Search results for: predictive data mining

Authors: H. S. Saini, K. Vijayalakshmi, Rishi Sayal

Abstract:

Network-based education has been growing rapidly in size and quality. Knowledge clustering becomes more important in personalized information retrieval for web-learning. A personalized-Learning service after the learners’ knowledge has been classified with clustering. Through automatic analysis of learners’ behaviors, their partition with similar data level and interests may be discovered so as to produce learners with contents that best match educational needs for collaborative learning. We present a specific mining tool and a recommender engine that we have integrated in the online learning in order to help the teacher to carry out the whole e-learning process. We propose to use sequential pattern mining algorithms to discover the most used path by the students and from this information can recommend links to the new students automatically meanwhile they browse in the course. We have Developed a specific author tool in order to help the teacher to apply all the data mining process. We tend to report on many experiments with real knowledge so as to indicate the quality of using both clustering and sequential pattern mining algorithms together for discovering personalized e-learning systems.

Keywords: e-learning, cluster, personalization, sequence, pattern

Procedia PDF Downloads 406

Authors: Shahin Mirshekari, Mohammadreza Moradi, Hossein Jafari, Mehdi Jafari, Mohammad Ensaf

Abstract:

This research employs Gaussian Process Regression (GPR) with an ensemble kernel, integrating Exponential Squared, Revised Matern, and Rational Quadratic kernels to analyze pharmaceutical sales data. Bayesian optimization was used to identify optimal kernel weights: 0.76 for Exponential Squared, 0.21 for Revised Matern, and 0.13 for Rational Quadratic. The ensemble kernel demonstrated superior performance in predictive accuracy, achieving an R² score near 1.0, and significantly lower values in MSE, MAE, and RMSE. These findings highlight the efficacy of ensemble kernels in GPR for predictive analytics in complex pharmaceutical sales datasets.

Keywords: Gaussian process regression, ensemble kernels, bayesian optimization, pharmaceutical sales analysis, time series forecasting, data analysis

Procedia PDF Downloads 47

Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem

Abstract:

In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.

Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data

Procedia PDF Downloads 140

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Due to increasing cost pressure in global markets, artificial intelligence is becoming a technology that is decisive for competition. Predictive quality enables machinery and plant manufacturers to ensure product quality by using data-driven forecasts via machine learning models as a decision-making basis for test results. The use of cross-process Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: predictive quality, hydraulics, machine learning, classification, supervised learning

Procedia PDF Downloads 208

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 35

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 364

Authors: E. Fathallahi Aghdam, V. Hosseini

Abstract:

Environmental pollution is not limited to a specific region or country; that is why sustainable development, as a necessary process for improvement, pays attention to issues such as destruction of natural resources, degradation of biological system, global pollution, and climate change in the world, especially in the developing countries. According to the World Health Organization, as a developing city, Tehran (capital of Iran) is one of the most polluted cities in the world in terms of air pollution. In this study, three pollutants including particulate matter less than 10 microns, nitrogen oxides, and sulfur dioxide were evaluated in Tehran using data mining techniques and through Crisp approach. The data from 21 air pollution measuring stations in different areas of Tehran were collected from 1999 to 2013. Commercial softwares Clementine was selected for this study. Tehran was divided into distinct clusters in terms of the mentioned pollutants using the software. As a data mining technique, clustering is usually used as a prologue for other analyses, therefore, the similarity of clusters was evaluated in this study through analyzing local conditions, traffic behavior, and industrial activities. In fact, the results of this research can support decision-making system, help managers improve the performance and decision making, and assist in urban studies.

Keywords: data mining, clustering, air pollution, crisp approach

Procedia PDF Downloads 410

Authors: Samuel Munaf, Kevin Swingler, Franz Brülisauer, Anthony O’Hare, George Gunn, Aaron Reeves

Abstract:

Web scraping and text mining are popular computer science methods deployed by public health researchers to augment traditional epidemiological surveillance. However, within veterinary disease surveillance, such techniques are still in the early stages of development and have not yet been fully utilised. This study presents an exploration into the utility of incorporating internet-based data to better understand the smallholder farming communities within Scotland by using online text extraction and the subsequent mining of this data. Web scraping of the livestock fora was conducted in conjunction with text mining of the data in search of common themes, words, and topics found within the text. Results from bi-grams and topic modelling uncover four main topics of interest within the data pertaining to aspects of livestock husbandry: feeding, breeding, slaughter, and disposal. These topics were found amongst both the poultry and pig sub-forums. Topic modeling appears to be a useful method of unsupervised classification regarding this form of data, as it has produced clusters that relate to biosecurity and animal welfare. Internet data can be a very effective tool in aiding traditional veterinary surveillance methods, but the requirement for human validation of said data is crucial. This opens avenues of research via the incorporation of other dynamic social media data, namely Twitter and Facebook/Meta, in addition to time series analysis to highlight temporal patterns.

Keywords: veterinary epidemiology, disease surveillance, infodemiology, infoveillance, smallholding, social media, web scraping, sentiment analysis, geolocation, text mining, NLP

Procedia PDF Downloads 72

Authors: Akshay Agrawal, Anand K. Srivastava

Abstract:

The increasing amount of XML datasets available to casual users increases the necessity of investigating techniques to extract knowledge from these data. Data mining is widely applied in the database research area in order to extract frequent correlations of values from both structured and semi-structured datasets. The increasing availability of heterogeneous XML sources has raised a number of issues concerning how to represent and manage these semi structured data. In recent years due to the importance of managing these resources and extracting knowledge from them, lots of methods have been proposed in order to represent and cluster them in different ways.

Keywords: XML, similarity measure, clustering, cluster quality, semantic clustering

Procedia PDF Downloads 353

Authors: Ayliana Dharmawan, Heng Yong Sheng, Zhang Xiaojin, Tan Thai Lian

Abstract:

To facilitate discharge planning, doctors are presently required to assign an Estimated Discharge Date (EDD) for each patient admitted to the hospital. This assignment of the EDD is largely based on the doctor’s judgment. This can be difficult for cases which are complex or relatively new to the doctor. It is hypothesized that a data-driven approach would be able to facilitate the doctors to make accurate estimations of the discharge date. Making use of routinely collected data on inpatient discharges between January 2013 and May 2016, a predictive model was developed using machine learning techniques to predict the Length of Stay (and hence the EDD) of inpatients, at the point of admission. The predictive performance of the model was compared to that of the clinicians using accuracy measures. Overall, the best performing model was found to be able to predict EDD with an accuracy improvement in Average Squared Error (ASE) by -38% as compared to the first EDD determined by the present method. It was found that important predictors of the EDD include the provisional diagnosis code, patient’s age, attending doctor at admission, medical specialty at admission, accommodation type, and the mean length of stay of the patient in the past year. The predictive model can be used as a tool to accurately predict the EDD.

Keywords: inpatient, estimated discharge date, EDD, prediction, data-driven

Procedia PDF Downloads 150

Authors: Diego Rodrigues, Marcelo Lisboa, Elismar Batista, Marcos Dias

Abstract:

Based on data on child labor, this work arises questions about how to understand and locate the factors that make up the child labor rates, and which properties are important to analyze these cases. Using data mining techniques to discover valid patterns on Brazilian social databases were evaluated data of child labor in the State of Tocantins (located north of Brazil with a territory of 277000 km2 and comprises 139 counties). This work aims to detect factors that are deterministic for the practice of child labor and their relationships with financial indicators, educational, regional and social, generating information that is not explicit in the government database, thus enabling better monitoring and updating policies for this purpose.

Keywords: social data, government decision making, association of social data, data mining

Procedia PDF Downloads 347

Authors: S. Cencek, A. Markun

Abstract:

Noise assessment methods are regularly used in scope of Environmental Impact Assessments for planned projects to assess (predict) the expected noise emissions of these projects. Different noise assessment methods could be used. In recent years, we had an opportunity to collaborate in some noise assessment procedures where noise assessments of different laboratories have been performed simultaneously. We identified some significant differences in noise assessment results between laboratories in Slovenia. We estimate that despite good input Georeferenced Data to set up acoustic model exists in Slovenia; there is no clear consensus on methods for predictive noise methods for planned projects. We analyzed input data, methods and results of predictive noise methods for two planned industrial projects, both were done independently by two laboratories. We also analyzed the data, methods and results of two interlaboratory collaborative noise models for two existing noise sources (railway and motorway). In cases of predictive noise modelling, the validations of acoustic models were performed by noise measurements of surrounding existing noise sources, but in varying durations. The acoustic characteristics of existing buildings were also not described identically. The planned noise sources were described and digitized differently. Differences in noise assessment results between different laboratories have ranged up to 10 dBA, which considerably exceeds the acceptable uncertainty ranged between 3 to 6 dBA. Contrary to predictive noise modelling, in cases of collaborative noise modelling for two existing noise sources the possibility to perform the validation noise measurements of existing noise sources greatly increased the comparability of noise modelling results. In both cases of collaborative noise modelling for existing motorway and railway, the modelling results of different laboratories were comparable. Differences in noise modeling results between different laboratories were below 5 dBA, which was acceptable uncertainty set up by interlaboratory noise modelling organizer. The lessons learned from the study were: 1) Predictive noise calculation using formulae from International standard SIST ISO 9613-2: 1997 is not an appropriate method to predict noise emissions of planned projects since due to complexity of procedure they are not used strictly, 2) The noise measurements are important tools to minimize noise assessment errors of planned projects and should be in cases of predictive noise modelling performed at least for validation of acoustic model, 3) National guidelines should be made on the appropriate data, methods, noise source digitalization, validation of acoustic model etc. in order to unify the predictive noise models and their results in scope of Environmental Impact Assessments for planned projects.

Keywords: environmental noise assessment, predictive noise modelling, spatial planning, noise measurements, national guidelines

Procedia PDF Downloads 214

Authors: Reza Mohammadzadeh

Abstract:

The major challenges in geotechnical engineering in underground spaces arise from uncertainties and different probabilities. The collection, collation, and collaboration of existing data to incorporate them in analysis and design for given prospect evaluation would be a reliable, practical problem solving method under uncertainty. Machine learning (ML) is a subfield of artificial intelligence in statistical science which applies different techniques (e.g., Regression, neural networks, support vector machines, decision trees, random forests, genetic programming, etc.) on data to automatically learn and improve from them without being explicitly programmed and make decisions and predictions. In this paper, a conceptual database schema of geotechnical risks in underground coal mining based on a cloud system architecture has been designed. A new approach of risk assessment using a three-dimensional risk matrix supported by the level of knowledge (LoK) has been proposed in this model. Subsequently, the model workflow methodology stages have been described. In order to train data and LoK models deployment, an ML platform has been implemented. IBM Watson Studio, as a leading data science tool and data-driven cloud integration ML platform, is employed in this study. As a Use case, a data set of geotechnical hazards and risk assessment in underground coal mining were prepared to demonstrate the performance of the model, and accordingly, the results have been outlined.

Keywords: data model, geotechnical risks, machine learning, underground coal mining

Procedia PDF Downloads 249

Authors: Kwan Hee Han

Abstract:

External environment of enterprise is rapidly changing majorly by global competition, cost reduction pressures, and new technology. In these situations, production scheduling function plays a critical role to meet customer requirements and to attain the goal of operational efficiency. It deals with short-term decision making in the production process of the whole supply chain. The major task of production scheduling is to seek a balance between customer orders and limited resources. In manufacturing companies, this task is so difficult because it should efficiently utilize resource capacity under the careful consideration of many interacting constraints. At present, many computerized software solutions have been utilized in many enterprises to generate a realistic production schedule to overcome the complexity of schedule generation. However, most production scheduling systems do not provide sufficient information about the validity of the generated schedule except limited statistics. Process mining only recently emerged as a sub-discipline of both data mining and business process management. Process mining techniques enable the useful analysis of a wide variety of processes such as process discovery, conformance checking, and bottleneck analysis. In this study, the performance of generated production schedule is evaluated by mining event log data of production scheduling software system by using the process mining techniques since every software system generates event logs for the further use such as security investigation, auditing and error bugging. An application of process mining approach is proposed for the validation of the goodness of production schedule generated by scheduling software systems in this study. By using process mining techniques, major evaluation criteria such as utilization of workstation, existence of bottleneck workstations, critical process route patterns, and work load balance of each machine over time are measured, and finally, the goodness of production schedule is evaluated. By using the proposed process mining approach for evaluating the performance of generated production schedule, the quality of production schedule of manufacturing enterprises can be improved.

Keywords: data mining, event log, process mining, production scheduling

Procedia PDF Downloads 259

Authors: Lubabatu Sada Sodangi

Abstract:

The rapid growth in exchange and accessibility of information via the internet makes many organisations acquire data on their own operation. The aim of data mining is to analyse the different behaviour of a dataset using observation. Although, the subset of the dataset being analysed may not display all the behaviours and relationships of the entire data and, therefore, may not represent other parts that exist in the dataset. There is a range of techniques used in data mining to determine the hidden or unknown information in datasets. In this paper, the performance of two algorithms Chi-Square Automatic Interaction Detection (CHAID) and multilayer perceptron (MLP) would be matched using an Adult dataset to find out the percentage of an/the adults that earn > 50k and those that earn <= 50k per year. The two algorithms were studied and compared using IBM SPSS statistics software. The result for CHAID shows that the most important predictors are relationship and education. The algorithm shows that those are married (husband) and have qualification: Bachelor, Masters, Doctorate or Prof-school whose their age is > 41<57 earn > 50k. Also, multilayer perceptron displays marital status and capital gain as the most important predictors of the income. It also shows that individuals that their capital gain is less than 6,849 and are single, separated or widow, earn <= 50K, whereas individuals with their capital gain is > 6,849, work > 35 hrs/wk, and > 27yrs their income will be > 50k. By comparing the two algorithms, it is observed that both algorithms are reliable but there is strong reliability in CHAID which clearly shows that relation and education contribute to the prediction as displayed in the data visualisation.

Keywords: data mining, CHAID, multi-layer perceptron, SPSS, Adult dataset

Procedia PDF Downloads 361

Authors: Azzaya Enkhjargal

Abstract:

Context: The mining industry has a long history of human rights abuses, including forced labor, environmental pollution, and displacement of communities. In recent years, there has been growing international pressure to hold mining companies accountable for these abuses. Research Aim: This study explores the legal liabilities of mining companies for human rights abuses. The study specifically examines the case of Erdenet Mining Corporation (EMC), a large mining company in Mongolia that has been accused of human rights abuses. Methodology: The study used a mixed-methods approach, which included a review of legal literature, interviews with community members and NGOs, and a case study of EMC. Findings: The study found that mining companies can be held liable for human rights abuses under a variety of regulatory frameworks, including soft law and self-regulatory instruments in the mining industry, international law, national law, and corporate law. The study also found that there are a number of challenges to holding mining companies accountable for human rights abuses, including the lack of effective enforcement mechanisms and the difficulty of proving causation. Theoretical Importance: The study contributes to the growing body of literature on the legal liabilities of mining companies for human rights abuses. The study also provides insights into the challenges of holding mining companies accountable for human rights abuses. Data Collection: The data for the study was collected through a variety of methods, including a review of legal literature, interviews with community members and NGOs, and a case study of EMC. Analysis Procedures: The data was analyzed using a variety of methods, including content analysis, thematic analysis, and case study analysis. Conclusion: The study concludes that mining companies can be held liable for human rights abuses under a variety of legal and regulatory frameworks. There are positive developments in ensuring greater accountability and protection of affected communities and the environment in countries with a strong economy. Regrettably, access to avenues of redress is reasonably low in less developed countries, where the governments have not implemented a robust mechanism to enforce liability requirements in the mining industry. The study recommends that governments and mining companies take more ambitious steps to enhance corporate accountability.

Keywords: human rights, human rights abuses, ESG, litigation, Erdenet Mining Corporation, corporate social responsibility, soft law, self-regulation, mining industry, parent company liability, sustainability, environment, UN

Procedia PDF Downloads 57

Authors: Novutry Siregar, Afdal, Emilzon Taslim

Abstract:

Hyaline Membrane Disease (HMD) is the main cause of respiratory failure in preterm neonates caused by surfactant deficiency. Nasal Continuous Positive Airway Pressure (NCPAP) is the therapy for HMD. The success of therapy is determined by gestational age, birth weight, HMD grade, time of NCAP administration, and time of breathing frequency recovery. The aim of this research is to identify the predictive factor of NCPAP therapy success in preterm neonates with HMD. This study used a cross-sectional design by using medical records of patients who were treated in the Perinatology of the Pediatric Department of Dr. M. Djamil Padang Central Hospital from January 2015 to December 2017. The samples were eighty-two neonates that were selected by using the total sampling technique. Data analysis was done by using the Chi-Square Test and the Multiple Logistic Regression Prediction Model. The results showed the success rate of NCPAP therapy reached 53.7%. Birth weight (p = 0.048, OR = 3.34 95% CI 1.01-11.07), HMD grade I (p = 0.018, OR = 4.95 CI 95% 1.31-18.68), HMD grade II (p = 0.044, OR = 5.52 95% CI 1.04-29.15), and time of breathing frequency recovery (p = 0,000, OR = 13.50 95% CI 3.58-50, 83) are the predictive factors of NCPAP therapy success in preterm neonates with HMD. The most significant predictive factor is the time of breathing frequency recovery.

Keywords: predictive factors, the success of therapy, NCPAP, preterm neonates, HMD

Procedia PDF Downloads 36

Authors: Rabia Bashir, Sajjad Akbar

Abstract:

There is an inevitable demand of web mining due to rapid increase of huge information on the Internet, but the striking variety of web structures has made required content retrieval a difficult task. To counter this issue, Web Content Mining (WCM) emerges as a potential candidate which extracts and integrates suitable resources of data to users. In past few years, research has been done on several extraction techniques for WCM i.e. agent-based, template-based, assumption-based, statistic-based, wrapper-based and machine learning. However, it is still unclear that either these approaches are efficiently tackling the significant challenges of WCM or not. To answer this question, this paper identifies these challenges such as language independency, structure flexibility, performance, automation, dynamicity, redundancy handling, intelligence, relevant content retrieval, and privacy. Further, mapping of these challenges is done with existing extraction mechanisms which helps to adopt the most suitable WCM approach, given some conditions and characteristics at hand.

Keywords: content mining challenges, web content mining, web content extraction approaches, web information retrieval

Procedia PDF Downloads 525

Authors: Beng Yew Low, Cher Liang Cha, Cheng Yong Teoh

Abstract:

Due to a lack of continual assessment or grade related data, identifying first-year engineering students in a polytechnic education at risk of failing is challenging. Our experience over the years tells us that there is no strong correlation between having good entry grades in Mathematics and the Sciences and excelling in hardcore engineering subjects. Hence, identifying students at risk of failure cannot be on the basis of entry grades in Mathematics and the Sciences alone. These factors compound the difficulty of early identification and intervention. This paper describes the development of a predictive analytics model in the early detection of students at risk of failing and evaluates its effectiveness. Data from continual assessments conducted in term one, supplemented by data of student psychological profiles such as interests and study habits, were used. Three classification techniques, namely Logistic Regression, K Nearest Neighbour, and Random Forest, were used in our predictive model. Based on our findings, Random Forest was determined to be the strongest predictor with an Area Under the Curve (AUC) value of 0.994. Correspondingly, the Accuracy, Precision, Recall, and F-Score were also highest among these three classifiers. Using this Random Forest Classification technique, students at risk of failure could be identified at the end of term one. They could then be assigned to a Learning Support Programme at the beginning of term two. This paper gathers the results of our findings. It also proposes further improvements that can be made to the model.

Keywords: continual assessment, predictive analytics, random forest, student psychological profile

Procedia PDF Downloads 110

Authors: Bruno Vilić Belina, Jadranko Matuško

Abstract:

The rapid development of cyber-physical systems significantly influences modern control systems introducing a whole new range of applications of control systems but also putting them under new challenges to ensure their resiliency to possible cyber attacks, either in the form of data integrity attacks or deception attacks. This paper presents a model predictive approach to the control of cyber-physical systems robust to cyber attacks. We assume that a cyber attack can be modelled as an additive disturbance that acts in the measuring channel. For such a system, we designed a tube-based predictive controller based. The performance of the designed controller has been verified in Matlab/Simulink environment.

Keywords: control systems, cyber attacks, resiliency, robustness, tube based model predictive control

Procedia PDF Downloads 46

Authors: Takashi Shimizu, Tomoaki Hashimoto

Abstract:

Recently, crystal growth technologies have made progress by the requirement for the high quality of crystal materials. To control the crystal growth dynamics actively by external forces is useuful for reducing composition non-uniformity. In this study, a control method based on model predictive control using thermal inputs is proposed for crystal growth dynamics of semiconductor materials. The control system of crystal growth dynamics considered here is governed by the continuity, momentum, energy, and mass transport equations. To establish the control method for such thermal fluid systems, we adopt model predictive control known as a kind of optimal feedback control in which the control performance over a finite future is optimized with a performance index that has a moving initial time and terminal time. The objective of this study is to establish a model predictive control method for crystal growth dynamics of semiconductor materials.

Keywords: model predictive control, optimal control, process control, crystal growth

Procedia PDF Downloads 338

Authors: Allmin Susaiyah, Aki Härmä, Milan Petković

Abstract:

Automatic generation of insights from data using insight mining systems (IMS) is useful in many applications, such as personal health tracking, patient monitoring, and business process management. Existing IMS face challenges in controlling insight extraction, scaling to large databases, and generalising to unseen domains. In this work, we propose a hybrid approach consisting of rule-based and neural components for generating insights from data while overcoming the aforementioned challenges. Firstly, a rule-based data 2CNL component is used to extract statistically significant insights from data and represent them in a controlled natural language (CNL). Secondly, a BERTSum-based CNL2NL component is used to convert these CNLs into natural language texts. We improve the model using task-specific and domain-specific fine-tuning. Our approach has been evaluated using statistical techniques and standard evaluation metrics. We overcame the aforementioned challenges and observed significant improvement with domain-specific fine-tuning.

Keywords: data mining, insight mining, natural language generation, pre-trained language models

Procedia PDF Downloads 84

Authors: Emin Gundogar, Burak Erkayman, Nusret Sazak

Abstract:

Providing effective management performance through the whole supply chain is critical issue and hard to applicate. The proper evaluation of integrated data may conclude with accurate information. Analysing the supply chain data through OLAP (On-Line Analytical Processing) technologies may provide multi-angle view of the work and consolidation. In this study, association rules and classification techniques are applied to measure the supply chain performance metrics of an automotive manufacturer in Turkey. Main criteria and important rules are determined. The comparison of the results of the algorithms is presented.

Keywords: supply chain performance, performance measurement, data mining, automotive

Procedia PDF Downloads 487

Authors: Faisal Alshuwaier, Ali Areshey

Abstract:

Text mining techniques are generally applied for classifying the text, finding fuzzy relations and structures in data sets. This research provides plenty text mining capabilities. One common application is text classification and event extraction, which encompass deducing specific knowledge concerning incidents referred to in texts. The main contribution of this paper is the clarification of a concept graph generation mechanism, which is based on a text classification and optimal fuzzy relationship extraction. Furthermore, the work presented in this paper explains the application of fuzzy relationship extraction and branch and bound method to simplify the texts.

Keywords: extraction, max-prod, fuzzy relations, text mining, memberships, classification, memberships, classification

Procedia PDF Downloads 554

Authors: Oktavian Prasetia Wardana, Martono Tri Utomo, Risa Etika, Kartika Darma Handayani, Dina Angelika, Wurry Ayuningtyas

Abstract:

Background: Critically ill neonates are newborn babies with high-risk factors that potentially cause disability and/or death. Scoring systems for determining the severity of the disease have been widely developed as well as some designs for use in neonates. The SNAPPE-II method, which has been used as a mortality predictor scoring system in several referral centers, was found to be slow in assessing the outcome of critically ill neonates in the Neonatal Intensive Care Unit (NICU). Objective: To analyze the predictive value of MSNS on the outcome of critically ill neonates at the time of arrival up to 24 hours after being admitted to the NICU. Methods: A longitudinal observational analytic study based on medical record data was conducted from January to August 2022. Each sample was recorded from medical record data, including data on gestational age, mode of delivery, APGAR score at birth, resuscitation measures at birth, duration of resuscitation, post-resuscitation ventilation, physical examination at birth (including vital signs and any congenital abnormalities), the results of routine laboratory examinations, as well as the neonatal outcomes. Results: This study involved 105 critically ill neonates who were admitted to the NICU. The outcome of critically ill neonates was 50 (47.6%) neonates died, and 55 (52.4%) neonates lived. There were more males than females (61% vs. 39%). The mean gestational age of the subjects in this study was 33.8 ± 4.28 weeks, with the mean birth weight of the subjects being 1820.31 ± 33.18 g. The mean MSNS score of neonates with a deadly outcome was lower than that of the lived outcome. ROC curve with a cut point MSNS score <10.5 obtained an AUC of 93.5% (95% CI: 88.3-98.6) with a sensitivity value of 84% (95% CI: 80.5-94.9), specificity 80 % (CI 95%: 88.3-98.6), Positive Predictive Value (PPV) 79.2%, Negative Predictive Value (NPV) 84.6%, Risk Ratio (RR) 5.14 with Hosmer & Lemeshow test results p>0.05. Conclusion: The MSNS score has a good predictive value and good calibration of the outcomes of critically ill neonates admitted to the NICU.

Keywords: critically ill neonate, outcome, MSNS, NICU, predictive value

Procedia PDF Downloads 47

Authors: J. K. Alhassan, S. A. Lawal

Abstract:

This work is on decision tree-based classification for the disbursement of scholarship. Tree-based data mining classification technique is used in other to determine the generic rule to be used to disburse the scholarship. The system based on the defined rules from the tree is able to determine the class (status) to which an applicant shall belong whether Granted or Not Granted. The applicants that fall to the class of granted denote a successful acquirement of scholarship while those in not granted class are unsuccessful in the scheme. An algorithm that can be used to classify the applicants based on the rules from tree-based classification was also developed. The tree-based classification is adopted because of its efficiency, effectiveness, and easy to comprehend features. The system was tested with the data of National Information Technology Development Agency (NITDA) Abuja, a Parastatal of Federal Ministry of Communication Technology that is mandated to develop and regulate information technology in Nigeria. The system was found working according to the specification. It is therefore recommended for all scholarship disbursement organizations.

Keywords: classification, data mining, decision tree, scholarship

Procedia PDF Downloads 348

Authors: Sidi Yang, Haiyi Zhang

Abstract:

Twitter is a microblogging platform, where millions of users daily share their attitudes, views, and opinions. Using a probabilistic Latent Dirichlet Allocation (LDA) topic model to discern the most popular topics in the Twitter data is an effective way to analyze a large set of tweets to find a set of topics in a computationally efficient manner. Sentiment analysis provides an effective method to show the emotions and sentiments found in each tweet and an efficient way to summarize the results in a manner that is clearly understood. The primary goal of this paper is to explore text mining, extract and analyze useful information from unstructured text using two approaches: LDA topic modelling and sentiment analysis by examining Twitter plain text data in English. These two methods allow people to dig data more effectively and efficiently. LDA topic model and sentiment analysis can also be applied to provide insight views in business and scientific fields.

Keywords: text mining, Twitter, topic model, sentiment analysis

Procedia PDF Downloads 155

Authors: M. T. Alodat

Abstract:

In this paper, we propose a generalization to the Gaussian process regression(GPR) model called the extended skew Gaussian process for regression(ESGPr) model. The ESGPR model works better than the GPR model when the errors are skewed. We derive the predictive distribution for the ESGPR model at a new input. Also we apply the ESGPR model to FOREX data and we find that it fits the Forex data better than the GPR model.

Keywords: extended skew normal distribution, Gaussian process for regression, predictive distribution, ESGPr model

Procedia PDF Downloads 527

Authors: Philipp Ruf, Massiwa Chabbi, Christoph Reich, Djaffar Ould-Abdeslam

Abstract:

In recent years, convolutional neural networks (CNN) have demonstrated high performance in image analysis, but oftentimes, there is only structured data available regarding a specific problem. By interpreting structured data as images, CNNs can effectively learn and extract valuable insights from tabular data, leading to improved predictive accuracy and uncovering hidden patterns that may not be apparent in traditional structured data analysis. In applying a single neural network for analyzing multimodal data, e.g., both structured and unstructured information, significant advantages in terms of time complexity and energy efficiency can be achieved. Converting structured data into images and merging them with existing visual material offers a promising solution for applying CNN in multimodal datasets, as they often occur in a medical context. By employing suitable preprocessing techniques, structured data is transformed into image representations, where the respective features are expressed as different formations of colors and shapes. In an additional step, these representations are fused with existing images to incorporate both types of information. This final image is finally analyzed using a CNN.

Keywords: CNN, image processing, tabular data, mixed dataset, data transformation, multimodal fusion

Procedia PDF Downloads 93

Authors: Oshin Anand, Atanu Rakshit

Abstract:

The vast increment in the e-commerce ventures makes this area a prominent research stream. Besides several quantified parameters, the textual content of reviews is a storehouse of many information that can educate companies and help them earn profit. This study is an attempt in this direction. The article attempts to categorize data based on a computed metric that quantifies the influencing capacity of reviews rendering two categories of high and low influential reviews. Further, each of these document is studied to conclude several product feature categories. Each of these categories along with the computed metric is converted to linguistic identifiers and are used in an association mining model. The article makes a novel attempt to combine feature attraction with quantified metric to categorize review text and finally provide frequent patterns that depict customer preferences. Frequent mentions in a highly influential score depict customer likes or preferred features in the product whereas prominent pattern in low influencing reviews highlights what is not important for customers. This is achieved using a hybrid approach of text mining for feature and term extraction, sentiment analysis, multicriteria decision-making technique and association mining model.

Keywords: association mining, customer preference, frequent pattern, online reviews, text mining

Procedia PDF Downloads 367