Search results for: predictive mining
1723 Data Mining Approach for Commercial Data Classification and Migration in Hybrid Storage Systems
Authors: Mais Haj Qasem, Maen M. Al Assaf, Ali Rodan
Abstract:
Parallel hybrid storage systems consist of a hierarchy of different storage devices that vary in terms of data reading speed performance. As we ascend in the hierarchy, data reading speed becomes faster. Thus, migrating the application’ important data that will be accessed in the near future to the uppermost level will reduce the application I/O waiting time; hence, reducing its execution elapsed time. In this research, we implement trace-driven two-levels parallel hybrid storage system prototype that consists of HDDs and SSDs. The prototype uses data mining techniques to classify application’ data in order to determine its near future data accesses in parallel with the its on-demand request. The important data (i.e. the data that the application will access in the near future) are continuously migrated to the uppermost level of the hierarchy. Our simulation results show that our data migration approach integrated with data mining techniques reduces the application execution elapsed time when using variety of traces in at least to 22%.Keywords: hybrid storage system, data mining, recurrent neural network, support vector machine
Procedia PDF Downloads 3021722 Trauma Scores and Outcome Prediction After Chest Trauma
Authors: Mohamed Abo El Nasr, Mohamed Shoeib, Abdelhamid Abdelkhalik, Amro Serag
Abstract:
Background: Early assessment of severity of chest trauma, either blunt or penetrating is of critical importance in prediction of patient outcome. Different trauma scoring systems are widely available and are based on anatomical or physiological parameters to expect patient morbidity or mortality. Up till now, there is no ideal, universally accepted trauma score that could be applied in all trauma centers and is suitable for assessment of severity of chest trauma patients. Aim: Our aim was to compare various trauma scoring systems regarding their predictability of morbidity and mortality in chest trauma patients. Patients and Methods: This study was a prospective study including 400 patients with chest trauma who were managed at Tanta University Emergency Hospital, Egypt during a period of 2 years (March 2014 until March 2016). The patients were divided into 2 groups according to the mode of trauma: blunt or penetrating. The collected data included age, sex, hemodynamic status on admission, intrathoracic injuries, and associated extra-thoracic injuries. The patients outcome including mortality, need of thoracotomy, need for ICU admission, need for mechanical ventilation, length of hospital stay and the development of acute respiratory distress syndrome were also recorded. The relevant data were used to calculate the following trauma scores: 1. Anatomical scores including abbreviated injury scale (AIS), Injury severity score (ISS), New injury severity score (NISS) and Chest wall injury scale (CWIS). 2. Physiological scores including revised trauma score (RTS), Acute physiology and chronic health evaluation II (APACHE II) score. 3. Combined score including Trauma and injury severity score (TRISS ) and 4. Chest-Specific score Thoracic trauma severity score (TTSS). All these scores were analyzed statistically to detect their sensitivity, specificity and compared regarding their predictive power of mortality and morbidity in blunt and penetrating chest trauma patients. Results: The incidence of mortality was 3.75% (15/400). Eleven patients (11/230) died in blunt chest trauma group, while (4/170) patients died in penetrating trauma group. The mortality rate increased more than three folds to reach 13% (13/100) in patients with severe chest trauma (ISS of >16). The physiological scores APACHE II and RTS had the highest predictive value for mortality in both blunt and penetrating chest injuries. The physiological score APACHE II followed by the combined score TRISS were more predictive for intensive care admission in penetrating injuries while RTS was more predictive in blunt trauma. Also, RTS had a higher predictive value for expectation of need for mechanical ventilation followed by the combined score TRISS. APACHE II score was more predictive for the need of thoracotomy in penetrating injuries and the Chest-Specific score TTSS was higher in blunt injuries. The anatomical score ISS and TTSS score were more predictive for prolonged hospital stay in penetrating and blunt injuries respectively. Conclusion: Trauma scores including physiological parameters have a higher predictive power for mortality in both blunt and penetrating chest trauma. They are more suitable for assessment of injury severity and prediction of patients outcome.Keywords: chest trauma, trauma scores, blunt injuries, penetrating injuries
Procedia PDF Downloads 4171721 A Data Mining Approach for Analysing and Predicting the Bank's Asset Liability Management Based on Basel III Norms
Authors: Nidhin Dani Abraham, T. K. Sri Shilpa
Abstract:
Asset liability management is an important aspect in banking business. Moreover, the today’s banking is based on BASEL III which strictly regulates on the counterparty default. This paper focuses on prediction and analysis of counter party default risk, which is a type of risk occurs when the customers fail to repay the amount back to the lender (bank or any financial institutions). This paper proposes an approach to reduce the counterparty risk occurring in the financial institutions using an appropriate data mining technique and thus predicts the occurrence of NPA. It also helps in asset building and restructuring quality. Liability management is very important to carry out banking business. To know and analyze the depth of liability of bank, a suitable technique is required. For that a data mining technique is being used to predict the dormant behaviour of various deposit bank customers. Various models are implemented and the results are analyzed of saving bank deposit customers. All these data are cleaned using data cleansing approach from the bank data warehouse.Keywords: data mining, asset liability management, BASEL III, banking
Procedia PDF Downloads 5441720 The Extended Skew Gaussian Process for Regression
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 5461719 A Web Service-Based Framework for Mining E-Learning Data
Authors: Felermino D. M. A. Ali, S. C. Ng
Abstract:
E-learning is an evolutionary form of distance learning and has become better over time as new technologies emerged. Today, efforts are still being made to embrace E-learning systems with emerging technologies in order to make them better. Among these advancements, Educational Data Mining (EDM) is one that is gaining a huge and increasing popularity due to its wide application for improving the teaching-learning process in online practices. However, even though EDM promises to bring many benefits to educational industry in general and E-learning environments in particular, its principal drawback is the lack of easy to use tools. The current EDM tools usually require users to have some additional technical expertise to effectively perform EDM tasks. Thus, in response to these limitations, this study intends to design and implement an EDM application framework which aims at automating and simplify the development of EDM in E-learning environment. The application framework introduces a Service-Oriented Architecture (SOA) that hides the complexity of technical details and enables users to perform EDM in an automated fashion. The framework was designed based on abstraction, extensibility, and interoperability principles. The framework implementation was made up of three major modules. The first module provides an abstraction for data gathering, which was done by extending Moodle LMS (Learning Management System) source code. The second module provides data mining methods and techniques as services; it was done by converting Weka API into a set of Web services. The third module acts as an intermediary between the first two modules, it contains a user-friendly interface that allows dynamically locating data provider services, and running knowledge discovery tasks on data mining services. An experiment was conducted to evaluate the overhead of the proposed framework through a combination of simulation and implementation. The experiments have shown that the overhead introduced by the SOA mechanism is relatively small, therefore, it has been concluded that a service-oriented architecture can be effectively used to facilitate educational data mining in E-learning environments.Keywords: educational data mining, e-learning, distributed data mining, moodle, service-oriented architecture, Weka
Procedia PDF Downloads 2331718 Trace Logo: A Notation for Representing Control-Flow of Operational Process
Authors: M. V. Manoj Kumar, Likewin Thomas, Annappa
Abstract:
Process mining research discipline bridges the gap between data mining and business process modeling and analysis, it offers the process-centric and end-to-end methods/techniques for analyzing information of real-world process detailed in operational event-logs. In this paper, we have proposed a notation called trace logo for graphically representing control-flow perspective (order of execution of activities) of process. A trace logo consists of a stack of activity names at each position, sizes of the activity name indicates their frequency in the traces and the total height of the activity depicts the information content of the position. A trace logo created from a set of aligned traces generated using Multiple Trace Alignment technique.Keywords: consensus trace, process mining, multiple trace alignment, trace logo
Procedia PDF Downloads 3421717 Data-Mining Approach to Analyzing Industrial Process Information for Real-Time Monitoring
Authors: Seung-Lock Seo
Abstract:
This work presents a data-mining empirical monitoring scheme for industrial processes with partially unbalanced data. Measurement data of good operations are relatively easy to gather, but in unusual special events or faults it is generally difficult to collect process information or almost impossible to analyze some noisy data of industrial processes. At this time some noise filtering techniques can be used to enhance process monitoring performance in a real-time basis. In addition, pre-processing of raw process data is helpful to eliminate unwanted variation of industrial process data. In this work, the performance of various monitoring schemes was tested and demonstrated for discrete batch process data. It showed that the monitoring performance was improved significantly in terms of monitoring success rate of given process faults.Keywords: data mining, process data, monitoring, safety, industrial processes
Procedia PDF Downloads 3911716 Predicting Medical Check-Up Patient Re-Coming Using Sequential Pattern Mining and Association Rules
Authors: Rizka Aisha Rahmi Hariadi, Chao Ou-Yang, Han-Cheng Wang, Rajesri Govindaraju
Abstract:
As the increasing of medical check-up popularity, there are a huge number of medical check-up data stored in database and have not been useful. These data actually can be very useful for future strategic planning if we mine it correctly. In other side, a lot of patients come with unpredictable coming and also limited available facilities make medical check-up service offered by hospital not maximal. To solve that problem, this study used those medical check-up data to predict patient re-coming. Sequential pattern mining (SPM) and association rules method were chosen because these methods are suitable for predicting patient re-coming using sequential data. First, based on patient personal information the data was grouped into … groups then discriminant analysis was done to check significant of the grouping. Second, for each group some frequent patterns were generated using SPM method. Third, based on frequent patterns of each group, pairs of variable can be extracted using association rules to get general pattern of re-coming patient. Last, discussion and conclusion was done to give some implications of the results.Keywords: patient re-coming, medical check-up, health examination, data mining, sequential pattern mining, association rules, discriminant analysis
Procedia PDF Downloads 6341715 Predictive Maintenance Based on Oil Analysis Applicable to Transportation Fleets
Authors: Israel Ibarra Solis, Juan Carlos Rodriguez Sierra, Ma. del Carmen Salazar Hernandez, Isis Rodriguez Sanchez, David Perez Guerrero
Abstract:
At the present paper we try to explain the analysis techniques use for the lubricating oil in a maintenance period of a city bus (Mercedes Benz Boxer 40), which is call ‘R-24 route’, line Coecillo Centro SA de CV in Leon Guanajuato, to estimate the optimal time for the oil change. Using devices such as the rotational viscometer and the atomic absorption spectrometer, they can detect the incipient form when the oil loses its lubricating properties and, therefore, cannot protect the mechanical components of diesel engines such these trucks. Timely detection of lost property in the oil, it allows us taking preventive plan maintenance for the fleet.Keywords: atomic absorption spectrometry, maintenance, predictive velocity rate, lubricating oils
Procedia PDF Downloads 5601714 Process Mining as an Ecosystem Platform to Mitigate a Deficiency of Processes Modelling
Authors: Yusra Abdulsalam Alqamati, Ahmed Alkilany
Abstract:
The teaching staff is a distinct group whose impact is on the educational process and which plays an important role in enhancing the quality of the academic education process. To improve the management effectiveness of the academy, the Teaching Staff Management System (TSMS) proposes that all teacher processes be digitized. Since the BPMN approach can accurately describe the processes, it lacks a clear picture of the process flow map, something that the process mining approach has, which is extracting information from event logs for discovery, monitoring, and model enhancement. Therefore, these two methodologies were combined to create the most accurate representation of system operations, the ability to extract data records and mining processes, recreate them in the form of a Petri net, and then generate them in a BPMN model for a more in-depth view of process flow. Additionally, the TSMS processes will be orchestrated to handle all requests in a guaranteed small-time manner thanks to the integration of the Google Cloud Platform (GCP), the BPM engine, and allowing business owners to take part throughout the entire TSMS project development lifecycle.Keywords: process mining, BPM, business process model and notation, Petri net, teaching staff, Google Cloud Platform
Procedia PDF Downloads 1321713 Optimization of Air Pollution Control Model for Mining
Authors: Zunaira Asif, Zhi Chen
Abstract:
The sustainable measures on air quality management are recognized as one of the most serious environmental concerns in the mining region. The mining operations emit various types of pollutants which have significant impacts on the environment. This study presents a stochastic control strategy by developing the air pollution control model to achieve a cost-effective solution. The optimization method is formulated to predict the cost of treatment using linear programming with an objective function and multi-constraints. The constraints mainly focus on two factors which are: production of metal should not exceed the available resources, and air quality should meet the standard criteria of the pollutant. The applicability of this model is explored through a case study of an open pit metal mine, Utah, USA. This method simultaneously uses meteorological data as a dispersion transfer function to support the practical local conditions. The probabilistic analysis and the uncertainties in the meteorological conditions are accomplished by Monte Carlo simulation. Reasonable results have been obtained to select the optimized treatment technology for PM2.5, PM10, NOx, and SO2. Additional comparison analysis shows that baghouse is the least cost option as compared to electrostatic precipitator and wet scrubbers for particulate matter, whereas non-selective catalytical reduction and dry-flue gas desulfurization are suitable for NOx and SO2 reduction respectively. Thus, this model can aid planners to reduce these pollutants at a marginal cost by suggesting control pollution devices, while accounting for dynamic meteorological conditions and mining activities.Keywords: air pollution, linear programming, mining, optimization, treatment technologies
Procedia PDF Downloads 2011712 Did Nature of Job Matters - Impact of Perceived Job Autonomy on Turnover Intention in Sales and Marketing Managers: Moderating Effect of Procedural and Distributive Justice
Authors: Muhammad Babar Shahzad
Abstract:
The purpose of our study is to investigate the relationship between perceived job autonomy and turnover intention in sales & marketing staff. Perceived job autonomy is considered one of most studied dimension of Job Characteristic Model. But still there is a confusion in scholars about predictive role of perceived job autonomy in turnover intention. In line of more complex research on this relation, we investigated the relationship between perceived job autonomy and turnover intention. Did nature of job have any impact on this relationship. On the call of different authors we take interactive effect of perceived job autonomy and procedural justice on turnover intention. Predictive role of distributive justice to employee outcomes is not deniable. But predictive role of distributive justice will be prone in different contextual influences. Interactive role of distributive justice and perceived job autonomy is also not tested before. We collected date from 279 marketing and sales managers working in financial institution, FMCG industries, Pharamesutical Industry & Bank. Strong and direct negative relation was found in perceived job autonomy, distributive justice & procedural justice on turnover intention. Distributive and procedural justice is also amplifying the negative relationship of perceived job autonomy and turnover intention. Limitation and future direction for research is also discussed.Keywords: perceived job autonomy, turnover intention, procedural justice, distributive job
Procedia PDF Downloads 5051711 Innovative Predictive Modeling and Characterization of Composite Material Properties Using Machine Learning and Genetic Algorithms
Authors: Hamdi Beji, Toufik Kanit, Tanguy Messager
Abstract:
This study aims to construct a predictive model proficient in foreseeing the linear elastic and thermal characteristics of composite materials, drawing on a multitude of influencing parameters. These parameters encompass the shape of inclusions (circular, elliptical, square, triangle), their spatial coordinates within the matrix, orientation, volume fraction (ranging from 0.05 to 0.4), and variations in contrast (spanning from 10 to 200). A variety of machine learning techniques are deployed, including decision trees, random forests, support vector machines, k-nearest neighbors, and an artificial neural network (ANN), to facilitate this predictive model. Moreover, this research goes beyond the predictive aspect by delving into an inverse analysis using genetic algorithms. The intent is to unveil the intrinsic characteristics of composite materials by evaluating their thermomechanical responses. The foundation of this research lies in the establishment of a comprehensive database that accounts for the array of input parameters mentioned earlier. This database, enriched with this diversity of input variables, serves as a bedrock for the creation of machine learning and genetic algorithm-based models. These models are meticulously trained to not only predict but also elucidate the mechanical and thermal conduct of composite materials. Remarkably, the coupling of machine learning and genetic algorithms has proven highly effective, yielding predictions with remarkable accuracy, boasting scores ranging between 0.97 and 0.99. This achievement marks a significant breakthrough, demonstrating the potential of this innovative approach in the field of materials engineering.Keywords: machine learning, composite materials, genetic algorithms, mechanical and thermal proprieties
Procedia PDF Downloads 521710 Data-Driven Approach to Predict Inpatient's Estimated Discharge Date
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 1661709 Emotion Classification Using Recurrent Neural Network and Scalable Pattern Mining
Authors: Jaishree Ranganathan, MuthuPriya Shanmugakani Velsamy, Shamika Kulkarni, Angelina Tzacheva
Abstract:
Emotions play an important role in everyday life. An-alyzing these emotions or feelings from social media platforms like Twitter, Facebook, blogs, and forums based on user comments and reviews plays an important role in various factors. Some of them include brand monitoring, marketing strategies, reputation, and competitor analysis. The opinions or sentiments mined from such data helps understand the current state of the user. It does not directly provide intuitive insights on what actions to be taken to benefit the end user or business. Actionable Pattern Mining method provides suggestions or actionable recommendations on what changes or actions need to be taken in order to benefit the end user. In this paper, we propose automatic classification of emotions in Twitter data using Recurrent Neural Network - Gated Recurrent Unit. We achieve training accuracy of 87.58% and validation accuracy of 86.16%. Also, we extract action rules with respect to the user emotion that helps to provide actionable suggestion.Keywords: emotion mining, twitter, recurrent neural network, gated recurrent unit, actionable pattern mining
Procedia PDF Downloads 1591708 Financial Assessment of the Hard Coal Mining in the Chosen Region in the Czech Republic: Real Options Methodology Application
Authors: Miroslav Čulík, Petr Gurný
Abstract:
This paper is aimed at the financial assessment of the hard coal mining in a given region by real option methodology application. Hard coal mining in this mine makes net loss for the owner during the last years due to the long-term unfavourable mining conditions and significant drop in the coal prices during the last years. Management is going to shut down the operation and abandon the project to reduce the loss of the company. The goal is to assess whether the shutting down the operation is the only and correct solution of the problem. Due to the uncertainty in the future hard coal price evolution, the production might be again restarted if the price raises enough to cover the cost of the production. For the assessment, real option methodology is applied, which captures two important aspect of the financial decision-making: risk and flexibility. The paper is structured as follows: first, current state is described and problem is analysed. Next, methodology of real options is described. At last, project is evaluated by applying real option methodology. The results are commented and recommendations are provided.Keywords: real option, investment, option to abandon, option to shut down and restart, risk, flexibility
Procedia PDF Downloads 5421707 Satellite Data to Understand Changes in Carbon Dioxide for Surface Mining and Green Zone
Authors: Carla Palencia-Aguilar
Abstract:
In order to attain the 2050’s zero emissions goal, it is necessary to know the carbon dioxide changes over time either from pollution to attenuations in the mining industry versus at green zones to establish real goals and redirect efforts to reduce greenhouse effects. Two methods were used to compute the amount of CO2 tons in specific mining zones in Colombia. The former by means of NPP with MODIS MOD17A3HGF from years 2000 to 2021. The latter by using MODIS MYD021KM bands 33 to 36 with maximum values of 644 data points distributed in 7 sites corresponding to surface mineral mining of: coal, nickel, iron and limestone. The green zones selected were located at the proximities of the studied sites, but further than 1 km to avoid information overlapping. Year 2012 was selected for method 2 to compare the results with data provided by the Colombian government to determine range of values. Some data was compared with 2022 MODIS energy values and converted to kton of CO2 by using the Greenhouse Gas Equivalencies Calculator by EPA. The results showed that Nickel mining was the least pollutant with 81 kton of CO2 e.q on average and maximum of 102 kton of CO2 e.q. per year, with green zones attenuating carbon dioxide in 103 kton of CO2 on average and 125 kton maximum per year in the last 22 years. Following Nickel, there was Coal with average kton of CO2 per year of 152 and maximum of 188, values very similar to the subjacent green zones with average and maximum kton of CO2 of 157 and 190 respectively. Iron had similar results with respect to 3 Limestone sites with average values of 287 kton of CO2 for mining and 310 kton for green zones, and maximum values of 310 kton for iron mining and 356 kton for green zones. One of the limestone sites exceeded the other sites with an average value of 441 kton per year and maximum of 490 kton per year, eventhough it had higher attenuation by green zones than a close Limestore site (3.5 Km apart): 371 kton versus 281 kton on average and maximum 416 kton versus 323 kton, such vegetation contribution is not enough, meaning that manufacturing process should be improved for the most pollutant site. By comparing bands 33 to 36 for years 2012 and 2022 from January to August, it can be seen that on average the kton of CO2 were similar for mining sites and green zones; showing an average yearly balance of carbon dioxide emissions and attenuation. However, efforts on improving manufacturing process are needed to overcome the carbon dioxide effects specially during emissions’ peaks because surrounding vegetation cannot fully attenuate it.Keywords: carbon dioxide, MODIS, surface mining, vegetation
Procedia PDF Downloads 941706 Predictive Modelling Approaches in Food Processing and Safety
Authors: Amandeep Sharma, Digvaijay Verma, Ruplal Choudhary
Abstract:
Food processing is an activity across the globe that help in better handling of agricultural produce, including dairy, meat, and fish. The operations carried out in the food industry includes raw material quality authenticity; sorting and grading; processing into various products using thermal treatments – heating, freezing, and chilling; packaging; and storage at the appropriate temperature to maximize the shelf life of the products. All this is done to safeguard the food products and to ensure the distribution up to the consumer. The approaches to develop predictive models based on mathematical or statistical tools or empirical models’ development has been reported for various milk processing activities, including plant maintenance and wastage. Recently AI is the key factor for the fourth industrial revolution. AI plays a vital role in the food industry, not only in quality and food security but also in different areas such as manufacturing, packaging, and cleaning. A new conceptual model was developed, which shows that smaller sample size as only spectra would be required to predict the other values hence leads to saving on raw materials and chemicals otherwise used for experimentation during the research and new product development activity. It would be a futuristic approach if these tools can be further clubbed with the mobile phones through some software development for their real time application in the field for quality check and traceability of the product.Keywords: predictive modlleing, ann, ai, food
Procedia PDF Downloads 781705 Predictive Maintenance: Machine Condition Real-Time Monitoring and Failure Prediction
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 3801704 A Framework of Product Information Service System Using Mobile Image Retrieval and Text Mining Techniques
Authors: Mei-Yi Wu, Shang-Ming Huang
Abstract:
The online shoppers nowadays often search the product information on the Internet using some keywords of products. To use this kind of information searching model, shoppers should have a preliminary understanding about their interesting products and choose the correct keywords. However, if the products are first contact (for example, the worn clothes or backpack of passengers which you do not have any idea about the brands), these products cannot be retrieved due to insufficient information. In this paper, we discuss and study the applications in E-commerce using image retrieval and text mining techniques. We design a reasonable E-commerce application system containing three layers in the architecture to provide users product information. The system can automatically search and retrieval similar images and corresponding web pages on Internet according to the target pictures which taken by users. Then text mining techniques are applied to extract important keywords from these retrieval web pages and search the prices on different online shopping stores with these keywords using a web crawler. Finally, the users can obtain the product information including photos and prices of their favorite products. The experiments shows the efficiency of proposed system.Keywords: mobile image retrieval, text mining, product information service system, online marketing
Procedia PDF Downloads 3521703 MP-SMC-I Method for Slip Suppression of Electric Vehicles under Braking
Authors: Tohru Kawabe
Abstract:
In this paper, a new SMC (Sliding Mode Control) method with MP (Model Predictive Control) integral action for the slip suppression of EV (Electric Vehicle) under braking is proposed. The proposed method introduce the integral term with standard SMC gain , where the integral gain is optimized for each control period by the MPC algorithms. The aim of this method is to improve the safety and the stability of EVs under braking by controlling the wheel slip ratio. There also include numerical simulation results to demonstrate the effectiveness of the method.Keywords: sliding mode control, model predictive control, integral action, electric vehicle, slip suppression
Procedia PDF Downloads 5511702 Discriminant Analysis as a Function of Predictive Learning to Select Evolutionary Algorithms in Intelligent Transportation System
Authors: Jorge A. Ruiz-Vanoye, Ocotlán Díaz-Parra, Alejandro Fuentes-Penna, Daniel Vélez-Díaz, Edith Olaco García
Abstract:
In this paper, we present the use of the discriminant analysis to select evolutionary algorithms that better solve instances of the vehicle routing problem with time windows. We use indicators as independent variables to obtain the classification criteria, and the best algorithm from the generic genetic algorithm (GA), random search (RS), steady-state genetic algorithm (SSGA), and sexual genetic algorithm (SXGA) as the dependent variable for the classification. The discriminant classification was trained with classic instances of the vehicle routing problem with time windows obtained from the Solomon benchmark. We obtained a classification of the discriminant analysis of 66.7%.Keywords: Intelligent Transportation Systems, data-mining techniques, evolutionary algorithms, discriminant analysis, machine learning
Procedia PDF Downloads 4591701 Real-Time Mine Safety System with the Internet of Things
Authors: Şakir Bingöl, Bayram İslamoğlu, Ebubekir Furkan Tepeli, Fatih Mehmet Karakule, Fatih Küçük, Merve Sena Arpacık, Mustafa Taha Kabar, Muhammet Metin Molak, Osman Emre Turan, Ömer Faruk Yesir, Sıla İnanır
Abstract:
This study introduces an IoT-based real-time safety system for mining, addressing global safety challenges. The wearable device, seamlessly integrated into miners' jackets, employs LoRa technology for communication and offers real-time monitoring of vital health and environmental data. Unique features include an LCD panel for immediate information display and sound-based location tracking for emergency response. The methodology involves sensor integration, data transmission, and ethical testing. Validation confirms the system's effectiveness in diverse mining scenarios. The study calls for ongoing research to adapt the system to different mining contexts, emphasizing its potential to significantly enhance safety standards in the industry.Keywords: mining safety, internet of things, wearable technology, LoRa, RFID tracking, real-time safety system, safety alerts, safety measures
Procedia PDF Downloads 541700 Predicting Expectations of Non-Monogamy in Long-Term Romantic Relationships
Authors: Michelle R. Sullivan
Abstract:
Positive romantic relationships and marriages offer a buffer against a host of physical and emotional difficulties. Conversely, poor relationship quality and marital discord can have deleterious consequences for individuals and families. Research has described non-monogamy, infidelity, and consensual non-monogamy, as both consequential and causal of relationship difficulty, or as a unique way a couple strives to make a relationship work. Much research on consensual non-monogamy has built on feminist theory and critique. To the author’s best knowledge, to date, no studies have examined the predictive relationship between individual and relationship characteristics and expectations of non-monogamy. The current longitudinal study: 1) estimated the prevalence of expectations of partner non-monogamy and 2) evaluated whether gender, sexual identity, age, education, how a couple met, and relationship quality were predictive expectations of partner non-monogamy. This study utilized the publically available longitudinal dataset, How Couples Meet and Stay Together. Adults aged 18- to 98-years old (n=4002) were surveyed by phone over 5 waves from 2009-2014. Demographics and how a couple met were gathered through self-report in Wave 1, and relationship quality and expectations of partner non-monogamy were gathered through self-report in Waves 4 and 5 (n=1047). The prevalence of expectations of partner non-monogamy (encompassing both infidelity and consensual non-monogamy) was 4.8%. Logistic regression models indicated that sexual identity, gender, education, and relationship quality were significantly predictive of expectations of partner non-monogamy. Specifically, male gender, lower education, identifying as lesbian, gay, or bisexual, and a lower relationship quality scores were predictive of expectations of partner non-monogamy. Male gender was not predictive of expectations of partner non-monogamy in the follow up logistic regression model. Age and whether a couple met online were not associated with expectations of partner non-monogamy. Clinical implications include awareness of the increased likelihood of lesbian, gay, and bisexual individuals to have an expectation of non-monogamy and the sequelae of relationship dissatisfaction that may be related. Future research directions could differentiate between non-monogamy subtypes and the person and relationship variables that lead to the likelihood of consensual non-monogamy and infidelity as separate constructs, as well as explore the relationship between predicting partner behavior and actual partner behavioral outcomes.Keywords: open relationship, polyamory, infidelity, relationship satisfaction
Procedia PDF Downloads 1531699 Sequential Pattern Mining from Data of Medical Record with Sequential Pattern Discovery Using Equivalent Classes (SPADE) Algorithm (A Case Study : Bolo Primary Health Care, Bima)
Authors: Rezky Rifaini, Raden Bagus Fajriya Hakim
Abstract:
This research was conducted at the Bolo primary health Care in Bima Regency. The purpose of the research is to find out the association pattern that is formed of medical record database from Bolo Primary health care’s patient. The data used is secondary data from medical records database PHC. Sequential pattern mining technique is the method that used to analysis. Transaction data generated from Patient_ID, Check_Date and diagnosis. Sequential Pattern Discovery Algorithms Using Equivalent Classes (SPADE) is one of the algorithm in sequential pattern mining, this algorithm find frequent sequences of data transaction, using vertical database and sequence join process. Results of the SPADE algorithm is frequent sequences that then used to form a rule. It technique is used to find the association pattern between items combination. Based on association rules sequential analysis with SPADE algorithm for minimum support 0,03 and minimum confidence 0,75 is gotten 3 association sequential pattern based on the sequence of patient_ID, check_Date and diagnosis data in the Bolo PHC.Keywords: diagnosis, primary health care, medical record, data mining, sequential pattern mining, SPADE algorithm
Procedia PDF Downloads 3941698 The Effect of Acute Rejection and Delayed Graft Function on Renal Transplant Fibrosis in Live Donor Renal Transplantation
Authors: Wisam Ismail, Sarah Hosgood, Michael Nicholson
Abstract:
The research hypothesis is that early post-transplant allograft fibrosis will be linked to donor factors and that acute rejection and/or delayed graft function in the recipient will be independent risk factors for the development of fibrosis. This research hypothesis is to explore whether acute rejection/delay graft function has an effect on the renal transplant fibrosis within the first year post live donor kidney transplant between 1998 and 2009. Methods: The study has been designed to identify five time points of the renal transplant biopsies [0 (pre-transplant), 1 month, 3 months, 6 months and 12 months] for 300 live donor renal transplant patients over 12 years period between March 1997 – August 2009. Paraffin fixed slides were collected from Leicester General Hospital and Leicester Royal Infirmary. These were routinely sectioned at a thickness of 4 Micro millimetres for standardization. Conclusions: Fibrosis at 1 month after the transplant was found significantly associated with baseline fibrosis (p<0.001) and HTN in the transplant recipient (p<0.001). Dialysis after the transplant showed a weak association with fibrosis at 1 month (p=0.07). The negative coefficient for HTN (-0.05) suggests a reduction in fibrosis in the absence of HTN. Fibrosis at 1 month was significantly associated with fibrosis at baseline (p 0.01 and 95%CI 0.11 to 0.67). Fibrosis at 3, 6 or 12 months was not found to be associated with fibrosis at baseline (p=0.70. 0.65 and 0.50 respectively). The amount of fibrosis at 1 month is significantly associated with graft survival (p=0.01 and 95%CI 0.02 to 0.14). Rejection and severity of rejection were not found to be associated with fibrosis at 1 month. The amount of fibrosis at 1 month was significantly associated with graft survival (p=0.02) after adjusting for baseline fibrosis (p=0.01). Both baseline fibrosis and graft survival were significant predictive factors. The amount of fibrosis at 1 month was not found to be significantly associated with rejection (p=0.64) after adjusting for baseline fibrosis (p=0.01). The amount of fibrosis at 1 month was not found to be significantly associated with rejection severity (p=0.29) after adjusting for baseline fibrosis (p=0.04). Fibrosis at baseline and HTN in the recipient were found to be predictive factors of fibrosis at 1 month. (p 0.02, p <0.001 respectively). Age of the donor, their relation to the patient, the pre-op Creatinine, artery, kidney weight and warm time were not found to be significantly associated with fibrosis at 1 month. In this complex model baseline fibrosis, HTN in the recipient and cold time were found to be predictive factors of fibrosis at 1 month (p=0.01,<0.001 and 0.03 respectively). Donor age was found to be a predictive factor of fibrosis at 6 months. The above analysis was repeated for 3, 6 and 12 months. No associations were detected between fibrosis and any of the explanatory variables with the exception of the donor age which was found to be a predictive factor of fibrosis at 6 months.Keywords: fibrosis, transplant, renal, rejection
Procedia PDF Downloads 2271697 Mining Coupled to Agriculture: Systems Thinking in Scalable Food Production
Authors: Jason West
Abstract:
Low profitability in agriculture production along with increasing scrutiny over environmental effects is limiting food production at scale. In contrast, the mining sector offers access to resources including energy, water, transport and chemicals for food production at low marginal cost. Scalable agricultural production can benefit from the nexus of resources (water, energy, transport) offered by mining activity in remote locations. A decision support bioeconomic model for controlled environment vertical farms was used. Four submodels were used: crop structure, nutrient requirements, resource-crop integration, and economic. They escalate to a macro mathematical model. A demonstrable dynamic systems framework is needed to prove productive outcomes are feasible. We demonstrate a generalized bioeconomic macro model for controlled environment production systems in minesites using systems dynamics modeling methodology. Despite the complexity of bioeconomic modelling of resource-agricultural dynamic processes and interactions, the economic potential greater than general economic models would assume. Scalability of production as an input becomes a key success feature.Keywords: crop production systems, mathematical model, mining, agriculture, dynamic systems
Procedia PDF Downloads 721696 Analytical Study of Data Mining Techniques for Software Quality Assurance
Authors: Mariam Bibi, Rubab Mehboob, Mehreen Sirshar
Abstract:
Satisfying the customer requirements is the ultimate goal of producing or developing any product. The quality of the product is decided on the bases of the level of customer satisfaction. There are different techniques which have been reported during the survey which enhance the quality of the product through software defect prediction and by locating the missing software requirements. Some mining techniques were proposed to assess the individual performance indicators in collaborative environment to reduce errors at individual level. The basic intention is to produce a product with zero or few defects thereby producing a best product quality wise. In the analysis of survey the techniques like Genetic algorithm, artificial neural network, classification and clustering techniques and decision tree are studied. After analysis it has been discovered that these techniques contributed much to the improvement and enhancement of the quality of the product.Keywords: data mining, defect prediction, missing requirements, software quality
Procedia PDF Downloads 4601695 Data Mining Spatial: Unsupervised Classification of Geographic Data
Authors: Chahrazed Zouaoui
Abstract:
In recent years, the volume of geospatial information is increasing due to the evolution of communication technologies and information, this information is presented often by geographic information systems (GIS) and stored on of spatial databases (BDS). The classical data mining revealed a weakness in knowledge extraction at these enormous amounts of data due to the particularity of these spatial entities, which are characterized by the interdependence between them (1st law of geography). This gave rise to spatial data mining. Spatial data mining is a process of analyzing geographic data, which allows the extraction of knowledge and spatial relationships from geospatial data, including methods of this process we distinguish the monothematic and thematic, geo- Clustering is one of the main tasks of spatial data mining, which is registered in the part of the monothematic method. It includes geo-spatial entities similar in the same class and it affects more dissimilar to the different classes. In other words, maximize intra-class similarity and minimize inter similarity classes. Taking account of the particularity of geo-spatial data. Two approaches to geo-clustering exist, the dynamic processing of data involves applying algorithms designed for the direct treatment of spatial data, and the approach based on the spatial data pre-processing, which consists of applying clustering algorithms classic pre-processed data (by integration of spatial relationships). This approach (based on pre-treatment) is quite complex in different cases, so the search for approximate solutions involves the use of approximation algorithms, including the algorithms we are interested in dedicated approaches (clustering methods for partitioning and methods for density) and approaching bees (biomimetic approach), our study is proposed to design very significant to this problem, using different algorithms for automatically detecting geo-spatial neighborhood in order to implement the method of geo- clustering by pre-treatment, and the application of the bees algorithm to this problem for the first time in the field of geo-spatial.Keywords: mining, GIS, geo-clustering, neighborhood
Procedia PDF Downloads 3701694 Decision Support System in Air Pollution Using Data Mining
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 424