Search results for: supervised dimension reduction

Authors: Hossein Havaeji, Tony Wong, Thien-My Dao

Abstract:

1. Research Problems and Research Objectives: Blockchain Technology-enabled Supply Chain System (BT-enabled SCS) is the system using BT to drive SCS transparency, security, durability, and process integrity as SCS data is not always visible, available, or trusted. The costs of operating BT in the SCS are a common problem in several organizations. The costs must be estimated as they can impact existing cost control strategies. To account for system and deployment costs, it is necessary to overcome the following hurdle. The problem is that the costs of developing and running a BT in SCS are not yet clear in most cases. Many industries aiming to use BT have special attention to the importance of BT installation cost which has a direct impact on the total costs of SCS. Predicting BT installation cost in SCS may help managers decide whether BT is to be an economic advantage. The purpose of the research is to identify some main BT installation cost components in SCS needed for deeper cost analysis. We then identify and categorize the main groups of cost components in more detail to utilize them in the prediction process. The second objective is to determine the suitable Supervised Learning technique in order to predict the costs of developing and running BT in SCS in a particular case study. The last aim is to investigate how the running BT cost can be involved in the total cost of SCS. 2. Work Performed: Applied successfully in various fields, Supervised Learning is a method to set the data frame, treat the data, and train/practice the method sort. It is a learning model directed to make predictions of an outcome measurement based on a set of unforeseen input data. The following steps must be conducted to search for the objectives of our subject. The first step is to make a literature review to identify the different cost components of BT installation in SCS. Based on the literature review, we should choose some Supervised Learning methods which are suitable for BT installation cost prediction in SCS. According to the literature review, some Supervised Learning algorithms which provide us with a powerful tool to classify BT installation components and predict BT installation cost are the Support Vector Regression (SVR) algorithm, Back Propagation (BP) neural network, and Artificial Neural Network (ANN). Choosing a case study to feed data into the models comes into the third step. Finally, we will propose the best predictive performance to find the minimum BT installation costs in SCS. 3. Expected Results and Conclusion: This study tends to propose a cost prediction of BT installation in SCS with the help of Supervised Learning algorithms. At first attempt, we will select a case study in the field of BT-enabled SCS, and then use some Supervised Learning algorithms to predict BT installation cost in SCS. We continue to find the best predictive performance for developing and running BT in SCS. Finally, the paper will be presented at the conference.

Keywords: blockchain technology, blockchain technology-enabled supply chain system, installation cost, supervised learning

Procedia PDF Downloads 122

Authors: Abraham Terán Salcedo, Didier Samayoa Ochoa

Abstract:

This work presents a numerical implementation of a method for estimating the box-counting dimension of self-avoiding curves on a planar space, fractal objects captured on digital images; this method is named fractioning estimator. Classical methods of digital image processing, such as noise filtering, contrast manipulation, and thresholding, among others, are used in order to obtain binary images that are suitable for performing the necessary computations of the fractioning estimator. A user interface is developed for performing the image processing operations and testing the fractioning estimator on different captured images of real-life fractal objects. To analyze the results, the estimations obtained through the fractioning estimator are compared to the results obtained through other methods that are already implemented on different available software for computing and estimating the box-counting dimension.

Keywords: box-counting, digital image processing, fractal dimension, numerical method

Procedia PDF Downloads 83

Authors: Sudhir Kumar Singh, Debashish Chakravarty

Abstract:

Slope stability analysis is an important aspect in the field of geotechnical engineering. It is also important from safety, and economic point of view as any slope failure leads to loss of valuable lives and damage to property worth millions. This paper aims at mitigating the risk of slope failure by studying the effect of different joint sets on the stability of mine pit slopes under the influence of various external factors, namely degree of saturation, rainfall intensity, and seismic coefficients. Supervised machine learning approach has been utilized for making accurate and reliable predictions regarding the stability of slopes based on the value of Factor of Safety. Numerous cases have been studied for analyzing the stability of slopes using the popular Finite Element Method, and the data thus obtained has been used as training data for the supervised machine learning models. The input data has been trained on different supervised machine learning models, namely Random Forest, Decision Tree, Support vector Machine, and XGBoost. Distinct test data that is not present in training data has been used for measuring the performance and accuracy of different models. Although all models have performed well on the test dataset but Random Forest stands out from others due to its high accuracy of greater than 95%, thus helping us by providing a valuable tool at our disposition which is neither computationally expensive nor time consuming and in good accordance with the numerical analysis result.

Keywords: finite element method, geotechnical engineering, machine learning, slope stability

Procedia PDF Downloads 101

Authors: Hadi Farhadian, Homayoon Katibeh

Abstract:

Groundwater inflow to the tunnels is one of the most important problems in tunneling operation. The objective of this study is the investigation of model dimension effects on tunnel inflow assessment in discontinuous rock masses using numerical modeling. In the numerical simulation, the model dimension has an important role in prediction of water inflow rate. When the model dimension is very small, due to low distance to the tunnel border, the model boundary conditions affect the estimated amount of groundwater flow into the tunnel and results show a very high inflow to tunnel. Hence, in this study, the two-dimensional universal distinct element code (UDEC) used and the impact of different model parameters, such as tunnel radius, joint spacing, horizontal and vertical model domain extent has been evaluated. Results show that the model domain extent is a function of the most significant parameters, which are tunnel radius and joint spacing.

Keywords: water inflow, tunnel, discontinues rock, numerical simulation

Procedia PDF Downloads 524

Authors: Abdelbaky Abouzeid

Abstract:

The study aimed at determining the effect of using the active learning on achievement and attitudes toward studying the human rights course for the Bahrain Teachers College students and the extent to which any differences of statistical significance according to gender and section can exist. To achieve the objectives of the study, the researcher developed and implemented research tools such as academic achievement test and the scale of attitudes towards the study of the Human Rights Course. The scale of attitudes towards Human Rights was constructed of 40 items investigating four dimensions; the cognitive dimension, the behavioral dimension, the affective dimension, and course quality dimension. The researcher then applied some of the active learning strategies in teaching this course to all students of the first year of the Bahrain Teachers College (102 male and female students) after excluding two students who did not complete the course requirements. Students were divided into five groups. These strategies included interactive lecturing, presentations, role playing, group projects, simulation, brainstorming, concept maps and mind maps, reflection and think-pair-share. The course was introduced to students during the second semester of the academic year 2016-2017. The study findings revealed that the use of active learning strategies affected the achievement of students of Bahrain Teachers College in the Human Rights course. The results of the T-test showed statistically significant differences on the pre-test and post-test in favor of the post-test. No statistically significant differences in the achievement of students according to the section and gender were found. The results also indicated that the use of active learning strategies had a positive effect on students' attitudes towards the study of the Human Rights Course on all the scale’s items. The general average reached (4.26) and the percentage reached (85.19%). Regarding the effect of using active learning strategies on students’ attitudes towards all the four dimensions of the scale, the study concluded that the behavioral dimension came first; the quality of the course came second, the cognitive dimension came third and in the fourth place came the affective dimension. No statistically significant differences in the attitude towards studying the Human Rights Course for the students according to their sections or gender were found. Based on the findings of the study, the researchers suggested some recommendations that can contribute to the development of teaching Human Rights Course at the University of Bahrain.

Keywords: attitudes, academic achievement, human rights, behavioral dimension, cognitive dimension, affective dimension, quality of the course

Procedia PDF Downloads 199

Authors: Aya Salama

Abstract:

Digital Twin is an emerging research topic that attracted researchers in the last decade. It is used in many fields, such as smart manufacturing and smart healthcare because it saves time and money. It is usually related to other technologies such as Data Mining, Artificial Intelligence, and Machine Learning. However, Human digital twin (HDT), in specific, is still a novel idea that still needs to prove its feasibility. HDT expands the idea of Digital Twin to human beings, which are living beings and different from the inanimate physical entities. The goal of this research was to create a Human digital twin that is responsible for real-time human replies automation by simulating human behavior. For this reason, clustering, supervised classification, topic extraction, and sentiment analysis were studied in this paper. The feasibility of the HDT for personal replies generation on social messaging applications was proved in this work. The overall accuracy of the proposed approach in this paper was 63% which is a very promising result that can open the way for researchers to expand the idea of HDT. This was achieved by using Random Forest for clustering the question data base and matching new questions. K-nearest neighbor was also applied for sentiment analysis.

Keywords: human digital twin, sentiment analysis, topic extraction, supervised machine learning, unsupervised machine learning, classification, clustering

Procedia PDF Downloads 87

Authors: Aswathi Thrivikraman, S. Advaith

Abstract:

The study is aimed at designing encoders for deciphering intricacies in time series data by redescribing the dynamics operating on a lower-dimensional manifold. A semi-supervised LSTM autoencoder is devised and investigated to see if the latent representation of the time series data can better forecast the data. End-to-end training of the LSTM autoencoder, together with another LSTM network that is connected to the latent space, forces the hidden states of the encoder to represent the most meaningful latent variables relevant for forecasting. Furthermore, the study compares the predictions with those of a traditional seq2seq model.

Keywords: LSTM, autoencoder, forecasting, seq2seq model

Procedia PDF Downloads 155

Authors: Salisu ibrahim, Abdalla Rababah

Abstract:

In this research, we use Weighted G2-Multi-degree reduction of Bezier curve of degree n to a Bezier curve of degree m, m < n. The degree reduction of Bezier curves is used to represent a given Bezier curve of n by a Bezier curve of degree m, m < n. Exact degree reduction is not possible, and degree reduction is approximate process in nature. We derive a weighted degree reducing method that is geometrically continuous at the end points. Different norms will be considered, several error minimizations will be given. The proposed methods produce error function that are less than the errors of existing methods.

Keywords: Bezier curves, multiple degree reduction, geometric continuity, error function

Procedia PDF Downloads 482

Authors: Ali Albadri

Abstract:

The logistics equation has never been used or studied in scientific fields outside the field of ecology. It has never been used to understand the behavior of a dynamic system of mechanical machines, like an escalator. We have studied the compatibility of the logistic map against real measurements from an escalator. This study has proven that there is good compatibility between the logistics equation and the experimental measurements. It has discovered the potential of a relationship between the fractal dimension and the non-linearity parameter, R, in the logistics equation. The fractal dimension increases as the R parameter (non-linear parameter) increases. It implies that the fractal dimension increases as the phase of the life span of the machine move from the steady/stable phase to the periodic double phase to a chaotic phase. The fractal dimension and the parameter R can be used as a tool to verify and check the health of machines. We have come up with a theory that there are three areas of behaviors, which they can be classified during the life span of a machine, a steady/stable stage, a periodic double stage, and a chaotic stage. The level of attention to the machine differs depending on the stage that the machine is in. The rate of faults in a machine increases as the machine moves through these three stages. During the double period and the chaotic stages, the number of faults starts to increase and become less predictable. The rate of predictability improves as our monitoring of the changes in the fractal dimension and the parameter R improves. The principles and foundations of our theory in this work have and will have a profound impact on the design of systems, on the way of operation of systems, and on the maintenance schedules of the systems. The systems can be mechanical, electrical, or electronic. The discussed methodology in this paper will give businesses the chance to be more careful at the design stage and planning for maintenance to control costs. The findings in this paper can be implied and used to correlate the three stages of a mechanical system to more in-depth mechanical parameters like wear and fatigue life.

Keywords: logistcs map, bifurcation map, fractal dimension, logistics equation

Procedia PDF Downloads 108

Authors: Muhammad Fiaz

Abstract:

The article in hand is the study of complex features like Zero Hopf Bifurcation, Chaos and Synchronization of integer and fractional order version of a new 3D finance system. Trusted tools of averaging theory and active control method are utilized for investigation of Zero Hopf bifurcation and synchronization for both versions respectively. Inventiveness of the paper is to find the answer of a question that is it possible to find a chaotic system which can be synchronized with any other of the same dimension? Based on different examples we categorically develop a theory that if a couple of master and slave chaotic dynamical system is synchronized by selecting a suitable gain matrix with special conditions then the master system is synchronized with any chaotic dynamical system of the same dimension. With the help of this study we developed generalized theorems for synchronization of n-dimension dynamical systems for integer as well as fractional versions. it proposed that this investigation will contribute a lot to control dynamical systems and only a suitable gain matrix with special conditions is enough to synchronize the system under consideration with any other chaotic system of the same dimension. Chaotic properties of fractional version of the new finance system are also analyzed at fractional order q=0.87. Simulations results, where required, also provided for authenticity of analytical study.

Keywords: complex analysis, chaos, generalized synchronization, control dynamics, fractional order analysis

Procedia PDF Downloads 68

Authors: Luciana Brandao Ferreira, Janaina de Moura Engracia Giraldi, Fabiana Gondim Mariutti, Marina Toledo de Arruda Lourencao

Abstract:

Developing countries, such as BRICS (Brazil, Russia, India, China and South Africa) are hosting sports mega-events to promote socio-economic development and image enhancement. Thus, this paper aims to verify the image of Rio de Janeiro, in Brazil, as the host city of 2016 Olympic Games, considering the main cognitive and affective image dimensions. The research design uses exploratory factorial analysis to find the most important factors highlighted in the city image dimensions. The data were collected by structured questionnaires with an international respondents sample (n=274) with high international travel experience. The results show that Rio’s image as a sport mega-event host city has two main factors in each dimension: Cognitive ('General Infrastructure'; 'Services and Attractions') and Affective ('Positive Feelings'; 'Negative Feelings'). The most important factor related to cognitive dimension was 'Services and Attractions' which is more related to tourism activities. In the affective dimension 'Positive Feelings' was the most important factor, which means a good result considering that is a city in an emerging country with many unmet social demands.

Keywords: Rio de Janeiro, 2016 olympic games, host city image, cognitive image dimension, affective image dimension

Procedia PDF Downloads 147

Authors: Reda Abdel Azim, Tariq Shehab

Abstract:

The main objective of this study is to develop a subsurface fracture map of naturally fractured reservoirs by overcoming the limitations associated with different data sources in characterising fracture properties. Some of these limitations are overcome by employing a nested neuro-stochastic technique to establish inter-relationship between different data, as conventional well logs, borehole images (FMI), core description, seismic attributes, and etc. and then characterise fracture properties in terms of fracture density and fractal dimension for each data source. Fracture density is an important property of a system of fracture network as it is a measure of the cumulative area of all the fractures in a unit volume of a fracture network system and Fractal dimension is also used to characterize self-similar objects such as fractures. At the wellbore locations, fracture density and fractal dimension can only be estimated for limited sections where FMI data are available. Therefore, artificial intelligence technique is applied to approximate the quantities at locations along the wellbore, where the hard data is not available. It should be noted that Artificial intelligence techniques have proven their effectiveness in this domain of applications.

Keywords: naturally fractured reservoirs, artificial intelligence, fracture intensity, fractal dimension

Procedia PDF Downloads 254

Authors: Jianqin Qu

Abstract:

This paper proposes a rigid point set matching algorithm in arbitrary dimensions based on the idea of symmetric covariant function. A group of functions of the points in the set are formulated using rigid invariants. Each of these functions computes a pair of correspondence from the given point set. Then the computed correspondences are used to recover the unknown rigid transform parameters. Each computed point can be geometrically interpreted as the weighted mean center of the point set. The algorithm is compact, fast, and dimension free without any optimization process. It either computes the desired transform for noiseless data in linear time, or fails quickly in exceptional cases. Experimental results for synthetic data and 2D/3D real data are provided, which demonstrate potential applications of the algorithm to a wide range of problems.

Keywords: covariant point, point matching, dimension free, rigid registration

Procedia PDF Downloads 168

Authors: Wenfu Zheng, Guanghe Zheng

Abstract:

The discussion on the social sustainability in existing literature is limited to two-dimension epistemology space with only two elements: the human and nature. Using the revelation of the Bible God, the paper adds a moral component to the two-dimension space. With the new variable being introduced, the authors formulate a to three-dimension epistemology space and discuss its implications. Based on the space, the authors explore the hierarchical structure of order principles for a sustainable society. The social order principle system hierarchically consists of three principles: moral, relational, and rational. The justification of every principle is analyzed briefly. The paper concluded that all these order principles are necessary assurance of building a sustainable society.

Keywords: common grace, saving grace, sustainable society, the image of God

Procedia PDF Downloads 192

Authors: Leizhang Wang, Baocang Wang

Abstract:

General Sieve Kernel (G6K) is considered as currently the fastest algorithm for the shortest vector problem (SVP) and record holder of open SVP challenge. We study the lattice basis quality improvement effects of the Workout proposed in G6K, which is composed of a series of pumps to solve SVP. Firstly, we use a low-dimensional pump output basis to propose a predictor to predict the quality of high-dimensional Pumps output basis. Both theoretical analysis and experimental tests are performed to illustrate that it is more computationally expensive to solve the LWE problems by using a G6K default SVP solving strategy (Workout) than these lattice reduction algorithms (e.g. BKZ 2.0, Progressive BKZ, Pump, and Jump BKZ) with sieving as their SVP oracle. Secondly, the default Workout in G6K is optimized to achieve a stronger reduction and lower computational cost. Thirdly, we combine the optimized Workout and the Pump output basis quality predictor to further reduce the computational cost by optimizing LWE instances selection strategy. In fact, we can solve the TU LWE challenge (n = 65, q = 4225, = 0:005) 13.6 times faster than the G6K default Workout. Fourthly, we consider a combined two-stage (Preprocessing by BKZ- and a big Pump) LWE solving strategy. Both stages use dimension for free technology to give new theoretical security estimations of several LWE-based cryptographic schemes. The security estimations show that the securities of these schemes with the conservative Newhope’s core-SVP model are somewhat overestimated. In addition, in the case of LAC scheme, LWE instances selection strategy can be optimized to further improve the LWE-solving efficiency even by 15% and 57%. Finally, some experiments are implemented to examine the effects of our strategies on the Normal Form LWE problems, and the results demonstrate that the combined strategy is four times faster than that of Newhope.

Keywords: LWE, G6K, pump estimator, LWE instances selection strategy, dimension for free

Procedia PDF Downloads 60

Authors: Jinho Hur, Minjung Shin, Heekyu Kim

Abstract:

In many places, new railway constructions in the city are being used to build a viaduct station to take advantage of the space below the line, for difficulty of securing railway site and disconnections of areas. The space under the viaduct has limited to use by noise and vibration. In order to use it for various purposes, reducing noise and vibration is required. The vibration reduction method for new structures is recently developed enough to use as accommodation, but the reduction method for existing structures is still far-off. In this study, it suggests vibration reduction method by filling vibration reduction material to column members which is path of structure-bone-noise from trains run. Because most of railroad stations are reinforced concrete structures. It compares vibration reduction of station applied the method and original station by FEM analysis. As a result, reduction of vibration acceleration level in bandwidth 15~30Hz can be reduced. Therefore, using this method for viaduct railroad station, vibration of station is expected to be reduced.

Keywords: structure borne noise, TPU, viaduct rail station, vibration reduction method

Procedia PDF Downloads 543

Authors: L. Chevez, A. Apaza, J. Rodriguez, R. Puga, H. Loro, Juan Z. Davalos

Abstract:

Virtual Dimension (VD) procedure is used to analyze Hyperspectral Image (HIS) treatment-data in order to estimate the abundance of mineral components of a mining sample. Hyperspectral images coming from reflectance spectra (NIR region) are pre-treated using Standard Normal Variance (SNV) and Minimum Noise Fraction (MNF) methodologies. The endmember components are identified by the Simplex Growing Algorithm (SVG) and after adjusted to the reflectance spectra of reference-databases using Simulated Annealing (SA) methodology. The obtained abundance of minerals of the sample studied is very near to the ones obtained using XRD with a total relative error of 2%.

Keywords: hyperspectral imaging, minimum noise fraction, MNF, simplex growing algorithm, SGA, standard normal variance, SNV, virtual dimension, XRD

Procedia PDF Downloads 158

Authors: Abd Latif Abdul Rahman, Zuraidah Arif, Muhammad Faizal Iylia, Mohd Ghazali, Asmadi Mohammed Ghazali

Abstract:

Mobile information is a significant access point for human information activities. Theories and models of human information behavior have developed over several decades but have not yet considered the role of the user’s computing device in digital information interactions. This paper reviews the literature that leads to developing a conceptual framework of a study on the managers mobile information behavior. Based on the literature review, dimensions of mobile information behavior are identified, namely, dimension information needs, dimension information access, information retrieval and dimension of information use. The study is significant to understand the nature of librarians’ behavior in searching, retrieving and using information via the mobile device. Secondly, the study would provide suggestions about various kinds of mobile applications which organization can provide for their staff to improve their services.

Keywords: mobile information behavior, information behavior, mobile information, mobile devices

Procedia PDF Downloads 349

Authors: Qingqing Gai, Junxing Shen, Yu Luo

Abstract:

Due to the hardware architecture characteristics, some operators tend to acquire better performance if the input/output tensor dimensions are aligned to a certain minimum granularity, such as convolution and deconvolution commonly used in deep learning. Furthermore, if the requirements are not met, the general strategy is to pad with 0 to satisfy the requirements, potentially leading to the under-utilization of the hardware resources. Therefore, for the convolution and deconvolution whose input and output channels do not meet the minimum granularity alignment, we propose to transfer the W-dimensional data to the C-dimension for computation (W2C) to enable the C-dimension to meet the hardware requirements. This scheme also reduces the number of computations in the W-dimension. Although this scheme substantially increases computation, the operator’s speed can improve significantly. It achieves remarkable speedups on multiple hardware accelerators, including Nvidia Tensor cores, Qualcomm digital signal processors (DSPs), and Huawei neural processing units (NPUs). All you need to do is modify the network structure and rearrange the operator weights offline without retraining. At the same time, for some operators, such as the Reducemax, we observe that transferring the Cdimensional data to the W-dimension(C2W) and replacing the Reducemax with the Maxpool can accomplish acceleration under certain circumstances.

Keywords: convolution, deconvolution, W2C, C2W, alignment, hardware accelerator

Procedia PDF Downloads 104

Authors: Chee Sun Won

Abstract:

This paper presents the size reduction of images for machine-to-machine communications. Here, the salient image regions to be preserved include the image patches of the key-points such as corners and blobs. Based on a saliency image map from the key-points and their image patches, an axis-aligned grid-size optimization is proposed for the reduction of image size. To increase the size-reduction efficiency the aspect ratio constraint is relaxed in the constraint optimization framework. The proposed method yields higher matching accuracy after the size reduction than the conventional content-aware image size-reduction methods.

Keywords: image compression, image matching, key-point detection and description, machine-to-machine communication

Procedia PDF Downloads 418

Authors: Nuraeni, Suryanti, Saida, Annas Boceng

Abstract:

Farm forestry is a forest where farmers or landowners do cultivation and farming activities on their land. This study aims to determine the dimensions of sustainable development of farm forestry and to analyze the leverage factors to improve the sustainability status of farm forestry management in Bulukumba Regency. This research was conducted in Kajang District, Bulukumba Regency. The analysis of the sustainability of farm forestry management applied Multi-Dimensional Scaling (MDS), a modification of the Rapid Appraisal of The Status of Farming (RAPFARM). The index value of farm forestry sustainability was by 62.01% for ecological dimension, 51.54% for economic dimension, 61.00% for the social and cultural dimension, and 63.24% for legal and institutional dimension with sustainable enough category status. Meanwhile, the index value for the technology and infrastructure was by 47.16% of less sustainable category status. The result of leverage analysis of attributes for the dimensions of ecological, economic, social and cultural, legal and institutional as well as infrastructure and technology afforded twenty-two (22) leverage sensitive factors that influence the sustainability of farm forestry.

Keywords: farm forestry, South Sulawesi, management, sustainability

Procedia PDF Downloads 367

Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara

Abstract:

In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.

Keywords: general metric, unsupervised learning, classification, intersection over union

Procedia PDF Downloads 47

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 80

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 189

Authors: Bruna Luisa Ramos Prado Vasques, Mariane Rembold Petraglia, Antonio Petraglia

Abstract:

This paper investigates MIMO (Multiple-Input Multiple-Output) adaptive filtering techniques for the application of supervised source separation in the context of convolutive mixtures. From the observation that there is correlation among the signals of the different mixtures, an improvement in the NSAF (Normalized Subband Adaptive Filter) algorithm is proposed in order to accelerate its convergence rate. Simulation results with mixtures of speech signals in reverberant environments show the superior performance of the proposed algorithm with respect to the performances of the NLMS (Normalized Least-Mean-Square) and conventional NSAF, considering both the convergence speed and SIR (Signal-to-Interference Ratio) after convergence.

Keywords: adaptive filtering, multi-rate processing, normalized subband adaptive filter, source separation

Procedia PDF Downloads 435

Authors: Chen-Yuan Hsu

Abstract:

Introduction Elderly is growing and results to live in the long-term care (LTC) and then due to the routine of the facilities in Taiwan, also resulted to losing of those people with environment interaction, so, the self-reliance support (SRS) for those people to experience environment interaction is an essential. Methods This study was recruited samples of a LTC in the central of Taiwan. There was a following research on the SRS group with 20 samples collected and routine care group with 20 samples. A structured questionnaire as the Environment Interaction Dimension, as data collection included demographic information and the dimensions of environment interaction. Data analysis used SPSS 22.0 for Window 2000 to report the finding. Results The Environment Interaction Dimension for Taiwanese is a Chinese version of the containing 8 items. The result of t-test analysis found that environment interaction showed a significant difference between groups (p＜.05), the result recommended that there was a higher score of environment interaction dimension on the SRS group (29.90±5.56) comparing with the routine care group (22.1±5.53). Conclusion This study showed that the SRS group was higher than the routine care group on the environment interaction dimension for Taiwanese elderly living in the LTC. The results can also provide the reference for LTC, to encourage those people to participate in SRS in LTC, and therefore also improving their environment interaction.

Keywords: self-reliance support, environment interaction, long-term care, elderly

Procedia PDF Downloads 105

Authors: Rodrigo Arnaldo Scarpel

Abstract:

Trend following is a widely accepted investment strategy that adopts a rule-based trading mechanism that rather than striving to predict market direction or on information gathering to decide when to buy and when to sell a stock. Thus, in trend following one must respond to market’s movements that has recently happen and what is currently happening, rather than on what will happen. Optimally, in trend following strategy, is to catch a bull market at its early stage, ride the trend, and liquidate the position at the first evidence of the subsequent bear market. For applying the trend following strategy one needs to find the trend and identify trade signals. In order to avoid false signals, i.e., identify fluctuations of short, mid and long terms and to separate noise from real changes in the trend, most academic works rely on moving averages and other technical analysis indicators, such as the moving average convergence divergence (MACD) and the relative strength index (RSI) to uncover intelligible stock trading rules following trend following strategy philosophy. Recently, some works has applied machine learning techniques for trade rules discovery. In those works, the process of rule construction is based on evolutionary learning which aims to adapt the rules to the current environment and searches for the global optimum rules in the search space. In this work, instead of focusing on the usage of machine learning techniques for creating trading rules, a time series trend classification employing a semi-supervised approach was used to early identify both the beginning and the end of upward and downward trends. Such classification model can be employed to identify trade signals and the decision-making procedure is that if an up-trend (down-trend) is identified, a buy (sell) signal is generated. Semi-supervised learning is used for model training when only part of the data is labeled and Semi-supervised classification aims to train a classifier from both the labeled and unlabeled data, such that it is better than the supervised classifier trained only on the labeled data. For illustrating the proposed approach, it was employed daily trade information, including the open, high, low and closing values and volume from January 1, 2000 to December 31, 2022, of the São Paulo Exchange Composite index (IBOVESPA). Through this time period it was visually identified consistent changes in price, upwards or downwards, for assigning labels and leaving the rest of the days (when there is not a consistent change in price) unlabeled. For training the classification model, a pseudo-label semi-supervised learning strategy was used employing different technical analysis indicators. In this learning strategy, the core is to use unlabeled data to generate a pseudo-label for supervised training. For evaluating the achieved results, it was considered the annualized return and excess return, the Sortino and the Sharpe indicators. Through the evaluated time period, the obtained results were very consistent and can be considered promising for generating the intended trading signals.

Keywords: evolutionary learning, semi-supervised classification, time series data, trading signals generation

Procedia PDF Downloads 89

Authors: Eng Lye, Ooi

Abstract:

The Old Man and The Sea is a novella written by Ernest Hemingway that depicts an old fisherman’ journey out into the deep sea in his pursuit to catch a big fish. Through this novella, Hemingway creates a world for his protagonist, Santiago who is portrayed as an old man who has gone eighty-four days without catching a fish, at last hooks an eighteen-foot marlin, the largest he ever known. The old man endures pain and struggles to bring back to shore. Looking through the lens of gerotranscendence, we can see that the old man has his dreams, and goals in life. In his pursuit for happiness, he has fought tirelessly to ward off the shark attacks and finally he won even though only half of his fish is left. Hemingway has portrayed Santiago as an old man as a transcendent self leaping from the dimension of “The Self” to the cosmic dimension with the personal and social relationship dimension in tow. The Old Man and The Sea offers a glimpse of the struggles of an old man, who is old and gaunt but spiritually undefeated in his battle out in the sea. He is surprisingly strong and powerful despite his old age, he respects the sea, the birds. the turtles, the sharks and the fish. He can endure suffering and is focussed on achieving his goals. This is what Hemingway has portrayed Santiago to be a gerotranscendent in the eyes of the gerotranscendental approach in respect of the changes and development as seen in Santiago, the protagonist in this novella.

Keywords: gerotranscendence, gerotranscendenatal, old man, the sea, hemingway

Procedia PDF Downloads 33

Authors: Seetanah Boopen, Padachi Kesseven, R. Juwaheer , R. V. Sannassee, M. L. Lamport

Abstract:

This study aims primarily at investigating the importance of soft infrastructure in tourism development for the case of an island economy namely Mauritius. The study in the first place assesses the level of perceived and actual satisfaction of the present state of the different types of soft tourism infrastructure and the allied services provided by tourism stakeholders in Mauritius and address the identified gaps. In order to address the study objectives, a rigorous survey analysis among 1741 international tourists at the departure lounge of the Sir Seewoosagur International Airport of Mauritius was carried out. The respondents placed significant emphasis on the different elements of the soft infrastructure dimension, where many of the elements falling under this dimension were rated with a high mean score. In particular the visitors rated communication, both internet and telephone services, and security to be most important. Significant gap has been found in the categories of ‘Health’ and ‘Security’. This indicates that the tourists ascribe high importance to the soft infrastructure dimension. The link between the respondent profile and the key variables which influence the tourist choice of the island as a destination are found to be equally important for most of the international tourists. However, these were deemed to be more critical for tourists travelling with family members. Although the survey instrument attempted to measure any gap between on the one hand, the importance of the infrastructure dimension and on the other hand, the level of satisfaction with the infrastructure dimension, overall the results do not show any statistically significant gap among the different elements of the infrastructural dimension. The study dwells into further analysis by engaging into an econometric framework related to a Probit Model, using the data collected, to gauge the effect of soft infrastructure on tourist intention to repeat or recommend the destination. The results confirm that soft infrastructure is found to be sensible to tourists, although relatively less sensitive as compared to tourism and transport and hotel infrastructure.

Keywords: tourism development, soft infrastructure, Mauritius, hotel infrastructure

Procedia PDF Downloads 487

Authors: Abdul Qadir Jangda, Khadija Mariam, Usman Ahmed, Sharib Ahmed

Abstract:

The Gafchromic EBT3 film has the characteristic of high spatial resolution, weak energy dependence and near tissue equivalence which makes them viable to be used for in-vivo dosimetry in External Beam and Brachytherapy applications. The aim of this study is to assess the smallest film dimension that may be feasible for the use in in-vivo dosimetry. To evaluate the viability, the film sizes from 3 x 3 mm to 20 x 20 mm were calibrated with 6 MV Photon and 6 MeV electron beams. The Gafchromic EBT3 (Lot no. A05151201, Make: ISP) film was cut into five different sizes in order to establish the relationship between absorbed dose vs. film dimensions. The film dimension were 3 x 3, 5 x 5, 10 x 10, 15 x 15, and 20 x 20 mm. The films were irradiated on Varian Clinac® 2100C linear accelerator for dose range from 0 to 1000 cGy using PTW solid water phantom. The irradiation was performed as per clinical absolute dose rate calibratin setup, i.e. 100 cm SAD, 5.0 cm depth and field size of 10x10 cm2 and 100 cm SSD, 1.4 cm depth and 15x15 cm2 applicator for photon and electron respectively. The irradiated films were scanned with the landscape orientation and a post development time of 48 hours (minimum). Film scanning accomplished using Epson Expression 10000 XL Flatbed Scanner and quantitative analysis carried out with ImageJ freeware software. Results show that the dose variation with different film dimension ranging from 3 x 3 mm to 20 x 20 mm is very minimal with a maximum standard deviation of 0.0058 in Optical Density for a dose level of 3000 cGy and the the standard deviation increases with the increase in dose level. So the precaution must be taken while using the small dimension films for higher doses. Analysis shows that there is insignificant variation in the absorbed dose with a change in film dimension of EBT3 film. Study concludes that the film dimension upto 3 x 3 mm can safely be used up to a dose level of 3000 cGy without the need of recalibration for particular dimension in use for dosimetric application. However, for higher dose levels, one may need to calibrate the films for a particular dimension in use for higher accuracy. It was also noticed that the crystalline structure of the film got damage at the edges while cutting the film, which can contribute to the wrong dose if the region of interest includes the damage area of the film

Keywords: external beam radiotherapy, film calibration, film dosimetery, in-vivo dosimetery

Procedia PDF Downloads 494