websites grow into millions in numbers, it is essential to ensure that the content reflects the needs of its students, staff, and other academic institution as their primary users. This research investigates the development of a new framework that uses machine learning techniques based on webometrics and web usability to classify the web pages of academic websites automatically. The framework briefly introduced how it can help classify web content and eliminate unrelated content and reduce storage space. The findings can also be used to analyse other web-based data to give additional insights that may be beneficial for webometrics studies and identify university website’ characteristics.

scholarly journals Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas

2020 ◽  
Vol 13 (1-2) ◽  
pp. 43-52
Author(s):  
Boudewijn van Leeuwen ◽  
Zalán Tobak ◽  
Ferenc Kovács
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Land Use ◽  
Land Cover ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Land Use Land Cover ◽  
Learning Techniques

AbstractClassification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image.

scholarly journals Efficient Machine Learning Techniques to Diagnose and Predict Alzheimer’s disease

2020 ◽  
Vol 9 (3) ◽  
pp. 3953-3960
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Diagnosis ◽  
Image Data ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Mechanisms ◽  
Learning Techniques

Recent research in computational engineering have evidenced the design and development numerous intelligent models to analyze medical data and derive inferences related to early diagnosis and prediction of disease severity. In this context, prediction and diagnosis of fatal neurodegenerative diseases that comes under the class of dementia from medical image data is considered as the challenging area of research for many researchers. Recently Alzheimer’s disease is considered as major category of dementia that affects major population. Despite of the development of numerous machine learning models for early diagnosis of Alzheimer’s disease, it is observed that there is a lot more scope of research. Addressing the same, this article presents a systematic literature review of machine learning techniques developed for early diagnosis of Alzheimer’s disease. Furthermore this article includes major categories of machine learning algorithms that include artificial neural networks, Support vector machines and Deep learning based ensemble models that helps the budding researchers to explore the scope of research in predicting Alzheimer’s disease. Implementation results depict the comparative analysis of state of art machine learning mechanisms.

Automatic Extraction of Conceptual Maps From Design Team Documents

2010 ◽  
Author(s):  
Sharad Oberoi ◽  
Dong Nguyen ◽  
Susan Finger ◽  
Carolyn Penstein Rose´
Keyword(s):  
Latent Dirichlet Allocation ◽  
Machine Learning Techniques ◽  
Design Team ◽  
Sources Of Information ◽  
Multiple Sources ◽  
Engineering Project ◽  
Web Based ◽  
Learning Techniques ◽  
Conceptual Maps ◽  
Big Picture

Most engineering project classes expect teams of students to collaborate and to build on existing knowledge to accomplish their project goals. As the project evolves, the team is expected to develop a shared understanding. However, students often become overwhelmed by the amount of information available and lose sight of the big picture. Instructors may also find it difficult to keep track of individual and team activities and are often forced to evaluate the product instead of the learning process. This paper presents preliminary results from a tool that supports effective knowledge management for engineering design projects. This framework, called DesignWebs, automatically extracts conceptual maps from the team’s evolving set of documents and discussions about an engineering artifact. It uses Latent Dirichlet Allocation, hierarchical clustering, and other machine learning techniques to generate a navigable web-based graph. Both instructors and students can browse this graph interactively to explore the concepts embedded inside design team documents and the connections between them. An experiment performed on documents obtained from a project course shows the effectiveness of DesignWebs in synthesizing the design knowledge from multiple sources of information in engineering project teams.

Analysis of Intrusion Detection and Classification using Machine Learning Approaches

2017 ◽  
Vol 3 (10) ◽  
Author(s):  
Anjum Khan ◽  
Anjana Nigam
Keyword(s):  
Machine Learning ◽  
Network Security ◽  
Intrusion Detection ◽  
Detection System ◽  
Real Data ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
High Detection Rate ◽  
Learning Techniques ◽  
Result Analysis

 As the network primarily based applications are growing quickly, the network security mechanisms need a lot of attention to enhance speed and preciseness. The ever evolving new intrusion types cause a significant threat to network security. Though varied network security tools are developed, however the quick growth of intrusive activities continues to be a significant issue. Intrusion detection systems (IDSs) are wont to detect intrusive activities on the network. Analysis showed that application of machine learning techniques in intrusion detection might reach high detection rate. Machine learning and classification algorithms facilitate to design “Intrusion Detection Models” which might classify the network traffic into intrusive or traditional traffic. This paper discusses some usually used machine learning techniques in Intrusion Detection System and conjointly reviews a number of the prevailing machine learning IDS proposed by researchers at different times. in this paper an experimental analysis is performed to demonstrate the performance analysis of some existing techniques in order that they will be used further in developing Hybrid Classifier for real data packets classification. The given result analysis shows that KNN, RF and SVM performs best for NSL-KDD dataset.

Sign in / Sign up

Export Citation Format

Share Document