Search results for: teaching learning based algorithm

Authors: Nadeem Hassan, Farooq Ahmad

Abstract:

The quality of education has a direct impact on individual, family, society, economy in general and the mankind as a whole. Because of that thousands of research papers and articles are written on the quality of education, billions of dollars are spent and continuously being spent on research and enhancing the quality of education. Academic programs accredited agencies define the various criterion of quality of education; academic institutions obtain accreditation from these agencies to ensure degree programs offered at their institution are of international standards. This R&D aims to build a web based analytical tool (OptiBaha) that finds the gaps in AlBaha University education system by taking input from stakeholders, including students, faculty, staff and management. The input/online-data collected by this tool will be analyzed on core areas of education as proposed by accredited agencies, CAC of ABET and NCAAA of KSA, including student background, language, culture, motivation, curriculum, teaching methodology, assessment and evaluation, performance and progress, facilities, availability of teaching materials, faculty qualification, monitoring, policies and procedures, and more. Based on different analytical reports, gaps will be highlighted, and remedial actions will be proposed. If the tool is implemented and made available through a continuous process the quality of education at AlBaha University can be enhanced, it will also help in fulfilling criterion of accreditation agencies. The tool will be generic in nature and ultimately can be used by any academic institution.

Keywords: academic quality, accreditation agencies, higher education, policies and procedures

Procedia PDF Downloads 304

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 128

Authors: S. O. Uwaifo

Abstract:

The paper examines the pivotal role of the library in university education through the provision of a wide range of information materials (print and non- print) required for the teaching, learning and research activities of the university. However certain impediments to the effectiveness of Nigerian university libraries, such as financial constraints, high foreign exchange, global disparities in accessing the internet, lack of local area networks, erratic electric power supply, absence of ICT literacy, poor maintenance culture, etc., were identified. Also, the necessity of repositioning Nigerian university libraries for effective information provision and delivery was stressed by pointing out their dividends, such as users’ access to Directory of Open Access Journals (DOAJ), Online Public Access Catalogue (OPAC), Institutional Repositories, Electronic Document Delivery, Social Media Networks, etc. It therefore becomes necessary for the libraries to be repositioned by way of being adequately automated or digitized for effective service delivery, in this age of globalization. Based on the identified barriers by this paper, some recommendations were proffered.

Keywords: repositioning, Nigerian university libraries, effective information provision and delivery, globalization

Procedia PDF Downloads 332

Authors: Sari Myréen

Abstract:

The aim of this study was to evaluate the role of multisensory elements in enhancing and facilitating foreign language acquisition among adult students in a language classroom. The use of multisensory elements enables the creation of a student-centered classroom, where the focus is on individual learner’s language learning process, perceptions and motivation. Multisensory language learning is a pedagogical approach where the language learner uses all the senses more effectively than in a traditional in-class environment. Language learning is facilitated due to multisensory stimuli which increase the number of cognitive connections in the learner and take into consideration different types of learners. A living lab called Multisensory Space creates a relaxed and receptive state in the learners through various multisensory stimuli, and thus promotes their natural foreign language acquisition. Qualitative and quantitative data were collected in two questionnaire inquiries among the Finnish students of a higher education institute at the end of their basic French courses in December 2014 and 2016. The inquiries discussed the effects of multisensory elements on the students’ motivation to study French as well as their learning outcomes. The results show that the French classes in the Multisensory Space provide the students with an encouraging and pleasant learning environment, which has a positive impact on their motivation to study the foreign language as well as their language learning outcomes.

Keywords: foreign language acquisition, pedagogical approach, multisensory learning, transcultural learning

Procedia PDF Downloads 388

Authors: Yu-Chi Chou

Abstract:

The purpose of this study was to establish a logical path of an instructional model of empathy and social regulation, providing feasibility evidence on the model implementation in students with autism spectrum disorder (ASD). This newly developed Emotional Bug-Out Bag (BoB) curriculum was designed to enhance the empathy and socially shared regulation of students with ASD. The BoB model encompassed three instructional phases of basic theory lessons (BTL), action plan practices (APP), and final theory practices (FTP) during implementation. Besides, a learning flow (teacher-directed instruction, student self-directed problem-solving, group-based task completion, group-based reflection) was infused into the progress of instructional phases to deliberately promote the social regulatory process in group-working activities. A total of 23 junior high school students with ASD were implemented with the BoB curriculum. To examine the logical path for model implementation, data was collected from the participating students’ self-report scores on the learning nodes and understanding questions. Path analysis using structural equation modeling (SEM) was utilized for analyzing scores on 10 learning nodes and 41 understanding questions through the three phases of the BoB model. Results showed (a) all participants progressed throughout the implementation of the BoB model, and (b) the models of learning nodes and phases were positive and significant as expected, confirming the hypothesized logic path of this curriculum.

Keywords: autism spectrum disorder, empathy, regulation, socially shared regulation

Procedia PDF Downloads 70

Authors: Songul Cinaroglu

Abstract:

Machine learning regression methods are recommended as an alternative to classical regression methods in the existence of variables which are difficult to model. Data for health expenditure is typically non-normal and have a heavily skewed distribution. This study aims to compare machine learning regression methods by hyperparameter tuning to predict health expenditure per capita. A multiple regression model was conducted and performance results of Lasso Regression, Random Forest Regression and Support Vector Machine Regression recorded when different hyperparameters are assigned. Lambda (λ) value for Lasso Regression, number of trees for Random Forest Regression, epsilon (ε) value for Support Vector Regression was determined as hyperparameters. Study results performed by using 'k' fold cross validation changed from 5 to 50, indicate the difference between machine learning regression results in terms of R², RMSE and MAE values that are statistically significant (p < 0.001). Study results reveal that Random Forest Regression (R² ˃ 0.7500, RMSE ≤ 0.6000 ve MAE ≤ 0.4000) outperforms other machine learning regression methods. It is highly advisable to use machine learning regression methods for modelling health expenditures.

Keywords: machine learning, lasso regression, random forest regression, support vector regression, hyperparameter tuning, health expenditure

Procedia PDF Downloads 230

Authors: Silvia Benvenuti, Alessandra Cardinali

Abstract:

In recent years, for instance, in relation to the Covid 19 pandemic and the evidence of climate change, it is becoming quite clear that the development of a young kid into an adult citizen requires a solid scientific background. Citizens are required to exert logical thinking and know the methods of science in order to adapt, understand, and develop as persons. Mathematics sits at the core of these required skills: learning the axiomatic method is fundamental to understand how hard sciences work and helps in consolidating logical thinking, which will be useful for the entire life of a student. At the same time, research shows that the axiomatic study of geometry is a problematic topic for students, even for those with interest in mathematics. With this in mind, the main goals of the research work we will describe are: (1) to show whether non-Euclidean geometries can be a tool to allow students to consolidate the knowledge of Euclidean geometries by developing it in a critical way; (2) to promote the understanding of the modern axiomatic method in geometry; (3) to give students a new perspective on mathematics so that they can see it as a creative activity and a widely discussed topic with a historical background. One of the main issues related to the state-of-the-art in this topic is the shortage of experimental studies with students. For this reason, our aim is to show further experimental evidence of the potential benefits of teaching non-Euclidean geometries at high school, based on data collected from a study started in 2005 in the frame of the Italian National Piano Lauree Scientifiche, continued by a teacher training organized in September 2018, perfected in a pilot study that involved 77 high school students during the school years 2018-2019 and 2019-2020. and finally implemented through an experimental study conducted in 2020-21 with 87 high school students. Our study shows that there is potential for further research to challenge current conceptions of the school mathematics curriculum and of the capabilities of high school mathematics students.

Keywords: Non-Euclidean geometries, beliefs about mathematics, questionnaires, modern axiomatic method

Procedia PDF Downloads 79

Authors: Luzia Dominguez

Abstract:

This paper explores the concept of ‘translanguaging’ and the relevance of its pedagogical application in the context of foreign language education in a multilingual urban environment. We review relevant literature discussing this theoretical concept, its scope, potential, and limitations when applied to the teaching of foreign languages. We then discuss its possible practical application in Welsh secondary schools, particularly in the most diverse areas of the Welsh capital, Cardiff (United Kingdom). The concept of translanguaging has evolved in scope, from its initial application in the teaching of Welsh and English in the Welsh bilingual context to finding a relevant space not only in the international arena of Sociolinguistics and language pedagogy but also being present in current Welsh educational policies and, presumably, practices. However, it is important to consider the actual pedagogical relevance of incorporating this concept into these policies, particularly in the teaching of Modern Foreign Languages. Additionally, it is important to examine any social factors that may influence the effectiveness of its application in the social context, in our case, a multilingual, ethnically diverse urban context. By analyzing these issues, we aim to explore possible teaching practices that could be pedagogically effective in applying the concept in Cardiff secondary schools.

Keywords: pedagogy, modern foreign languages, applied linguistics, sociolinguistics

Procedia PDF Downloads 61

Authors: Nelson Kimeli Kemboi Yego, Juma Kasozi, Joseph Nkruzinza, Francis Kipkogei

Abstract:

The study investigated the low uptake of health insurance in Kenya despite efforts to achieve universal health coverage through various health insurance schemes. Unsupervised machine learning techniques were employed to identify patterns in health insurance uptake based on sociodemographic factors among Kenyan households. The aim was to identify key demographic groups that are underinsured and to provide insights for the development of effective policies and outreach programs. Using the 2021 FinAccess Survey, the study clustered Kenyan households based on their health insurance uptake and sociodemographic features to reveal patterns in health insurance uptake across the country. The effectiveness of k-prototypes clustering, hierarchical clustering, and agglomerative hierarchical clustering in clustering based on sociodemographic factors was compared. The k-prototypes approach was found to be the most effective at uncovering distinct and well-separated clusters in the Kenyan sociodemographic data related to health insurance uptake based on silhouette, Calinski-Harabasz, Davies-Bouldin, and Rand indices. Hence, it was utilized in uncovering the patterns in uptake. The results of the analysis indicate that inclusivity in health insurance is greatly related to affordability. The findings suggest that targeted policy interventions and outreach programs are necessary to increase health insurance uptake in Kenya, with the ultimate goal of achieving universal health coverage. The study provides important insights for policymakers and stakeholders in the health insurance sector to address the low uptake of health insurance and to ensure that healthcare services are accessible and affordable to all Kenyans, regardless of their socio-demographic status. The study highlights the potential of unsupervised machine learning techniques to provide insights into complex health policy issues and improve decision-making in the health sector.

Keywords: health insurance, unsupervised learning, clustering algorithms, machine learning

Procedia PDF Downloads 148

Authors: Paolo Lenzuni

Abstract:

Cost-effectiveness of noise abatement treatments at the workplace has not yet received adequate consideration. Furthermore, most of the published work is focused on productivity, despite the poor correlation of this quantity with noise levels. There is currently no tool to estimate the social benefit associated to a specific noise abatement treatment, and no comparison among different options is accordingly possible. In this paper, we present an algorithm which has been developed to predict the cost-effectiveness of any planned noise control treatment in a workplace. This algorithm is based the estimates of hearing threshold shifts included in ISO 1999, and on compensations that workers are entitled to once their work-related hearing impairments have been certified. The benefits of a noise abatement treatment are estimated by means of the lower compensation costs which are paid to the impaired workers. Although such benefits have no real meaning in strictly monetary terms, they allow a reliable comparison between different treatments, since actual social costs can be assumed to be proportional to compensation costs. The existing European legislation on occupational exposure to noise it mandates that the noise exposure level be reduced below the upper action limit (85 dBA). There is accordingly little or no motivation for employers to sustain the extra costs required to lower the noise exposure below the lower action limit (80 dBA). In order to make this goal more appealing for employers, the algorithm proposed in this work also includes an ad-hoc element that promotes actions which bring the noise exposure down below 80 dBA. The algorithm has a twofold potential: 1) it can be used as a quality index to promote cost-effective practices; 2) it can be added to the existing criteria used by workers’ compensation authorities to evaluate the cost-effectiveness of technical actions, and support dedicated employers.

Keywords: cost-effectiveness, noise, occupational exposure, treatment

Procedia PDF Downloads 326

Authors: Abdullah A. AlShaher

Abstract:

In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2^nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We then proceed by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.

Keywords: character recognition, regression curves, handwritten Arabic letters, expectation maximization algorithm

Procedia PDF Downloads 150

Authors: Wala A. Bagunaid, Maram Meccawy, Arwa Allinjawi, Zilal Meccawy

Abstract:

Continuous self-assessment becomes crucial in self-paced online learning environments. Students often depend on themselves to assess their progress; which is considered an essential requirement for any successful learning process. Today’s education institutions face major problems around student motivation and engagement. Thus, personalized e-learning systems aim to help and guide the students. Gamification provides an opportunity to help students for self-assessment and social comparison with other students through attempting to harness the motivational power of games and apply it to the learning environment. Furthermore, Open Social Student Modeling (OSSM) as considered as the latest user modeling technologies is believed to improve students’ self-assessment and to allow them to social comparison with other students. This research integrates OSSM approach and gamification concepts in order to provide self-assessment for English language learners at King Abdulaziz University (KAU). This is achieved through an interactive visual representation of their learning progress.

Keywords: e-learning system, gamification, motivation, social comparison, visualization

Procedia PDF Downloads 156

Authors: An-Jui. Li, Kelvin Lim, Chien-Kuo Chiu, Benson Hsiung

Abstract:

This paper details the utilization of artificial intelligence (AI) in the field of slope stability whereby quick and convenient solutions can be obtained using the developed tool. The AI tool used in this study is the artificial neural network (ANN), while the slope stability analysis methods are the finite element limit analysis methods. The developed tool allows for the prompt prediction of the safety factors of fill slopes and their corresponding probability of failure (depending on the degree of variation of the soil parameters), which can give the practicing engineer a reasonable basis in their decision making. In fact, the successful use of the Extreme Learning Machine (ELM) algorithm shows that slope stability analysis is no longer confined to the conventional methods of modeling, which at times may be tedious and repetitive during the preliminary design stage where the focus is more on cost saving options rather than detailed design. Therefore, similar ANN-based tools can be further developed to assist engineers in this aspect.

Keywords: landslide, limit analysis, artificial neural network, soil properties

Procedia PDF Downloads 212

Authors: P. Halder, A. Zaman

Abstract:

It is estimated that heart disease accounts for one in ten deaths worldwide. United States deaths due to heart disease are among the leading causes of death according to the World Health Organization. Cardiovascular diseases (CVDs) account for one in four U.S. deaths, according to the Centers for Disease Control and Prevention (CDC). According to statistics, women are more likely than men to die from heart disease as a result of strokes. A 50% increase in men's mortality was reported by the World Health Organization in 2009. The consequences of cardiovascular disease are severe. The causes of heart disease include diabetes, high blood pressure, high cholesterol, abnormal pulse rates, etc. Machine learning (ML) can be used to make predictions and decisions in the healthcare industry. Thus, scientists have turned to modern technologies like Machine Learning and Data Mining to predict diseases. The disease prediction is based on four algorithms. Compared to other boosts, the Ada boost is much more accurate.

Keywords: heart disease, cardiovascular disease, coronary artery disease, feature selection, random forest, AdaBoost, SVM, decision tree

Procedia PDF Downloads 159

Authors: Levente Varga, Dávid Deritei, Mária Ercsey-Ravasz, Răzvan Florian, Zsolt I. Lázár, István Papp, Ferenc Járai-Szabó

Abstract:

One of the major shortcomings of widely used scientometric indicators is that different disciplines cannot be compared with each other. The issue of cross-disciplinary normalization has been long discussed, but even the classification of publications into scientific domains poses problems. Structural properties of citation networks offer new possibilities, however, the large size and constant growth of these networks asks for precaution. Here we present a new tool that in order to perform cross-field normalization of scientometric indicators of individual publications relays on the structural properties of citation networks. Due to the large size of the networks, a systematic procedure for identifying scientific domains based on a local community detection algorithm is proposed. The algorithm is tested with different benchmark and real-world networks. Then, by the use of this algorithm, the mechanism of the scientometric indicator normalization process is shown for a few indicators like the citation number, P-index and a local version of the PageRank indicator. The fat-tail trend of the article indicator distribution enables us to successfully perform the indicator normalization process.

Keywords: citation networks, cross-field normalization, local cluster detection, scientometric indicators

Procedia PDF Downloads 208

Authors: Zeinabsadat Haghshenas

Abstract:

Bloom’s Taxonomy has been changed during the years. The idea of this writing is about the revision that has happened in both facts and terms. It also contains case studies of using cognitive Bloom’s taxonomy in teaching geometric solids to the secondary school students, affective objectives in a creative workshop for adults and psychomotor objectives in fixing a malfunctioned refrigerator lamp. There is also pointed to the important role of classification objectives in adult education as a way to prevent memory loss.

Keywords: adult education, affective domain, cognitive domain, memory loss, psychomotor domain

Procedia PDF Downloads 473

Authors: Sofia Ayouche, Rachid Ellaia, Rajae Aboulaich

Abstract:

Today, insurers may use the yield curve as an indicator evaluation of the profit or the performance of their portfolios; therefore, they modeled it by one class of model that has the ability to fit and forecast the future term structure of interest rates. This class of model is the Nelson-Siegel-Svensson model. Unfortunately, many authors have reported a lot of difficulties when they want to calibrate the model because the optimization problem is not convex and has multiple local optima. In this context, we implement a hybrid Particle Swarm optimization and Nelder Mead algorithm in order to minimize by least squares method, the difference between the zero-coupon curve and the NSS curve.

Keywords: optimization, zero-coupon curve, Nelson-Siegel-Svensson, particle swarm optimization, Nelder-Mead algorithm

Procedia PDF Downloads 434

Authors: Sylvia Nkiru Ogbuoji

Abstract:

This paper discussed the consequences of inadequate funding in Nigerian education system. It briefly explained the meaning of education in relation to the context and identified various ways education in Nigeria can be funded. It highlighted some of the consequences of inadequate funding education system to include: Inadequate facilitates for teaching and learning, western brain drain, unemployment, crises of poverty, low staff morale it. Finally, some recommendations were put forward, the government should improve the annual budget allocation to education, in order to achieve educational objective, also government should monitor the utilization of allocated funds to minimize embezzlement.

Keywords: consequences, corruption, education, funding

Procedia PDF Downloads 458

Authors: M. Nemer, E. I. Konukseven

Abstract:

In this paper, a motion generation algorithm for a six Degrees of Freedom (DoF) robotic hand in a static environment is presented. The purpose of developing this method is to be used in the path generation of the end-effector for edge finishing and inspection processes by utilizing the CAD model of the considered workpiece. Nonetheless, the proposed algorithm may be extended to be applicable for other similar manufacturing processes. A software package programmed in the application programming interface (API) of SolidWorks generates tool path data for the robot. The proposed method significantly simplifies the given problem, resulting in a reduction in the CPU time needed to generate the path, and offers an efficient overall solution. The ABB IRB2000 robot is chosen for executing the generated tool path.

Keywords: CAD-based tools, edge deburring, edge scanning, offline programming, path generation

Procedia PDF Downloads 286

Authors: Reggie Chandra

Abstract:

Trafficaccidents and traffic signal optimization are correlated. However, 70-90% of the traffic signals across the USA are not synchronized. The reason behind that is insufficient resources to create and implement timing plans. In this work, we will discuss the use of a breakthrough Artificial Intelligence (AI) technology to optimize traffic flow and collect 24/7/365 accurate traffic data using a vehicle detection system. We will discuss what are recent advances in Artificial Intelligence technology, how does AI work in vehicles, pedestrians, and bike data collection, creating timing plans, and what is the best workflow for that. Apart from that, this paper will showcase how Artificial Intelligence makes signal timing affordable. We will introduce a technology that uses Convolutional Neural Networks (CNN) and deep learning algorithms to detect, collect data, develop timing plans and deploy them in the field. Convolutional Neural Networks are a class of deep learning networks inspired by the biological processes in the visual cortex. A neural net is modeled after the human brain. It consists of millions of densely connected processing nodes. It is a form of machine learning where the neural net learns to recognize vehicles through training - which is called Deep Learning. The well-trained algorithm overcomes most of the issues faced by other detection methods and provides nearly 100% traffic data accuracy. Through this continuous learning-based method, we can constantly update traffic patterns, generate an unlimited number of timing plans and thus improve vehicle flow. Convolutional Neural Networks not only outperform other detection algorithms but also, in cases such as classifying objects into fine-grained categories, outperform humans. Safety is of primary importance to traffic professionals, but they don't have the studies or data to support their decisions. Currently, one-third of transportation agencies do not collect pedestrian and bike data. We will discuss how the use of Artificial Intelligence for data collection can help reduce pedestrian fatalities and enhance the safety of all vulnerable road users. Moreover, it provides traffic engineers with tools that allow them to unleash their potential, instead of dealing with constant complaints, a snapshot of limited handpicked data, dealing with multiple systems requiring additional work for adaptation. The methodologies used and proposed in the research contain a camera model identification method based on deep Convolutional Neural Networks. The proposed application was evaluated on our data sets acquired through a variety of daily real-world road conditions and compared with the performance of the commonly used methods requiring data collection by counting, evaluating, and adapting it, and running it through well-established algorithms, and then deploying it to the field. This work explores themes such as how technologies powered by Artificial Intelligence can benefit your community and how to translate the complex and often overwhelming benefits into a language accessible to elected officials, community leaders, and the public. Exploring such topics empowers citizens with insider knowledge about the potential of better traffic technology to save lives and improve communities. The synergies that Artificial Intelligence brings to traffic signal control and data collection are unsurpassed.

Keywords: artificial intelligence, convolutional neural networks, data collection, signal control, traffic signal

Procedia PDF Downloads 176

Authors: S. Neelima, P. S. Subramanyam

Abstract:

A distribution system is an interface between the bulk power system and the consumers. Among these systems, radial distributions system is popular because of low cost and simple design. In distribution systems, the voltages at buses reduces when moved away from the substation, also the losses are high. The reason for a decrease in voltage and high losses is the insufficient amount of reactive power, which can be provided by the shunt capacitors. But the placement of the capacitor with an appropriate size is always a challenge. Thus, the optimal capacitor placement problem is to determine the location and size of capacitors to be placed in distribution networks in an efficient way to reduce the power losses and improve the voltage profile of the system. For this purpose, in this paper, two stage methodologies are used. In the first stage, the load flow of pre-compensated distribution system is carried out using ‘dimension reducing distribution load flow algorithm (DRDLFA)’. On the basis of this load flow the potential locations of compensation are computed. In the second stage, Genetic Algorithm (GA) technique is used to determine the optimal location and size of the capacitors such that the cost of the energy loss and capacitor cost to be a minimum. The above method is tested on IEEE 9 and 34 bus system and compared with other methods in the literature.

Keywords: dimension reducing distribution load flow algorithm, DRDLFA, genetic algorithm, electrical distribution network, optimal capacitors placement, voltage profile improvement, loss reduction

Procedia PDF Downloads 396

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 21

Authors: Walid Cherif

Abstract:

Data mining has, over recent years, seen big advances because of the spread of internet, which generates everyday a tremendous volume of data, and also the immense advances in technologies which facilitate the analysis of these data. In particular, classification techniques are a subdomain of Data Mining which determines in which group each data instance is related within a given dataset. It is used to classify data into different classes according to desired criteria. Generally, a classification technique is either statistical or machine learning. Each type of these techniques has its own limits. Nowadays, current data are becoming increasingly heterogeneous; consequently, current classification techniques are encountering many difficulties. This paper defines new measure functions to quantify the resemblance between instances and then combines them in a new approach which is different from actual algorithms by its reliability computations. Results of the proposed approach exceeded most common classification techniques with an f-measure exceeding 97% on the IRIS Dataset.

Keywords: data mining, knowledge discovery, machine learning, similarity measurement, supervised classification

Procedia PDF Downloads 468

Authors: Muhammad Umar Kiani, Muhammad Shahbaz

Abstract:

Performance of any vehicle can be predicted by its design/modeling and optimization. Design optimization leads to efficient performance. Followed by horizontal launch, the air launch re-entry vehicle undergoes a launch maneuver by introducing a carefully selected angle of attack profile. This angle of attack profile is the basic element to complete a specified mission. Flight program of said vehicle is optimized under the constraints of the maximum allowed angle of attack, lateral and axial loads and with the objective of reaching maximum altitude. The main focus of this study is the endo-atmospheric phase of the ascent trajectory. A three degrees of freedom trajectory model is simulated in MATLAB. The optimization process uses evolutionary algorithm, because of its robustness and efficient capacity to explore the design space in search of the global optimum. Evolutionary Algorithm based trajectory optimization also offers the added benefit of being a generalized method that may work with continuous, discontinuous, linear, and non-linear performance matrix. It also eliminates the requirement of a starting solution. Optimization is particularly beneficial to achieve maximum advantage without increasing the computational cost and affecting the output of the system. For the case of launch vehicles we are immensely anxious to achieve maximum performance and efficiency under different constraints. In a launch vehicle, flight program means the prescribed variation of vehicle pitching angle during the flight which has substantial influence reachable altitude and accuracy of orbit insertion and aerodynamic loading. Results reveal that the angle of attack profile significantly affects the performance of the vehicle.

Keywords: endo-atmospheric, evolutionary algorithm, efficient performance, optimization process

Procedia PDF Downloads 412

Authors: John Lorenzo Bautista, Yoon-Joong Kim

Abstract:

In this paper, a set of Filipino Phonetically Balanced Word list consisting of 250 words (PBW250) were constructed for a phoneme-level ASR system for the Filipino language. The Entropy Maximization is used to obtain phonological balance in the list. Entropy of phonemes in a word is maximized, providing an optimal balance in each word’s phonological distribution using the Add-Delete Method (PBW algorithm) and is compared to the modified PBW algorithm implemented in a dynamic algorithm approach to obtain optimization. The gained entropy score of 4.2791 and 4.2902 for the PBW and modified algorithm respectively. The PBW250 was recorded by 40 respondents, each with 2 sets data. Recordings from 30 respondents were trained to produce an acoustic model that were tested using recordings from 10 respondents using the HMM Toolkit (HTK). The results of test gave the maximum accuracy rate of 97.77% for a speaker dependent test and 89.36% for a speaker independent test.

Keywords: entropy maximization, Filipino language, Hidden Markov Model, phonetically balanced words, speech recognition

Procedia PDF Downloads 459

Authors: Zhihua Yu, Qi Zhang, Mingyu Zhang, Haolong Dai

Abstract:

Distributed fiber-optic vibration sensors are gaining extensive attention, for the advantages of high sensitivity, accurate location, light weight, large-scale monitoring, good concealment, and etc. In this paper, a novel optical fiber distributed vibration sensing system is proposed, which is based on self-interference of Rayleigh backscattering with phase generated carrier (PGC) demodulation algorithm. Pulsed lights are sent into the sensing fiber and the Rayleigh backscattering light from a certain position along the sensing fiber would interfere through an unbalanced Michelson Interferometry (MI) to generate the interference light. An improved PGC demodulation algorithm is carried out to recover the phase information of the interference signal, which carries the sensing information. Three vibration events were applied simultaneously to different positions over 2000m sensing fiber and demodulated correctly. Experiments show that the spatial resolution of is 10 m, and the noise level of the Φ-OTDR system is about 10-3 rad/√Hz, and the signal to noise ratio (SNR) is about 30.34dB. This vibration measurement scheme can be applied at surface, seabed or downhole for vibration measurements or distributed acoustic sensing (DAS).

Keywords: fiber optics sensors, Michelson interferometry, MI, phase-sensitive optical time domain reflectometry, Φ-OTDR, phase generated carrier, PGC

Procedia PDF Downloads 193

Authors: Luiz G. Véras, Felipe L. Medeiros, Lamartine F. Guimarães

Abstract:

This work approaches the automatic planning of paths for Unmanned Aerial Vehicles (UAVs) through the application of the Rapidly Exploring Random Tree Star-Smart (RRT*-Smart) algorithm. RRT*-Smart is a sampling process of positions of a navigation environment through a tree-type graph. The algorithm consists of randomly expanding a tree from an initial position (root node) until one of its branches reaches the final position of the path to be planned. The algorithm ensures the planning of the shortest path, considering the number of iterations tending to infinity. When a new node is inserted into the tree, each neighbor node of the new node is connected to it, if and only if the extension of the path between the root node and that neighbor node, with this new connection, is less than the current extension of the path between those two nodes. RRT*-smart uses an intelligent sampling strategy to plan less extensive routes by spending a smaller number of iterations. This strategy is based on the creation of samples/nodes near to the convex vertices of the navigation environment obstacles. The planned paths are smoothed through the application of the method called quintic pythagorean hodograph curves. The smoothing process converts a route into a dynamically-viable one based on the kinematic constraints of the vehicle. This smoothing method models the hodograph components of a curve with polynomials that obey the Pythagorean Theorem. Its advantage is that the obtained structure allows computation of the curve length in an exact way, without the need for quadratural techniques for the resolution of integrals.

Keywords: path planning, path smoothing, Pythagorean hodograph curve, RRT*-Smart

Procedia PDF Downloads 170

Authors: Stephen Grant Atkins

Abstract:

Radical use of project-based learning (PBL) in a small New Zealand business school provides an opportunity to longitudinally examine its effects over a decade of pre-Covid data. Prior to this business school’s implementation of PBL, starting in 2012, the business pedagogy literature presented just one example of PBL replacing an entire core-set of courses. In that instance, a British business school merged four of its ‘degree Year 3’ accounting courses into one PBL semester. As radical as that would have seemed, to students aged 20-to-22, the PBL experiment conducted in a New Zealand business school was notably more extreme: 41 nationally-approved Learning Outcomes (L.O.s), these deriving from 8 separate core courses, were aggregated into one grand set of L.O.s, and then treated as a ‘full-year’/‘full-time’ single course. The 8 courses in question were all components of this business school’s compulsory ‘degree Year 1’ curriculum. Thus, the students involved were notably younger (…ages 17-to-19…), and no ‘part-time’ enrolments were allowed. Of interest are this PBL experiment’s effects on subsequent performance outcomes in ‘degree Years 2 & 3’ (….which continued to operate in their traditional ways). Of special interest is the quality of ‘group project’ outcomes. This is because traditionally, ‘degree Year 1’ course assessments are only minimally based on group work. This PBL experiment altered that practice radically, such that PBL ‘degree Year 1’ alumni entered their remaining two years of business coursework with far more ‘project group’ experience. Timeline-wise, thus of interest here, firstly, is ‘degree Year 2’ performance outcomes data from years 2010-2012 + 2016-2018, and likewise ‘degree Year 3’ data for years 2011-2013 + 2017-2019. Those years provide a pre-&-post comparative baseline for performance outcomes in students never exposed to this school’s radical PBL experiment. That baseline is then compared to PBL alumni outcomes (2013-2016….including’Student Evaluation of Course Quality’ outcomes…) to clarify ‘radical PBL’ effects.

Keywords: project-based learning, longitudinal mixed-methods, students criticism, effects-on-learning

Procedia PDF Downloads 101

Authors: Peter Adekunle, Clinton Aigbavboa, Matthew Ikuabe, Opeoluwa Akinradewo

Abstract:

The future of machine learning (ML) in building may seem like a distant idea that will take decades to materialize, but it is actually far closer than previously believed. In reality, the built environment has been progressively increasing interest in machine learning. Although it could appear to be a very technical, impersonal approach, it can really make things more personable. Instead of eliminating humans out of the equation, machine learning allows people do their real work more efficiently. It is therefore vital to evaluate the factors influencing the implementation and challenges of implementing machine learning techniques in the South African built environment. The study's design was one of a survey. In South Africa, construction workers and professionals were given a total of one hundred fifty (150) questionnaires, of which one hundred and twenty-four (124) were returned and deemed eligible for study. Utilizing percentage, mean item scores, standard deviation, and Kruskal-Wallis, the collected data was analyzed. The results demonstrate that the top factors influencing the adoption of machine learning are knowledge level and a lack of understanding of its potential benefits. While lack of collaboration among stakeholders and lack of tools and services are the key hurdles to the deployment of machine learning within the South African built environment. The study came to the conclusion that ML adoption should be promoted in order to increase safety, productivity, and service quality within the built environment.

Keywords: machine learning, implementation, built environment, construction stakeholders

Procedia PDF Downloads 138

Authors: Muhammad R. Ahmed, Mohammed Aseeri

Abstract:

Wireless Sensor Network (WSN) consists of low-cost and multi functional resources constrain nodes that communicate at short distances through wireless links. It is open media and underpinned by an application driven technology for information gathering and processing. It can be used for many different applications range from military implementation in the battlefield, environmental monitoring, health sector as well as emergency response of surveillance. With its nature and application scenario, security of WSN had drawn a great attention. It is known to be valuable to variety of attacks for the construction of nodes and distributed network infrastructure. In order to ensure its functionality especially in malicious environments, security mechanisms are essential. Malicious or internal attacker has gained prominence and poses the most challenging attacks to WSN. Many works have been done to secure WSN from internal attacks but most of it relay on either training data set or predefined threshold. Without a fixed security infrastructure a WSN needs to find the internal attacks is a challenge. In this paper we present an internal attack detection method based on maximum entropy model. The final experimental works showed that the proposed algorithm does work well at the designed level.

Keywords: internal attack, wireless sensor network, network security, entropy

Procedia PDF Downloads 459