Search results for: deep graphical model

Authors: Entisar A. Elgmati

Abstract:

Recurrent infant diarrhea is studied using daily data collected in Salvador, Brazil over one year and three months. A logistic regression model is fitted instead of Aalen's additive model using the same covariates that were used in the analysis with the additive model. The model gives reasonably similar results to that using additive regression model. In addition, the problem with the estimated conditional probabilities not being constrained between zero and one in additive model is solved here. Also martingale residuals that have been used to judge the goodness of fit for the additive model are shown to be useful for judging the goodness of fit of the logistic model.

Keywords: additive model, cumulative probabilities, infant diarrhoea, recurrent event

Procedia PDF Downloads 613

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: classification, singing, spectral analysis, vocal emission, vocal register

Procedia PDF Downloads 286

Authors: John Eric C. Bargas, Ma. Cecilia M. Marcos

Abstract:

One of the most common ground improvement techniques is Deep Soil Mixing (DSM). As the technique progresses, there is still lack in the development when it comes to depth control. This was the issue experienced during the installation of DSM in one of the National projects in the Philippines. This study assesses the feasibility of using equipment drilling parameters such as hydraulic pressure, drilling speed and rotational speed in determining the Standard Penetration Test N-value of a specific soil. Hydraulic pressure and drilling speed with a constant rotational speed of 30 rpm have a positive correlation with SPT N-value for cohesive soil and sand. A linear trend was observed for cohesive soil. The correlation of SPT N-value and hydraulic pressure yielded a R²=0.5377 while the correlation of SPT N-value and drilling speed has a R²=0.6355. While the best fitted model for sand is polynomial trend. The correlation of SPT N-value and hydraulic pressure yielded a R²=0.7088 while the correlation of SPT N-value and drilling speed has a R²=0.4354. The low correlation may be attributed to the behavior of sand when the auger penetrates. Sand tends to follow the rotation of the auger rather than resisting which was observed for very loose to medium dense sand. Specific Energy and the product of hydraulic pressure and drilling speed yielded same R² with a positive correlation. Linear trend was observed for cohesive soil while polynomial trend for sand. Cohesive soil yielded a R²=0.7320 which has a strong relationship. Sand also yielded a strong relationship having a coefficient of determination, R²=0.7203. It is feasible to use hydraulic pressure and drilling speed to estimate the SPT N-value of the soil. Also, the product of hydraulic pressure and drilling speed can be a substitute to specific energy when estimating the SPT N-value of a soil. However, additional considerations are necessary to account for other influencing factors like ground water and physical and mechanical properties of soil.

Keywords: ground improvement, equipment drilling parameters, standard penetration test, deep soil mixing

Procedia PDF Downloads 6

Authors: AnjalI A. Prasad

Abstract:

Nowadays, social media played an important role in spreading misinformation or fake news. This study analyzes the fake news related to the COVID-19 pandemic spread in social media. This paper aims at evaluating and comparing different approaches that are used to mitigate this issue, including popular deep learning approaches, such as CNN, RNN, LSTM, and BERT algorithm for classification. To evaluate models’ performance, we used accuracy, precision, recall, and F1-score as the evaluation metrics. And finally, compare which algorithm shows better result among the four algorithms.

Keywords: BERT, CNN, LSTM, RNN

Procedia PDF Downloads 189

Authors: Gholba Niranjan Dilip, Anil Kumar

Abstract:

Conduct of accurate reliable mapping of oil palm plantations and census of individual palm trees is a huge challenge. This study addresses this challenge and developed an optimized solution implemented deep learning techniques on remote sensing data. The oil palm is a very important tropical crop. To improve its productivity and land management, it is imperative to have accurate census over large areas. Since, manual census is costly and prone to approximations, a methodology for automated census using panchromatic images from Cartosat-2, SkySat and World View-3 satellites is demonstrated. It is selected two different study sites in Indonesia. The customized set of training data and ground-truth data are created for this study from Cartosat-2 images. The pre-trained model of Single Shot MultiBox Detector (SSD) Lite MobileNet V2 Convolutional Neural Network (CNN) from the TensorFlow Object Detection API is subjected to transfer learning on this customized dataset. The SSD model is able to generate the bounding boxes for each oil palm and also do the counting of palms with good accuracy on the panchromatic images. The detection yielded an F-Score of 83.16 % on seven different images. The detections are buffered and dissolved to generate polygons demarcating the boundaries of the oil palm plantations. This provided the area under the plantations and also gave maps of their location, thereby completing the automated census, with a fairly high accuracy (≈100%). The trained CNN was found competent enough to detect oil palm crowns from images obtained from multiple satellite sensors and of varying temporal vintage. It helped to estimate the increase in oil palm plantations from 2014 to 2021 in the study area. The study proved that high-resolution panchromatic satellite image can successfully be used to undertake census of oil palm plantations using CNNs.

Keywords: object detection, oil palm tree census, panchromatic images, single shot multibox detector

Procedia PDF Downloads 145

Authors: P. S. Jagadeesh Kumar, Tracy Lin Huan, S. Meenakshi Sundaram

Abstract:

Alzheimer’s disease is one of the prevalent kind of ailment, expected for impudent reconciliation or an effectual therapy is to be accredited hitherto. Probable detonation of patients in the upcoming years, and consequently an enormous deal of apprehension in early discovery of the disorder, this will conceivably chaperon to enhanced healing outcomes. Complex impetuosity of the brain is an observant symbolic of the disease and a unique recognition of genetic sign of the disease. Machine learning alongside deep learning and decision tree reinforces the aptitude to absorb characteristics from multi-dimensional data’s and thus simplifies automatic classification of Alzheimer’s disease. Susceptible testing was prophesied and realized in training the prospect of Alzheimer’s disease classification built on machine learning advances. It was shrewd that the decision trees trained with deep neural network fashioned the excellent results parallel to related pattern classification.

Keywords: Alzheimer's diagnosis, decision trees, deep neural network, machine learning, pattern classification

Procedia PDF Downloads 279

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 423

Authors: Vania Helena Tonussi Vidal, Ester Eliane Jeunon

Abstract:

This article aims to analyze the change processes of management related bureaucracy and learning organization model. The theoretical framework was based on Beer and Nohria (2001) model, identified as E and O Theory. Based on this theory the empirical research was conducted in connection with six key dimensions: goal, leadership, focus, process, reward systems and consulting. We used a case study of an educational Institution located in Barbacena, Minas Gerais. This traditional center of technical knowledge for long time adopted the bureaucratic way of management. After many changes in a business model, as the creation of graduate and undergraduate courses they decided to make a deep change in management model that is our research focus. The data were collected through semi-structured interviews with director, managers and courses supervisors. The analysis were processed by the procedures of Collective Subject Discourse (CSD) method, develop by Lefèvre & Lefèvre (2000), Results showed the incremental growing of management model toward a learning organization. Many impacts could be seeing. As negative factors we have: people resistance; poor information about the planning and implementation process; old politics inside the new model and so on. Positive impacts are: new procedures in human resources, mainly related to manager skills and empowerment; structure downsizing, open discussions channel; integrated information system. The process is still under construction and now great stimulus is done to managers and employee commitment in the process.

Keywords: bureaucracy, organizational learning, organizational change, E and O theory

Procedia PDF Downloads 411

Authors: Biniam Seifu Debelo, Bheema Lingaiah Thamineni, Hanumesh Kumar Dasari, Ahmed Ali Dawud

Abstract:

Background: One of the most frequent neurological conditions in newborns is neonatal seizures, which may indicate severe neurological dysfunction. They may be caused by a broad range of problems with the central nervous system during or after pregnancy, infections, brain injuries, and/or other health conditions. These seizures may have very subtle or very modest clinical indications because patterns like oscillatory (spike) trains begin with relatively low amplitude and gradually increase over time. This becomes very challenging and erroneous if clinical observation is the primary basis for identifying newborn seizures. Objectives: In this study, a diagnosis system using deep convolutional neural networks is proposed to determine and classify the severity level of neonatal seizures using multichannel neonatal EEG data. Methods: Clinical multichannel EEG datasets were compiled using datasets from publicly accessible online sources. Various preprocessing steps were taken, including converting 2D time series data to equivalent waveform pictures. The proposed models underwent training, and their performance was evaluated. Results: The proposed CNN was used to perform binary classification with an accuracy of 92.6%, F1-score of 92.7%, specificity of 92.8%, and precision of 92.6%. To detect newborn seizures, this model is utilized. Using the proposed CNN model, multiclassification was performed with accuracy rates of 88.6%, specificity rates of 92.18%, F1-score rates of 85.61%, and precision rates of 88.9%. A multiclassification model is used to classify the severity level of neonatal seizures. The results demonstrated that the suggested strategy can assist medical professionals in making accurate diagnoses close to healthcare institutions. Conclusion: The developed system was capable of detecting neonatal seizures and has the potential to be used as a decision-making tool in resource-limited areas with a scarcity of expert neurologists.

Keywords: CNN, multichannel EEG, neonatal seizure, severity identification

Procedia PDF Downloads 8

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 75

Authors: Amina Boukelkoul, Rahil Boukelkoul, Leila Maachia

Abstract:

The cumulative vapors emitted from the service stations may represent a hazard to the environment and the population. Besides fuel spill and their penetration into deep soil layers are the main contributors to soil and ground-water contamination in the vicinity of the petrol stations. The amount of the effluents from the service stations depends on strategy of maintenance and the policy adopted by the management to reduce the pollution. One key of the proposed approach is the idea of managing the effluents from the service stations which can be captured via use of a finite state Markov chain. Such a model can be embedded within a probabilistic operation and maintenance simulation reflecting the action to be done. In this paper, an approach of estimating a probabilistic percentage of the amount of emitted pollutants is presented. The finite state Markov model is used for decision problems with number of determined periods (life cycle) to predict the amount according to various options of operation.

Keywords: environment, markov modeling, pollution, service station

Procedia PDF Downloads 453

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

Abstract:

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

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

Procedia PDF Downloads 322

Authors: A. I. O. Zaid

Abstract:

Deep drawing is considered to be the most widely used sheet metal forming processes among the particularly in automobile and aircraft industries. It is widely used for manufacturing a large number of the body and spare parts. In its simplest form it may be defined as a secondary forming process by which a sheet metal is formed into a cylinder or alike by subjecting the sheet to compressive force through a punch with a flat end of the same geometry as the required shape of the cylinder end while it is held by a blank holder which hinders its movement but does not stop it. The punch and die profile radii play In this paper, the effects of punch and die profile radii on the autographic record, the minimum thickness strain location where the cracks normally start and cause the fracture, the maximum deep drawing force and the total consumed work in the drawing flat ended cylindrical brass cups are investigated. Five punches and five dies each having different profile radii were manufactured for this investigation. Furthermore, their effect on the quality of the drawn cups is also presented and discussed. It was found that the die profile radius has more effect on the maximum drawing force and the total consumed work than the punch profile radius.

Keywords: punch and die profile radii, deep drawing process, maximum drawing force, total consumed work, quality of produced parts, flat ended cylindrical brass cups

Procedia PDF Downloads 322

Authors: Manaranjan Pradhan, Shailaja Grover, U. Dinesh Kumar

Abstract:

Farming community in India, as well as other parts of the world, is one of the highly stressed communities due to reasons such as increasing input costs (cost of seeds, fertilizers, pesticide), droughts, reduced revenue leading to farmer suicides. Lack of integrated farm advisory system in India adds to the farmers problems. Farmers need right information during the early stages of crop’s lifecycle to prevent damage and loss in revenue. In this paper, we use deep learning techniques to develop an early warning system for detection of crop diseases using images taken by farmers using their smart phone. The research work leads to building a smart assistant using analytics and big data which could help the farmers with early diagnosis of the crop diseases and corrective actions. The classical approach for crop disease management has been to identify diseases at crop level. Recently, ImageNet Classification using the convolutional neural network (CNN) has been successfully used to identify diseases at individual plant level. Our model uses convolution filters, max pooling, dense layers and dropouts (to avoid overfitting). The models are built for binary classification (healthy or not healthy) and multi class classification (identifying which disease). Transfer learning is used to modify the weights of parameters learnt through ImageNet dataset and apply them on crop diseases, which reduces number of epochs to learn. One shot learning is used to learn from very few images, while data augmentation techniques are used to improve accuracy with images taken from farms by using techniques such as rotation, zoom, shift and blurred images. Models built using combination of these techniques are more robust for deploying in the real world. Our model is validated using tomato crop. In India, tomato is affected by 10 different diseases. Our model achieves an accuracy of more than 95% in correctly classifying the diseases. The main contribution of our research is to create a personal assistant for farmers for managing plant disease, although the model was validated using tomato crop, it can be easily extended to other crops. The advancement of technology in computing and availability of large data has made possible the success of deep learning applications in computer vision, natural language processing, image recognition, etc. With these robust models and huge smartphone penetration, feasibility of implementation of these models is high resulting in timely advise to the farmers and thus increasing the farmers' income and reducing the input costs.

Keywords: analytics in agriculture, CNN, crop disease detection, data augmentation, image recognition, one shot learning, transfer learning

Procedia PDF Downloads 103

Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav

Abstract:

Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.

Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining

Procedia PDF Downloads 127

Authors: Diana G. Ramirez-Wong, Marius Ramirez, Regina Sanchez-Leija, Adriana Rugerio, R. Araceli Mauricio-Sanchez, Martin A. Hernandez-Landaverde, Arturo Carranza, John A. Pojman, Josue D. Mota-Morales, Gabriel Luna-Barcenas

Abstract:

Chitin films were prepared using alpha-chitin from shrimp shells as raw material and a simple method of precipitation-evaporation. Choline chloride: urea Deep Eutectic Solvent (DES) was used to disperse chitin and compared against hexafluoroisopropanol (HFIP). A careful analysis of the chemical and crystalline structure was followed along the synthesis of the films, revealing crystalline-phase transitions. The full conversion of alpha- to beta-, or alpha- to gamma-chitin structure were detected by XRD and NMR on the films. The synthesis of highly crystalline monophasic gamma-chitin films was achieved using a DES; whereas HFIP helps to promote the beta-phase. These results are encouraging to continue in the study of DES as good processing media to control the final properties of chitin based materials.

Keywords: chitin, deep eutectic solvent, polymorph, phase transformation

Procedia PDF Downloads 515

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 115

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 117

Authors: L. Cesari, D. Alonso, F. Mutelet

Abstract:

The interest in cold production has been on the increase in absorption chillers for many years. In fact, the absorption cycles replace the compressor and thus reduce electrical consumption. The devices also allow waste heat generated through industrial activities to be recovered and cooled to a moderate temperature in accordance with regulatory guidelines. Many working fluids were investigated but could not compete with the commonly used {H2O + LiBr} and {H2O + NH3} to author’s best knowledge. Yet, the corrosion, toxicity and crystallization phenomena of these mixtures prevent the development of the absorption technology. This work investigates the possible use of a glyceline deep eutectic solvent (DES) and CO2 as working fluid in an absorption chiller. To do so, good knowledge of the mixtures is required. Experimental measurements (vapor-liquid equilibria, density, and heat capacity) were performed to complete the data lacking in the literature. The performance of the mixtures was quantified by the calculation of the coefficient of performance (COP). The results show that working fluids containing DES + CO2 are an interesting alternative and lead to different trails of working mixtures for absorption and chiller.

Keywords: absorption devices, deep eutectic solvent, energy valorization, experimental data, simulation

Procedia PDF Downloads 95

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 89

Authors: Omer Cahana, Maya Herman, Ofer Levi

Abstract:

Magnetic resonance imaging (MRI) is a long medical scan that stems from a long acquisition time. This length is mainly due to the traditional sampling theorem, which defines a lower boundary for sampling. However, it is still possible to accelerate the scan by using a different approach, such as compress sensing (CS) or parallel imaging (PI). These two complementary methods can be combined to achieve a faster scan with high-fidelity imaging. In order to achieve that, two properties have to exist: i) the signal must be sparse under a known transform domain, ii) the sampling method must be incoherent. In addition, a nonlinear reconstruction algorithm needs to be applied to recover the signal. While the rapid advance in the deep learning (DL) field, which has demonstrated tremendous successes in various computer vision task’s, the field of MRI reconstruction is still in an early stage. In this paper, we present an extension of the state-of-the-art model in MRI reconstruction -VarNet. We utilize VarNet by using dilated convolution in different scales, which extends the receptive field to capture more contextual information. Moreover, we simplified the sensitivity map estimation (SME), for it holds many unnecessary layers for this task. Those improvements have shown significant decreases in computation costs as well as higher accuracy.

Keywords: MRI, deep learning, variational network, computer vision, compress sensing

Procedia PDF Downloads 129

Authors: Devatha Kalyan Kumar, Aravindraj D., Sadathulla A.

Abstract:

Big data are now rapidly expanding in all engineering and science and many other domains. The potential of large or massive data is undoubtedly significant, make sense to require new ways of thinking and learning techniques to address the various big data challenges. Machine learning is continuously unleashing its power in a wide range of applications. In this paper, the latest advances and advancements in the researches on machine learning for big data processing. First, the machine learning techniques methods in recent studies, such as deep learning, representation learning, transfer learning, active learning and distributed and parallel learning. Then focus on the challenges and possible solutions of machine learning for big data.

Keywords: active learning, big data, deep learning, machine learning

Procedia PDF Downloads 411

Authors: Kwi Young Kang

Abstract:

Objective: To determine the association between inflammatory and structural lesions on sacroiliac joint (SIJ) MRI and BMD and to identify risk factors for low BMD in patients with axial spondyloarthritis (axSpA). Methods: Seventy-six patients who fulfilled the ASAS axSpA criteria were enrolled. All underwent SIJ MRI and BMD measurement at the lumbar spine, femoral neck, and total hip. Inflammatory and structural lesions on SIJ MRI were scored. Laboratory tests and assessment of radiographic and disease activity were performed at the time of MRI. The association between SIJ MRI findings and BMD was evaluated. Results: Among the 76 patients, 14 (18%) had low BMD. Patients with low BMD showed significantly higher bone marrow edema (BME) and deep BME scores on MRI than those with normal BMD (p<0.047 and 0.007, respectively). Inflammatory lesions on SIJ MRI correlated with BMD at the femoral neck and total hip. Multivariate analysis identified the presence of deep BME on SIJ MRI, increased CRP, and sacroiliitis on X-ray as risk factors for low BMD (OR: 5.6, 14.6, and 2.5, respectively). Conclusion: The presence of deep BME on SIJ MRI, increased CRP levels, and severity of sacroiliitis on X-ray were independent risk factors for low BMD.

Keywords: axial spondyloarthritis, sacroiliac joint MRI, bone mineral density, sacroiliitis

Procedia PDF Downloads 514

Authors: M. Devaki, K. B. Jayanthi

Abstract:

The identification of water bodies from satellite images has recently received a great deal of attention. Different methods have been developed to distinguish water bodies from various satellite images that vary in terms of time and space. Urban water identification issues body manifests in numerous applications with a great deal of certainty. There has been a sharp rise in the usage of satellite images to map natural resources, including urban water bodies and forests, during the past several years. This is because water and forest resources depend on each other so heavily that ongoing monitoring of both is essential to their sustainable management. The relevant elements from satellite pictures have been chosen using a variety of techniques, including machine learning. Then, a convolution neural network (CNN) architecture is created that can identify a superpixel as either one of two classes, one that includes water or doesn't from input data in a complex metropolitan scene. The deep learning technique, CNN, has advanced tremendously in a variety of visual-related tasks. CNN can improve classification performance by reducing the spectral-spatial regularities of the input data and extracting deep features hierarchically from raw pictures. Calculate the water body using the satellite image's resolution. Experimental results demonstrate that the suggested method outperformed conventional approaches in terms of water extraction accuracy from remote-sensing images, with an average overall accuracy of 97%.

Keywords: water body, Deep learning, satellite images, convolution neural network

Procedia PDF Downloads 64

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 263

Authors: Muhammad Kamran Asif

Abstract:

MPLS stands for Multi-Protocol Label Switching. It is the technology which replaces ATM (Asynchronous Transfer Mode) and frame relay. In this paper, we have designed a full fledge small scale MPLS based service provider network core network model, which provides communication services (e.g. voice, video and data) to the customer more efficiently using label switching technique. Using MPLS VPN provides security to the customers which are either on LAN or WAN. It protects its single customer sites from being attacked by any intruder from outside world along with the provision of concept of extension of a private network over an internet. In this paper, we tried to implement a service provider network using minimum available resources i.e. five 3800 series CISCO routers comprises of service provider core, provider edge routers and customer edge routers. The customers on the one end of the network (customer side) is capable of sending any kind of data to the customers at the other end using service provider cloud which is MPLS VPN enabled. We have also done simulation and emulation for the model using GNS3 (Graphical Network Simulator-3) and achieved the real time scenarios. We have also deployed a NMS system which monitors our service provider cloud and generates alarm in case of any intrusion or malfunctioning in the network. Moreover, we have also provided a video help desk facility between customers and service provider cloud to resolve the network issues more effectively.

Keywords: MPLS, VPN, NMS, ATM, asynchronous transfer mode

Procedia PDF Downloads 315

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 152

Authors: Farzaneh Sarbandi Farahani

Abstract:

Drought and decrease in the level of lakes in recent years due to global warming and excessive use of water resources feeding lakes are of great importance, and this research has provided a structure to investigate this issue. First, the information required for simulating lake drought is provided with strong references and necessary assumptions. Entity-Component-System (ECS) structure has been used for simulation, which can consider assumptions flexibly in simulation. Three major users (i.e., Industry, agriculture, and Domestic users) consume water from groundwater and surface water (i.e., streams, rivers and lakes). Lake Mead has been considered for simulation, and the information necessary to investigate its drought has also been provided. The results are presented in the form of a scenario-based design and optimal strategy selection. For optimal strategy selection, a deep reinforcement algorithm is developed to select the best set of strategies among all possible projects. These results can provide a better view of how to plan to prevent lake drought.

Keywords: drought simulation, Mead lake, entity component system programming, deep reinforcement learning

Procedia PDF Downloads 67

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 68

Authors: Keyi Wang

Abstract:

Similar to the touchscreen, hand gesture based human-computer interaction (HCI) is a technology that could allow people to perform a variety of tasks faster and more conveniently. This paper proposes a training method of an image-based hand gesture image and video clip recognition system using a CNN (Convolutional Neural Network) with a dataset. A dataset containing 6 hand gesture images is used to train a 2D CNN model. ~98% accuracy is achieved. Furthermore, a 3D CNN model is trained on a dataset containing 4 hand gesture video clips resulting in ~83% accuracy. It is demonstrated that a Cozmo robot loaded with pre-trained models is able to recognize static and dynamic hand gestures.

Keywords: deep learning, hand gesture recognition, computer vision, image processing

Procedia PDF Downloads 115