Search results for: learning environments
1737 Hybrid Reliability-Similarity-Based Approach for Supervised Machine Learning
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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15161736 Adaptability of ‘Monti Dauni’ Bean Ecotypes in Plain Areas
Authors: Disciglio G., Nardella E., Gatta G., Giuliani M.M., Tarantino A.
Abstract:
The bean (Phaseolus vulgaris L.) is one of the best known of the legumes, and it has a long cultivation tradition in Italy. The territory of “Subappennino Dauno” (southern Italy) is at around 700 m a.s.l. and is predominantly grown with cereals, olive trees and grapevines. Ecotypes of white beans to eat dry (such as cannellini beans) are also grown, which are sought for their palatability, high digestibility, and ease of cooking. However, these are not easy to find on the market due to their low production in relatively small areas and on small family farms that use seeds handed down from generation to generation. The introduction of these ecotypes in plain areas of the Puglia region would provide an opportunity to promote the diffusion of this type of bean. To investigate the adaptability of these ecotypes in plain environments (Cerignola, in southern Italy) a comparative trial was carried out between three ‘Monti Dauni’ ecotypes (E1, E2, E3) that are native to mountain areas and the similar commercial variety, ‘Cannellini’. The data provide useful information about the quantitative and qualitative characteristics of these ecotypes when grown in lowland environments. Ecotype E3 provided the greatest bean production (2.34 t ha-1) compared to ‘Cannellini’ (1.28 t ha-1) and the other ecotypes (0.55 and 0.40 t ha-1, for E1 and E2, respectively), due to its greater plant growth and the larger size of the seed (and thickness, in particular). Finally, ecotype E2 provided the greatest protein content (31.2%), although not significantly different from the commercial cultivar ‘Cannellini’ (32.1%).
Keywords: 'Monti Dauni' bean, ecotypes, adaptability in plain areas, quali-quantitive.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15421735 A Case Study of Mobile Game Based Learning Design for Gender Responsive STEM Education
Authors: Raluca Ionela Maxim
Abstract:
Designing a gender responsive Science, Technology, Engineering and Mathematics (STEM) mobile game based learning solution (mGBL) is a challenge in terms of content, gamification level and equal engagement of girls and boys. The goal of this case study was to research and create a high-fidelity prototype design of a mobile game that contains role-models as avatars that guide and expose girls and boys to STEM learning content. For this research purpose it was applied the methodology of design sprint with five-phase process that combines design thinking principles. The technique of this methodology comprises smart interviews with STEM experts, mind-map creation, sketching, prototyping and usability testing of the interactive prototype of the gender responsive STEM mGBL. The results have shown that the effect of the avatar/role model had a positive impact. Therefore, by exposing students (boys and girls) to STEM role models in an mGBL tool is helpful for the decreasing of the gender inequalities in STEM fields.
Keywords: Design thinking, design sprint, gender-responsive STEM education, mobile game based learning, role-models.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13371734 Online Think–Pair–Share in a Third-Age ICT Course
Authors: Daniele Traversaro
Abstract:
Problem: Senior citizens have been facing a challenging reality as a result of strict public health measures designed to protect people from the COVID-19 outbreak. These include the risk of social isolation due to the inability of the elderly to integrate with technology. Never before have Information and Communication Technology (ICT) skills become essential for their everyday life. Although third-age ICT education and lifelong learning are widely supported by universities and governments, there is a lack of literature on which teaching strategy/methodology to adopt in an entirely online ICT course aimed at third-age learners. This contribution aims to present an application of the Think-Pair-Share (TPS) learning method in an ICT third-age virtual classroom with an intergenerational approach to conducting online group labs and review activities. Research Question: Is collaborative learning suitable and effective, in terms of student engagement and learning outcomes, in an online ICT course for the elderly? Methods: In the TPS strategy a problem is posed by the teacher, students have time to think about it individually, and then they work in pairs (or small groups) to solve the problem and share their ideas with the entire class. We performed four experiments in the ICT course of the University of the Third Age of Genova (University of Genova, Italy) on the Microsoft Teams platform. The study cohort consisted of 26 students over the age of 45. Data were collected through online questionnaires. Two have been proposed, one at the end of the first activity and another at the end of the course. They consisted of five and three close-ended questions, respectively. The answers were on a Likert scale (from 1 to 4) except two questions (which asked the number of correct answers given individually and in groups) and the field for free comments/suggestions. Results: Groups achieve better results than individual students (with scores greater than one order of magnitude) and most students found TPS helpful to work in groups and interact with their peers. Insights: From these early results, it appears that TPS is suitable for an online third-age ICT classroom and useful for promoting discussion and active learning. Despite this, our work has several limitations. First of all, the results highlight the need for more data to be able to perform a statistical analysis in order to determine the effectiveness of this methodology in terms of student engagement and learning outcomes as future direction.
Keywords: Collaborative learning, information technology education, lifelong learning, older adult education, think-pair-share.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6091733 The Effect of the Andalus Knowledge Phases and Times Model of Learning on the Development of Students’ Academic Performance and Emotional Quotient
Authors: Sobhy Fathy A. Hashesh
Abstract:
This study aimed at investigating the effect of Andalus Knowledge Phases and Times (ANPT) model of learning and the effect of 'Intel Education Contribution in ANPT' on the development of students’ academic performance and emotional quotient. The society of the study composed of Andalus Private Schools, elementary school students (N=700), while the sample of the study composed of four randomly assigned groups (N=80) with one experimental group and one control group to study "ANPT" effect and the "Intel Contribution in ANPT" effect respectively. The study followed the quantitative and qualitative approaches in collecting and analyzing data to answer the study questions. Results of the study revealed that there were significant statistical differences between students’ academic performances and emotional quotients for the favor of the experimental groups. The study recommended applying this model on different educational variables and on other age groups to generate more data leading to more educational results for the favor of students’ learning outcomes.
Keywords: ANPT, Flipped Classroom, 5Es learning Model, Kagan structures.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12471732 A Hybrid Feature Selection and Deep Learning Algorithm for Cancer Disease Classification
Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh
Abstract:
Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.
Keywords: Cancer classification, feature selection, deep learning, genetic algorithm.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12331731 Resilient Machine Learning in the Nuclear Industry: Crack Detection as a Case Study
Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple
Abstract:
There is a dramatic surge in the adoption of Machine Learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. Artificial Intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and two defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt ML techniques without rigorous testing, since they may be vulnerable to adversarial attacks, especially in security-critical areas such as the nuclear industry. We observed that while the adopted defence methods can effectively defend against different attacks, none of them could protect against all five adversarial attacks entirely.
Keywords: Resilient Machine Learning, attacks, defences, nuclear industry, crack detection.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4651730 A Machine Learning Approach for Anomaly Detection in Environmental IoT-Driven Wastewater Purification Systems
Authors: Giovanni Cicceri, Roberta Maisano, Nathalie Morey, Salvatore Distefano
Abstract:
The main goal of this paper is to present a solution for a water purification system based on an Environmental Internet of Things (EIoT) platform to monitor and control water quality and machine learning (ML) models to support decision making and speed up the processes of purification of water. A real case study has been implemented by deploying an EIoT platform and a network of devices, called Gramb meters and belonging to the Gramb project, on wastewater purification systems located in Calabria, south of Italy. The data thus collected are used to control the wastewater quality, detect anomalies and predict the behaviour of the purification system. To this extent, three different statistical and machine learning models have been adopted and thus compared: Autoregressive Integrated Moving Average (ARIMA), Long Short Term Memory (LSTM) autoencoder, and Facebook Prophet (FP). The results demonstrated that the ML solution (LSTM) out-perform classical statistical approaches (ARIMA, FP), in terms of both accuracy, efficiency and effectiveness in monitoring and controlling the wastewater purification processes.Keywords: EIoT, machine learning, anomaly detection, environment monitoring.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9871729 Application of Machine Learning Methods to Online Test Error Detection in Semiconductor Test
Authors: Matthias Kirmse, Uwe Petersohn, Elief Paffrath
Abstract:
As in today's semiconductor industries test costs can make up to 50 percent of the total production costs, an efficient test error detection becomes more and more important. In this paper, we present a new machine learning approach to test error detection that should provide a faster recognition of test system faults as well as an improved test error recall. The key idea is to learn a classifier ensemble, detecting typical test error patterns in wafer test results immediately after finishing these tests. Since test error detection has not yet been discussed in the machine learning community, we define central problem-relevant terms and provide an analysis of important domain properties. Finally, we present comparative studies reflecting the failure detection performance of three individual classifiers and three ensemble methods based upon them. As base classifiers we chose a decision tree learner, a support vector machine and a Bayesian network, while the compared ensemble methods were simple and weighted majority vote as well as stacking. For the evaluation, we used cross validation and a specially designed practical simulation. By implementing our approach in a semiconductor test department for the observation of two products, we proofed its practical applicability.
Keywords: Ensemble methods, fault detection, machine learning, semiconductor test.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22541728 Neural-Symbolic Machine-Learning for Knowledge Discovery and Adaptive Information Retrieval
Authors: Hager Kammoun, Jean Charles Lamirel, Mohamed Ben Ahmed
Abstract:
In this paper, a model for an information retrieval system is proposed which takes into account that knowledge about documents and information need of users are dynamic. Two methods are combined, one qualitative or symbolic and the other quantitative or numeric, which are deemed suitable for many clustering contexts, data analysis, concept exploring and knowledge discovery. These two methods may be classified as inductive learning techniques. In this model, they are introduced to build “long term" knowledge about past queries and concepts in a collection of documents. The “long term" knowledge can guide and assist the user to formulate an initial query and can be exploited in the process of retrieving relevant information. The different kinds of knowledge are organized in different points of view. This may be considered an enrichment of the exploration level which is coherent with the concept of document/query structure.Keywords: Information Retrieval Systems, machine learning, classification, Galois lattices, Self Organizing Map.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 11741727 Modeling Language for Machine Learning
Authors: Tsuyoshi Okita, Tatsuya Niwa
Abstract:
For a given specific problem an efficient algorithm has been the matter of study. However, an alternative approach orthogonal to this approach comes out, which is called a reduction. In general for a given specific problem this reduction approach studies how to convert an original problem into subproblems. This paper proposes a formal modeling language to support this reduction approach. We show three examples from the wide area of learning problems. The benefit is a fast prototyping of algorithms for a given new problem.Keywords: Formal language, statistical inference problem, reduction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16001726 Forecasting Fraudulent Financial Statements using Data Mining
Authors: S. Kotsiantis, E. Koumanakos, D. Tzelepis, V. Tampakas
Abstract:
This paper explores the effectiveness of machine learning techniques in detecting firms that issue fraudulent financial statements (FFS) and deals with the identification of factors associated to FFS. To this end, a number of experiments have been conducted using representative learning algorithms, which were trained using a data set of 164 fraud and non-fraud Greek firms in the recent period 2001-2002. The decision of which particular method to choose is a complicated problem. A good alternative to choosing only one method is to create a hybrid forecasting system incorporating a number of possible solution methods as components (an ensemble of classifiers). For this purpose, we have implemented a hybrid decision support system that combines the representative algorithms using a stacking variant methodology and achieves better performance than any examined simple and ensemble method. To sum up, this study indicates that the investigation of financial information can be used in the identification of FFS and underline the importance of financial ratios.Keywords: Machine learning, stacking, classifier.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 30361725 Gene Expression Data Classification Using Discriminatively Regularized Sparse Subspace Learning
Authors: Chunming Xu
Abstract:
Sparse representation which can represent high dimensional data effectively has been successfully used in computer vision and pattern recognition problems. However, it doesn-t consider the label information of data samples. To overcome this limitation, we develop a novel dimensionality reduction algorithm namely dscriminatively regularized sparse subspace learning(DR-SSL) in this paper. The proposed DR-SSL algorithm can not only make use of the sparse representation to model the data, but also can effective employ the label information to guide the procedure of dimensionality reduction. In addition,the presented algorithm can effectively deal with the out-of-sample problem.The experiments on gene-expression data sets show that the proposed algorithm is an effective tool for dimensionality reduction and gene-expression data classification.Keywords: sparse representation, dimensionality reduction, labelinformation, sparse subspace learning, gene-expression data classification.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14361724 Implementing Education 4.0 Trends in Language Learning
Authors: Luz Janeth Ospina M.
Abstract:
The fourth industrial revolution is changing the role of education substantially and, therefore, the role of instructors and learners at all levels. Education 4.0 is an imminent response to the needs of a globalized world where humans and technology are being aligned to enable endless possibilities, among them the need for students, as digital natives, to communicate effectively in at least one language besides their mother tongue, and also the requirement of developing theirs. This is an exploratory study in which a control group (N = 21), all of the students of Spanish as a foreign language at the university level, after taking a Spanish class, responded to an online questionnaire about the engagement, atmosphere, and environment in which their course was delivered. These aspects considered in the survey were relative to the instructor’s teaching style, including: (a) active, hands-on learning; (b) flexibility for in-class activities, easily switching between small group work, individual work, and whole-class discussion; and (c) integrating technology into the classroom. Strongly believing in these principles, the instructor deliberately taught the course in a SCALE-UP room, as it could facilitate such a positive and encouraging learning environment. These aspects are trends related to Education 4.0 and have become integral to the instructor’s pedagogical stance that calls for a constructive-affective role, instead of a transmissive one. As expected, with a learning environment that (a) fosters student engagement and (b) improves student outcomes, the subjects were highly engaged, which was partially due to the learning environment. An overwhelming majority (all but one) of students agreed or strongly agreed that the atmosphere and the environment were ideal. Outcomes of this study are relevant and indicate that it is about time for teachers to build up a meaningful correlation between humans and technology. We should see the trends of Education 4.0 not as a threat but as practices that should be in the hands of critical and creative instructors whose pedagogical stance responds to the needs of the learners in the 21st century.
Keywords: Active learning, education 4.0, higher education, pedagogical stance.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6851723 Least Square-SVM Detector for Wireless BPSK in Multi-Environmental Noise
Authors: J. P. Dubois, Omar M. Abdul-Latif
Abstract:
Support Vector Machine (SVM) is a statistical learning tool developed to a more complex concept of structural risk minimization (SRM). In this paper, SVM is applied to signal detection in communication systems in the presence of channel noise in various environments in the form of Rayleigh fading, additive white Gaussian background noise (AWGN), and interference noise generalized as additive color Gaussian noise (ACGN). The structure and performance of SVM in terms of the bit error rate (BER) metric is derived and simulated for these advanced stochastic noise models and the computational complexity of the implementation, in terms of average computational time per bit, is also presented. The performance of SVM is then compared to conventional binary signaling optimal model-based detector driven by binary phase shift keying (BPSK) modulation. We show that the SVM performance is superior to that of conventional matched filter-, innovation filter-, and Wiener filter-driven detectors, even in the presence of random Doppler carrier deviation, especially for low SNR (signal-to-noise ratio) ranges. For large SNR, the performance of the SVM was similar to that of the classical detectors. However, the convergence between SVM and maximum likelihood detection occurred at a higher SNR as the noise environment became more hostile.Keywords: Colour noise, Doppler shift, innovation filter, least square-support vector machine, matched filter, Rayleigh fading, Wiener filter.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18001722 Towards an E-Learning Platform Multi-Agent Based On the E-Tutoring for Collaborative Work
Authors: Badr Hssina, Belaid Bouikhalene, Abdelkrim Merbouha
Abstract:
This article presents our prototype MASET (Multi Agents System for E-Tutoring Learners engaged in online collaborative work). MASET that we propose is a system which basically aims to help tutors in monitoring the collaborative work of students and their various interactions. The evaluation of such interactions by the tutor is based on the results provided by the automatic analysis of the interaction indicators. This system is predicated upon the middleware JADE (Java Agent Development Framework) and e-learning Moodle platform. The MASET environment is modeled by AUML which allows structuring the different interactions between agents for the fulfillment and performance of online collaborative work. This multi-agent system has been the subject of a practical experimentation based on the interactions data between Master Computer Engineering and System students.Keywords: AUML, Collaborative work, E-learning, E-tutoring, JADE, Moodle, SMA, Web Agent.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18201721 Evaluating the Effectiveness of Electronic Response Systems in Technology-Oriented Classes
Authors: Ahmad Salman
Abstract:
Electronic Response Systems such as Kahoot, Poll Everywhere, and Google Classroom are gaining a lot of popularity when surveying audiences in events, meetings, and classroom. The reason is mainly because of the ease of use and the convenience these tools bring since they provide mobile applications with a simple user interface. In this paper, we present a case study on the effectiveness of using Electronic Response Systems on student participation and learning experience in a classroom. We use a polling application for class exercises in two different technology-oriented classes. We evaluate the effectiveness of the usage of the polling applications through statistical analysis of the students performance in these two classes and compare them to the performances of students who took the same classes without using the polling application for class participation. Our results show an increase in the performances of the students who used the Electronic Response System when compared to those who did not by an average of 11%.Keywords: Interactive learning, classroom technology, electronic response systems, polling applications, learning evaluation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6241720 Influence and Dissemination of Solecism among Moroccan High School and University Students
Authors: Rachid Ed-Dali, Khalid Elasri
Abstract:
Mass media seem to provide a rich content for language acquisition. Exposure to television, the Internet, the mobile phone and other technological gadgets and devices helps enrich the student’s lexicon positively as well as negatively. The difficulties encountered by students while learning and acquiring second languages in addition to their eagerness to comprehend the content of a particular program prompt them to diversify their methods so as to achieve their targets. The present study highlights the significance of certain media channels and their involvement in language acquisition with the employment of the Natural Approach to further grasp whether students, especially secondary and high school students, learn and acquire errors through watching subtitled television programs. The chief objective is investigating the deductive and inductive relevance of certain programs beside the involvement of peripheral learning while acquiring mistakes.
Keywords: Errors, mistakes, natural Approach, peripheral learning, solecism.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5491719 Train the Trainer: The Bricks in the Learning Community Scaffold of Professional Development
Authors: S. Pancucci
Abstract:
Professional development is the focus of this study. It reports on questionnaire data that examined the perceived effectiveness of the Train the Trainer model of technology professional development for elementary teachers. Eighty-three selected teachers called Information Technology Coaches received four half-day and one after-school in-service sessions. Subsequently, coaches shared the information and skills acquired during training with colleagues. Results indicated that participants felt comfortable as Information Technology Coaches and felt well prepared because of their technological professional development. Overall, participants perceived the Train the Trainer model to be effective. The outcomes of this study suggest that the use of the Train the Trainer model, a known professional development model, can be an integral and interdependent component of the newer more comprehensive learning community professional development model.Keywords: change, education, learning community, professional development, school improvement, technology coach, Train the Trainer.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 26251718 Time Series Forecasting Using Various Deep Learning Models
Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan
Abstract:
Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.
Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 11061717 Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion
Authors: Adrià Arbués-Sangüesa, Coloma Ballester, Gloria Haro
Abstract:
Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.Keywords: Basketball, deep learning, feature extraction, single-camera, tracking.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6761716 Toward Understanding and Testing Deep Learning Information Flow in Deep Learning-Based Android Apps
Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li
Abstract:
The widespread popularity of mobile devices and the development of artificial intelligence (AI) have led to the widespread adoption of deep learning (DL) in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace, a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Additionally, we propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. Using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We conduct an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace outperformed FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.
Keywords: Mobile computing, deep learning apps, sensitive information, static analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5521715 An Experimental Comparison of Unsupervised Learning Techniques for Face Recognition
Authors: Dinesh Kumar, C.S. Rai, Shakti Kumar
Abstract:
Face Recognition has always been a fascinating research area. It has drawn the attention of many researchers because of its various potential applications such as security systems, entertainment, criminal identification etc. Many supervised and unsupervised learning techniques have been reported so far. Principal Component Analysis (PCA), Self Organizing Maps (SOM) and Independent Component Analysis (ICA) are the three techniques among many others as proposed by different researchers for Face Recognition, known as the unsupervised techniques. This paper proposes integration of the two techniques, SOM and PCA, for dimensionality reduction and feature selection. Simulation results show that, though, the individual techniques SOM and PCA itself give excellent performance but the combination of these two can also be utilized for face recognition. Experimental results also indicate that for the given face database and the classifier used, SOM performs better as compared to other unsupervised learning techniques. A comparison of two proposed methodologies of SOM, Local and Global processing, shows the superiority of the later but at the cost of more computational time.
Keywords: Face Recognition, Principal Component Analysis, Self Organizing Maps, Independent Component Analysis
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18661714 A Development of Online Lessons to Strengthen the Learning Process of Master's Degree Students Majoring in Curriculum and Instruction at Suan Sunandha Rajabhat University
Authors: Chaiwat Waree
Abstract:
The purposes of the research were to develop online lessons to strengthen the learning process of Master's degree students majoring in Curriculum and Instruction at Suan Sunandha Rajabhat University; to achieve the efficiency criteria of 80/80; and to study the satisfaction of students who use online lessons to strengthen the learning process of Master’s degree students majoring in Curriculum and Instruction at Suan Sunandha Rajabhat University. The sample consisted of 40 university students studying in semester 1, academic year 2012. The sample was determined by Purposive Sampling. Selected students were from the class which the researcher was the homeroom tutor. The tutor was responsible for the teaching of learning process. Tools used in the study were online lessons, 60-point performance test, and evaluation test of satisfaction of students on online lessons. Data analysis yielded the following results; 83.66/88.29 efficiency of online lessons measured against the criteria; the comparison of performance before and after taking online lessons using t-test yielded 29.67. The statistical significance was at 0.05; the average satisfaction level of forty students on online lessons was 4.46 with standard deviation of 0.68.
Keywords: Online Lessons, Curriculum and Instruction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14201713 Natural Ventilation for the Sustainable Tall Office Buildings of the Future
Authors: Ayşin Sev, Görkem Aslan
Abstract:
Sustainable tall buildings that provide comfortable, healthy and efficient indoor environments are clearly desirable as the densification of living and working space for the world’s increasing population proceeds. For environmental concerns, these buildings must also be energy efficient. One component of these tasks is the provision of indoor air quality and thermal comfort, which can be enhanced with natural ventilation by the supply of fresh air. Working spaces can only be naturally ventilated with connections to the outdoors utilizing operable windows, double facades, ventilation stacks, balconies, patios, terraces and skygardens. Large amounts of fresh air can be provided to the indoor spaces without mechanical air-conditioning systems, which are widely employed in contemporary tall buildings. This paper tends to present the concept of natural ventilation for sustainable tall office buildings in order to achieve healthy and comfortable working spaces, as well as energy efficient environments. Initially the historical evolution of ventilation strategies for tall buildings is presented, beginning with natural ventilation and continuing with the introduction of mechanical airconditioning systems. Then the emergence of natural ventilation due to the health and environmental concerns in tall buildings is handled, and the strategies for implementing this strategy are revealed. In the next section, a number of case studies that utilize this strategy are investigated. Finally, how tall office buildings can benefit from this strategy is discussed.
Keywords: Tall office building, natural ventilation, energy efficiency, double-skin façade, stack ventilation, air conditioning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 78651712 Near Field Focusing Behaviour of Airborne Ultrasonic Phased Arrays Influenced by Airflows
Authors: D. Sun, T. F. Lu, A. Zander, M. Trinkle
Abstract:
This paper investigates the potential use of airborne ultrasonic phased arrays for imaging in outdoor environments as a means of overcoming the limitations experienced by kinect sensors, which may fail to work in the outdoor environments due to the oversaturation of the infrared photo diodes. Ultrasonic phased arrays have been well studied for static media, yet there appears to be no comparable examination in the literature of the impact of a flowing medium on the focusing behaviour of near field focused ultrasonic arrays. This paper presents a method for predicting the sound pressure fields produced by a single ultrasound element or an ultrasonic phased array influenced by airflows. The approach can be used to determine the actual focal point location of an array exposed in a known flow field. From the presented simulation results based upon this model, it can be concluded that uniform flows in the direction orthogonal to the acoustic propagation have a noticeable influence on the sound pressure field, which is reflected in the twisting of the steering angle of the array. Uniform flows in the same direction as the acoustic propagation have negligible influence on the array. For an array impacted by a turbulent flow, determining the location of the focused sound field becomes difficult due to the irregularity and continuously changing direction and the speed of the turbulent flow. In some circumstances, ultrasonic phased arrays impacted by turbulent flows may not be capable of producing a focused sound field.
Keywords: Airborne, airflow, focused sound field, ultrasonic phased array.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16141711 4D Modelling of Low Visibility Underwater Archaeological Excavations Using Multi-Source Photogrammetry in the Bulgarian Black Sea
Authors: Rodrigo Pacheco-Ruiz, Jonathan Adams, Felix Pedrotti
Abstract:
This paper introduces the applicability of underwater photogrammetric survey within challenging conditions as the main tool to enhance and enrich the process of documenting archaeological excavation through the creation of 4D models. Photogrammetry was being attempted on underwater archaeological sites at least as early as the 1970s’ and today the production of traditional 3D models is becoming a common practice within the discipline. Photogrammetry underwater is more often implemented to record exposed underwater archaeological remains and less so as a dynamic interpretative tool. Therefore, it tends to be applied in bright environments and when underwater visibility is > 1m, reducing its implementation on most submerged archaeological sites in more turbid conditions. Recent years have seen significant development of better digital photographic sensors and the improvement of optical technology, ideal for darker environments. Such developments, in tandem with powerful processing computing systems, have allowed underwater photogrammetry to be used by this research as a standard recording and interpretative tool. Using multi-source photogrammetry (5, GoPro5 Hero Black cameras) this paper presents the accumulation of daily (4D) underwater surveys carried out in the Early Bronze Age (3,300 BC) to Late Ottoman (17th Century AD) archaeological site of Ropotamo in the Bulgarian Black Sea under challenging conditions (< 0.5m visibility). It proves that underwater photogrammetry can and should be used as one of the main recording methods even in low light and poor underwater conditions as a way to better understand the complexity of the underwater archaeological record.Keywords: 4D modelling, Black Sea, maritime archaeology, underwater photogrammetry, Bronze Age, low visibility.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15201710 A New Method for Multiobjective Optimization Based on Learning Automata
Authors: M. R. Aghaebrahimi, S. H. Zahiri, M. Amiri
Abstract:
The necessity of solving multi dimensional complicated scientific problems beside the necessity of several objective functions optimization are the most motive reason of born of artificial intelligence and heuristic methods. In this paper, we introduce a new method for multiobjective optimization based on learning automata. In the proposed method, search space divides into separate hyper-cubes and each cube is considered as an action. After gathering of all objective functions with separate weights, the cumulative function is considered as the fitness function. By the application of all the cubes to the cumulative function, we calculate the amount of amplification of each action and the algorithm continues its way to find the best solutions. In this Method, a lateral memory is used to gather the significant points of each iteration of the algorithm. Finally, by considering the domination factor, pareto front is estimated. Results of several experiments show the effectiveness of this method in comparison with genetic algorithm based method.Keywords: Function optimization, Multiobjective optimization, Learning automata.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16671709 Media Pedagogy - The Medium is the Message
Authors: Syed Sultan Ahmed
Abstract:
The current education system in India is adept in equipping and assessing the scholastic development of children. However, there is an immediate need to strengthen co-scholastic areas like life-skills, values and attitudes to equip students to face real life challenges. Audio-visual technology and their respective media can make a significant contribution to a value based learning curriculum. Thus, co-scholastic skills need to be effectively nurtured by a medium that is entertaining and impactful. Films in general have a tremendous impact in our society. Films with a positive message make a formidable learning experience that can influence and inspire generations of learners. Leveraging on this powerful medium, EduMedia India Pvt. Ltd. has introduced School Cinema a well researched film-based learning module supported by a fun and exciting workbook, designed to introduce and reaffirm life-skills and values to children, thereby having a positive influence on their attitudes.Keywords: Co-Scholastics, Entertaining, Educative, Holistic- Development
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16631708 The Development of Online Lessons in Integration Model
Authors: Chalermpol Tapsai
Abstract:
The objectives of this research were to develop and find the efficiency of integrated online lessons by investigating the usage of online lessons, the relationship between learners’ background knowledge, and the achievement after learning with online lessons. The sample group in this study consisted of 97 students randomly selected from 121 students registering in 1/2012 at Trimitwittayaram Learning Center. The sample technique employed stratified sample technique of 4 groups according to their proficiency, i.e. high, moderate, low, and non-knowledge. The research instrument included online lessons in integration model on the topic of Java Programming, test after each lesson, the achievement test at the end of the course, and the questionnaires to find learners’ satisfaction. The results showed that the efficiency of online lessons was 90.20/89.18 with the achievement of after learning with the lessons higher than that before the lessons at the statistically significant level of 0.05. Moreover, the background knowledge of the learners on the programming showed the positive relationship with the achievement learning at the statistically significant level at 0.05. Learners with high background knowledge employed less exercises and samples than those with lower background knowledge. While learners with different background in the group of moderate and low did not show the significant difference in employing samples and exercises.
Keywords: Integration model, Online lessons.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1480