Search results for: score prediction

Authors: Abeer K. Jameel, Harry Evdorides

Abstract:

The Assessment of the road safety performance is a challengeable issue. This is not only because of the ineffective and unreliability of road and traffic crash data system but also because of its systematic character. Recent strategic plans and interventions implemented in some of the developed countries where a significant decline in the rate of traffic and road crashes considers that the road safety is a system. This system consists of four main elements which are: road user, road infrastructure, vehicles and speed in addition to other supporting elements such as the institutional framework and post-crash care system. To assess the performance of a system, it is required to assess all its elements. To present an understandable results of the assessment, it is required to present a unique term representing the performance of the overall system. This paper aims to develop an overall performance indicator which may be used to assess the road safety system. The variables of this indicators are the main elements of the road safety system. The data regarding these variables will be collected from the World Health Organization report. Multi-criteria analysis method is used to aggregate the four sub-indicators for the four variables. Two weighting methods will be assumed, equal weights and different weights. For the different weights method, the factor analysis method is used. The weights then will be converting to scores. The total score will be the overall indicator for the road safety performance in a national scale. This indicator will be used to compare and rank countries according to their road safety performance indicator. The country with the higher score is the country which provides most sustainable and effective interventions for successful road safety system. These indicator will be tested by comparing them with the aggregate real crash rate for each country.

Keywords: factor analysis, Multi-criteria analysis, road safety assessment, safe system indicator

Procedia PDF Downloads 271

Authors: D. P. Lawrence, T. M. M. D. Ariyarathna, W. N. K. De Silva, M. D. S. C. De Silva, Lasantha Abeysiri, Pradeep Abeygunawardhna

Abstract:

Safari traveling is one of the most famous hobbies all over the world. In Sri Lanka, 'Yala' is the second-largest national park, which is a better place to go for a safari. Many number of local and foreign travelers are coming to go for a safari in 'Yala'. But 'Yala' does not have a mobile application that is made to facilitate the traveler with some important features that the traveler wants to achieve in the safari experience. To overcome these difficulties, the proposed mobile application by adding those identified features to make travelers, guiders, and administration's works easier. The proposed safari traveling guidance mobile application is called 'SMART SAFARI' for the 'Yala' National Park in Sri Lanka. There are four facilities in this mobile application that provide for travelers as well as the guiders. As the first facility, the guider and traveler can view the created map of the park, and the guider can add temporary locations of animals and special locations on the map. This is a Geographic Information System (GIS) to capture, analyze, and display geographical data. And as the second facility is to generate optimal paths according to the travelers' requirements through the park by using machine learning techniques. In the third part, the traveler can get information about animals using an animal identification system by capturing the animal. As in the other facility, the traveler will be facilitated to add reviews and a rate and view those comments under categorized sections and pre-defined score range. With those facilities, this user-friendly mobile application provides the user to get a better experience in safari traveling, and it will probably help to develop tourism culture in Sri Lanka.

Keywords: animal identification system, geographic information system, machine learning techniques, pre defined score range

Procedia PDF Downloads 134

Authors: Ibrahim Alhassan Libata

Abstract:

This study was carried out to assess attitude of secondary school students towards science and technical education in Yauri metropolis, Kebbi State, Nigeria. The population of the study was 200. Proportionate random sampling method was used in selecting 132 as sample size. Science and technical education is the most powerful forces for change in the world today, and students who hope to have a hand in shaping a better future must participate for their advancements. Four Null hypotheses were generated to guide the conduct of the study, questionnaire was the only instrument used in the study; the instrument was subjected to test-retest reliability. The reliability index of the instrument was 0.69. Overall scores of the Students were analyzed and a mean score was determined, the mean score of students was 85. There were no significant differences between the attitudes of male and female students towards science and technical education. The results also revealed that there was significant difference between the attitude of boding and day school students towards science and technical education, personality constraints of students is one factor militating against the participation of students in science and technical education, socio-economic status of the parents over the years have been the dominant factor of student’s inadequate representation in the field of science and technical education. Based on the findings of this study, the researcher recommended that teachers should motivate students, which they can do through their teaching styles and by showing them the relevance of the learning topics to their everyday lives. Government and the school management should create the learning environment that helps motivate students not only to come to classes but also want to learn and enjoy learning science and technical education, establishment of more Science and Technical Colleges education, more Public enlightenment campaigns to motivate parents and the entire community to support their children in studying science and technical education.

Keywords: attitude, students, science, Yauri

Procedia PDF Downloads 258

Authors: Balaji Viswanathan, Tim Oates

Abstract:

A number of pilot projects have commenced across the world to use robots for senior care. We aim to measure the likeability of these robots among seniors and help robot designers focus on the features that matter. We built a robot likability score with over 30 parameters and used this to interview 50 seniors in various locations in the United States. This paper presents the results of this field research.

Keywords: HRI, assistive robotics, social robotics, HCI, aging

Procedia PDF Downloads 106

Authors: Ruttana Phetsitong, Patama Vapattanawong, Malee Sunpuwan, Marc Voelker

Abstract:

The majority of care for older people at home in Thai society falls upon caregivers resulting in caregiver’s mental health problem. Beyond individual characteristics, household factors might have a profound effect on the caregiver’s mental health. But reliable data capturing this at the household level have been limited to date. The objectives of the present study were to explore the levels of Thai caregiver’s mental health and to investigate the factors affecting the mental health at household level. Data were obtained from the 2011 National Survey of Thai Older Persons conducted by the National Statistical Office of Thailand. Caregiver’s mental health was measured by using the 15- items-short version of the Thai Mental Health Indicator (TMHI-15) developed by the Department of Mental Health, the Ministry of Public Health. Multivariate logistic regression models were used to explore the impact of potential factors on caregiver’s mental health. The THMI-15 produced an overall average caregiver mental health score of 30.9 out of 45 (SD 5.3). The score can be categorized into good (34.02-45), fair (27.01-34), and poor (0-27). Duration of care for older people, household wealth, and functional dependency of the older people significantly predicted total caregiver’s mental health. Household economic factor was key in predicting better mental health. Compared to those poorest households, the adjusted effect of the fifth quintile household wealth was high (OR=2.34; 95%CI=1.47-3.73). The findings of this study provide a fuller picture to a better understanding of the level and factors that cause the mental health of Thai caregivers. Health care providers and policymakers should consider these factors when designing interventions aimed at alleviating caregiver’s psychological burden when provided care for older people at home.

Keywords: caregiver’s mental health, household, older people, Thailand

Procedia PDF Downloads 146

Authors: Ranjith Menon, Abathar Aladi, Hans-Christean Nahser, Maneesh Bhojak, Sacha Nevin, Paul Eldridge

Abstract:

Background: Spontaneous subarachnoid haemorrhage (SAH) accounts for approximately 5% of all strokes. Patients with spontaneous SAH (as shown by CT or lumbar puncture) undergo investigations to identify or exclude an underlying structural cause, typically cerebral aneurysm. However in 10 - 20% of cases, no structural cause is found. This includes more than one imaging modality (intracranial MRA, CTA, 4DCTA and/or DSA) and in some spinal MRI. Objective: To determine; 1) If an underlying structural or vascular cause can be identified in non-aneurysmal SAH patients by comparing different imaging modalities at presentation and at follow-up. 2) If MRI spine in patients with non-aneurysmal SAH reveals an underlying SAH cause. 3)The functional outcome at discharge. Results: We performed a retrospective analysis of all non-traumatic SAH patients admitted to the Walton centre from January 2009 to December 2015. There were 1457 patients with non-traumatic SAH admitted to the Walton centre of whom 21.8% (n=300) patients were diagnosed with non-aneurysmal SAH. Males were 65.6% and females were 43.3%. The presenting symptoms were sudden onset headache (93.6%), the focal neurological deficit (12%), loss of consciousness (10.6%) and others (6%). About 285 patients received 2 modalities of imaging (CTA & DSA), 192 received 3 modalities of imaging (CTA, MRA & DSA) and 137 received MRI spine (51/137 whole spine). The modified Rankin Score at discharge were: mRS 0 = 292 (97.33%), mRS 1-2 = 6, mRS 6 = 1 (cardiac arrest in IHD patient) and unknown in 1. Follow-up imaging at 3 to 6 months in 190 (63.3%) patients did not identify an underlying cause. Conclusion: This retrospective analysis concludes that non-aneurysmal SAH has a good functional outcome. A single imaging modality (CTA (4DCTA) or MRA or DSA) was adequate to exclude an underlying cause of SAH and a delayed imaging failed to identify a cause. Routinely performing MRI spine in this group of patients appears not to be necessary according to this evidence.

Keywords: stroke, non-aneurysmal subarachnoid haemorrhage, neuroimaging, modified rankin score

Procedia PDF Downloads 268

Authors: Nurin Amalina Widityani, Adinda Syifa Azhari, Twin Aji Kusumagiani, Eleonora Agustine

Abstract:

Fertilizer industry activities contribute to environmental changes. Changes to the environment became one of a few problems in this era of globalization. Parameters that can be seen as criteria to identify changes in the environment can be seen from the aspects of physics, chemistry, and biology. One aspect that can be assessed quickly and efficiently to describe environmental change is the aspect of physics, one of which is the value of magnetic susceptibility (χ). The rock magnetism method can be used as a proxy indicator of environmental changes, seen from the value of magnetic susceptibility. The rock magnetism method is based on magnetic susceptibility studies to measure and classify the degree of pollutant elements that cause changes in the environment. This research was conducted in the area around the fertilizer plant, with five coring points on each track, each coring point a depth of 15 cm. Magnetic susceptibility measurements were performed by in-situ and ex-situ. In-situ measurements were carried out directly by using the SM30 tool by putting the tools on the soil surface at each measurement point and by that obtaining the value of the magnetic susceptibility. Meanwhile, ex-situ measurements are performed in the laboratory by using the Bartington MS2B tool’s susceptibility, which is done on a coring sample which is taken every 5 cm. In-situ measurement shows results that the value of magnetic susceptibility at the surface varies, with the lowest score on the second and fifth points with the -0.81 value and the highest value at the third point, with the score of 0,345. Ex-situ measurements can find out the variations of magnetic susceptibility values at each depth point of coring. At a depth of 0-5 cm, the value of the highest XLF = 494.8 (x10-8m³/kg) is at the third point, while the value of the lowest XLF = 187.1 (x10-8m³/kg) at first. At a depth of 6-10 cm, the highest value of the XLF was at the second point, which was 832.7 (x10-8m³/kg) while the lowest XLF is at the first point, at 211 (x10-8m³/kg). At a depth of 11-15 cm, the XLF’s highest value = 857.7 (x10-8m³/kg) is at the second point, whereas the value of the lowest XLF = 83.3 (x10-8m³/kg) is at the fifth point. Based on the in situ and exsit measurements, it can be seen that the highest magnetic susceptibility values from the surface samples are at the third point.

Keywords: magnetic susceptibility, fertilizer plant, Bartington MS2B, SM30

Procedia PDF Downloads 344

Authors: Man-Yu Wong, Siyu Zhou, Zhiqiang Cao

Abstract:

In quality of life, health service utilization is an important determinant of medical resource expenditures on Colorectal cancer (CRC) care, a better understanding of the increased utilization of health services is essential for optimizing the allocation of healthcare resources to services and thus for enhancing the service quality, especially for high expenditure on CRC care like Hong Kong region. In assessing the association between the health-related quality of life (HRQOL) and health service utilization in patients with colorectal neoplasm, count data models can be used, which account for over dispersion or extra zero counts. In our data, the HRQOL evaluation is a self-reported measure obtained from a questionnaire completed by the patients, misreports and variations in the data are inevitable. Besides, there are more zero counts from the observed number of clinical consultations (observed frequency of zero counts = 206) than those from a Poisson distribution with mean equal to 1.33 (expected frequency of zero counts = 156). This suggests that excess of zero counts may exist. Therefore, we study tests for detecting zero-inflation in models with measurement error in covariates. Method: Under classical measurement error model, the approximate likelihood function for zero-inflation Poisson regression model can be obtained, then Approximate Maximum Likelihood Estimation(AMLE) can be derived accordingly, which is consistent and asymptotically normally distributed. By calculating score function and Fisher information based on AMLE, a score test is proposed to detect zero-inflation effect in ZIP model with measurement error. The proposed test follows asymptotically standard normal distribution under H0, and it is consistent with the test proposed for zero-inflation effect when there is no measurement error. Results: Simulation results show that empirical power of our proposed test is the highest among existing tests for zero-inflation in ZIP model with measurement error. In real data analysis, with or without considering measurement error in covariates, existing tests, and our proposed test all imply H0 should be rejected with P-value less than 0.001, i.e., zero-inflation effect is very significant, ZIP model is superior to Poisson model for analyzing this data. However, if measurement error in covariates is not considered, only one covariate is significant; if measurement error in covariates is considered, only another covariate is significant. Moreover, the direction of coefficient estimations for these two covariates is different in ZIP regression model with or without considering measurement error. Conclusion: In our study, compared to Poisson model, ZIP model should be chosen when assessing the association between condition-specific HRQOL and health service utilization in patients with colorectal neoplasm. and models taking measurement error into account will result in statistically more reliable and precise information.

Keywords: count data, measurement error, score test, zero inflation

Procedia PDF Downloads 289

Authors: Kayne Uriel K. Rodrigo, Jerriane Hillary Heart S. Marcial, Samuel C. Brillo

Abstract:

Rice leaf diseases significantly impact yield production in rice-dependent countries, affecting their agricultural sectors. As part of precision agriculture, early and accurate detection of these diseases is crucial for effective mitigation practices and minimizing crop losses. Hence, this study proposes an enhancement to the Convolutional Neural Network (CNN), a widely-used method for Rice Leaf Disease Image Classification, by incorporating MobileViTV2—a recently advanced architecture that combines CNN and Vision Transformer models while maintaining fewer parameters, making it suitable for broader deployment on edge devices. Our methodology utilizes a publicly available rice disease image dataset from Kaggle, which was validated by a university structural biologist following the guidelines provided by the Philippine Rice Institute (PhilRice). Modifications to the dataset include renaming certain disease categories and augmenting the rice leaf image data through rotation, scaling, and flipping. The enhanced dataset was then used to train the MobileViTV2 model using the Timm library. The results of our approach are as follows: the model achieved notable performance, with 98% accuracy in both training and validation, 6% training and validation loss, and a Receiver Operating Characteristic (ROC) curve ranging from 95% to 100% for each label. Additionally, the F1 score was 97%. These metrics demonstrate a significant improvement compared to a conventional CNN-based approach, which, in a previous 2022 study, achieved only 78% accuracy after using 5 convolutional layers and 2 dense layers. Thus, it can be concluded that MobileViTV2, with its fewer parameters, outperforms traditional CNN models, particularly when applied to Rice Leaf Disease Image Identification. For future work, we recommend extending this model to include datasets validated by international rice experts and broadening the scope to accommodate biotic factors such as rice pest classification, as well as abiotic stressors such as climate, soil quality, and geographic information, which could improve the accuracy of disease prediction.

Keywords: convolutional neural network, MobileViTV2, rice leaf disease, precision agriculture, image classification, vision transformer

Procedia PDF Downloads 29

Authors: P. T. Collett, M. Kershaw

Abstract:

Introduction: The discussion regarding which method of anesthesia provides better results for lower limb arthroplasty is a continuing debate. Multiple meta-analysis has been performed with no clear consensus. The current recommendation is to use neuraxial anesthesia for lower limb arthroplasty; however, the evidence to support this decision is weak. The Enhanced Recovery After Surgery (ERAS) society has recommended, either technique can be used as part of a multimodal anesthetic regimen. A local study was performed to see if the current anesthetic practice correlates with the current recommendations and to evaluate the efficacy of the different techniques utilized. Method: 90 patients who underwent total hip or total knee replacements at Nevill Hall Hospital between February 2019 to July 2019 were reviewed. Data collected included the anesthetic technique, day one opiate use, pain score, and length of stay. The data was collected from anesthetic charts, and the pain team follows up forms. Analysis: The average of patients undergoing lower limb arthroplasty was 70. Of those 83% (n=75) received a spinal anaesthetic and 17% (n=15) received a general anaesthetic. For patients undergoing knee replacement under general anesthetic the average day, one pain score was 2.29 and 1.94 if a spinal anesthetic was performed. For hip replacements, the scores were 1.87 and 1.8, respectively. There was no statistical significance between these scores. Day 1 opiate usage was significantly higher in knee replacement patients who were given a general anesthetic (45.7mg IV morphine equivalent) vs. those who were operated on under spinal anesthetic (19.7mg). This difference was not noticeable in hip replacement patients. There was no significant difference in length of stay between the two anesthetic techniques. Discussion: There was no significant difference in the day one pain score between the patients who received a general or spinal anesthetic for either knee or hip replacements. The higher pain scores in the knee replacement group overall are consistent with this being a more painful procedure. This is a small patient population, which means any difference between the two groups is unlikely to be representative of a larger population. The pain scale has 4 points, which means it is difficult to identify a significant difference between pain scores. Conclusion: There is currently little standardization between the different anesthetic approaches utilized in Nevill Hall Hospital. This is likely due to the lack of adherence to a standardized anesthetic regimen. In accordance with ERAS recommends a standard anesthetic protocol is a core component. The results of this study and the guidance from the ERAS society will support the implementation of a new health board wide ERAS protocol.

Keywords: anaesthesia, orthopaedics, intensive care, patient centered decision making, treatment escalation

Procedia PDF Downloads 128

Authors: Jairson Barbosa Rodrigues, Paulo Romero Martins Maciel, Germano Crispim Vasconcelos

Abstract:

This paper presents an investigation of the performance impacts regarding the variation of five factors (input data size, node number, cores, memory, and disks) when applying a distributed implementation of Naïve Bayes for text classification of a large Corpus on the Spark big data processing framework. Problem: The algorithm's performance depends on multiple factors, and knowing before-hand the effects of each factor becomes especially critical as hardware is priced by time slice in cloud environments. Objectives: To explain the functional relationship between factors and performance and to develop linear predictor models for time and cost. Methods: the solid statistical principles of Design of Experiments (DoE), particularly the randomized two-level fractional factorial design with replications. This research involved 48 real clusters with different hardware arrangements. The metrics were analyzed using linear models for screening, ranking, and measurement of each factor's impact. Results: Our findings include prediction models and show some non-intuitive results about the small influence of cores and the neutrality of memory and disks on total execution time, and the non-significant impact of data input scale on costs, although notably impacts the execution time.

Keywords: big data, design of experiments, distributed machine learning, natural language processing, spark

Procedia PDF Downloads 120

Authors: Alireza Dantism

Abstract:

Presently, describing the function of a protein sequence is one of the most common problems in biology. Usually, this problem can be facilitated by studying the three-dimensional structure of proteins. In the absence of a protein structure, comparative modeling often provides a useful three-dimensional model of the protein that is dependent on at least one known protein structure. Comparative modeling predicts the three-dimensional structure of a given protein sequence (target) mainly based on its alignment with one or more proteins of known structure (templates). Comparative modeling consists of four main steps 1. Similarity between the target sequence and at least one known template structure 2. Alignment of target sequence and template(s) 3. Build a model based on alignment with the selected template(s). 4. Prediction of model errors 5. Optimization of the built model There are many computer programs and web servers that automate the comparative modeling process. One of the most important advantages of these servers is that it makes comparative modeling available to both experts and non-experts, and they can easily do their own modeling without the need for programming knowledge, but some other experts prefer using programming knowledge and do their modeling manually because by doing this they can maximize the accuracy of their modeling. In this study, a web-based tool has been designed to predict the tertiary structure of proteins using PHP and Python programming languages. This tool is called EasyModel. EasyModel can receive, according to the user's inputs, the desired unknown sequence (which we know as the target) in this study, the protein sequence file (template), etc., which also has a percentage of similarity with the primary sequence, and its third structure Predict the unknown sequence and present the results in the form of graphs and constructed protein files.

Keywords: structural bioinformatics, protein tertiary structure prediction, modeling, comparative modeling, modeller

Procedia PDF Downloads 98

Authors: Omar Dib, Rita Yaacoub, Luc Eveleigh, Nathalie Locquet, Hussein Dib, Ali Bassal, Christophe B. Y. Cordella

Abstract:

The potential of front-face fluorescence coupled with chemometric techniques, namely parallel factor analysis (PARAFAC) and multiple linear regression (MLR) as a rapid analysis tool to characterize Lebanese virgin olive oils was investigated. Fluorescence fingerprints were acquired directly on 102 Lebanese virgin olive oil samples in the range of 280-540 nm in excitation and 280-700 nm in emission. A PARAFAC model with seven components was considered optimal with a residual of 99.64% and core consistency value of 78.65. The model revealed seven main fluorescence profiles in olive oil and was mainly associated with tocopherols, polyphenols, chlorophyllic compounds and oxidation/hydrolysis products. 23 MLR regression models based on PARAFAC scores were generated, the majority of which showed a good correlation coefficient (R > 0.7 for 12 predicted variables), thus satisfactory prediction performances. Acid values, peroxide values, and Delta K had the models with the highest predictions, with R values of 0.89, 0.84 and 0.81 respectively. Among fatty acids, linoleic and oleic acids were also highly predicted with R values of 0.8 and 0.76, respectively. Factors contributing to the model's construction were related to common fluorophores found in olive oil, mainly chlorophyll, polyphenols, and oxidation products. This study demonstrates the interest of front-face fluorescence as a promising tool for quality control of Lebanese virgin olive oils.

Keywords: front-face fluorescence, Lebanese virgin olive oils, multiple Linear regressions, PARAFAC analysis

Procedia PDF Downloads 453

Authors: C. Sridawruang

Abstract:

Young people today has sexual activities differing from those of earlier generations, in that teenagers are likely to have multiple partners, and are frequently in short-term relationships or with partners that are not well known to them. The proportion of teenage mothers in Thailand has increased. Young people were not specifically addressed during the overall very successful HIV-prevention campaigns. Because of this missed opportunity, they are still unaware of the risk of unsafe sexual behavior. Aims: To describe the reproductive health care services in perspectives of rural Thai teenagers Methods: This survey was one part of a mixed method approach taken using survey and focus groups with 439 teenagers aged 12-18 years in 5 villages, Udon Thani, Thailand. The standard questionnaire survey had been used for collecting data. The numeric data was checked and analyzed by using descriptive statistics. Results: Most teenager respondents stated that they do not know where sexual reproductive health services provided for them. Most teenagers felt difficult to access and talk with health staff about sexual related issues. They stated that discussing, or consulting with health providers might not be safe. Teenagers might lose opportunities to access and get advice from health care services. The mean knowledge score of contraception and condom reproductive was 6.34 from a total score 11. Most teenagers especially girls expressed a need for counseling services and reported a need for telephone services. Conclusions: The need of appropriate information focusing on sexual relationships and contraception should be designed to help young people make wise decisions and there should be set health care services for Thai teenagers to make sure that teenagers could access easily. Health care providers need to be trained to improve their knowledge, attitudes and skills in reproductive health care practices for Thai teenagers.

Keywords: youth friendly health services, rural, Thai, teenagers

Procedia PDF Downloads 341

Authors: Muhammad Ahnaf Zahin, Yaw Adu-Gyamfi

Abstract:

Bus transit is a crucial component of transportation networks, especially in urban areas. Any intelligent transportation system must have accurate real-time information on bus travel times since it minimizes waiting times for passengers at different stations along a route, improves service reliability, and significantly optimizes travel patterns. Bus agencies must enhance the quality of their information service to serve their passengers better and draw in more travelers since people waiting at bus stops are frequently anxious about when the bus will arrive at their starting point and when it will reach their destination. For solving this issue, different models have been developed for predicting bus travel times recently, but most of them are focused on smaller road networks due to their relatively subpar performance in high-density urban areas on a vast network. This paper develops a deep learning-based architecture using a single-step multi-station forecasting approach to predict average bus travel times for numerous routes, stops, and trips on a large-scale network using heterogeneous bus transit data collected from the GTFS database. Over one week, data was gathered from multiple bus routes in Saint Louis, Missouri. In this study, Gated Recurrent Unit (GRU) neural network was followed to predict the mean vehicle travel times for different hours of the day for multiple stations along multiple routes. Historical time steps and prediction horizon were set up to 5 and 1, respectively, which means that five hours of historical average travel time data were used to predict average travel time for the following hour. The spatial and temporal information and the historical average travel times were captured from the dataset for model input parameters. As adjacency matrices for the spatial input parameters, the station distances and sequence numbers were used, and the time of day (hour) was considered for the temporal inputs. Other inputs, including volatility information such as standard deviation and variance of journey durations, were also included in the model to make it more robust. The model's performance was evaluated based on a metric called mean absolute percentage error (MAPE). The observed prediction errors for various routes, trips, and stations remained consistent throughout the day. The results showed that the developed model could predict travel times more accurately during peak traffic hours, having a MAPE of around 14%, and performed less accurately during the latter part of the day. In the context of a complicated transportation network in high-density urban areas, the model showed its applicability for real-time travel time prediction of public transportation and ensured the high quality of the predictions generated by the model.

Keywords: gated recurrent unit, mean absolute percentage error, single-step forecasting, travel time prediction.

Procedia PDF Downloads 73

Authors: Mostafa Fanaei, Shahram R. Sistani, Athare Nazri-Panjaki

Abstract:

Introduction: Critical thinking skills are increasingly recognized as vital for academic success, particularly in higher education. This study examines the influence of critical thinking on learning achievement among undergraduate and master's students enrolled in foreign language programs. By investigating this correlation, educators can gain valuable insights into optimizing teaching methodologies and enhancing academic outcomes. Methods: This cross-sectional study involved 150 students from the Shahid Bahonar University of Kerman, recruited via random sampling. Participants completed the Critical Thinking Questionnaire (CThQ), assessing dimensions such as analysis, evaluation, creation, remembering, understanding, and application. Academic performance was measured using the students' GPA (0-20). Results: The participants' mean age was 21.46 ± 5.2 years, with 62.15% being female. The mean scores for critical thinking subscales were as follows: Analyzing (13.2 ± 3.5), Evaluating (12.8 ± 3.4), Creating (18.6 ± 4.8), Remembering (9.4 ± 2.1), Understanding (12.9 ± 3.3), and Applying (12.5 ± 3.2). The overall critical thinking score was 79.4 ± 18.1, and the average GPA was 15.7 ± 2.4. Significant positive correlations were found between GPA and several critical thinking subscales: Analyzing (r = 0.45, p = 0.013), Creating (r = 0.52, p < 0.001), Remembering (r = 0.29, p = 0.021), Understanding (r = 0.41, p = 0.002), and the overall CThQ score (r = 0.54, p = 0.043). Conclusion: The study demonstrates a significant positive relationship between critical thinking skills and learning achievement in foreign language programs. Enhancing critical thinking skills through educational interventions could potentially improve academic performance. Further research is recommended to explore the underlying mechanisms and long-term impacts of critical thinking on academic success.

Keywords: critical thinking, learning achievement, higher education, foreign language programs, student success

Procedia PDF Downloads 43

Authors: Michael A. Kraus, Navid Pourmoghaddam, Martin Botz, Jens Schneider, Geralt Siebert

Abstract:

Fragmentation analysis of tempered glass gives insight into the quality of the tempering process and defines a certain degree of safety as well. Different standard such as the European EN 12150-1 or the American ASTM C 1048/CPSC 16 CFR 1201 define a minimum number of fragments required for soda-lime safety glass on the basis of fragmentation test results for classification. This work presents an approach for the glass breakage pattern prediction using a Voronoi Tesselation over Random Fields. The random Voronoi tessellation is trained with and validated against data from several breakage patterns. The fragments in observation areas of 50 mm x 50 mm were used for training and validation. All glass specimen used in this study were commercially available soda-lime glasses at three different thicknesses levels of 4 mm, 8 mm and 12 mm. The results of this work form a Bayesian framework for the training and prediction of breakage patterns of tempered soda-lime glass using a Voronoi Random Field Tesselation. Uncertainties occurring in this process can be well quantified, and several statistical measures of the pattern can be preservation with this method. Within this work it was found, that different Random Fields as basis for the Voronoi Tesselation lead to differently well fitted statistical properties of the glass breakage patterns. As the methodology is derived and kept general, the framework could be also applied to other random tesselations and crack pattern modelling purposes.

Keywords: glass breakage predicition, Voronoi Random Field Tessellation, fragmentation analysis, Bayesian parameter identification

Procedia PDF Downloads 161

Authors: Rahaf Alasiri, Tarek Alghamdi, Abdullah Zarkan

Abstract:

Background: Due to measures such as school closure, social distancing, and virtual teaching during the pandemic, primary school children's psychological well-being is greatly affected. These measures have short and long-term consequences on the children's well-being and mental health. Identifying these consequences is important. Aim: This study aimed to evaluate mood and behavior changes in children who attended school virtually. Subjects and methods: This is a cross-sectional study conducted among children and their parents who visited the outpatient clinic. A self-administered questionnaire was given to the parents of children aged between 6 to 14 years. The questionnaire includes socio-demographic characteristics, Conor's modifies scale to assess the attention deficit hyperactivity disorder (ADHD) of children, and the parental stress scale (PSS) to assess the stress symptoms of the parents. Results: Of the 66 surveyed children, 60.6% were aged between 10 to 14 years old, with the female being dominant (77.3%). The most common medical condition was asthma (7.6%), and nearly two-thirds (63.6%) indicated good health conditions during the pandemic. There was a significant inverse correlation observed between ADHD score and PSS score (r=-0.387). No significant differences are in ADHD and PSS scores in relation to the socio-demographic characteristics of the children, including age, gender, and having an associated medical condition (p>0.05). Conclusion: During the pandemic, children who attended virtual classes did not seem to affect even with restrictions. Most children indicated good health conditions during the pandemic. However, it is surprising to know that in spite of children’s high spirits during the pandemic, their parents were seen to have an increased level of stress. Strategies to address parents’ psychological disorders during the pandemic are warranted.

Keywords: children's mood, COVID-19, ADHD, parental stress

Procedia PDF Downloads 73

Authors: Suikinai Nobre Santos, Ranko Gacesa, Paul F. Long, Itamar Soares de Melo

Abstract:

Extremophilic microorganism are adapted to biotopes combining several stress factors (temperature, pressure, radiation, salinity and pH), which indicate the richness valuable resource for the exploitation of novel biotechnological processes and constitute unique models for investigations their biomolecules (1, 2). The above information encourages us investigate bioprospecting synthesized compounds by a noval actinomycete, designated thermotolerant Streptomyces caatingaensis CMAA 1322, isolated from sample soil tropical dry forest (Caatinga) in the Brazilian semiarid region (3-17°S and 35-45°W). This set of constrating physical and climatic factores provide the unique conditions and a diversity of well adapted species, interesting site for biotechnological purposes. Preliminary studies have shown the great potential in the production of cytotoxic, pesticidal and antimicrobial molecules (3). Thus, to extend knowledge of the genes clusters responsible for producing biosynthetic pathways of natural products in strain CMAA1322, whole-genome shotgun (WGS) DNA sequencing was performed using paired-end long sequencing with PacBio RS (Pacific Biosciences). Genomic DNA was extracted from a pure culture grown overnight on LB medium using the PureLink genomic DNA kit (Life Technologies). An approximately 3- to 20-kb-insert PacBio library was constructed and sequenced on an 8 single-molecule real-time (SMRT) cell, yielding 116,269 reads (average length, 7,446 bp), which were allocated into 18 contigs, with 142.11x coverage and N50 value of 20.548 bp (BioProject number PRJNA288757). The assembled data were analyzed by Rapid Annotations using Subsystems Technology (RAST) (4) the genome size was found to be 7.055.077 bp, comprising 6167 open reading frames (ORFs) and 413 subsystems. The G+C content was estimated to be 72 mol%. The closest-neighbors tool, available in RAST through functional comparison of the genome, revealed that strain CMAA1322 is more closely related to Streptomyces hygroscopicus ATCC 53653 (similarity score value, 537), S. violaceusniger Tu 4113 (score value, 483), S. avermitilis MA-4680 (score value, 475), S. albus J1074 (score value, 447). The Streptomyces sp. CMAA1322 genome contains 98 tRNA genes and 135 genes copies related to stress response, mainly osmotic stress (14), heat shock (16), oxidative stress (49). Functional annotation by antiSMASH version 3.0 (5) identified 41 clusters for secondary metabolites (including two clusters for lanthipeptides, ten clusters for nonribosomal peptide synthetases [NRPS], three clusters for siderophores, fourteen for polyketide synthetase [PKS], six clusters encoding a terpene, two clusters encoding a bacteriocin, and one cluster encoding a phenazine). Our work provide in comparative analyse of genome and extract produced (data no published) by lineage CMAA1322, revealing the potential of microorganisms accessed from extreme environments as Caatinga” to produce a wide range of biotechnological relevant compounds.

Keywords: caatinga, streptomyces, environmental stresses, biosynthetic pathways

Procedia PDF Downloads 244

Authors: Goodness Onwuka, Khaled Abou-El-Hossein

Abstract:

Borosilicate-crown (BK7) glass has found broad application in the optic and automotive industries and the growing demands for nanometric surface finishes is becoming a necessity in such applications. Thus, it has become paramount to optimize the parameters influencing the surface roughness of this precision lens. The research was carried out on a 4-axes Nanoform 250 precision lathe machine with an ultra-high precision grinding spindle. The experiment varied the machining parameters of feed rate, wheel speed and depth of cut at three levels for different combinations using Box Behnken design of experiment and the resulting surface roughness values were measured using a Taylor Hobson Dimension XL optical profiler. Acoustic emission monitoring technique was applied at a high sampling rate to monitor the machining process while further signal processing and feature extraction methods were implemented to generate the input to a neural network algorithm. This paper highlights the training and development of a back propagation neural network prediction algorithm through careful selection of parameters and the result show a better classification accuracy when compared to a previously developed response surface model with very similar machining parameters. Hence artificial neural network algorithms provide better surface roughness prediction accuracy in the ultra-high precision grinding of BK7 glass.

Keywords: acoustic emission technique, artificial neural network, surface roughness, ultra-high precision grinding

Procedia PDF Downloads 305

Authors: Naduni Ranasinghe

Abstract:

E-learning environments are getting more popular than any other due to the impact of COVID19. Even though e-learning is one of the best solutions for the teaching-learning process in the academic process, it’s not without major challenges. Nowadays, machine learning approaches are utilized in the analysis of how behavioral factors lead to better adoption and how they related to better performance of the students in eLearning environments. During the pandemic, we realized the academic process in the eLearning approach had a major issue, especially for the performance of the students. Therefore, an approach that investigates student behaviors in eLearning environments using a data-intensive machine learning approach is appreciated. A hybrid approach was used to understand how each previously told variables are related to the other. A more quantitative approach was used referred to literature to understand the weights of each factor for adoption and in terms of performance. The data set was collected from previously done research to help the training and testing process in ML. Special attention was made to incorporating different dimensionality of the data to understand the dependency levels of each. Five independent variables out of twelve variables were chosen based on their impact on the dependent variable, and by considering the descriptive statistics, out of three models developed (Random Forest classifier, SVM, and Decision tree classifier), random forest Classifier (Accuracy – 0.8542) gave the highest value for accuracy. Overall, this work met its goals of improving student performance by identifying students who are at-risk and dropout, emphasizing the necessity of using both static and dynamic data.

Keywords: academic performance prediction, e learning, learning analytics, machine learning, predictive model

Procedia PDF Downloads 157

Authors: ShuJiang Jiang

Abstract:

The interaction of turbulence with airfoil is an important noise source in many engineering fields, including helicopters, turbofan, and contra-rotating open rotor engines, where turbulence generated in the wake of upstream blades interacts with the leading edge of downstream blades and produces aerodynamic noise. One approach to study turbulence-airfoil interaction noise is to model the oncoming turbulence as harmonic gusts. A compact noise source produces a dipole-like sound directivity pattern. However, when the acoustic wavelength is much smaller than the airfoil chord length, the airfoil needs to be treated as a non-compact source, and the gust-airfoil interaction becomes more complicated and results in multiple lobes generated in the radiated sound directivity. Capturing the short acoustic wavelength is a challenge for numerical simulations. In this work, simulations are performed for gust-airfoil interaction at different Mach numbers, using a high-fidelity direct Computational AeroAcoustic (CAA) approach based on a spectral/hp element method, verified by a CAA benchmark case. It is found that the squared sound pressure varies approximately as the 5th power of Mach number, which changes slightly with the observer location. This scaling law can give a better sound prediction than the flat-plate theory for thicker airfoils. Besides, another prediction method, based on the flat-plate theory and CAA simulation, has been proposed to give better predictions than the scaling law for thicker airfoils.

Keywords: aeroacoustics, gust-airfoil interaction, CFD, CAA

Procedia PDF Downloads 79

Authors: Restituto I. Rodelas

Abstract:

The higher education has adopted the outcomes-based education from K-12. In this approach, the teacher uses any teaching and learning strategies that enable the students to achieve the learning outcomes. The students may be required to exert more effort and figure things out on their own. Hence, outcomes-based students are assumed to be more responsible and more capable of applying the knowledge learned. Another approach that the higher education in the Philippines is starting to adopt from other countries is blended learning. This combination of classroom and fully online instruction and learning is expected to be more effective. Participating in the online sessions, however, is entirely up to the students. Thus, the effect of blended learning on the performance of students in Statistics may be mediated by outcomes-based education. If there is a significant positive mediating effect, then blended learning can be optimized by integrating outcomes-based education. In this study, the sample will consist of four blended learning Statistics classes at Jose Rizal University in the second semester of AY 2015–2016. Two of these classes will be assigned randomly to the experimental group that will be handled using outcomes-based education. The two classes in the control group will be handled using the traditional lecture approach. Prior to the discussion of the first topic, a pre-test will be administered. The same test will be given as posttest after the last topic is covered. In order to establish equality of the groups’ initial knowledge, single factor ANOVA of the pretest scores will be performed. Single factor ANOVA of the posttest-pretest score differences will also be conducted to compare the performance of the experimental and control groups. When a significant difference is obtained in any of these ANOVAs, post hoc analysis will be done using Tukey's honestly significant difference test (HSD). Mediating effect will be evaluated using correlation and regression analyses. The groups’ initial knowledge are equal when the result of pretest scores ANOVA is not significant. If the result of score differences ANOVA is significant and the post hoc test indicates that the classes in the experimental group have significantly different scores from those in the control group, then outcomes-based education has a positive effect. Let blended learning be the independent variable (IV), outcomes-based education be the mediating variable (MV), and score difference be the dependent variable (DV). There is mediating effect when the following requirements are satisfied: significant correlation of IV to DV, significant correlation of IV to MV, significant relationship of MV to DV when both IV and MV are predictors in a regression model, and the absolute value of the coefficient of IV as sole predictor is larger than that when both IV and MV are predictors. With a positive mediating effect of outcomes-base education on the effect of blended learning on student performance, it will be recommended to integrate outcomes-based education into blended learning. This will yield the best learning results.

Keywords: outcome-based teaching, blended learning, face-to-face, student-centered

Procedia PDF Downloads 291

Authors: Matthew T. McCarthy, Sarah Janse, Natalie M. Pizzimenti, Anthony K. Savino, Brian Crosser, Sean C. Rose

Abstract:

Concussion is diagnosed clinically using a comprehensive history and exam, supported by ancillary testing. Frequently, symptom checklists are used as part of the evaluation of concussion. Existing symptom scales are based on a subjective Likert scale, without relation of symptoms to clinical or functional impairment. This is a retrospective review of 133 patients under age 30 seen in an outpatient neurology practice within 30 days of a probable or definite concussion. Each patient completed 2 symptom checklists at the initial visit – the SCAT-3 symptom evaluation (22 symptoms, 0-6 scale) and a scale based on the degree of clinical impairment for each symptom (22 symptoms, 0-3 scale related to functional impact of the symptom). Final clearance date was determined by the treating physician. 60.9% of patients were male with mean age 15.7 years (SD 2.3). Mean time from concussion to first visit was 6.9 days (SD 6.2), and 101 patients had definite concussions (75.9%), while 32 were diagnosed as probable (24.1%). 94 patients had a known clearance date (70.7%) with mean clearance time of 20.6 days (SD 18.6) and median clearance time of 19 days (95% CI 16-21). Mean total symptom score was 27.2 (SD 22.9) on the SCAT-3 and 14.7 (SD 11.9) for the functional impairment scale. Pearson’s correlation between the two scales was 0.98 (p < 0.001). After adjusting for patient and injury characteristics, an equivalent increase in score on each scale was associated with longer time to clearance (SCAT-3 hazard ratio 0.885, 95%CI 0.835-0.938, p < 0.001; functional impairment scale hazard ratio 0.851, 95%CI 0.802-0.902, p < 0.001). A concussion symptom scale based on degree of functional impairment correlates strongly with the SCAT-3 scale and demonstrates a similar association with time to clearance. By assessing the degree of impact on clinical functioning, this symptom scale reflects a more intuitive approach to rating symptoms and can be used in the management of concussion.

Keywords: checklist, concussion, neurology, scale, sports, symptoms

Procedia PDF Downloads 153

Authors: Benedictus Asriparusa, Lathifah Al Hakimi, Aulia Husada

Abstract:

A large amount of energy is being wasted by the release of natural gas associated with the oil industry. This release interrupts the environment particularly atmosphere layer condition globally which contributes to global warming impact. This research presents an overview of the methods employed by researchers in PT. Chevron Pacific Indonesia in the Minas area to determine a new prediction method of measuring and reducing gas flaring and its emission. The method emphasizes advanced research which involved analytical studies, numerical studies, modeling, and computer simulations, amongst other techniques. A flaring system is the controlled burning of natural gas in the course of routine oil and gas production operations. This burning occurs at the end of a flare stack or boom. The combustion process releases emissions of greenhouse gases such as NO2, CO2, SO2, etc. This condition will affect the chemical composition of air and environment around the boundary layer mainly during transition season. Transition season in Indonesia is absolutely very difficult condition to predict its pattern caused by the difference of two air mass conditions. This paper research focused on transition season in 2013. A simulation to create the new pattern of the pollutants distribution is needed. This paper has outlines trends in gas flaring modeling and current developments to predict the dominant variables in the pollutants distribution. A Fluent model is used to simulate the distribution of pollutants gas coming out of the stack, whereas WRF model output is used to overcome the limitations of the analysis of meteorological data and atmospheric conditions in the study area. Based on the running model, the most influence factor was wind speed. The goal of the simulation is to predict the new pattern based on the time of fastest wind and slowest wind occurs for pollutants distribution. According to the simulation results, it can be seen that the fastest wind (last of March) moves pollutants in a horizontal direction and the slowest wind (middle of May) moves pollutants vertically. Besides, the design of flare stack in compliance according to EPA Oil and Gas Facility Stack Parameters likely shows pollutants concentration remains on the under threshold NAAQS (National Ambient Air Quality Standards).

Keywords: flare motion, new prediction, pollutants distribution, transition season, WRF model

Procedia PDF Downloads 556

Authors: Tatiana G. Smirnova, Stan G. Benjamin

Abstract:

Rapid Update Cycle (RUC) land surface model (LSM) was a land-surface component in several generations of operational weather prediction models at the National Center for Environment Prediction (NCEP) at the National Oceanic and Atmospheric Administration (NOAA). It was designed for short-range weather predictions with an emphasis on severe weather and originally was intentionally simple to avoid uncertainties from poorly known parameters. Nevertheless, the RUC LSM, when coupled with the hourly-assimilating atmospheric model, can produce a realistic evolution of time-varying soil moisture and temperature, as well as the evolution of snow cover on the ground surface. This result is possible only if the soil/vegetation/snow component of the coupled weather prediction model has sufficient skill to avoid long-term drift. RUC LSM was first implemented in the operational NCEP Rapid Update Cycle (RUC) weather model in 1998 and later in the Weather Research Forecasting Model (WRF)-based Rapid Refresh (RAP) and High-resolution Rapid Refresh (HRRR). Being available to the international WRF community, it was implemented in operational weather models in Austria, New Zealand, and Switzerland. Based on the feedback from the US weather service offices and the international WRF community and also based on our own validation, RUC LSM has matured over the years. Also, a sea-ice module was added to RUC LSM for surface predictions over the Arctic sea-ice. Other modifications include refinements to the snow model and a more accurate specification of albedo, roughness length, and other surface properties. At present, RUC LSM is being tested in the regional application of the Unified Forecast System (UFS). The next generation UFS-based regional Rapid Refresh FV3 Standalone (RRFS) model will replace operational RAP and HRRR at NCEP. Over time, RUC LSM participated in several international model intercomparison projects to verify its skill using observed atmospheric forcing. The ESM-SnowMIP was the last of these experiments focused on the verification of snow models for open and forested regions. The simulations were performed for ten sites located in different climatic zones of the world forced with observed atmospheric conditions. While most of the 26 participating models have more sophisticated snow parameterizations than in RUC, RUC LSM got a high ranking in simulations of both snow water equivalent and surface temperature. However, ESM-SnowMIP experiment also revealed some issues in the RUC snow model, which will be addressed in this paper. One of them is the treatment of grid cells partially covered with snow. RUC snow module computes energy and moisture budgets of snow-covered and snow-free areas separately by aggregating the solutions at the end of each time step. Such treatment elevates the importance of computing in the model snow cover fraction. Improvements to the original simplistic threshold-based approach have been implemented and tested both offline and in the coupled weather model. The detailed description of changes to the snow cover fraction and other modifications to RUC soil and snow parameterizations will be described in this paper.

Keywords: land-surface models, weather prediction, hydrology, boundary-layer processes

Procedia PDF Downloads 89

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 140

Authors: Soheila Sadeghi

Abstract:

Construction projects are complex and often subject to significant cost overruns due to the multifaceted nature of the activities involved. Accurate cost estimation is crucial for effective budget planning and resource allocation. Traditional methods for predicting overruns often rely on expert judgment or analysis of historical data, which can be time-consuming, subjective, and may fail to consider important factors. However, with the increasing availability of data from construction projects, machine learning techniques can be leveraged to improve the accuracy of overrun predictions. This study applied machine learning algorithms to enhance the prediction of cost overruns in a case study of a construction project. The methodology involved the development and evaluation of two machine learning models: Random Forest and Neural Networks. Random Forest can handle high-dimensional data, capture complex relationships, and provide feature importance estimates. Neural Networks, particularly Deep Neural Networks (DNNs), are capable of automatically learning and modeling complex, non-linear relationships between input features and the target variable. These models can adapt to new data, reduce human bias, and uncover hidden patterns in the dataset. The findings of this study demonstrate that both Random Forest and Neural Networks can significantly improve the accuracy of cost overrun predictions compared to traditional methods. The Random Forest model also identified key cost drivers and risk factors, such as changes in the scope of work and delays in material delivery, which can inform better project risk management. However, the study acknowledges several limitations. First, the findings are based on a single construction project, which may limit the generalizability of the results to other projects or contexts. Second, the dataset, although comprehensive, may not capture all relevant factors influencing cost overruns, such as external economic conditions or political factors. Third, the study focuses primarily on cost overruns, while schedule overruns are not explicitly addressed. Future research should explore the application of machine learning techniques to a broader range of projects, incorporate additional data sources, and investigate the prediction of both cost and schedule overruns simultaneously.

Keywords: cost prediction, machine learning, project management, random forest, neural networks

Procedia PDF Downloads 60

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: retail stores, faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition

Procedia PDF Downloads 157

Authors: Zhaoan Wang

Abstract:

Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.

Keywords: automated supply chain, intelligent manufacturing, predictive maintenance machine learning, feature engineering, model interpretation

Procedia PDF Downloads 133