Search results for: recurrent neural network

Authors: Parisa Mansour

Abstract:

Cystic fibrosis (CF) is one of the most common autosomal recessive diseases among whites. It mostly affects the lungs, causing infections and inflammation that account for 90% of deaths in CF patients. Because of this high variability in clinical presentation and organ involvement, investigating treatment responses and evaluating lung changes over time is critical to preventing CF progression. High-resolution computed tomography (HRCT) greatly facilitates the assessment of lung disease progression in CF patients. Recently, artificial intelligence was used to analyze chest CT scans of CF patients. In this paper, we propose a convolutional neural network (CNN) approach to classify CF lung patterns in HRCT images. The proposed network consists of two convolutional layers with 3 × 3 kernels and maximally connected in each layer, followed by two dense layers with 1024 and 10 neurons, respectively. The softmax layer prepares a predicted output probability distribution between classes. This layer has three exits corresponding to the categories of normal (healthy), bronchitis and inflammation. To train and evaluate the network, we constructed a patch-based dataset extracted from more than 1100 lung HRCT slices obtained from 45 CF patients. Comparative evaluation showed the effectiveness of the proposed CNN compared to its close peers. Classification accuracy, average sensitivity and specificity of 93.64%, 93.47% and 96.61% were achieved, indicating the potential of CNNs in analyzing lung CF patterns and monitoring lung health. In addition, the visual features extracted by our proposed method can be useful for automatic measurement and finally evaluation of the severity of CF patterns in lung HRCT images.

Keywords: HRCT, CF, cystic fibrosis, chest CT, artificial intelligence

Procedia PDF Downloads 65

Authors: Radwa El Shorbagy, Alaa El Din Balbaa, Khaled Ayad, Waleed Reda

Abstract:

Ankle sprain is a common lower limb injury that is complicated by high recurrence rate. The cause of recurrence is not clear; however, changes in motor control have been postulated.Objective: to determine the contribution of proximal hip strategy to dynamic posture control in patients with recurrent ankle sprain. Methods:Fifteen subjects with recurrent ankle sprain (Group A) and fifteen healthy control subjects (Group B) participated in this study. Abductor-adductor as well as flexor-extensor hip musculature control was abolished by fatigue using the Biodex Isokinatic System. Dynamic posture control was measured before and after fatigue by the Biodex Balance System. Results: Repeated measures MANOVA was used to compare within group differences. In group A fatiguing of hip muscles (flexors-extensors and abductors-adductors) lowered overall stability index (OASI), anteroposterior stability index (APSI) and mediolateral stability index (MLSI) significantly (p=0.00) whereas; in group B fatiguing of hip flexors-extensors lowered significantly OASI and APSI only (p= 0.017, 0.010; respectively) while fatiguing of hip abductors-adductors has no significant effect on these variables. Conclusion: fatiguing of hip muscles has a significant deleterious effect on dynamic posture control in patient with recurrent ankle sprain indicating their increased dependence on hip strategy.

Keywords: ankle sprain, fatigue hip muscles, dynamic balance, ankle sprain

Procedia PDF Downloads 355

Authors: G. Ravindranath, S. Savitha

Abstract:

This paper presents heat transfer analysis of single horizontal bare tube and heat transfer analysis of staggered arrangement of bare tube bundles bare tube bundles in gas-solid (air-solid) fluidized bed and predictions are done by using Artificial Neural Network (ANN) based on experimental data. Fluidized bed provide nearly isothermal environment with high heat transfer rate to submerged objects i.e. due to through mixing and large contact area between the gas and the particle, a fully fluidized bed has little temperature variation and gas leaves at a temperature which is close to that of the bed. Measurement of average heat transfer coefficient was made by local thermal simulation technique in a cold bubbling air-fluidized bed of size 0.305 m. x 0.305 m. Studies were conducted for single horizontal Bare Tube of length 305mm and 28.6mm outer diameter and for bare tube bundles of staggered arrangement using beds of large (average particle diameter greater than 1 mm) particle (raagi and mustard). Within the range of experimental conditions influence of bed particle diameter ( Dp), Fluidizing Velocity (U) were studied, which are significant parameters affecting heat transfer. Artificial Neural Networks (ANNs) have been receiving an increasing attention for simulating engineering systems due to some interesting characteristics such as learning capability, fault tolerance, and non-linearity. Here, feed-forward architecture and trained by back-propagation technique is adopted to predict heat transfer analysis found from experimental results. The ANN is designed to suit the present system which has 3 inputs and 2 out puts. The network predictions are found to be in very good agreement with the experimental observed values of bare heat transfer coefficient (hb) and nusselt number of bare tube (Nub).

Keywords: fluidized bed, large particles, particle diameter, ANN

Procedia PDF Downloads 364

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Babak Bahri, Fatemeh Yassaee Meybodi, Changiz Eslahchi

Abstract:

In the pursuit of effective cancer therapies, the exploration of combinatorial drug regimens is crucial to leverage synergistic interactions between drugs, thereby improving treatment efficacy and overcoming drug resistance. However, identifying synergistic drug pairs poses challenges due to the vast combinatorial space and limitations of experimental approaches. This study introduces ClusterSyn, a machine learning (ML)-powered framework for classifying anti-cancer drug synergy scores. ClusterSyn employs a two-step approach involving drug clustering and synergy score prediction using a fully connected deep neural network. For each cell line in the training dataset, a drug graph is constructed, with nodes representing drugs and edge weights denoting synergy scores between drug pairs. Drugs are clustered using the Markov clustering (MCL) algorithm, and vectors representing the similarity of drug pairs to each cluster are input into the deep neural network for synergy score prediction (synergy or antagonism). Clustering results demonstrate effective grouping of drugs based on synergy scores, aligning similar synergy profiles. Subsequently, neural network predictions and synergy scores of the two drugs on others within their clusters are used to predict the synergy score of the considered drug pair. This approach facilitates comparative analysis with clustering and regression-based methods, revealing the superior performance of ClusterSyn over state-of-the-art methods like DeepSynergy and DeepDDS on diverse datasets such as Oniel and Almanac. The results highlight the remarkable potential of ClusterSyn as a versatile tool for predicting anti-cancer drug synergy scores.

Keywords: drug synergy, clustering, prediction, machine learning., deep learning

Procedia PDF Downloads 79

Authors: Deepika Christopher, Garima Anand

Abstract:

To determine the best model for churn prediction in the telecom industry, this paper compares 11 machine learning algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, XGBoost, LightGBM, Cat Boost, AdaBoost, Extra Trees, Deep Neural Network, and Hybrid Model (MLPClassifier). It also aims to pinpoint the top three factors that lead to customer churn and conducts customer segmentation to identify vulnerable groups. According to the data, the Logistic Regression model performs the best, with an F1 score of 0.6215, 81.76% accuracy, 68.95% precision, and 56.57% recall. The top three attributes that cause churn are found to be tenure, Internet Service Fiber optic, and Internet Service DSL; conversely, the top three models in this article that perform the best are Logistic Regression, Deep Neural Network, and AdaBoost. The K means algorithm is applied to establish and analyze four different customer clusters. This study has effectively identified customers that are at risk of churn and may be utilized to develop and execute strategies that lower customer attrition.

Keywords: attrition, retention, predictive modeling, customer segmentation, telecommunications

Procedia PDF Downloads 57

Authors: Stuti Modi, Aditi Kambli

Abstract:

This paper addresses the need for intelligent water management and distribution system in smart cities to ensure optimal consumption and distribution of water for drinking and sanitation purposes. Water being a limited resource in cities require an effective system for collection, storage and distribution. In this paper, applications of two mostly widely used particular types of data-driven models, namely artificial neural networks (ANN) and fuzzy logic-based models, to modelling in the water resources management field are considered. The objective of this paper is to review the principles of various types and architectures of neural network and fuzzy adaptive systems and their applications to integrated water resources management. Final goal of the review is to expose and formulate progressive direction of their applicability and further research of the AI-related and data-driven techniques application and to demonstrate applicability of the neural networks, fuzzy systems and other machine learning techniques in the practical issues of the regional water management. Apart from this the paper will deal with water storage, using ANN to find optimum reservoir level and predicting peak daily demands.

Keywords: artificial neural networks, fuzzy systems, peak daily demand prediction, water management and distribution

Procedia PDF Downloads 186

Authors: Shweta Singh, Sudaman Katti

Abstract:

The most well-known sequence models make use of complex recurrent neural networks in an encoder-decoder configuration. The model used in this research makes use of a transformer, which is based purely on a self-attention mechanism, without relying on recurrence at all. More specifically, encoders and decoders which make use of self-attention and operate based on a memory, are used. In this research work, results for various 3D visual and non-visual reinforcement learning tasks designed in Unity software were obtained. Convolutional neural networks, more specifically, nature CNN architecture, are used for input processing in visual tasks, and comparison with standard long short-term memory (LSTM) architecture is performed for both visual tasks based on CNNs and non-visual tasks based on coordinate inputs. This research work combines the transformer architecture with the proximal policy optimization technique used popularly in reinforcement learning for stability and better policy updates while training, especially for continuous action spaces, which are used in this research work. Certain tasks in this paper are long horizon tasks that carry on for a longer duration and require extensive use of memory-based functionalities like storage of experiences and choosing appropriate actions based on recall. The transformer, which makes use of memory and self-attention mechanism in an encoder-decoder configuration proved to have better performance when compared to LSTM in terms of exploration and rewards achieved. Such memory based architectures can be used extensively in the field of cognitive robotics and reinforcement learning.

Keywords: convolutional neural networks, reinforcement learning, self-attention, transformers, unity

Procedia PDF Downloads 136

Authors: Nihal Murali, Kunal Gupta, Surekha Bhanot

Abstract:

Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without any hand-engineered features or domain heuristics. In this paper, the standard control problem of line following robot was used as a test-bed, and an ANN controller for the robot was trained on images from a live video feed using Q-learning. A virtual agent was first trained in simulation environment and then deployed onto a robot’s hardware. The robot successfully learns to traverse a wide range of curves and displays excellent generalization ability. Qualitative analysis of the evolution of policies, performance and weights of the network provide insights into the nature and convergence of the learning algorithm.

Keywords: artificial neural networks, q-learning, reinforcement learning, robot learning

Procedia PDF Downloads 372

Authors: Dongkwon Han, Sangho Kim, Sunil Kwon

Abstract:

Unconventional gas resources have dramatically changed the future energy landscape. Unlike conventional gas resources, the key challenges in unconventional gas have been the requirement that applies to advanced approaches for production forecasting due to uncertainty and complexity of fluid flow. In this study, artificial neural network (ANN) model which integrates machine learning and data-driven approach was developed to predict productivity in shale gas. The database of 129 wells of Eagle Ford shale basin used for testing and training of the ANN model. The Input data related to hydraulic fracturing, well completion and productivity of shale gas were selected and the output data is a cumulative production. The performance of the ANN using all data sets, clustering and variables importance (VI) models were compared in the mean absolute percentage error (MAPE). ANN model using all data sets, clustering, and VI were obtained as 44.22%, 10.08% (cluster 1), 5.26% (cluster 2), 6.35%(cluster 3), and 32.23% (ANN VI), 23.19% (SVM VI), respectively. The results showed that the pre-trained ANN model provides more accurate results than the ANN model using all data sets.

Keywords: unconventional gas, artificial neural network, machine learning, clustering, variables importance

Procedia PDF Downloads 196

Authors: J. K. Adedeji, M. O. Oyekanmi

Abstract:

This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.

Keywords: biometric characters, facial recognition, neural network, OpenCV

Procedia PDF Downloads 256

Authors: Olivia Borgue, Massimo Panarotto, Ola Isaksson

Abstract:

This article presents a neural networks-based strategy for reducing the need for support structures when designing for additive manufacturing (AM). Additive manufacturing is a relatively new and immature industrial technology, and the information to make confident decisions when designing for AM is limited. This lack of information impacts especially the early stages of engineering design, for instance, it is difficult to actively consider the support structures needed for manufacturing a part. This difficulty is related to the challenge of designing a product geometry accounting for customer requirements, manufacturing constraints and minimization of support structure. The approach presented in this article proposes an automatized geometry modification technique for reducing the use of the support structures while designing for AM. This strategy starts with a neural network-based strategy for shape recognition to achieve product classification, using an STL file of the product as input. Based on the classification, an automatic part geometry modification based on MATLAB© is implemented. At the end of the process, the strategy presents different geometry modification alternatives depending on the type of product to be designed. The geometry alternatives are then evaluated adopting a QFD-like decision support tool.

Keywords: additive manufacturing, engineering design, geometry modification optimization, neural networks

Procedia PDF Downloads 252

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs, and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine-learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient but not the magnitude. A neural network with two hidden layers were then used to learn the coefficient magnitudes along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction

Procedia PDF Downloads 113

Authors: Rodrigo S. Fonseca, Antônio C. P. Veiga

Abstract:

Aiming at helping people with some movement limitation that makes typing and communication difficult, there is a need to customize an assistive tool with a learning environment that helps the user in order to optimize text input, identifying the error and providing the correction and possibilities of choice in the Portuguese language. The work presents an Orthographic and Grammatical System that can be incorporated into writing environments, improving and facilitating the use of an alphanumeric keyboard, using a prototype built using a genetic algorithm in addition to carrying out the prediction, which can occur based on the quantity and position of the inserted letters and even placement in the sentence, ensuring the sequence of ideas using a Long Short Term Memory (LSTM) neural network. The prototype optimizes data entry, being a component of assistive technology for the textual formulation, detecting errors, seeking solutions and informing the user of accurate predictions quickly and effectively through machine learning.

Keywords: genetic algorithm, neural networks, word prediction, machine learning

Procedia PDF Downloads 194

Authors: Gaurav Sancheti

Abstract:

This study presents an impacting approach of Artificial Neural Networks (ANNs) in determining the quantity of High Tensile Steel (HTS) strands required in post-tensioned (PT) slabs. Various PT slab configurations were generated by varying the span and depth of the slab. For each of these slab configurations, quantity of required HTS strands were recorded. ANNs with backpropagation algorithm and varying architectures were developed and their performance was evaluated in terms of Mean Square Error (MSE). The recorded data for the quantity of HTS strands was used as a feeder database for training the developed ANNs. The networks were validated using various validation techniques. The results show that the proposed ANNs have a great potential with good prediction and generalization capability.

Keywords: artificial neural networks, back propagation, conceptual design, high tensile steel strands, post tensioned slabs, validation techniques

Procedia PDF Downloads 221

Authors: Laheeb M. Ibrahim, Ibrahim A. Salih

Abstract:

Biometrics is a technology that has been widely used in many official and commercial identification applications. The increased concerns in security during recent years (especially during the last decades) have essentially resulted in more attention being given to biometric-based verification techniques. Here, a novel fusion approach of palmprint, dental traits has been suggested. These traits which are authentication techniques have been employed in a range of biometric applications that can identify any postmortem PM person and antemortem AM. Besides improving the accuracy, the fusion of biometrics has several advantages such as increasing, deterring spoofing activities and reducing enrolment failure. In this paper, a first unimodel biometric system has been made by using (palmprint and dental) traits, for each one classification applying an artificial neural network and a hybrid technique that combines swarm intelligence and neural network together, then attempt has been made to combine palmprint and dental biometrics. Principally, the fusion of palmprint and dental biometrics and their potential application has been explored as biometric identifiers. To address this issue, investigations have been carried out about the relative performance of several statistical data fusion techniques for integrating the information in both unimodal and multimodal biometrics. Also the results of the multimodal approach have been compared with each one of these two traits authentication approaches. This paper studies the features and decision fusion levels in multimodal biometrics. To determine the accuracy of GAR to parallel system decision-fusion including (AND, OR, Majority fating) has been used. The backpropagation method has been used for classification and has come out with result (92%, 99%, 97%) respectively for GAR, while the GAR) for this algorithm using hybrid technique for classification (95%, 99%, 98%) respectively. To determine the accuracy of the multibiometric system for feature level fusion has been used, while the same preceding methods have been used for classification. The results have been (98%, 99%) respectively while to determine the GAR of feature level different methods have been used and have come out with (98%).

Keywords: back propagation neural network BP ANN, multibiometric system, parallel system decision-fusion, practical swarm intelligent PSO

Procedia PDF Downloads 532

Authors: Likewin Thomas, M. V. Manoj Kumar, B. Annappa

Abstract:

The aim of this study was to develop an Artificial Neural Network0 s recommendation model for an online process using the complexity of load, performance, and average servicing time of the resources. Here, the proposed model investigates the resource performance using stochastic gradient decent method for learning ranking function. A probabilistic cost function is implemented to identify the optimal θ values (load) on each resource. Based on this result the recommendation of resource suitable for performing the currently executing task is made. The test result of CoSeLoG project is presented with an accuracy of 72.856%.

Keywords: ADALINE, neural network, gradient decent, process mining, resource behaviour, polynomial regression model

Procedia PDF Downloads 390

Authors: Nantakrit Yodpijit, Teppakorn Sittiwanchai

Abstract:

The number of older adults is rising rapidly. The world’s population becomes aging. Falls is one of common and major health problems in the elderly. Falls may lead to acute and chronic injuries and deaths. The fall-prone individuals are at greater risk for decreased quality of life, lowered productivity and poverty, social problems, and additional health problems. A number of studies on falls prevention using fall detection system have been conducted. Many available technologies for fall detection system are laboratory-based and can incur substantial costs for falls prevention. The utilization of alternative technologies can potentially reduce costs. This paper presents the new design and development of a wearable-based fall detection system using an Accelerometer and Gyroscope as motion sensors for the detection of body orientation and movement. Algorithms are developed to differentiate between Activities of Daily Living (ADL) and falls by comparing Threshold-based values with Artificial Neural Networks (ANN). Results indicate the possibility of using the new threshold-based method with neural network algorithm to reduce the number of false positive (false alarm) and improve the accuracy of fall detection system.

Keywords: aging, algorithm, artificial neural networks (ANN), fall detection system, motion sensorsthreshold

Procedia PDF Downloads 496

Authors: Giselle Maggie Fer Castañeda, Diego Iván González

Abstract:

The objective of this work was to study the autoshaped choice behavior in the Donahoe, Burgos and Palmer (DBP) neural network model and analyze it under the matching law. Autoshaped choice can be viewed as a form of economic behavior defined as the preference between alternatives according to their relative outcomes. The Donahoe, Burgos and Palmer (DBP) model is a connectionist proposal that unifies operant and Pavlovian conditioning. This model has been used for more than three decades as a neurobehavioral explanation of conditioning phenomena, as well as a generator of predictions suitable for experimental testing with non-human animals and humans. The study consisted of different simulations in which, in each one, a ratio of reinforcement was established for two alternatives, and the responses (i.e., activations) in each of them were measured. Choice studies with animals have demonstrated that the data generally conform closely to the generalized matching law equation, which states that the response ratio equals proportionally to the reinforcement ratio; therefore, it was expected to find similar results with the neural networks of the Donahoe, Burgos and Palmer (DBP) model since these networks have simulated and predicted various conditioning phenomena. The results were analyzed by the generalized matching law equation, and it was observed that under some contingencies, the data from the networks adjusted approximately to what was established by the equation. Implications and limitations are discussed.

Keywords: matching law, neural networks, computational models, behavioral sciences

Procedia PDF Downloads 74

Authors: Wei-Han Wang, Hsiang-Yu Yu, Mau-Sun Hua

Abstract:

Theory of Mind (ToM) refers to the ability to infer another’s mental state. With appropriate ToM, one can behave well in social interactions. A growing body of evidence has demonstrated that patients with temporal lobe epilepsy (TLE) may have damaged ToM due to impact on regions of the underlying neural network of ToM. However, the question of whether there is cerebral laterality for ToM functions remains open. This study aimed to examine whether there is cerebral lateralization for ToM abilities in TLE patients. Sixty-seven adult TLE patients and 30 matched healthy controls (HC) were recruited. Patients were classified into right (RTLE), left (LTLE), and bilateral (BTLE) TLE groups on the basis of a consensus panel review of their seizure semiology, EEG findings, and brain imaging results. All participants completed an intellectual test and four tasks measuring basic and advanced ToM. The results showed that, on all ToM tasks; (1)each patient group performed worse than HC; (2)there were no significant differences between LTLE and RTLE groups; (3)the BTLE group performed the worst. It appears that the neural network responsible for ToM is distributed evenly between the cerebral hemispheres.

Keywords: cerebral lateralization, social cognition, temporal lobe epilepsy, theory of mind

Procedia PDF Downloads 420

Authors: Ashish James, Anusha James

Abstract:

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Ensemble of NNs typically produce good predictions but uncertainty estimates tend to be inconsistent. Inspired by these, this paper presents a framework that can quantitatively estimate the uncertainties by leveraging the advances in transfer learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments with known and unknown distributions show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Keywords: uncertainty estimation, neural networks, transfer learning, regression

Procedia PDF Downloads 135

Authors: Kefaya Qaddoum

Abstract:

The aim of this study is to predict breast cancer and to construct a supportive model that will stimulate a more reliable prediction as a factor that is fundamental for public health. In this study, we utilize general regression neural networks (GRNN) to replace the normal predictions with prediction periods to achieve a reasonable percentage of confidence. The mechanism employed here utilises a machine learning system called conformal prediction (CP), in order to assign consistent confidence measures to predictions, which are combined with GRNN. We apply the resulting algorithm to the problem of breast cancer diagnosis. The results show that the prediction constructed by this method is reasonable and could be useful in practice.

Keywords: neural network, conformal prediction, cancer classification, regression

Procedia PDF Downloads 291

Authors: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is the coagulation using alum and poly aluminum chloride (PACL), and the value of usage per day is a hundred thousand baht. Therefore, determining the dosage of alum and PACL are the most important factors to be prescribed. Water production is economical and valuable. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for prediction chemical dose used to coagulation such as alum and PACL, which input data consists of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of Bangkhen water treatment plant (BKWTP) Metropolitan Waterworks Authority. The data collected from 1 January 2019 to 31 December 2019 cover changing seasons of Thailand. The input data of ANN is divided into three groups training set, test set, and validation set, which the best model performance with a coefficient of determination and mean absolute error of alum are 0.73, 3.18, and PACL is 0.59, 3.21 respectively.

Keywords: soft jar test, jar test, water treatment plant process, artificial neural network

Procedia PDF Downloads 165

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 262

Authors: Mylena McCoggle, Shyra Wilson, Andrea Rivera, Rocio Alba-Flores

Abstract:

This work introduces the use of EMGs (electromyography) from muscle sensors to develop an Artificial Neural Network (ANN) for pattern recognition to control a small unmanned aerial vehicle. The objective of this endeavor exhibits interfacing drone applications beyond manual control directly. MyoWare Muscle sensor contains three EMG electrodes (dual and single type) used to collect signals from the posterior (extensor) and anterior (flexor) forearm and the bicep. Collection of raw voltages from each sensor were connected to an Arduino Uno and a data processing algorithm was developed with the purpose of interpreting the voltage signals given when performing flexing, resting, and motion of the arm. Each sensor collected eight values over a two-second period for the duration of one minute, per assessment. During each two-second interval, the movements were alternating between a resting reference class and an active motion class, resulting in controlling the motion of the drone with left and right movements. This paper further investigated adding up to three sensors to differentiate between hand gestures to control the principal motions of the drone (left, right, up, and land). The hand gestures chosen to execute these movements were: a resting position, a thumbs up, a hand swipe right motion, and a flexing position. The MATLAB software was utilized to collect, process, and analyze the signals from the sensors. The protocol (machine learning tool) was used to classify the hand gestures. To generate the input vector to the ANN, the mean, root means squared, and standard deviation was processed for every two-second interval of the hand gestures. The neuromuscular information was then trained using an artificial neural network with one hidden layer of 10 neurons to categorize the four targets, one for each hand gesture. Once the machine learning training was completed, the resulting network interpreted the processed inputs and returned the probabilities of each class. Based on the resultant probability of the application process, once an output was greater or equal to 80% of matching a specific target class, the drone would perform the motion expected. Afterward, each movement was sent from the computer to the drone through a Wi-Fi network connection. These procedures have been successfully tested and integrated into trial flights, where the drone has responded successfully in real-time to predefined command inputs with the machine learning algorithm through the MyoWare sensor interface. The full paper will describe in detail the database of the hand gestures, the details of the ANN architecture, and confusion matrices results.

Keywords: artificial neural network, biosensors, electromyography, machine learning, MyoWare muscle sensors, Arduino

Procedia PDF Downloads 174

Authors: Tim Farrelly

Abstract:

In recent years, AI-powered object detection systems have opened the doors for innovative new applications and products, especially those operating in the real world or ‘on edge’ – namely, in sport. This paper investigates the viability of an ultra-low parameter convolutional neural network specially designed for the detection of footballs on ‘on the edge’ devices. The main contribution of this paper is the exploration of integrating new design features (depth-wise separable convolutional blocks and squeezed and excitation modules) into an ultra-low parameter network and demonstrating subsequent improvements in performance. The results show that tracking the ball from Full HD images with negligibly high accu-racy is possible in real-time.

Keywords: deep learning, object detection, machine vision applications, sport, network design

Procedia PDF Downloads 144

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 145

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 186

Authors: Ahmet Faruk Akyuz, Hasan Sakir Bilge

Abstract:

Depth estimation using stereo images is a challenging problem in computer vision. Many different studies have been carried out to solve this problem. With advancing machine learning, tackling this problem is often done with neural network-based solutions. The images used in these studies are mostly in the visible spectrum. However, the need to use the Infrared (IR) spectrum for depth estimation has emerged because it gives better results than visible spectra in some conditions. At this point, we recommend using thermal-thermal (IR) image pairs for depth estimation. In this study, we used two well-known networks (PSMNet, FADNet) with minor modifications to demonstrate the viability of this idea.

Keywords: thermal stereo matching, deep neural networks, CNN, Depth estimation

Procedia PDF Downloads 279

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 68