Search results for: ground truth for supervised learning

Authors: Jarek Krajewski, David Daxberger

Abstract:

We propose a stress detection method based on an RGB camera using heart rate detection, also known as Photoplethysmography Imaging (PPGI). This technique focuses on the measurement of the small changes in skin colour caused by blood perfusion. A stationary lab setting with simulated video conferences is chosen using constant light conditions and a sampling rate of 30 fps. The ground truth measurement of heart rate is conducted with a common PPG system. The proposed approach for pulse peak detection is based on a machine learning-based approach, applying brute force feature extraction for the prediction of heart rate pulses. The statistical analysis showed good agreement (correlation r = .79, p<0.05) between the reference heart rate system and the proposed method. Based on these findings, the proposed method could provide a reliable, low-cost, and contactless way of measuring HR parameters in daily-life environments.

Keywords: heart rate, PPGI, machine learning, brute force feature extraction

Procedia PDF Downloads 100

Authors: Karen Armstrong

Abstract:

This paper considers the importance of acquiring, cultivating, and protecting one’s personal online reputation in a post-truth era. Although the idea of the individual is essential psychological construct, the concept necessarily now includes our online reputation. The idea of this online reputation has expanded to become almost more important than any other factor in terms of our professional, social and psychological development. The discussion will first consider philosophical ideas of the self, followed by an examination of underlying concepts of perception and interpretation in a post-truth world. Then, the idea of the recent shift to a consideration of posted images, through words and photos, in the construction of self, will be discussed. Next, the relation between private personal life and exterior social life, including our reputation in a variety of realms will be addressed. This will include the adoption of specific strategies and behaviors, which facilitate accuracy, currency and necessary modifications with regard to our online reputation. Finally, specific ways in which we can negotiate the fluid dynamic between reputation, and inner and outer selves to optimum effect will conclude the discussion.

Keywords: image, post-truth, privacy, reputation, surveillance

Procedia PDF Downloads 228

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 88

Authors: César Garza

Abstract:

In supervised binary classification and regression problems, it is well-known that learnability is equivalent to a uniform convergence of the hypothesis class, and if a problem is learnable, it is learnable by empirical risk minimization. For the general learning setting of unsupervised learning tasks, there are non-trivial learning problems where uniform convergence does not hold. We present here the task of learning centers of mass with an extra feature that “activates” some of the coordinates over the unit ball in a Hilbert space. We show that the learning problem is learnable under a stable RLM rule. We introduce a family of distributions over the domain space with some mild restrictions for which the sample complexity of uniform convergence for these problems must grow logarithmically with the dimension of the Hilbert space. If we take this dimension to infinity, we obtain a learnable problem for which the uniform convergence property fails for a vast family of distributions.

Keywords: statistical learning theory, learnability, uniform convergence, stability, regularized loss minimization

Procedia PDF Downloads 92

Authors: Prachi Desai, Ankita Gandhi, Mitali Acharya

Abstract:

Rainfall forecast is mainly used for predictions of rainfall in a specified area and determining their future rainfall conditions. Rainfall is always a global issue as it affects all major aspects of one's life. Agricultural, fisheries, forestry, tourism industry and other industries are widely affected by these conditions. The studies have resulted in insufficient availability of water resources and an increase in water demand in the near future. We already have a new forecast system that uses the deep Convolutional Neural Network (CNN) to forecast monthly rainfall and climate changes. We have also compared CNN against Artificial Neural Networks (ANN). Machine Learning techniques that are used in rainfall predictions include ARIMA Model, ANN, LR, SVM etc. The dataset on which we are experimenting is gathered online over the year 1901 to 20118. Test results have suggested more realistic improvements than conventional rainfall forecasts.

Keywords: ANN, CNN, supervised learning, machine learning, deep learning

Procedia PDF Downloads 153

Authors: Zarine Avetisyan

Abstract:

The process of speech production and transmission naturally implies the occurrence of certain defective assumptions and erroneous formulations which may be both spontaneous, caused by haste, carelessness, etc., or deliberate. Whether deliberate or not, fallacies always act by way of “faux pas”. In the latter case, we deal with fake or deceptive arguments which are the focus of the given paper. The paper departs from the assumption that fallacies are arguments that prove nothing. Additionally and more importantly, political discourse becomes the main domain for scholarly “cultivation” while pinning down fallacies. The fallacy of telling the truth but deliberately omitting important key details in order to falsify the larger picture called “the half truth” captures special attention in the given paper.

Keywords: break in the information chain, fallacy, half truth, political discourse

Procedia PDF Downloads 353

Authors: Seyed-Ali Sadegh-Zadeh, Kaveh Kavianpour, Hamed Atashbar, Elham Heidari, Saeed Shiry Ghidary, Amir M. Hajiyavand

Abstract:

Evaluation metrics play a critical role in assessing the performance of machine learning models. In this review paper, we provide a comprehensive overview of performance measurement approaches for machine learning models. For each category, we discuss the most widely used metrics, including their mathematical formulations and interpretation. Additionally, we provide a comparative analysis of performance measurement approaches for metric combinations. Our review paper aims to provide researchers and practitioners with a better understanding of performance measurement approaches and to aid in the selection of appropriate evaluation metrics for their specific applications.

Keywords: evaluation metrics, performance measurement, supervised learning, unsupervised learning, reinforcement learning, model robustness and stability, comparative analysis

Procedia PDF Downloads 22

Authors: Chung-Yuan Huang, Yu-Hsiang Fu, Chuen-Tsai Sun

Abstract:

Community detection represents an important data-mining tool for analyzing and understanding real-world complex network structures and functions. We believe that at least four criteria determine the appropriateness of a community detection algorithm: (a) it produces useable normalized mutual information (NMI) and modularity results for social networks, (b) it overcomes resolution limitation problems associated with synthetic networks, (c) it produces good NMI results and performance efficiency for Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks, and (d) it produces good modularity and performance efficiency for large-scale real-world complex networks. To our knowledge, no existing community detection algorithm meets all four criteria. In this paper, we describe a simple hierarchical arc-merging (HAM) algorithm that uses network topologies and rule-based arc-merging strategies to identify community structures that satisfy the criteria. We used five well-studied social network datasets and eight sets of LFR benchmark networks to validate the ground-truth community correctness of HAM, eight large-scale real-world complex networks to measure its performance efficiency, and two synthetic networks to determine its susceptibility to resolution limitation problems. Our results indicate that the proposed HAM algorithm is capable of providing satisfactory performance efficiency and that HAM-identified communities were close to ground-truth communities in social and LFR benchmark networks while overcoming resolution limitation problems.

Keywords: complex network, social network, community detection, network hierarchy

Procedia PDF Downloads 190

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 69

Authors: Farah Vierra

Abstract:

Following the 2016 US presidential election and the advancement of the Brexit referendum, the concept of “post-truth”, defined by Oxford Dictionary as “relating to or denoting circumstances in which objective facts are less influential in shaping public opinion than appeals to emotion and personal belief”, came into prominent use in public, political and educational circles. What this essentially entails is that in this age, individuals are increasingly confronted with subjective perpetuations of truth in their discourse spheres that are informed by beliefs and opinions as opposed to any form of coherence to the reality of those who these truth claims concern. In principle, a subjective delineation of truth is progressive and liberating – especially considering its potential in providing marginalised groups in the diverse communities of our globalised world with the voice to articulate truths that are representative of themselves and their experiences. However, any form of human flourishing that seems to be promised here collapses as the tenets of subjective truths initially in place to liberate has been distorted through post-truth to allow individuals to purport selective and individualistic truth claims that further oppress and silence certain groups within society without due accountability. The evidence of which is prevalent through the conception of terms such as "alternative facts" and "fake news" that we observe individuals declare when their problematic truth claims are questioned. Considering the pervasiveness of post-truth and the ethical issues that accompany it, educators and scholars alike have increasingly noted the need to adapt educational practices and pedagogies to account for the diminishing objectivity of truth in the twenty-first century, especially because students, as digital natives, find themselves in the firing line of post-truth; engulfed in digital societies that proliferate post-truth through the surge of truth claims allowed in various media sites. In an attempt to equip students with the vital skills to navigate the post-truth age and oppose its proliferation of social injustices, English educators find themselves having to devise instructional strategies that not only teach students the ways they can critically and ethically scrutinise truth claims but also teach them to mediate the subjectivity of truth in a manner that does not undermine the voices of diverse communities. In hopes of providing educators with the roadmap to do so, this paper will first examine the challenges that confront students as a result of post-truth. Following which, the paper will elucidate the role English education can play in helping students overcome the complex ramifications of post-truth. Scholars have consistently touted the affordances of literary texts in providing students with imagined spaces to explore societal issues through a critical discernment of language and an ethical engagement with its narrative developments. Therefore, this paper will explain and demonstrate how literary texts, when used alongside a critical-ethical post-truth pedagogy that equips students with interpretive strategies informed by literary traditions such as literary and ethical criticism, can be effective in helping students develop the pertinent skills to comprehensively examine truth claims and overcome the challenges of the post-truth age.

Keywords: post-truth, pedagogy, ethics, English, education

Procedia PDF Downloads 45

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 87

Authors: Farah Vierra

Abstract:

Following the 2016 US presidential election and the advancement of the Brexit referendum, the concept of “post-truth,” defined by the Oxford Dictionary as “relating to or denoting circumstances in which objective facts are less influential in shaping public opinion than appeals to emotion and personal belief,” came into prominent use in public, political and educational circles. What this essentially entails is that in this age, individuals are increasingly confronted with subjective perpetuations of truth in their discourse spheres that are informed by beliefs and opinions as opposed to any form of coherence to the reality of those to who this truth claims concern. In principle, a subjective delineation of truth is progressive and liberating – especially considering its potential to provide marginalised groups in the diverse communities of our globalised world with the voice to articulate truths that are representative of themselves and their experiences. However, any form of human flourishing that seems to be promised here collapses as the tenets of subjective truths initially in place to liberate have been distorted through post-truth to allow individuals to purport selective and individualistic truth claims that further oppress and silence certain groups within society without due accountability. The evidence of this is prevalent through the conception of terms such as "alternative facts" and "fake news" that we observe individuals declare when their problematic truth claims are being questioned. Considering the pervasiveness of post-truth and the ethical issues that accompany it, educators and scholars alike have increasingly noted the need to adapt educational practices and pedagogies to account for the diminishing objectivity of truth in the twenty-first century, especially because students, as digital natives, find themselves in the firing line of post-truth; engulfed in digital societies that proliferate post-truth through the surge of truth claims allowed in various media sites. In an attempt to equip students with the vital skills to navigate the post-truth age and oppose its proliferation of social injustices, English educators find themselves having to contend with a complex question: how can the teaching of English equip students with the ability to critically and ethically scrutinise truth claims whilst also mediating the subjectivity of truth in a manner that does not undermine the voices of diverse communities. In order to address this question, this paper will first examine the challenges that confront students as a result of post-truth. Following this, the paper will elucidate the role English education can play in helping students overcome the complex demands of the post-truth age. Scholars have consistently touted the affordances of literary texts in providing students with imagined spaces to explore societal issues through a critical discernment of language and an ethical engagement with its narrative developments. Therefore, this paper will explain and demonstrate how literary texts, when used alongside a critical-ethical post-truth pedagogy that equips students with interpretive strategies informed by literary traditions such as literary and ethical criticism, can be effective in helping students develop the pertinent skills to comprehensively examine truth claims and overcome the challenges of the post-truth age.

Keywords: post-truth, pedagogy, ethics, english, education

Procedia PDF Downloads 37

Authors: Dim En Nyaung, Thin Lai Lai Thein

Abstract:

Due to the rapid increase of Internet, web opinion sources dynamically emerge which is useful for both potential customers and product manufacturers for prediction and decision purposes. These are the user generated contents written in natural languages and are unstructured-free-texts scheme. Therefore, opinion mining techniques become popular to automatically process customer reviews for extracting product features and user opinions expressed over them. Since customer reviews may contain both opinionated and factual sentences, a supervised machine learning technique applies for subjectivity classification to improve the mining performance. In this paper, we dedicate our work is the task of opinion summarization. Therefore, product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the identification of semantic relationships. The polarity and numeric score of all the features are determined by Senti-WordNet Lexicon. The problem of opinion summarization refers how to relate the opinion words with respect to a certain feature. Probabilistic based model of supervised learning will improve the result that is more flexible and effective.

Keywords: opinion mining, opinion summarization, sentiment analysis, text mining

Procedia PDF Downloads 307

Authors: Ng Liang Shen, Hau Yuan Wen

Abstract:

Arrhythmia analysis of ECG signal plays a major role in diagnosing most of the cardiac diseases. Therefore, a single arrhythmia detection of an electrocardiographic (ECG) record can determine multiple pattern of various algorithms and match accordingly each ECG beats based on Machine Learning supervised learning. These researchers used different features and classification methods to classify different arrhythmia types. A major problem in these studies is the fact that the symptoms of the disease do not show all the time in the ECG record. Hence, a successful diagnosis might require the manual investigation of several hours of ECG records. The point of this paper presents investigations cardiovascular ailment in Electrocardiogram (ECG) Signals for Cardiac Arrhythmia utilizing examination of ECG irregular wave frames via heart beat as correspond arrhythmia which with Machine Learning Pattern Recognition.

Keywords: electrocardiogram, ECG, classification, machine learning, pattern recognition, detection, QRS

Procedia PDF Downloads 339

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 149

Authors: B. Selma

Abstract:

The aim of this study is to test the feasibility of SIPINA method to predict the harmfulness parameters controlling the seismic response. The approach developed takes into consideration both the focal depth and the peak ground acceleration. The parameter to determine is displacement. The data used for the learning of this method and analysis nonlinear seismic are described and applied to a class of models damaged to some typical structures of the existing urban infrastructure of Jassy, Romania. The results obtained indicate an influence of the focal depth and the peak ground acceleration on the displacement.

Keywords: SIPINA algorithm, seism, focal depth, peak ground acceleration, displacement

Procedia PDF Downloads 283

Authors: Mehmet Akköse

Abstract:

In ground motions recorded in recent major earthquakes such as 1994 Northridge earthquake in US, 1995 Kobe earthquake in Japan, 1999 Chi-Chi earthquake in Taiwan, and 1999 Kocaeli earthquake in Turkey, it is noticed that they have large velocity pulses. The ground motions with the velocity pulses recorded in the vicinity of an earthquake fault are quite different from the usual far-fault earthquake ground motions. The velocity pulse duration in the near-fault ground motions is larger than 1.0 sec. In addition, the ratio of the peak ground velocity (PGV) to the peak ground acceleration (PGA) of the near-fault ground motions is larger than 0.1 sec. The ground motions having these characteristics expose the structure to high input energy in the beginning of the earthquake and cause large structural responses. Therefore, structural response to near-fault ground motions has received much attention in recent years. Interactions between neighboring, inadequately separated buildings have been repeatedly observed during earthquakes. This phenomenon often referred to as earthquake-induced structural pounding, may result in substantial damage or even total destruction of colliding structures during strong ground motions. This study focuses on effects of near-fault ground motions on earthquake-induced pounding response of RC buildings. The program SAP2000 is employed in the response calculations. The results obtained from the pounding analyses for near-fault and far-fault ground motions are compared with each other.

Keywords: near-fault ground motion, pounding analysis, RC buildings, SAP2000

Procedia PDF Downloads 233

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 316

Authors: Ana Paula Melchiors Stahlschmidt, Cristina Py de Pinto Gomes Mairesse

Abstract:

This paper presents observations on the early supervised internships in Psychology, currently called basic internships in Brazil, and its importance in professional training. The work is an experience report and focuses on the Professional training, illustrated by the reality of a Brazilian institution, used as a case study. It was developed from the authors' experience as academic supervisors of this kind of practice throughout this undergraduate course, combined with aspects investigated in the post-doctoral research of one of them. Theoretical references on the subject and related national legislation are analyzed, as well as reports of students who experienced at least one semester of this type of practice, articulated to the observations of the authors. The results demonstrate the importance of the early supervised internships as a way of creating opportunities for the students of a first contact with the professional reality and the practice of psychologists in different fields of insertion, preparing them for further experiments that require more involvement in activities of training and practices in Psychology.

Keywords: training of psychologists, internships in psychology, supervised internships, combination of theory and practice

Procedia PDF Downloads 422

Authors: Reni Francis

Abstract:

Learning has transcended the classroom boundaries to create a learner centric, interactive, and integrative teaching learning environment. This study analysed the impact of iLearn on the teaching, learning, and evaluation among 100 teacher trainees. The objectives were to cater to the different learning styles of the teacher trainees, to incorporate innovative teaching learning activities, to assist in peer tutoring, to implement different evaluation processes. i: Identifying the learning styles among the teacher trainees through VARK Learning style checklist was followed by planning the teaching-learning process to meet the learning styles of the teacher trainees. L: Leveraging innovations in teaching- learning by planning and creating modules incorporating innovative teaching learning and hence the concept based year plan was prepared. E: Engage learning through constructivism using different teaching methodology to engage the teacher trainees in the learning process through Workshop, Round Robin, Gallery walk, Co-Operative learning, Think-Pair-Share, EDMODO, Course Networking, Concept Map, Brainstorming Sessions, Video Clippings. A: Assessing the learning through an Open Book assignment, Closed book assignment, and Multiple Choice Questions and Seminar presentation. R: Remediation through peer tutoring through Mentor-mentee approach in the tutorial groups, Group work, Library Hours. N: Norming new standards. This was done in the form of extended remediation and tutorials to understand the need of the teacher trainee and support them for further achievements in learning through Face to face interaction, Supervised Study Circle, Mobile (Device) learning. The findings of the study revealed the positive impact of iLearn towards student achievement and enhanced social skills.

Keywords: academic achievement, innovative strategy, learning styles, social skills

Procedia PDF Downloads 330

Authors: Muhammad Luqman, Yusuf Kurniawan

Abstract:

S-Boxes is one of the linear parts of the cryptographic algorithm. The existence of S-Box in the cryptographic algorithm is needed to maintain non-linearity of the algorithm. Nowadays, modern cryptographic algorithms use an S-Box as a part of algorithm process. Despite the fact that several cryptographic algorithms today reuse theoretically secure and carefully constructed S-Boxes, there is an evaluation characteristic that can measure security properties of S-Boxes and hence the corresponding primitives. Analysis of an S-Box usually is done using manual mathematics calculation. Several S-Boxes are presented as a Truth Table without any mathematical background algorithm. Then, it’s rather difficult to determine the strength of Truth Table S-Box without a mathematical algorithm. A comprehensive analysis should be applied to the Truth Table S-Box to determine the characteristic. Several important characteristics should be owned by the S-Boxes, they are Nonlinearity, Balancedness, Algebraic degree, LAT, DAT, differential delta uniformity, correlation immunity and global avalanche criterion. Then, a comprehensive tool will be present to automatically calculate the characteristics of S-Boxes and determine the strength of S-Box. Comprehensive analysis is done on a deterministic process to produce a sequence of S-Boxes characteristic and give advice for a better S-Box construction.

Keywords: cryptographic properties, Truth Table S-Boxes, S-Boxes characteristic, deterministic process

Procedia PDF Downloads 334

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 236

Authors: Spencer Jay Knafelc

Abstract:

Some mental health practitioners and theorists have suggested that we approach remedying psychological problems by centering and intervening upon patients’ narrations. Such theorists and their corresponding therapeutic approaches see persons as narrators of their lives, where the stories they tell constitute and reflect their sense-making of the world. Psychological problems, according to these approaches to therapy, are often the result of problematic narratives. The solution is the construction of more salubrious narratives through therapy. There is trouble lurking within the history of these narrative approaches. These thinkers tend to denigrate the importance of truth, insisting that narratives are not to be thought of as aiming at truth, and thus the truth of our self-narratives is not important. There are multiple motivations for the tendency to eschew truth’s importance within the tradition of narrative approaches to therapy. The most plausible and interesting motivation comes from the observation that, in general, all dominant approaches to therapy are equally effective. The theoretical commitments of each approach are quite different and are often ostensibly incompatible (psychodynamic therapists see psychological problems as resulting from unconscious conflict and repressed desires, Cognitive-Behavioral approaches see them as resulting from distorted cognitions). This strongly suggests that there must be some cases in which therapeutic efficacy does not depend on truth and that insisting that patient’s therapeutic narratives be true in all instances is a mistake. Lewis’ solution is to suggest that narratives are metaphors. Lewis’ account appreciates that there are many ways to tell a story and that many different approaches to mental health treatment can be appropriate without committing us to any contradictions, providing us with an ostensibly coherent way to treat narratives as non-literal, instead of seeing them as tools that can be more or less apt. Here, it is argued that Lewis’ metaphor approach fails. Narratives do not have the right kind of structure to be metaphors. Still, another way to understand Lewis’ view might be that self-narratives, especially when articulated in the language of any specific approach, should not be taken literally. This is an idea at the core of the narrative theorists’ tendency to eschew the importance of the ordinary understanding of truth. This very tendency will be critiqued. The view defended in this paper more accurately captures the nature of self-narratives. The truth of one’s self-narrative is important. Not only do people care about having the right conception of their abilities, who they are, and the way the world is, but self-narratives are composed of beliefs, and the nature of belief is to aim at truth. This view also allows the recognition of the importance of developing accurate representations of oneself and reality for one’s psychological well-being. It is also argued that in many cases, truth factors in as a mechanism of change over the course of therapy. Therapeutic benefit can be achieved by coming to have a better understanding of the nature of oneself and the world. Finally, the view defended here allows for the recognition of the nature of the tension between values: truth and efficacy. It is better to recognize this tension and develop strategies to navigate it as opposed to insisting that it doesn’t exist.

Keywords: philosophy, narrative, psychotherapy, truth

Procedia PDF Downloads 69

Authors: Abdool Qaiyum Mohabuth, Syed Munir Ahmad

Abstract:

Assessment enables students to focus on their learning, assessment. It engages them to work hard and motivates them in devoting time to their studies. Student learning is directly influenced by the type of assessment involved in the programme. Summative Assessment aims at providing measurement of student understanding. In fact, it is argued that summative assessment is used for reporting and reviewing, besides providing an overall judgement of achievement. While summative assessment is a well defined process for learning that takes place in the classroom environment, its application within the practice environment is still being researched. This paper discusses findings from a mixed-method study for exploring the effectiveness of summative assessment in practice learning. A survey questionnaire was designed for exploring the perceptions of mentors and students about summative assessment in practice learning. The questionnaire was administered to the University of Mauritius students and mentors who supervised students for their Work-Based Learning (WBL) practice at the respective placement settings. Some students, having undertaken their WBL practice, were interviewed, for capturing their views and experiences about the application of summative assessment in practice learning. Semi-structured interviews were also conducted with three experienced mentors who have assessed students on practice learning. The findings reveal that though learning in the workplace is entirely different from learning at the University, most students had positive experiences about their summative assessments in practice learning. They felt comfortable and confident to be assessed by their mentors in their placement settings and wished that the effort and time that they devoted to their learning be recognised and valued. Mentors on their side confirmed that the summative assessment is valid and reliable, enabling them to better monitor and coach students to achieve the expected learning outcomes.

Keywords: practice learning, judgement, summative assessment, knowledge, skills, workplace

Procedia PDF Downloads 319

Authors: Jason T. Hilton

Abstract:

The ‘post-truth era’ is marked by a shift toward a period in which objective facts are less influential in shaping public opinion than appeals to emotion and personal belief. Applying narrative analysis techniques to current public discourses in education that run counter to scientific findings, it becomes possible to identify weakness in modern pedagogy and suggest ways to counter false narratives in the classroom. Results of this study indicate that a failure to engage with popular narratives lessens teachers’ ability to be convincing in the classroom, even when presenting information supported by scientific evidence. This study seeks to empower teachers by illustrating the influence of story within the post-truth era and the ways in which narrative and rhetorical elements take hold in social media contexts. Equipped with this knowledge, teachers can create a shift in pedagogy, away from transmission of knowledge toward the crafting of powerful narratives, built upon evidence, and connected to the lives of modern learners.

Keywords: 21st century learner, critical pedagogy, culture, narrative, post-truth era, social media

Procedia PDF Downloads 235

Authors: Brandon Foggo, Nanpeng Yu

Abstract:

Power distribution circuits undergo frequent network topology changes that are often left undocumented. As a result, the documentation of a circuit’s connectivity becomes inaccurate with time. The lack of reliable circuit connectivity information is one of the biggest obstacles to model, monitor, and control modern distribution systems. To enhance the reliability and efficiency of electric power distribution systems, the circuit’s connectivity information must be updated periodically. This paper focuses on one critical component of a distribution circuit’s topology - the secondary transformer to phase association. This topology component describes the set of phase lines that feed power to a given secondary transformer (and therefore a given group of power consumers). Finding the documentation of this component is call Phase Identification, and is typically performed with physical measurements. These measurements can take time lengths on the order of several months, but with supervised learning, the time length can be reduced significantly. This paper compares several such methods applied to Phase Identification for a large range of real distribution circuits, describes a method of training data selection, describes preprocessing steps unique to the Phase Identification problem, and ultimately describes a method which obtains high accuracy (> 96% in most cases, > 92% in the worst case) using only 5% of the measurements typically used for Phase Identification.

Keywords: distribution network, machine learning, network topology, phase identification, smart grid

Procedia PDF Downloads 273

Authors: Farid Khosravikia, Patricia Clayton

Abstract:

The main objective of this study is to evaluate the advantages and disadvantages of various machine learning techniques in forecasting ground-motion intensity measures given source characteristics, source-to-site distance, and local site condition. Intensity measures such as peak ground acceleration and velocity (PGA and PGV, respectively) as well as 5% damped elastic pseudospectral accelerations at different periods (PSA), are indicators of the strength of shaking at the ground surface. Estimating these variables for future earthquake events is a key step in seismic hazard assessment and potentially subsequent risk assessment of different types of structures. Typically, linear regression-based models, with pre-defined equations and coefficients, are used in ground motion prediction. However, due to the restrictions of the linear regression methods, such models may not capture more complex nonlinear behaviors that exist in the data. Thus, this study comparatively investigates potential benefits from employing other machine learning techniques as a statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. The algorithms are adjusted to quantify event-to-event and site-to-site variability of the ground motions by implementing them as random effects in the proposed models to reduce the aleatory uncertainty. All the algorithms are trained using a selected database of 4,528 ground-motions, including 376 seismic events with magnitude 3 to 5.8, recorded over the hypocentral distance range of 4 to 500 km in Oklahoma, Kansas, and Texas since 2005. The main reason of the considered database stems from the recent increase in the seismicity rate of these states attributed to petroleum production and wastewater disposal activities, which necessities further investigation in the ground motion models developed for these states. Accuracy of the models in predicting intensity measures, generalization capability of the models for future data, as well as usability of the models are discussed in the evaluation process. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring pre-defined equations or coefficients. Moreover, it is shown that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available.

Keywords: artificial neural network, ground-motion models, machine learning, random forest, support vector machine

Procedia PDF Downloads 92

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 313

Authors: Hanene Sahli, Aymen Mouelhi, Marwa Hajji, Amine Ben Slama, Mounir Sayadi, Farhat Fnaiech, Radhwane Rachdi

Abstract:

Fetal abnormality is still a public health problem of interest to both mother and baby. Head defect is one of the most high-risk fetal deformities. Fetal head categorization is a sensitive task that needs a massive attention from neurological experts. In this sense, biometrical measurements can be extracted by gynecologist doctors and compared with ground truth charts to identify normal or abnormal growth. The fetal head biometric measurements such as Biparietal Diameter (BPD), Occipito-Frontal Diameter (OFD) and Head Circumference (HC) needs to be monitored, and expert should carry out its manual delineations. This work proposes a new approach to automatically compute BPD, OFD and HC based on morphological characteristics extracted from head shape. Hence, the studied data selected at the same Gestational Age (GA) from the fetal Ultrasound images (US) are classified into two categories: Normal and abnormal. The abnormal subjects include hydrocephalus, microcephaly and dolichocephaly anomalies. By the use of a support vector machines (SVM) method, this study achieved high classification for automated detection of anomalies. The proposed method is promising although it doesn't need expert interventions.

Keywords: biometric measurements, fetal head malformations, machine learning methods, US images

Procedia PDF Downloads 256

Authors: Anum Ali, Kashaf ad Dooja, Asif Saleem

Abstract:

The future smart cities trend will be towards Internet of Things (IoT); IoT creates dynamic connections in a ubiquitous manner. Smart cities offer ease and flexibility for daily life matters. By using small devices that are connected to cloud servers based on IoT, network traffic between these devices is growing exponentially, whose security is a concerned issue, since ratio of cyber attack may make the network traffic vulnerable. This paper discusses the latest machine learning approaches in related work further to tackle the increasing rate of cyber attacks, machine learning algorithm is applied to IoT-based network traffic data. The proposed algorithm train itself on data and identify different sections of devices interaction by using supervised learning which is considered as a classifier related to a specific IoT device class. The simulation results clearly identify the attacks and produce fewer false detections.

Keywords: IoT, traffic security, deep learning, classification

Procedia PDF Downloads 123