World Academy of Science, Engineering and Technology

Authors: Zhifeng Kong

Abstract:

Over-parameterized neural networks have attracted a great deal of attention in recent deep learning theory research, as they challenge the classic perspective of over-fitting when the model has excessive parameters and have gained empirical success in various settings. While a number of theoretical works have been presented to demystify properties of such models, the convergence properties of such models are still far from being thoroughly understood. In this work, we study the convergence properties of training two-hidden-layer partially over-parameterized fully connected networks with the Rectified Linear Unit activation via gradient descent. To our knowledge, this is the first theoretical work to understand convergence properties of deep over-parameterized networks without the equally-wide-hidden-layer assumption and other unrealistic assumptions. We provide a probabilistic lower bound of the widths of hidden layers and proved linear convergence rate of gradient descent. We also conducted experiments on synthetic and real-world datasets to validate our theory.

Keywords: over-parameterization, rectified linear units ReLU, convergence, gradient descent, neural networks

Procedia PDF Downloads 142

Authors: S. Benkraouda, Z. Djelloul-Khedda, B. Yagoubi

Abstract:

we present a method for early detection of forest fires from a thermal infrared satellite image, using the image matrix of the probability of belonging. The principle of the method is to compare a theoretical mathematical model to an experimental model. We considered that each line of the image matrix, as an embodiment of a non-stationary random process. Since the distribution of pixels in the satellite image is statistically dependent, we divided these lines into small stationary and ergodic intervals to characterize the image by an adequate mathematical model. A standard deviation was chosen to generate random variables, so each interval behaves naturally like white Gaussian noise. The latter has been selected as the mathematical model that represents a set of very majority pixels, which we can be considered as the image background. Before modeling the image, we made a few pretreatments, then the parameters of the theoretical Gaussian model were extracted from the modeled image, these settings will be used to calculate the probability of each interval of the modeled image to belong to the theoretical Gaussian model. The high intensities pixels are regarded as foreign elements to it, so they will have a low probability, and the pixels that belong to the background image will have a high probability. Finally, we did present the reverse of the matrix of probabilities of these intervals for a better fire detection.

Keywords: forest fire, forest fire detection, satellite image, normal distribution, theoretical gaussian model, thermal infrared matrix image

Procedia PDF Downloads 142

Authors: Jalil Boudjadar

Abstract:

Dynamic Voltage and Frequency Scaling (DVFS) multicore platforms are promising execution platforms that enable high computational performance, less energy consumption and flexibility in scheduling the system processes. However, the resulting interleaving and memory interference together with per-core frequency tuning make real-time guarantees hard to be delivered. Besides, energy consumption represents a strong constraint for the deployment of such systems on energy-limited settings. Identifying the system configurations that would achieve a high performance and consume less energy while guaranteeing the system schedulability is a complex task in the design of modern embedded systems. This work studies the trade-off between energy consumption, cores utilization and memory bottleneck and their impact on the schedulability of DVFS multicore time-critical systems with a hierarchy of shared memories. We build a model-based framework using Parametrized Timed Automata of UPPAAL to analyze the mutual impact of performance, energy consumption and schedulability of DVFS multicore systems, and demonstrate the trade-off on an actual case study.

Keywords: time-critical systems, multicore systems, schedulability analysis, energy consumption, performance analysis

Procedia PDF Downloads 107

Authors: Spyridon Plakoudas

Abstract:

After the capture of Al-Raqqah and the defeat of the short-lived Islamic Caliphate in 2017, everyone predicted the end of ISIS. However, ISIS proved far more resilient than initially thought. The militant group quickly regrouped from its defeat and started a low-intensity guerrilla campaign in central Iraq (near Kirkuk and Mosul) and north-eastern Syria (near Deir ez-Zorr). At the same time, ISIS doubled down on its cyber-campaign; actually, ISIS is as active on the cyber-domain as during the peak of its power in 2015. This paper, a spin-off paper from a co-authored book on the Syrian Civil War (due to be published by Rowman and Littlefield), intends to examine how ISIS operates in the cyber-domain and how this "Cyber-Caliphate" under re-construction is associated with its post-2017 strategy. This paper will draw on the discipline of War Studies (with an emphasis on Cyber-Security and Insurgency / Counter-Insurgency) and will benefit from the insights of interviewed experts on the field (e.g., Hassan Hasssan). This paper will explain how the successful operation of ISIS in the cyber-space preserves the myth of the “caliphate” amongst its worldwide followers (against the odds) and sustains the group’s ongoing insurgency in Syria and Iraq; in addition, this paper will suggest how this cyber-threat can be countered best.

Keywords: ISIS, cyber-jihad, Syrian Civil War, cyber-terrorism, insurgency and counter-insurgency

Procedia PDF Downloads 134

Authors: Emine Laarouchi, Daniela Cancila, Laurent Soulier, Hakima Chaouchi

Abstract:

Cyber-Physical Systems as drones proved their efficiency for supporting emergency applications. For these particular applications, travel time and autonomous navigation algorithms are of paramount importance, especially when missions are performed in urban environments with high obstacle density. In this context, however, safety properties are not properly addressed. Our ambition is to optimize the system safety level under autonomous navigation systems, by preserving performance of the CPS. At this aim, we introduce genetic algorithms in the autonomous navigation process of the drone to better infer its trajectory considering the possible obstacles. We first model the wished safety requirements through a cost function and then seek to optimize it though genetics algorithms (GA). The main advantage in the use of GA is to consider different parameters together, for example, the level of battery for navigation system selection. Our tests show that the GA introduction in the autonomous navigation systems minimize the risk of safety lossless. Finally, although our simulation has been tested for autonomous drones, our approach and results could be extended for other autonomous navigation systems such as autonomous cars, robots, etc.

Keywords: safety, unmanned aerial vehicles , CPS, ACPS, drones, path planning, genetic algorithms

Procedia PDF Downloads 181

Authors: Fahad Alhussein, Huaping Liu

Abstract:

This paper compares the multipath mitigation performance of code correlation reference waveform receivers with variable and fixed window width, for binary offset carrier and multiplexed binary offset carrier signals typically used in global navigation satellite systems. In the variable window width method, such width is iteratively reduced until the distortion on the discriminator with multipath is eliminated. This distortion is measured as the Euclidean distance between the actual discriminator (obtained with the incoming signal), and the local discriminator (generated with a local copy of the signal). The variable window width have shown better performance compared to the fixed window width. In particular, the former yields zero error for all delays for the BOC and MBOC signals considered, while the latter gives rather large nonzero errors for small delays in all cases. Due to its computational simplicity, the variable window width method is perfectly suitable for implementation in low-cost receivers.

Keywords: correlation reference waveform receivers, binary offset carrier, multiplexed binary offset carrier, global navigation satellite systems

Procedia PDF Downloads 131

Authors: Sylvester Akpah, Selasi Vondee

Abstract:

Unmanned Aerial Vehicles (UAV) as they are also known, drones have attracted increasing attention in recent years due to their ubiquitous nature and boundless applications in the areas of communication, surveying, aerial photography, weather forecasting, medical delivery, surveillance amongst others. Operated remotely in real-time or pre-programmed, drones can fly autonomously or on pre-defined routes. The application of these aerial vehicles has successfully penetrated the world due to technological evolution, thus a lot more businesses are utilizing their capabilities. Unfortunately, while drones are replete with the benefits stated supra, they are riddled with some problems, mainly attributed to the complexities in learning how to master drone flights, collision avoidance and enterprise security. Additional challenges, such as the analysis of flight data recorded by sensors attached to the drone may take time and require expert help to analyse and understand. This paper presents an autonomous drone control system using a chatbot. The system allows for easy control of drones using conversations with the aid of Natural Language Processing, thus to reduce the workload needed to set up, deploy, control, and monitor drone flight missions. The results obtained at the end of the study revealed that the drone connected to the chatbot was able to initiate flight missions with just text and voice commands, enable conversation and give real-time feedback from data and requests made to the chatbot. The results further revealed that the system was able to process natural language and produced human-like conversational abilities using Artificial Intelligence (Natural Language Understanding). It is recommended that radio signal adapters be used instead of wireless connections thus to increase the range of communication with the aerial vehicle.

Keywords: artificial ntelligence, chatbot, natural language processing, unmanned aerial vehicle

Procedia PDF Downloads 142

Authors: Asma’a Mahfoud, Abu Bakar Md. Sultan, Abdul Azim Abd, Norhayati Mohd Ali, Novia Admodisastro

Abstract:

Obfuscation is a practice to make something difficult and complicated. Programming code is ordinarily obfuscated to protect the intellectual property (IP) and prevent the attacker from reverse engineering (RE) a copyrighted software program. Obfuscation may involve encrypting some or all the code, transforming out potentially revealing data, renaming useful classes and variables (identifiers) names to meaningless labels, or adding unused or meaningless code to an application binary. Obfuscation techniques were not performing effectively recently as the reversing tools are able to break the obfuscated code. We propose in this paper a hybrid obfuscation technique that contains three approaches of renaming. Experimentation was conducted to test the effectiveness of the proposed technique. The experimentation has presented a promising result, where the reversing tools were not able to read the code.

Keywords: intellectual property, obfuscation, software security, reverse engineering

Procedia PDF Downloads 146

Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas

Abstract:

This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).

Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems

Procedia PDF Downloads 134

Authors: L. S. Godlevsky, N. V. Kresyun, V. P. Martsenyuk, K. S. Shakun, T. V. Tatarchuk, K. O. Prybolovets, L. F. Kalinichenko, M. Karpinski, T. Gancarczyk

Abstract:

Structures of eye bottom were extracted using multiscale texture gradient method and color characteristics of macular zone and vessels were verified in CIELAB scale. The difference of average values of L*, a* and b* coordinates of CIE (International Commision of Illumination) scale in patients with diabetes and healthy volunteers was compared. The average value of L* in diabetic patients exceeded such one in the group of practically healthy persons by 2.71 times (P < 0.05), while the value of a* index was reduced by 3.8 times when compared with control one (P < 0.05). b* index exceeded such one in the control group by 12.4 times (P < 0.05). The integrated index on color difference (ΔE) exceeded control value by 2.87 times (P < 0.05). More pronounced differences with ΔE were followed by a shorter period of MA appearance with a correlation level at -0.56 (P < 0.05). The specificity of diagnostics raised by 2.17 times (P < 0.05) and negative prognostic index exceeded such one determined with the expert method by 2.26 times (P < 0.05).

Keywords: diabetic retinopathy, multiscale texture gradient, color spectrum analysis, medical diagnostics

Procedia PDF Downloads 115

Authors: Ahmed Tarek, Ahmed Alveed

Abstract:

In the theory of computing, there are a wide variety of direct and indirect proof techniques. However, mathematical induction (MI) stands out to be one of the most powerful proof techniques for proving hypotheses, theorems, and new results. There are variations of mathematical induction-based proof techniques, which are broadly classified into three categories, such as structural induction (SI), weak induction (WI), and strong induction (SI). In this expository paper, several different variants of the mathematical induction techniques are explored, and the specific scenarios are discussed where a specific induction technique stands out to be more advantageous as compared to other induction strategies. Also, the essential difference among the variants of mathematical induction are explored. The points of separation among mathematical induction, recursion, and logical deduction are precisely analyzed, and the relationship among variations of recurrence relations, and mathematical induction are being explored. In this context, the application of recurrence relations, and mathematical inductions are considered together in a single framework for codewords over a given alphabet.

Keywords: alphabet, codeword, deduction, mathematical, induction, recurrence relation, strong induction, structural induction, weak induction

Procedia PDF Downloads 164

Authors: Saleh Alshehri

Abstract:

Thermoelectric technology is currently being used in many industrial applications for cooling, heating and generating electricity. This research mainly focuses on using thermoelectric to cool down high-speed computer chips at different operating conditions. A previously developed and validated three-dimensional model for optimizing and assessing the performance of cascaded thermoelectric and non-cascaded thermoelectric is used in this study to investigate the possibility of decreasing the hotspot temperature of computer chip. Additionally, a test assembly is built and tested at steady-state and transient conditions. The obtained optimum thermoelectric current at steady-state condition is used to conduct a number of pulsed tests (i.e. transient tests) with different shapes to cool the computer chips hotspots. The results of the steady-state tests showed that at hotspot heat rate of 15.58 W (5.97 W/cm²), using thermoelectric current of 4.5 A has resulted in decreasing the hotspot temperature at open circuit condition (89.3 °C) by 50.1 °C. Maximum and minimum hotspot temperatures have been affected by ON and OFF duration of the electrical current pulse. Maximum hotspot temperature was resulted by longer OFF pulse period. In addition, longer ON pulse period has generated the minimum hotspot temperature.

Keywords: thermoelectric generator, TEG, thermoelectric cooler, TEC, chip hotspots, electronic cooling

Procedia PDF Downloads 143

Authors: Osama Elsarrar, Marjorie Darrah, Richard Devin

Abstract:

This paper discusses the idea of capturing an expert’s knowledge in the form of human understandable rules and then inserting these rules into a dynamic cell structure (DCS) neural network. The DCS is a form of self-organizing map that can be used for many purposes, including classification and prediction. This particular neural network is considered to be a topology preserving network that starts with no pre-structure, but assumes a structure once trained. The DCS has been used in mission and safety-critical applications, including adaptive flight control and health-monitoring in aerial vehicles. The approach is to insert expert knowledge into the DCS before training. Rules are translated into a pre-structure and then training data are presented. This idea has been demonstrated using the well-known Iris data set and it has been shown that inserting the pre-structure results in better accuracy with the same training.

Keywords: neural network, self-organizing map, rule extraction, rule insertion

Procedia PDF Downloads 172

Authors: Syed Iftikhar Hussain Shah, Vasilis Peristeras, Ioannis Magnisalis

Abstract:

Data that is high in volume, velocity, veracity and comes from a variety of sources is usually generated in all sectors including the government sector. Globally public administrations are pursuing (big) data as new technology and trying to adopt a data-centric architecture for hosting and sharing data. Properly executed, big data and data analytics in the government (big) data ecosystem can be led to data-driven government and have a direct impact on the way policymakers work and citizens interact with governments. In this research paper, we conduct a systematic literature review. The main aims of this paper are to highlight essential aspects of the government (big) data ecosystem and to explore the most critical socio-technical factors that contribute to the successful implementation of government (big) data ecosystem. The essential aspects of government (big) data ecosystem include definition, data types, data lifecycle models, and actors and their roles. We also discuss the potential impact of (big) data in public administration and gaps in the government data ecosystems literature. As this is a new topic, we did not find specific articles on government (big) data ecosystem and therefore focused our research on various relevant areas like humanitarian data, open government data, scientific research data, industry data, etc.

Keywords: applications of big data, big data, big data types. big data ecosystem, critical success factors, data-driven government, egovernment, gaps in data ecosystems, government (big) data, literature review, public administration, systematic review

Procedia PDF Downloads 228

Authors: Malay Bhattacharyya, Saparya Suresh

Abstract:

The Correlation Structure associated with a portfolio is subjected to vary across time. Studying the structural breaks in the time-dependent Correlation matrix associated with a collection had been a subject of interest for a better understanding of the market movements, portfolio selection, etc. The current paper proposes a methodology for testing the change in the time-dependent correlation structure of a portfolio in the high dimensional data using the techniques of generalized inverse, singular valued decomposition and multivariate distribution theory which has not been addressed so far. The asymptotic properties of the proposed test are derived. Also, the performance and the validity of the method is tested on a real data set. The proposed test performs well for detecting the change in the dependence of global markets in the context of high dimensional data.

Keywords: correlation structure, high dimensional data, multivariate distribution theory, singular valued decomposition

Procedia PDF Downloads 125

Authors: Yaolin Tian, Shanxiong Chen, Fujia Zhao, Xiaoyu Lin, Hailing Xiong

Abstract:

Ancient books are significant culture inheritors and their background textures convey the potential history information. However, multi-style texture recovery of ancient books has received little attention. Restricted by insufficient ancient textures and complex handling process, the generation of ancient textures confronts with new challenges. For instance, training without sufficient data usually brings about overfitting or mode collapse, so some of the outputs are prone to be fake. Recently, image generation and style transfer based on deep learning are widely applied in computer vision. Breakthroughs within the field make it possible to conduct research upon multi-style texture recovery of ancient books. Under the circumstances, we proposed a network of layout analysis and image fusion system. Firstly, we trained models by using Deep Convolution Generative against Networks (DCGAN) to synthesize multi-style ancient textures; then, we analyzed layouts based on the Position Rearrangement (PR) algorithm that we proposed to adjust the layout structure of foreground content; at last, we realized our goal by fusing rearranged foreground texts and generated background. In experiments, diversified samples such as ancient Yi, Jurchen, Seal were selected as our training sets. Then, the performances of different fine-turning models were gradually improved by adjusting DCGAN model in parameters as well as structures. In order to evaluate the results scientifically, cross entropy loss function and Fréchet Inception Distance (FID) are selected to be our assessment criteria. Eventually, we got model M8 with lowest FID score. Compared with DCGAN model proposed by Radford at el., the FID score of M8 improved by 19.26%, enhancing the quality of the synthetic images profoundly.

Keywords: deep learning, image fusion, image generation, layout analysis

Procedia PDF Downloads 157

Authors: Giriraj Achari, Malay Bhattacharyya

Abstract:

In this paper, the effectiveness of Copula Markov Switching Multifractal (MSM) models at forecasting Value-at-Risk of a two-stock portfolio is studied. The innovations are allowed to be drawn from distributions that can capture skewness and leptokurtosis, which are well documented empirical characteristics observed in financial returns. The candidate distributions considered for this purpose are Johnson-SU, Pearson Type-IV and α-Stable distributions. The two univariate marginal distributions are combined using the Student-t copula. The estimation of all parameters is performed by Maximum Likelihood Estimation. Finally, the models are compared in terms of accurate Value-at-Risk (VaR) forecasts using tests of unconditional coverage and independence. It is found that Copula-MSM-models with leptokurtic innovation distributions perform slightly better than Copula-MSM model with Normal innovations. Copula-MSM models, in general, produce better VaR forecasts as compared to traditional methods like Historical Simulation method, Variance-Covariance approach and Copula-Generalized Autoregressive Conditional Heteroscedasticity (Copula-GARCH) models.

Keywords: Copula, Markov Switching, multifractal, value-at-risk

Procedia PDF Downloads 165

Authors: Xu Han, Shanxiong Chen, Shiyu Zhu, Xiaoyu Lin, Fujia Zhao, Dingwang Wang

Abstract:

Character detection is an important issue for character recognition of ancient Yi books. The accuracy of detection directly affects the recognition effect of ancient Yi books. Considering the complex layout, the lack of standard typesetting and the mixed arrangement between images and texts, we propose a character detection method for ancient Yi books based on connected components and regressive character segmentation. First, the scanned images of ancient Yi books are preprocessed with nonlocal mean filtering, and then a modified local adaptive threshold binarization algorithm is used to obtain the binary images to segment the foreground and background for the images. Second, the non-text areas are removed by the method based on connected components. Finally, the single character in the ancient Yi books is segmented by our method. The experimental results show that the method can effectively separate the text areas and non-text areas for ancient Yi books and achieve higher accuracy and recall rate in the experiment of character detection, and effectively solve the problem of character detection and segmentation in character recognition of ancient books.

Keywords: CCS concepts, computing methodologies, interest point, salient region detections, image segmentation

Procedia PDF Downloads 132

Authors: Joseph Lillington, Tom Gout, Mike Harrison, Ian Farnan

Abstract:

The vitrification of high-level nuclear waste within borosilicate glass and its incorporation within a multi-barrier repository deep underground is widely accepted as the preferred disposal method. However, for this to happen, any safety case will require validation that the initially localized radionuclides will not be considerably released into the near/far-field. Therefore, accurate mechanistic models are necessary to predict glass dissolution, and these should be robust to a variety of incorporated waste species and leaching test conditions, particularly given substantial variations across international waste-streams. Here, machine learning is used to predict glass material properties (viscosity, density) and glass leaching model parameters from large-scale industrial data. A variety of different machine learning algorithms have been compared to assess performance. Density was predicted solely from composition, whereas viscosity additionally considered temperature. To predict suitable glass leaching model parameters, a large simulated dataset was created by coupling MATLAB and the chemical reactive-transport code HYTEC, considering the state-of-the-art GRAAL model (glass reactivity in allowance of the alteration layer). The trained models were then subsequently applied to the large-scale industrial, experimental data to identify potentially appropriate model parameters. Results indicate that ensemble methods can accurately predict viscosity as a function of temperature and composition across all three industrial datasets. Glass density prediction shows reliable learning performance with predictions primarily being within the experimental uncertainty of the test data. Furthermore, machine learning can predict glass dissolution model parameters behavior, demonstrating potential value in GRAAL model development and in assessing suitable model parameters for large-scale industrial glass dissolution data.

Keywords: machine learning, predictive modelling, pattern recognition, radioactive waste glass

Procedia PDF Downloads 116

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 146

Authors: Zeyu Zhang, Guisheng Yin, Ziying Zhang, Liguo Zhang

Abstract:

This paper mainly studies the path planning method based on ant colony optimization (ACO), and proposes heuristic integration ant colony optimization (HIACO). This paper not only analyzes and optimizes the principle, but also simulates and analyzes the parameters related to the application of HIACO in path planning. Compared with the original algorithm, the improved algorithm optimizes probability formula, tabu table mechanism and updating mechanism, and introduces more reasonable heuristic factors. The optimized HIACO not only draws on the excellent ideas of the original algorithm, but also solves the problems of premature convergence, convergence to the sub optimal solution and improper exploration to some extent. HIACO can be used to achieve better simulation results and achieve the desired optimization. Combined with the probability formula and update formula, several parameters of HIACO are tested. This paper proves the principle of the HIACO and gives the best parameter range in the research of path planning.

Keywords: ant colony optimization, heuristic integration, path planning, probability formula

Procedia PDF Downloads 251

Authors: Hana Rabbouch

Abstract:

In recent years, there has been considerable growth of denoising techniques mainly devoted to medical imaging. This important evolution is not only due to the progress of computing techniques, but also to the emergence of multi-resolution analysis (MRA) on both mathematical and algorithmic bases. In this paper, a comparative study is conducted between the two best-known MRA-based decomposition techniques: the Empirical Mode Decomposition (EMD) and the Discrete Wavelet Transform (DWT). The comparison is carried out in a framework of multi-scale denoising, where a Non-Local Means (NLM) filter is performed scale-by-scale to a sample of benchmark medical images. The results prove the effectiveness of the multiscaled denoising, especially when the NLM filtering is coupled with the EMD.

Keywords: medical imaging, non local means, denoising, multiscaled analysis, empirical mode decomposition, wavelets

Procedia PDF Downloads 141

Authors: Abrar R. Al-Hasan

Abstract:

Despite the widespread use of social media by consumers and marketers, empirical research investigating their economic value in the healthcare industry still lags. This study explores the impact of the use of social media marketing efforts on a hospital's brand equity and, ultimately, consumer response. Using social media data from Twitter and Facebook, along with an online and offline survey methodology, data is analyzed using logistic regression models. A random sample of (728) residents of the Kuwaiti population is used. The results of this study found that social media marketing efforts (SMME) in terms of use and validation lead to higher hospital brand equity and in turn, patient loyalty and patient visit. The study highlights the impact of SMME on hospital brand equity and patient response. Healthcare organizations should guide their marketing efforts to better manage this new way of marketing and communicating with patients to enhance their consumer loyalty and financial performance.

Keywords: brand equity, healthcare marketing, patient visit, social media, SMME

Procedia PDF Downloads 173

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, student engagement

Procedia PDF Downloads 94

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 148

Authors: Paraskevi Theodorou, Apostolos Meliones

Abstract:

In the context of the development process of two assistive navigation mobile apps for blind and visually impaired people (BVI) an extensive qualitative analysis of the requirements of potential users has been conducted. The analysis was based on interviews with BVIs and aimed to elicit not only their needs with respect to autonomous navigation but also their preferences on specific features of the apps under development. The elicited requirements were structured into four main categories, namely, requirements concerning the capabilities, functionality and usability of the apps, as well as compatibility requirements with respect to other apps and services. The main categories were then further divided into nine sub-categories. This classification, along with its content, aims to become a useful tool for the researcher or the developer who is involved in the development of digital services for BVI.

Keywords: accessibility, assistive mobile apps, blind and visually impaired people, user requirements analysis

Procedia PDF Downloads 123

Authors: Faraji Sepideh

Abstract:

Nowadays, purchase rate of the smart device is increasing and user authentication is one of the important issues in information security. Alphanumeric strong passwords are difficult to memorize and also owners write them down on papers or save them in a computer file. In addition, text password has its own flaws and is vulnerable to attacks. Graphical password can be used as an alternative to alphanumeric password that users choose images as a password. This type of password is easier to use and memorize and also more secure from pervious password types. In this paper we have designed a more secure graphical password system to prevent shoulder surfing, smudge and brute force attack. This scheme is a combination of two types of graphical passwords recognition based and Cued recall based. Evaluation the usability and security of our proposed scheme have been explained in conclusion part.

Keywords: brute force attack, graphical password, shoulder surfing attack, smudge attack

Procedia PDF Downloads 161

Authors: Rongbo Shen, Jianhua Yao, Kezhou Yan, Kuan Tian, Cheng Jiang, Ke Zhou

Abstract:

This study proposes a generative adversarial networks (GAN) framework to perform synthetic sampling in feature space, i.e., feature augmentation, to address the class imbalance problem in medical image analysis. A feature extraction network is first trained to convert images into feature space. Then the GAN framework incorporates adversarial learning to train a feature generator for the minority class through playing a minimax game with a discriminator. The feature generator then generates features for minority class from arbitrary latent distributions to balance the data between the majority class and the minority class. Additionally, a data cleaning technique, i.e., Tomek link, is employed to clean up undesirable conflicting features introduced from the feature augmentation and thus establish well-defined class clusters for the training. The experiment section evaluates the proposed method on two medical image analysis tasks, i.e., mass classification on mammogram and cancer metastasis classification on histopathological images. Experimental results suggest that the proposed method obtains superior or comparable performance over the state-of-the-art counterparts. Compared to all counterparts, our proposed method improves more than 1.5 percentage of accuracy.

Keywords: class imbalance, synthetic sampling, feature augmentation, generative adversarial networks, data cleaning

Procedia PDF Downloads 127

Authors: Uwaruile Austin Obuh

Abstract:

This research work focuses on the use of computers in improving the academic performance of students in mathematics in Benin City, Edo State. To guide this study, two research questions were raised, and two corresponding hypotheses were formulated. A total of one hundred and twenty (120) respondents were randomly selected from four schools in the city (60 boys and 60 girls). The instrument employed for the collation of data for the study was the multiple-choice test items on geometry (MCTIOG), drawn from past senior school certificate examinations (SSCE) questions. The instrument was validated by an expert in mathematics and measurement and evaluation. The data obtained from the pre and post-test were analysed using the mean, standard deviation, and T-test. The study revealed a non-significant difference between the experimental and control group in the pre-test, and the two groups were found to be the same before treatment began. The study also revealed that the experimental group performed better than the control group. One can, therefore, conclude that the use of computers for mathematics instruction has improved the performance of students in Geometry. Therefore, the hypothesis was rejected. The study finally revealed that there was no significant difference between the boys and girls taught mathematics using a computer. Therefore, the hypothesis which states there will be no significant difference in the performance of boys and girls taught mathematics using the computer was not rejected. Consequent upon the findings of this study, a number of recommendations were postulated that would enhance the performance of teachers in the use of computer-aided instruction.

Keywords: computer, teaching, learning, mathematics

Procedia PDF Downloads 123

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: cancer classification, feature selection, deep learning, genetic algorithm

Procedia PDF Downloads 111