Search results for: large classes

Authors: Gizem Eser Erdek

Abstract:

This study is research on predicting the remaining life of industrial cutting tools used in the industrial production process with deep learning methods. When the life of cutting tools decreases, they cause destruction to the raw material they are processing. This study it is aimed to predict the remaining life of the cutting tool based on the damage caused by the cutting tools to the raw material. For this, hole photos were collected from the hole-drilling machine for 8 months. Photos were labeled in 5 classes according to hole quality. In this way, the problem was transformed into a classification problem. Using the prepared data set, a model was created with convolutional neural networks, which is a deep learning method. In addition, VGGNet and ResNet architectures, which have been successful in the literature, have been tested on the data set. A hybrid model using convolutional neural networks and support vector machines is also used for comparison. When all models are compared, it has been determined that the model in which convolutional neural networks are used gives successful results of a %74 accuracy rate. In the preliminary studies, the data set was arranged to include only the best and worst classes, and the study gave ~93% accuracy when the binary classification model was applied. The results of this study showed that the remaining life of the cutting tools could be predicted by deep learning methods based on the damage to the raw material. Experiments have proven that deep learning methods can be used as an alternative for cutting tool life estimation.

Keywords: classification, convolutional neural network, deep learning, remaining life of industrial cutting tools, ResNet, support vector machine, VggNet

Procedia PDF Downloads 47

Authors: Debjani Ghosh, Goutam Chowdhury, Prosenjit Samanta, Asish Kumar Mukhopadhyay

Abstract:

Acute diarrhoea caused by diarrheagenic Escherichia coli (DEC) is one of the major public health problem in developing countries, mainly in Asia and Africa. DEC consists of six pathogroups, but the majority of the cases were associated with the three pathogropus, enterotoxigenic E. coli (ETEC), enteroaggregative E. coli (EAEC), and enteropathogenic E. coli (EPEC). Hence, we studied the prevalence and antimicrobial resistance of these three major DEC pathogroups in hospitalized diarrheal patients in Kolkata, India, during 2012-2019 with a large sample size. 8,891 stool samples were processed, and 7.8% of them was identified as DEC infection screened by multiplex PCR, in which ETEC was most common (47.7%) followed by EAEC (38.4%) and EPEC (13.9%). Clinical patient history suggested that children <5 years of age were mostly affected with ETEC and EAEC, whereas people within >5-14 years of age were significantly associated with EPEC and ETEC infections. Antibiogram profile showed a high prevalence of multidrug resistant (MDR) isolates among DEC (56.9%), in which 9% were resistant to antibiotics of six different antimicrobial classes. Screening of the antibiotic resistance conferring genes in DEC showed the presence of blaCTX-M (30.2%) in highest number followed by blaTEM (27.5%), tetB (18%), sul2 (12.6%), strA (11.8%), aadA1 (9.8%), blaOXA-1 (9%), dfrA1 (1.6%) and blaSHV (1.2%) which indicates the existence of mobile genetic elements in those isolates. Therefore, the presence of MDR DEC strains in higher number alarms the public health authorities to take preventive measures before the upsurge of the DEC caused diarrhea cases in near future.

Keywords: diarrheagenic escherichia coli, ETEC, EAEC, EPEC

Procedia PDF Downloads 127

Authors: R. Benakcha, M. Omari

Abstract:

Powders of La1-xMgxAlO3 (0 ≤ x ≤ 5) oxides, with large surface areas were synthesized by sol-gel process, utilizing citric acid. Heating of a mixed solution of CA, EtOH, and nitrates of lanthanum, aluminium and magnesium at 70°C gave transparent gel without any precipitation. The formation of pure perovskite La1-xMgxAlO3, occurred when the precursor was heat-treated at 800°C for 6 h. No X-ray diffraction evidence for the presence of crystalline impurities was obtained. The La1-xMgxAlO3 powders prepared by the sol-gel method have a considerably large surface area in the range of 12.9–20 m^2.g^-1 when compared with 0.3 m^2.g^-1 for the conventional solid-state reaction of LaAlO3. The structural characteristics were examined by means of conventional techniques namely X-ray diffraction, infrared spectroscopy, thermogravimetry and differential thermal (TG-DTA) and specific surface SBET. Pore diameters and crystallite sizes are in the 8.8-11.28 nm and 25.4-30.5 nm ranges, respectively. The sol-gel method is a simple technique that has several advantages. In addition to that of not requiring high temperatures, it has the potential to synthesize many kinds of mixed oxides and obtain other materials homogeneous and large purities. It also allows formatting a variety of materials: very fine powders, fibers and films.

Keywords: aluminate, lanthan, perovskite, sol-gel

Procedia PDF Downloads 253

Authors: Benjamin Leiby, Darryl Ahner

Abstract:

This study demonstrates an alternative stochastic imputation approach for large datasets when preferred commercial packages struggle to iterate due to numerical problems. A large country conflict dataset motivates the search to impute missing values well over a common threshold of 20% missingness. The methodology capitalizes on correlation while using model residuals to provide the uncertainty in estimating unknown values. Examination of the methodology provides insight toward choosing linear or nonlinear modeling terms. Static tolerances common in most packages are replaced with tailorable tolerances that exploit residuals to fit each data element. The methodology evaluation includes observing computation time, model fit, and the comparison of known values to replaced values created through imputation. Overall, the country conflict dataset illustrates promise with modeling first-order interactions while presenting a need for further refinement that mimics predictive mean matching.

Keywords: correlation, country conflict, imputation, stochastic regression

Procedia PDF Downloads 93

Authors: Gholam Reza Parvizi, Hossein Azad, Ali Reza Kargar

Abstract:

This article investigated the impact of task-based language teaching (TBLT) on writing performance of the Iranian intermediate EFL learners. There were two groups of forty students of the intermediate female learners studying English in Jahad-e-Daneshgahi language institute, ranging in age from thirteen to nineteen. They participated in their regular classes in the institute and were assigned to two groups including an experimental group of task-based language teaching and a control group for the purpose of homogeneity, all students in two groups took an achievement test before the treatment. As a pre-test; students were assigned to write a task at the beginning of the course. One of the classes was conducted through talking a TBLT approach on their writing, while the other class followed regular patterns of teaching, namely traditional approach for TBLT group. There were some tasks chosen from learners’ textbook. The task selection was in accordance with learning standards for ESL and TOFEL writing sections. At the end of the treatment, a post-test was administered to both experimental group and the control group. Scoring was done on the basis of scoring scale of “expository writing quality scale”. The researcher used paired samples t-test to analyze the effect of TBLT teaching approach on the writing performance of the learners. The data analysis revealed that the subjects in TBLT group performed better on the writing performance post-test than the subjects in control group. The findings of the study also demonstrated that TBLT would enhance writing performance in the group of learners. Moreover, it was indicated that TBLT has been effective in teaching writing performance to Iranian EFL learners

Keywords: task-based language teaching, task, language teaching approach, writing proficiency, EFL learners

Procedia PDF Downloads 395

Authors: Ubaka Chukwuemeka Michael, Ukwe Chinwe Victoria

Abstract:

Background: The use of antipsychotic monotherapy remains the standard for schizophrenic disorders so also a prescription switch from older typical to newer atypical classes of antipsychotics on the basis of better efficacy and tolerability. However, surveys on the quality of antipsychotic drug use and substitution in developing countries are very scarce. This study was intended to evaluate quality and factors that drive the prescription and substitution of antipsychotic drugs among schizophrenic patients visiting a regional psychiatric hospital. Methods: Case files of patients visiting a federal government funded Neuropsychiatric Hospital between July 2012 and July 2014 were systematically retrieved. Patient demographic characteristics, clinical details and drug management data were collected and subjected to descriptive and inferential data analysis to determine quality and predictors of utilization. Results: Of the 600 case files used, there were more male patients (55.3%) with an overall mean age of 33.7±14.4 years. Typical antipsychotic agents accounted for over 85% of prescriptions, with majority of the patients receiving more than 2 drugs in at least a visit (80.9%). Fluphenazine (25.2%) and Haloperidol (18.8%) were mostly given as antipsychotics for treatment initiation while Olazenpine (23.0%) and Benzhexol (18.3%) were the most currently prescribed antipsychotics. Nearly half (42%, 252/600) of these patients were switched from one class to another, with 34.5% (207/600) of them switched from typical to atypical drug classes. No demographic or clinical factors influenced drug substitutions but a younger age and being married influenced being prescribed a polypharmacy regimen (more than 2 drugs) and an injectable antipsychotic agent. Conclusion: The prevalence of antipsychotic polypharmacy and use of typical agents among these patients was high. However, only age and marital status affected the quality of antipsychotic prescriptions among these patients.

Keywords: antipsychotics, drug substitution, pharmacoepidemiology, polypharmacy

Procedia PDF Downloads 443

Authors: Debarag Banerjee, Pooja Singh, Arjun Avadhanam, Saksham Srivastava

Abstract:

Autonomous conversational agents, i.e., chatbots, are becoming an increasingly common mechanism for enterprises to provide support to customers and partners. In order to rate chatbots, especially ones powered by Generative AI tools like Large Language Models (LLMs), we need to be able to accurately assess their performance. This is where chatbot benchmarking becomes important. In this paper, authors propose the use of a benchmark that they call the E2E (End to End) benchmark and show how the E2E benchmark can be used to evaluate the accuracy and usefulness of the answers provided by chatbots, especially ones powered by LLMs. The authors evaluate an example chatbot at different levels of sophistication based on both our E2E benchmark as well as other available metrics commonly used in the state of the art and observe that the proposed benchmark shows better results compared to others. In addition, while some metrics proved to be unpredictable, the metric associated with the E2E benchmark, which uses cosine similarity, performed well in evaluating chatbots. The performance of our best models shows that there are several benefits of using the cosine similarity score as a metric in the E2E benchmark.

Keywords: chatbot benchmarking, end-to-end (E2E) benchmarking, large language model, user centric evaluation.

Procedia PDF Downloads 41

Authors: Saria Almarzook, Monika Reissmann, Gudrun Brockmann

Abstract:

Due to its history, occurrence in different ecosystems and diverse using, the modern horse (Equus caballus) shows large variability in size, appearance, behavior and habits. At all times, breeders try to create groups (breeds, strains) representing high homology but showing clear differences in comparison to other groups. A great interest of analyzing phenotypic and genetic traits looking for real diversity and genetic uniqueness existents for Arabian horses in Syria. 90 Arabian horses from governmental research center of Arabian horses in Damascus were included. The horses represent three strains (Kahlawi, Saklawi, Hamdani) originated from different geographical zones. They were raised on the same farm, under stable conditions. Twelve phenotypic traits were measured: wither height (WH), croup width (CW), croup height (CH), neck girth (NG), thorax girth (TG), chest girth (ChG), chest depth (ChD), chest width (ChW), back line length (BLL), body length (BL), fore cannon length (FCL) and hind cannon length (HCL). The horses were divided into groups according to age (less than 2 years, 2-4 years, 4-9 years, over 9 years) and to sex (male, female). The statistical analyzes show that age has significant influence of WH while the strain has only a very limited effect. On CW, NG, BLL, FCL and HCL, there is only a significant influence of sex. Age has significant effect on CH and BL. All sources of classes have a significant effect on TG, ChG, ChD and ChW. Strain has a significant effect on the BL. These results provide first information for real biodiversity in and between the strains and can be used to develop the breeding work in the Arabian horse breed.

Keywords: Arabian horse, phenotypic traits, strains, Syria

Procedia PDF Downloads 361

Authors: M. Aghili, S. Tabarestani, C. Freytes, M. Shojaie, M. Cabrerizo, A. Barreto, N. Rishe, R. E. Curiel, D. Loewenstein, R. Duara, M. Adjouadi

Abstract:

A major challenge in medical studies, especially those that are longitudinal, is the problem of missing measurements which hinders the effective application of many machine learning algorithms. Furthermore, recent Alzheimer's Disease studies have focused on the delineation of Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI) from cognitively normal controls (CN) which is essential for developing effective and early treatment methods. To address the aforementioned challenges, this paper explores the potential of using the eXtreme Gradient Boosting (XGBoost) algorithm in handling missing values in multiclass classification. We seek a generalized classification scheme where all prodromal stages of the disease are considered simultaneously in the classification and decision-making processes. Given the large number of subjects (1631) included in this study and in the presence of almost 28% missing values, we investigated the performance of XGBoost on the classification of the four classes of AD, NC, EMCI, and LMCI. Using 10-fold cross validation technique, XGBoost is shown to outperform other state-of-the-art classification algorithms by 3% in terms of accuracy and F-score. Our model achieved an accuracy of 80.52%, a precision of 80.62% and recall of 80.51%, supporting the more natural and promising multiclass classification.

Keywords: eXtreme gradient boosting, missing data, Alzheimer disease, early mild cognitive impairment, late mild cognitive impair, multiclass classification, ADNI, support vector machine, random forest

Procedia PDF Downloads 160

Authors: Ming-Dong Wang, Abigail F. Ruby, Michelle E. Ross

Abstract:

Methylphenidate is a first-line treatment drug for attention deficit hyperactivity disorder (ADHD), a common mental health disorder in children and adolescents. Over the last several decades, the rate of children and adolescents using ADHD medication has been increasing in many countries. A recent study found that the prevalence of ADHD medication use among children aged 3-18 years increased in 13 different world regions between 2001 and 2015, where the absolute increase ranged from 0.02 to 0.26% per year. The goal of this study was to examine the use of methylphenidate in Canadian children and its associated adverse reactions. Methylphenidate use information among young Canadians aged 0-14 years was extracted from IQVIA data on prescriptions dispensed by pharmacies between April 2014 and June 2020. The adverse reaction information associated with methylphenidate use was extracted from the Canada Vigilance database for the same time period. Methylphenidate use trends were analyzed based on sex, age group (0-4 years, 5-9 years, and 10-14 years), and geographical location (province). The common classes of adverse reactions associated with methylphenidate use were sorted, and the relative risks associated with methylphenidate use as compared with two second-line amphetamine medications for ADHD were estimated. This study revealed that among Canadians aged 0-14 years, every 100 people used about 25 prescriptions (or 23,000 mg) of methylphenidate per year during the study period, and the use increased with time. Boys used almost three times more methylphenidate than girls. The amount of drug used was inversely associated with age: Canadians aged 10-14 years used nearly three times as many drugs compared to those aged 5-9 years. Seasonal methylphenidate use patterns were apparent among young Canadians, but the seasonal trends differed among the three age groups. Methylphenidate use varied from region to region, and the highest methylphenidate use was observed in Quebec, where the use of methylphenidate was at least double that of any other province. During the study period, Health Canada received 304 adverse reaction reports associated with the use of methylphenidate for Canadians aged 0-14 years. The number of adverse reaction reports received for boys was 3.5 times higher than that for girls. The three most common adverse reaction classes were psychiatric disorders, nervous system disorders and injury, poisoning procedural complications. The number one commonly reported adverse reaction for boys was aggression (11.2%), while for girls, it was a tremor (9.6%). The safety profile in terms of adverse reaction classes associated with methylphenidate use was similar to that of the selected control products. Methylphenidate is a commonly used pharmaceutical product in young Canadians, particularly in the province of Quebec. Boys used approximately three times more of this product as compared to girls. Future investigation is needed to determine what factors are associated with the observed geographic variations in Canada.

Keywords: adverse reaction risk, methylphenidate, prescription trend, use variation

Procedia PDF Downloads 134

Authors: Emilija Tribocka

Abstract:

This contribution presents parts of an ongoing study of a diachronic relationship between two weak verb classes in Norwegian, the a-class (cf. the paradigm of ‘throw’: kasta – kastar – kasta – kasta) and the e-class (cf. the paradigm of ‘buy’: kjøpa – kjøper – kjøpte – kjøpt). The study investigates inflection class shifts between the two classes with Old Norse, the ancestor of Modern Norwegian, as a starting point. Examination of inflection in 38 verbs in four chosen dialect areas (106 places of attestations) demonstrates that the shifts from the a-class to the e-class are widespread to varying degrees in three out of four investigated areas and are more common than the shifts in the opposite direction. The diachronic productivity of the e-class is unexpected for several reasons. There is general agreement that type frequency is an important factor influencing productivity. The a-class (53% of all weak verbs) was more type frequent in Old Norse than the e-class (42% of all weak verbs). Thus, given the type frequency, the expansion of the e-class is unexpected. Furthermore, in the ‘core’ areas of expanded e-class inflection, the shifts disregard phonological principles creating forms with uncomfortable consonant clusters, e.g., fiskte instead of fiska, the preterit of fiska ‘fish’. Later on, these forms may be contracted, i.e., fiskte > fiste. In this contribution, two factors influencing the shifts are presented: phonological form and token frequency. Verbs with the stem ending in a consonant cluster, particularly when the cluster ends in -t, hardly ever shift to the e-class. As a matter of fact, verbs with this structure belonging to the e-class in Old Norse shift to the a-class in Modern Norwegian, e.g., ON e-class verb skipta ‘change’ shifts to the a-class. This shift occurs as a result of the lack of morpho-phonological transparency between the stem and the preterit suffix of the e-class, -te. As there is a phonological fusion between the stem ending in -t and the suffix beginning in -t, the transparent a-class inflection is chosen. Token frequency plays an important role in the shifts, too, in some dialects. In one of the investigated areas, the most token frequent verbs of the ON e-class remain in the e-class (e.g., høyra ‘hear’, leva ‘live’, kjøpa ‘buy’), while less frequent verbs may shift to the a-class. Furthermore, the results indicate that the shift from the a-class to the e-class occurs in some of the most token frequent verbs of the ON a-class in this area, e.g., lika ‘like’, lova ‘promise’, svara ‘answer’. The latter is unexpected as frequent items tend to remain stable. This study presents a case of unexpected productivity, demonstrating that minor patterns can grow and outdo major patterns. Thus, type frequency is not the only factor that determines productivity. The study addresses the role of phonological form and token frequency in the spread of inflection patterns.

Keywords: inflection class, productivity, token frequency, phonological form

Procedia PDF Downloads 32

Authors: Kadidiatou Toure

Abstract:

Mali has started experimentation of teaching the national languages at school through the convergent pedagogy in 1987. Then, it is in 1994 that it will become widespread with eleven of the thirteen former national languages used at primary school. The aim was to improve the Malian educational system because the use of French as the only medium of instruction was considered a contributing factor to the significant number of student dropouts and the high rate of repetition. The Convergent pedagogy highlights the knowledge acquired by children at home, their vision of the world and especially the knowledge they have of their mother tongue. That pedagogy requires the use of a specific medium only during classroom practices and teachers have been trained in this sense. The specific medium depends on the learning content, which sometimes is French, other times, it is the national language. Research has shown that bilingual learners do not only use the required medium in their learning activities, but they code switch. It is part of their learning processes. Currently, many scholars agree on the importance of CS in bilingual classes, and teachers have been told about the necessity of integrating it into their classroom practices. One of the challenges of the Malian bilingual education curriculum is the question of ‘effective languages management’. Theoretically, depending on the classrooms, an average have been established for each of the involved language. Following that, teachers make use of CS differently, sometimes, it favors the learners, other times, it contributes to the development of some linguistic weaknesses. The present research tries to fill that gap through a tentative model of didactization of CS, which simply means the practical management of the languages involved in the bilingual classrooms. It is to know how to use CS for effective learning. Moreover, the didactization of CS tends to sensitize the teachers about the functional role of CS so that they may overcome their own weaknesses. The overall goal of this research is to make code switching a real tool for bilingual education. The specific objectives are: to identify the types of CS used during classroom activities to present the functional role of CS for the teachers as well as the pupils. to develop a tentative model of code-switching, which will help the teachers in transitional classes of bilingual schools to recognize the appropriate moment for making use of code switching in their classrooms. The methodology adopted is a qualitative one. The study is based on recorded videos of teachers of 3rd year of primary school during their classroom activities and interviews with the teachers in order to confirm the functional role of CS in bilingual classes. The theoretical framework adopted is the typology of CS proposed by Poplack (1980) to identify the types of CS used. The study reveals that teachers need to be trained on the types of CS and the different functions they assume and on the consequences of inappropriate use of language alternation.

Keywords: bilingual curriculum, code switching, didactization, national languages

Procedia PDF Downloads 36

Authors: Salma El Hajjami, Jamal Malki, Alain Bouju, Mohammed Berrada

Abstract:

With the expansion of machine learning and data mining in the context of Big Data analytics, the common problem that affects data is class imbalance. It refers to an imbalanced distribution of instances belonging to each class. This problem is present in many real world applications such as fraud detection, network intrusion detection, medical diagnostics, etc. In these cases, data instances labeled negatively are significantly more numerous than the instances labeled positively. When this difference is too large, the learning system may face difficulty when tackling this problem, since it is initially designed to work in relatively balanced class distribution scenarios. Another important problem, which usually accompanies these imbalanced data, is the overlapping instances between the two classes. It is commonly referred to as noise or overlapping data. In this article, we propose an approach called: One Side Behavioral Noise Reduction (OSBNR). This approach presents a way to deal with the problem of class imbalance in the presence of a high noise level. OSBNR is based on two steps. Firstly, a cluster analysis is applied to groups similar instances from the minority class into several behavior clusters. Secondly, we select and eliminate the instances of the majority class, considered as behavioral noise, which overlap with behavior clusters of the minority class. The results of experiments carried out on a representative public dataset confirm that the proposed approach is efficient for the treatment of class imbalances in the presence of noise.

Keywords: machine learning, imbalanced data, data mining, big data

Procedia PDF Downloads 106

Authors: Lu Si, Jie Yu, Shasha Li, Jun Ma, Lei Luo, Qingbo Wu, Yongqi Ma, Zhengji Liu

Abstract:

Instance selection (IS) technique is used to reduce the data size to improve the performance of data mining methods. Recently, to process very large data set, several proposed methods divide the training set into some disjoint subsets and apply IS algorithms independently to each subset. In this paper, we analyze the limitation of these methods and give our viewpoint about how to divide and conquer in IS procedure. Then, based on fast condensed nearest neighbor (FCNN) rule, we propose a large data sets instance selection method with MapReduce framework. Besides ensuring the prediction accuracy and reduction rate, it has two desirable properties: First, it reduces the work load in the aggregation node; Second and most important, it produces the same result with the sequential version, which other parallel methods cannot achieve. We evaluate the performance of FCNN-MR on one small data set and two large data sets. The experimental results show that it is effective and practical.

Keywords: instance selection, data reduction, MapReduce, kNN

Procedia PDF Downloads 232

Authors: Mangana B. Rampheri, Timothy Dube, Farai Dondofema, Tatenda Dalu

Abstract:

Identifying and delineating groundwater-dependent ecosystems (GDEs) is critical to the well understanding of the GDEs spatial distribution as well as groundwater allocation. However, this information is inadequately understood due to limited available data for the most area of concerns. Thus, this study aims to address this gap using remotely sensed, analytical hierarchy process (AHP) and in-situ data to identify and delineate GDEs in Khakea-Bray Transboundary Aquifer. Our study developed GDEs index, which integrates seven explanatory variables, namely, Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Land-use and landcover (LULC), slope, Topographic Wetness Index (TWI), flow accumulation and curvature. The GDEs map was delineated using the weighted overlay tool in ArcGIS environments. The map was spatially classified into two classes, namely, GDEs and Non-GDEs. The results showed that only 1,34 % (721,91 km2) of the area is characterised by GDEs. Finally, groundwater level (GWL) data was used for validation through correlation analysis. Our results indicated that: 1) GDEs are concentrated at the northern, central, and south-western part of our study area, and 2) the validation results showed that GDEs classes do not overlap with GWL located in the 22 boreholes found in the given area. However, the results show a possible delineation of GDEs in the study area using remote sensing and GIS techniques along with AHP. The results of this study further contribute to identifying and delineating priority areas where appropriate water conservation programs, as well as strategies for sustainable groundwater development, can be implemented.

Keywords: analytical hierarchy process (AHP), explanatory variables, groundwater-dependent ecosystems (GDEs), khakea-bray transboundary aquifer, sentinel-2

Procedia PDF Downloads 80

Authors: Youssef Abdelli, Rachid Nasri

Abstract:

The large amplitude free vibration analysis of three-layered symmetric sandwich beams is carried out using two different approaches. The governing nonlinear partial differential equations of motion in free natural vibration are derived using Hamilton's principle. The formulation leads to two nonlinear partial differential equations that are coupled both in axial and binding deformations. In the first approach, the method of multiple scales is applied directly to the governing equation that is a nonlinear partial differential equation. In the second approach, we discretize the governing equation by using Galerkin's procedure and then apply the shooting method to the obtained ordinary differential equations. In order to check the validity of the solutions obtained by the two approaches, they are compared with the solutions obtained by two approaches; they are compared with the solutions obtained numerically by the finite difference method.

Keywords: finite difference method, large amplitude vibration, multiple scales, nonlinear vibration

Procedia PDF Downloads 430

Authors: Gangmin Li, Fan Yang

Abstract:

Personalized recommendation is crucial for any recommendation system. One of the techniques for personalized recommendation is to identify the intention. Traditional user intention identification uses the user’s selection when facing multiple items. This modeling relies primarily on historical behaviour data resulting in challenges such as the cold start, unintended choice, and failure to capture intention when items are new. Motivated by recent advancements in Large Language Models (LLMs) like ChatGPT, we present an approach for user intention identification by embracing LLMs with Chain-of-Thought (CoT) prompting. We use the initial user profile as input to LLMs and design a collection of prompts to align the LLM's response through various recommendation tasks encompassing rating prediction, search and browse history, user clarification, etc. Our tests on real-world datasets demonstrate the improvements in recommendation by explicit user intention identification and, with that intention, merged into a user model.

Keywords: personalized recommendation, generative user modelling, user intention identification, large language models, chain-of-thought prompting

Procedia PDF Downloads 12

Authors: A.Knox

Abstract:

Student diversity in postgraduate classes puts major challenges on educators seeking to encourage student engagement and desired to learn outcomes. This paper outlines the impact of a set of teaching initiatives aimed at addressing challenges associated with teaching and learning in an environment characterized by diversity in the student cohort. The study examines postgraduate students completing the core capstone unit within a specialized business degree. Although relatively small, the student cohort is highly diverse in terms of cultural backgrounds represented, prior learning and/or qualifications, as well as duration and type of work experience relevant to the degree, is completed. The wide range of cultures, existing knowledge and experience create enormous challenges with respect to students’ learning needs and outcomes. Subsequently, a suite of teaching innovations has been adopted to enhance curriculum content/delivery and the design of assessments. This paper explores the impact of these specific teaching and learning practices, examining the ways they have supported students’ diverse needs and enhanced students’ learning outcomes. Data from surveys and focus groups are used to assess the effectiveness of these practices. The results highlight the effectiveness of peer-assisted learning, cultural competence-building, and advanced assessment options in addressing diverse student needs and enhancing student engagement and learning outcomes. These findings suggest that such practices would benefit students’ learning in environments marked by diversity in the student cohort. Specific recommendations are offered for other educators working with diverse classes.

Keywords: assessment design, curriculum content, curriculum delivery, student diversity

Procedia PDF Downloads 84

Authors: Somayeh Komeylian

Abstract:

The direction of arrival (DoA) estimation is the crucial aspect of the radar technologies for detecting and dividing several signal sources. In this scenario, the antenna array output modeling involves numerous parameters including noise samples, signal waveform, signal directions, signal number, and signal to noise ratio (SNR), and thereby the methods of the DoA estimation rely heavily on the generalization characteristic for establishing a large number of the training data sets. Hence, we have analogously represented the two different optimization models of the DoA estimation; (1) the implementation of the decision directed acyclic graph (DDAG) for the multiclass least-squares support vector machine (LS-SVM), and (2) the optimization method of the deep neural network (DNN) radial basis function (RBF). We have rigorously verified that the LS-SVM DDAG algorithm is capable of accurately classifying DoAs for the three classes. However, the accuracy and robustness of the DoA estimation are still highly sensitive to technological imperfections of the antenna arrays such as non-ideal array design and manufacture, array implementation, mutual coupling effect, and background radiation and thereby the method may fail in representing high precision for the DoA estimation. Therefore, this work has a further contribution on developing the DNN-RBF model for the DoA estimation for overcoming the limitations of the non-parametric and data-driven methods in terms of array imperfection and generalization. The numerical results of implementing the DNN-RBF model have confirmed the better performance of the DoA estimation compared with the LS-SVM algorithm. Consequently, we have analogously evaluated the performance of utilizing the two aforementioned optimization methods for the DoA estimation using the concept of the mean squared error (MSE).

Keywords: DoA estimation, Adaptive antenna array, Deep Neural Network, LS-SVM optimization model, Radial basis function, and MSE

Procedia PDF Downloads 74

Authors: Shaukat Ali Shahee, Usha Ananthakumar

Abstract:

A data set exhibits class imbalance problem when one class has very few examples compared to the other class, and this is also referred to as between class imbalance. The traditional classifiers fail to classify the minority class examples correctly due to its bias towards the majority class. Apart from between-class imbalance, imbalance within classes where classes are composed of a different number of sub-clusters with these sub-clusters containing different number of examples also deteriorates the performance of the classifier. Previously, many methods have been proposed for handling imbalanced dataset problem. These methods can be classified into four categories: data preprocessing, algorithmic based, cost-based methods and ensemble of classifier. Data preprocessing techniques have shown great potential as they attempt to improve data distribution rather than the classifier. Data preprocessing technique handles class imbalance either by increasing the minority class examples or by decreasing the majority class examples. Decreasing the majority class examples lead to loss of information and also when minority class has an absolute rarity, removing the majority class examples is generally not recommended. Existing methods available for handling class imbalance do not address both between-class imbalance and within-class imbalance simultaneously. In this paper, we propose a method that handles between class imbalance and within class imbalance simultaneously for binary classification problem. Removing between class imbalance and within class imbalance simultaneously eliminates the biases of the classifier towards bigger sub-clusters by minimizing the error domination of bigger sub-clusters in total error. The proposed method uses model-based clustering to find the presence of sub-clusters or sub-concepts in the dataset. The number of examples oversampled among the sub-clusters is determined based on the complexity of sub-clusters. The method also takes into consideration the scatter of the data in the feature space and also adaptively copes up with unseen test data using Lowner-John ellipsoid for increasing the accuracy of the classifier. In this study, neural network is being used as this is one such classifier where the total error is minimized and removing the between-class imbalance and within class imbalance simultaneously help the classifier in giving equal weight to all the sub-clusters irrespective of the classes. The proposed method is validated on 9 publicly available data sets and compared with three existing oversampling techniques that rely on the spatial location of minority class examples in the euclidean feature space. The experimental results show the proposed method to be statistically significantly superior to other methods in terms of various accuracy measures. Thus the proposed method can serve as a good alternative to handle various problem domains like credit scoring, customer churn prediction, financial distress, etc., that typically involve imbalanced data sets.

Keywords: classification, imbalanced dataset, Lowner-John ellipsoid, model based clustering, oversampling

Procedia PDF Downloads 390

Authors: Teerada Apibunyopas, Nithinant Thammakoranonta

Abstract:

Many organizations bring e-Learning to use as a tool in their training and human development department. It is getting more popular because it is easy to access to get knowledge all the time and also it provides a rich content, which can develop the employees skill efficiently. This study focused on the factors that affect using e-Learning efficiently, so it will make job satisfaction increased. The questionnaires were sent to employees in large commercial banks, which use e-Learning located in Bangkok, the results from multiple linear regression analysis showed that employee’s characteristics, characteristics of e-Learning, learning and growth have influence on job satisfaction.

Keywords: e-Learning, job satisfaction, learning and growth, Bangkok

Procedia PDF Downloads 469

Authors: E. Behmanesh, J. Pannek

Abstract:

The distribution-allocation problem is known as one of the most comprehensive strategic decision. In real-world cases, it is impossible to solve a distribution-allocation problem in traditional ways with acceptable time. Hence researchers develop efficient non-traditional techniques for the large-term operation of the whole supply chain. These techniques provide near-optimal solutions particularly for large scales test problems. This paper, presents an integrated supply chain model which is flexible in the delivery path. As the solution methodology, we apply a memetic algorithm with a novelty in population presentation. To illustrate the performance of the proposed memetic algorithm, LINGO optimization software serves as a comparison basis for small size problems. In large size cases that we are dealing with in the real world, the Genetic algorithm as the second metaheuristic algorithm is considered to compare the results and show the efficiency of the memetic algorithm.

Keywords: integrated logistics network, flexible path, memetic algorithm, genetic algorithm

Procedia PDF Downloads 350

Authors: Noman Shabbir, Roheel Nawaz, Muhammad N. Iqbal, Junaid Zafar

Abstract:

This paper focuses on the performance evaluation of routing protocols in WLAN based Wireless Sensor Networks (WSNs). A comparative analysis of routing protocols such as Ad-hoc On-demand Distance Vector Routing System (AODV), Dynamic Source Routing (DSR) and Optimized Link State Routing (OLSR) is been made against different network parameters like network load, end to end delay and throughput in small, medium and large-scale sensor network scenarios to identify the best performing protocol. Simulation results indicate that OLSR gives minimum network load in all three scenarios while AODV gives the best throughput in small scale network but in medium and large scale networks, DSR is better. In terms of delay, OLSR is more efficient in small and medium scale network while AODV is slightly better in large networks.

Keywords: WLAN, WSN, AODV, DSR, OLSR

Procedia PDF Downloads 408

Authors: Liz Carmem Silva-Pereira, Raffael Alencar Mesquita Rodrigues, Francisco Helton Mendes Barbosa, Emerson de Freitas Ferreira

Abstract:

Due to the Covid-19 pandemic declared in March 2020 by the World Health Organization, the way of social coexistence across the planet was affected, especially in educational processes, from the implementation of the remote modality as a teaching strategy. This teaching-learning modality caused a change in the routine and learning of basic education students, which resulted in serious consequences for the return to face-to-face teaching in 2021. 2022, at the Federal Institute of Education, Science and Technology of Pará (IFPA) – Campus Paragominas had their training process severely affected, having studied the initial half of their training in the remote modality, which compromised the carrying out of practical classes, technical visits and field classes, essential for the student formation on the environmental technician. With the objective of promoting the recomposition of these students' learning after returning to the face-to-face modality, an educational strategy was developed in the last period of the course. As teaching methodologies were used for research as an educational principle, the integrative project and the parallel recovery action applied jointly, aiming at recomposing the basic knowledge of the natural sciences, together with the technical knowledge of the environmental area applied to the course. The project assisted 58 finalist students of the environmental technical course. A research instrument was elaborated with parameters of evaluation of the environmental quality for study in 19 collection points, in the Uraim River urban hydrographic basin, in the Paragominas City – Pará – Brazilian Amazon. Students were separated into groups under the professors' and laboratory assistants’ orientation, and in the field, they observed and evaluated the places' environmental conditions and collected physical data and water samples, which were taken to the chemistry and biology laboratories at Campus Paragominas for further analysis. With the results obtained, each group prepared a technical report on the environmental conditions of each evaluated point. This work methodology enabled the practical application of theoretical knowledge received in various disciplines during the remote teaching modality, contemplating the integration of knowledge, people, skills, and abilities for the best technical training of finalist students. At the activity end, the satisfaction of the involved students in the project was evaluated, through a form, with the signing of the informed consent term, using the Likert scale as an evaluation parameter. The results obtained in the satisfaction survey were: on the use of research projects within the disciplines attended, 82% of satisfaction was obtained; regarding the revision of contents in the execution of the project, 84% of satisfaction was obtained; regarding the acquired field experience, 76.9% of satisfaction was obtained, regarding the laboratory experience, 86.2% of satisfaction was obtained, and regarding the use of this methodology as parallel recovery, 71.8% was obtained of satisfaction. In addition to the excellent performance of students in acquiring knowledge, it was possible to remedy the deficiencies caused by the absence of practical classes, technical visits, and field classes, which occurred during the execution of the remote teaching modality, fulfilling the desired educational recomposition.

Keywords: integrative project, parallel recovery, research as an educational principle, teaching-learning

Procedia PDF Downloads 34

Authors: Libin Ouyang

Abstract:

China has experienced a very fast urbanization process in the past two decades. Due to the uncoordinated characteristics of regional development in China, a large number of people from rural areas or small towns have flooded into regional central cities, which are building new cities around them due to the shortage of construction land or the need for urban development. However, the construction of some new cities has not achieved the expected effect, the absorption capacity of industry and population is limited, and the phenomenon of capital and land waste is obvious. This paper takes the Xixian New Area in Shaanxi Province, an inland region in Northwest China, as an example, and tries to analyse the reasons for the lack of vitality in the current situation of the Xixian New Area from the perspective of site layout and urban design, analyses the practical experience of the construction of new city cores in developed countries and regions, and studies how to optimise at the level of site layout planning and urban design to improve the vitality and attractiveness of the new city, decongest the population of large cities, effectively solve the problems of large cities, and promote The study will also examine how to optimise land use planning and urban design to enhance the vitality and attractiveness of new cities, relieve the population of large cities, effectively solve the problems of large cities and promote sustainable development of new cities. The study can serve as a reference for urban planners and policy makers, provide theoretical assistance for new city construction in other less developed regions of China, and provide some case references for urban construction in other developing countries undergoing rapid urbanisation.

Keywords: new city, land use layout, urban design, attraction

Procedia PDF Downloads 91

Authors: Alvaro Javier Ortega

Abstract:

A large number of companies face the challenge of matching highly-skilled professionals to high-end positions by human resource deployment professionals. However, when the professional list and tasks to be matched are larger than a few dozens, this process result is far from optimal and takes a long time to be made. Therefore, an automated assignment algorithm for this workforce management problem is needed. The majority of companies are divided into several sectors or departments, where trained employees with different experience levels deal with a large number of tasks daily. Also, the execution order of all tasks is of mater consequence, due to some of these tasks just can be run it if the result of another task is provided. Thus, a wrong execution order leads to large waiting times between consecutive tasks. The desired goal is, therefore, creating accurate matches and a near-optimal execution order that maximizes the number of tasks performed and minimizes the idle time of the expensive skilled employees. The problem described before can be model as a mixed-integer non-linear programming (MINLP) as it will be shown in detail through this paper. A large number of MINLP algorithms have been proposed in the literature. Here, genetic algorithm solutions are considered and a comparison between two different mutation approaches is presented. The simulated results considering different complexity levels of assignment decisions show the appropriateness of the proposed model.

Keywords: employees, genetic algorithm, industry management, workforce

Procedia PDF Downloads 132

Authors: Yilei Song, Linlin Tian, Ning Zhao

Abstract:

Turbulence energetics and structures in the wake of large-scale wind turbines under the stably-stratified atmospheric boundary layer (SABL) can be complicated due to the presence of low-level jets (LLJs), a region of higher wind speeds than the geostrophic wind speed. With a modified one-k-equation, eddy viscosity model specified for atmospheric flows as the sub-grid scale (SGS) model, a realistic atmospheric state of the stable ABL is well reproduced by large-eddy simulation (LES) techniques. Corresponding to the precursor stably stratification, the detailed wake properties of a standard 5-MW wind turbine represented as an actuator line model are provided. An engineering model is proposed for wake prediction based on the simulation statistics and gets validated. Results confirm that the proposed wake model can provide good predictions for wind turbines under the SABL.

Keywords: large-eddy simulation, stably-stratified atmospheric boundary layer, wake model, wind turbine wake

Procedia PDF Downloads 143

Authors: Andrey A. Chernousov, Ben Y. B. Chan

Abstract:

The thermal behavior of a large-scale, phase change material (PCM) enhanced building envelope system was studied in regard to the need for pre-fabricated construction in subtropical regions. The proposed large-scale envelope consists of a reinforced aluminum skin, insulation core, phase change material and reinforced gypsum board. The PCM impact on an energy efficiency of an enveloped room was resolved by validation of the Energy Plus numerical scheme and optimization of a smart material location in the core. The PCM location was optimized by a minimization method of a cooling energy demand. It has been shown that there is good agreement between the test and simulation results. The optimal location of the PCM layer in Hong Kong summer conditions has been then recomputed for core thicknesses of 40, 60 and 80 mm. A non-dimensional value of the optimal PCM location was obtained to be same for all the studied cases and the considered external and internal conditions.

Keywords: thermal performance, phase change material, energy efficiency, PCM optimization

Procedia PDF Downloads 381

Authors: Siwapong Dheera-Aumpon

Abstract:

Resource misallocation is known to be prevalent in many countries. Such misallocation in the manufacturing sector is large and has a considerable negative effect on aggregate productivity. Thailand is one of the countries having large resource misallocation in the manufacturing sector. Resource misallocation is also known to be widespread in the agricultural sector. It is, therefore, likely that resource misallocation exists in the agricultural sector of Thailand as well. This study aims to evaluate the extent of resource misallocation in Thai rice farming. Using household-level data from 2013 Thai Agricultural Census, this study calculates farm total factor productivity (TFP) controlling for land quality and rain. Similar to the case of Malawi, marginal products of land and capital are found to be related to farm TFP implying large resource misallocation. The output gain from a reallocation of resources to their best use is 67 percent. The gain from reallocation is highest for farms in the southern region and followed by the northeastern region.

Keywords: agriculture, misallocation, productivity, rice

Procedia PDF Downloads 207

Authors: Ellen Van Den Oord, Julien Marie Jan Ferdinand Van Campen

Abstract:

This article introduces a computationally efficient method for stacking sequence blending of composite structures. The computational efficiency makes the presented method especially interesting for composite structures with a large number of design regions. Optimization of composite structures with an unequal load distribution may lead to locally optimized thicknesses and ply orientations that are incompatible with one another. Blending constraints can be enforced to achieve structural continuity. In literature, many methods can be found to implement structural continuity by means of stacking sequence blending in one way or another. The complexity of the problem makes the blending of a structure with a large number of adjacent design regions, and thus stacking sequences, prohibitive. In this work the local stacking sequence optimization is preconditioned using a method found in the literature that couples the mechanical behavior of the laminate, in the form of lamination parameters, to blending constraints, yielding near-optimal easy-to-blend designs. The preconditioned design is then fed to the scheme using cellular automata that have been developed by the authors. The method is applied to the benchmark 18-panel horseshoe blending problem to demonstrate its performance. The computational efficiency of the proposed method makes it especially suited for composite structures with a large number of design regions.

Keywords: composite, blending, optimization, lamination parameters

Procedia PDF Downloads 193