Search results for: deep feed forward neural network

Authors: Sukhbir Singh

Abstract:

This paper describes the modeling of novel solar air collector (NSAC) system by using artificial neural network (ANN) model. The objective of the study is to demonstrate the application of the ANN model to predict the performance of the NSAC with acetamide as a phase change material (PCM) storage. Input data set consist of time, solar intensity and ambient temperature wherever as outlet air temperature of NSAC was considered as output. Experiments were conducted between 9.00 and 24.00 h in June and July 2014 underneath the prevailing atmospheric condition of Kurukshetra (city of the India). After that, experimental results were utilized to train the back propagation neural network (BPNN) to predict the outlet air temperature of NSAC. The results of proposed algorithm show that the BPNN is effective tool for the prediction of responses. The BPNN predicted results are 99% in agreement with the experimental results.

Keywords: Evacuated tube solar air collector, Artificial neural network, Phase change material, solar air collector

Procedia PDF Downloads 96

Authors: Tatiana A. Dolenko, Sergey A. Burikov, Alexander O. Efitorov, Sergey A. Dolenko

Abstract:

In this study, a comparative analysis of the approaches associated with the use of neural network algorithms for effective solution of a complex inverse problem – the problem of identifying and determining the individual concentrations of inorganic salts in multicomponent aqueous solutions by the spectra of Raman scattering of light – is performed. It is shown that application of artificial neural networks provides the average accuracy of determination of concentration of each salt no worse than 0.025 M. The results of comparative analysis of input data compression methods are presented. It is demonstrated that use of uniform aggregation of input features allows decreasing the error of determination of individual concentrations of components by 16-18% on the average.

Keywords: inverse problems, multi-component solutions, neural networks, Raman spectroscopy

Procedia PDF Downloads 500

Authors: Harold Mauricio Díaz-Vargas, Cristian Alfonso Jimenez-Castaño, David Augusto Cárdenas-Peña, Guillermo Alberto Ortiz-Gómez, Alvaro Angel Orozco-Gutierrez

Abstract:

Precise identification of the nerves is a crucial task performed by anesthesiologists for an effective Peripheral Nerve Blocking (PNB). Now, anesthesiologists use ultrasound imaging equipment to guide the PNB and detect nervous structures. However, visual identification of the nerves from ultrasound images is difficult, even for trained specialists, due to artifacts and low contrast. The recent advances in deep learning make neural networks a potential tool for accurate nerve segmentation systems, so addressing the above issues from raw data. The most widely spread U-Net network yields pixel-by-pixel segmentation by encoding the input image and decoding the attained feature vector into a semantic image. This work proposes a conditioning approach and encoder pre-training to enhance the nerve segmentation of traditional U-Nets. Conditioning is achieved by the one-hot encoding of the kind of target nerve a the network input, while the pre-training considers five well-known deep networks for image classification. The proposed approach is tested in a collection of 619 US images, where the best C-UNet architecture yields an 81% Dice coefficient, outperforming the 74% of the best traditional U-Net. Results prove that pre-trained models with the conditional approach outperform their equivalent baseline by supporting learning new features and enriching the discriminant capability of the tested networks.

Keywords: nerve segmentation, U-Net, deep learning, ultrasound imaging, peripheral nerve blocking

Procedia PDF Downloads 80

Authors: Yulin Rao, Zhixuan Li, Burra Venkata Durga Kumar

Abstract:

Intrusion detection refers to monitoring the actions of internal and external intruders on the system and detecting the behaviours that violate security policies in real-time. In intrusion detection, there has been much discussion about the application of neural network technology and artificial immune system (AIS). However, many solutions use static methods (signature-based and stateful protocol analysis) or centralized intrusion detection systems (CIDS), which are unsuitable for real-time intrusion detection systems that need to process large amounts of data and detect unknown intrusions. This article proposes a framework for a distributed intrusion detection system (DIDS) with multi-agents based on the concept of AIS and neural network technology to detect anomalies and intrusions. In this framework, multiple agents are assigned to each host and work together, improving the system's detection efficiency and robustness. The trainer agent in the central server of the framework uses the artificial neural network (ANN) rather than the negative selection algorithm of AIS to generate mature detectors. Mature detectors can distinguish between self-files and non-self-files after learning. Our analyzer agents use genetic algorithms to generate memory cell detectors. This kind of detector will effectively reduce false positive and false negative errors and act quickly on known intrusions.

Keywords: artificial immune system, distributed artificial intelligence, multi-agent, intrusion detection system, neural network

Procedia PDF Downloads 86

Authors: Mariyam Arif, Ye Liu, Israr Ul Haq, Ahsan Ashfaq

Abstract:

High cost of fossil fuels and intensifying installations of alternate energy generation sources are intimidating main challenges in power systems. Making accurate load forecasting an important and challenging task for optimal energy planning and management at both distribution and generation side. There are many techniques to forecast load but each technique comes with its own limitation and requires data to accurately predict the forecast load. Artificial Neural Network (ANN) is one such technique to efficiently forecast the load. Comparison between two different ranges of input datasets has been applied to dynamic ANN technique using MATLAB Neural Network Toolbox. It has been observed that selection of input data on training of a network has significant effects on forecasted results. Day-wise input data forecasted the load accurately as compared to year-wise input data. The forecasted load is then distributed among the six generators by using the linear programming to get the optimal point of generation. The algorithm is then verified by comparing the results of each generator with their respective generation limits.

Keywords: artificial neural networks, demand-side management, economic dispatch, linear programming, power generation dispatch

Procedia PDF Downloads 166

Authors: J. K Adedeji, O. H Olowomofe, C. O Alo, S.T Ijatuyi

Abstract:

The issue of high blood sugar level, the effects of which might end up as diabetes mellitus, is now becoming a rampant cardiovascular disorder in our community. In recent times, a lack of awareness among most people makes this disease a silent killer. The situation calls for urgency, hence the need to design a device that serves as a monitoring tool such as a wrist watch to give an alert of the danger a head of time to those living with high blood glucose, as well as to introduce a mechanism for checks and balances. The neural network architecture assumed 8-15-10 configuration with eight neurons at the input stage including a bias, 15 neurons at the hidden layer at the processing stage, and 10 neurons at the output stage indicating likely symptoms cases. The inputs are formed using the exclusive OR (XOR), with the expectation of getting an XOR output as the threshold value for diabetic symptom cases. The neural algorithm is coded in Java language with 1000 epoch runs to bring the errors into the barest minimum. The internal circuitry of the device comprises the compatible hardware requirement that matches the nature of each of the input neurons. The light emitting diodes (LED) of red, green, and yellow colors are used as the output for the neural network to show pattern recognition for severe cases, pre-hypertensive cases and normal without the traces of diabetes mellitus. The research concluded that neural network is an efficient Accu-Chek design tool for the proper monitoring of high glucose levels than the conventional methods of carrying out blood test.

Keywords: Accu-Check, diabetes, neural network, pattern recognition

Procedia PDF Downloads 127

Authors: Nathenal Thomas Lambamo

Abstract:

Based on the fact that more than 85% of the labor force and 90% of the export earnings are taken by agriculture in Ethiopia and it can be said that it is the backbone of the overall socio-economic activities in the country. Among the cereal crops that the agriculture sector provides for the country, wheat is the third-ranking one preceding teff and maize. In the present day, wheat is in higher demand related to the expansion of industries that use them as the main ingredient for their products. The local supply of wheat for these companies covers only 35 to 40% and the rest 60 to 65% percent is imported on behalf of potential customers that exhaust the country’s foreign currency reserves. The above facts show that the need for this crop in the country is too high and in reverse, the productivity of the crop is very less because of these reasons. Wheat disease is the most devastating disease that contributes a lot to this unbalance in the demand and supply status of the crop. It reduces both the yield and quality of the crop by 27% on average and up to 37% when it is severe. This study aims to detect the most frequent and degrading wheat diseases, Septoria and Leaf rust, using the most efficiently used subset of machine learning technology, deep learning. As a state of the art, a deep learning class classification technique called Convolutional Neural Network (CNN) has been used to detect diseases and has an accuracy of 99.01% is achieved.

Keywords: septoria, leaf rust, deep learning, CNN

Procedia PDF Downloads 51

Authors: A. Clementking, C. Jothi Venkateswaran

Abstract:

Mathematical and computational functionalities such as descriptive mining, optimization, and predictions are espoused to resolve natural resource planning. The water quality prediction and its attributes influence determinations are adopted optimization techniques. The water properties are tainted while merging water resource one with another. This work aimed to predict influencing water resource distribution connectivity in accordance to water quality and sediment using an innovative proposed master-slave neural network back-propagation model. The experiment results are arrived through collecting water quality attributes, computation of water quality index, design and development of neural network model to determine water quality and sediment, master–slave back propagation neural network back-propagation model to determine variations on water quality and sediment attributes between the water resources and the recommendation for connectivity. The homogeneous and parallel biochemical reactions are influences water quality and sediment while distributing water from one location to another. Therefore, an innovative master-slave neural network model [M (9:9:2)::S(9:9:2)] designed and developed to predict the attribute variations. The result of training dataset given as an input to master model and its maximum weights are assigned as an input to the slave model to predict the water quality. The developed master-slave model is predicted physicochemical attributes weight variations for 85 % to 90% of water quality as a target values.The sediment level variations also predicated from 0.01 to 0.05% of each water quality percentage. The model produced the significant variations on physiochemical attribute weights. According to the predicated experimental weight variation on training data set, effective recommendations are made to connect different resources.

Keywords: master-slave back propagation neural network model(MSBPNNM), water quality analysis, multivariate analysis, environmental mining

Procedia PDF Downloads 447

Authors: Kais Manai

Abstract:

The main part of this work focuses on the study of pion/muon separation at low energy using a nuclear Emulsion Cloud Chamber (ECC) made of lead and nuclear emulsion films. The work consists of two parts: particle reconstruction algorithm and a Neural Network that assigns to each reconstructed particle the probability to be a muon or a pion. The pion/muon separation algorithm has been optimized by using a detailed Monte Carlo simulation of the ECC and tested on real data. The algorithm allows to achieve a 60% muon identification efficiency with a pion misidentification smaller than 3%.

Keywords: nuclear emulsion, particle identification, tracking, neural network

Procedia PDF Downloads 477

Authors: Anas H. Aljemely, Jianping Xuan

Abstract:

Rolling bearing fault diagnosis plays a pivotal issue in the rotating machinery of modern manufacturing. In this research, a raw vibration signal and improved deep learning method for bearing fault diagnosis are proposed. The multi-dimensional scales of raw vibration signals are selected for evaluation condition monitoring system, and the deep learning process has shown its effectiveness in fault diagnosis. In the proposed method, employing an Exponential linear unit (ELU) layer in a convolutional neural network (CNN) that conducts the identical function on positive data, an exponential nonlinearity on negative inputs, and a particular convolutional operation to extract valuable features. The identification results show the improved method has achieved the highest accuracy with a 100-dimensional scale and increase the training and testing speed.

Keywords: bearing fault prognostics, developed CNN model, multiple-scale evaluation, deep learning features

Procedia PDF Downloads 176

Authors: Rakesh Kumar, A. K. Ghosh

Abstract:

The paper presents the modeling of linear and nonlinear longitudinal aerodynamics using real flight data of Hansa-3 aircraft gathered at low and high angles of attack. The Neural-Gauss-Newton (NGN) method has been applied to model the linear and nonlinear longitudinal dynamics and estimate parameters from flight data. Unsteady aerodynamics due to flow separation at high angles of attack near stall has been included in the aerodynamic model using Kirchhoff’s quasi-steady stall model. NGN method is an algorithm that utilizes Feed Forward Neural Network (FFNN) and Gauss-Newton optimization to estimate the parameters and it does not require any a priori postulation of mathematical model or solving of equations of motion. NGN method was validated on real flight data generated at moderate angles of attack before application to the data at high angles of attack. The estimates obtained from compatible flight data using NGN method were validated by comparing with wind tunnel values and the maximum likelihood estimates. Validation was also carried out by comparing the response of measured motion variables with the response generated by using estimates a different control input. Next, NGN method was applied to real flight data generated by executing a well-designed quasi-steady stall maneuver. The results obtained in terms of stall characteristics and aerodynamic parameters were encouraging and reasonably accurate to establish NGN as a method for modeling nonlinear aerodynamics from real flight data at high angles of attack.

Keywords: parameter estimation, NGN method, linear and nonlinear, aerodynamic modeling

Procedia PDF Downloads 417

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 185

Authors: D. G. Badagha, C. D. Modhera, S. A. Vasanwala

Abstract:

There is a great challenge for civil engineering field to contribute in environment prevention by finding out alternatives of cement and natural aggregates. There is a problem of global warming due to cement utilization in concrete, so it is necessary to give sustainable solution to produce concrete containing waste. It is very difficult to produce designated grade of concrete containing different ingredient and water cement ratio including waste to achieve desired fresh and harden properties of concrete as per requirement and specifications. To achieve the desired grade of concrete, a number of trials have to be taken, and then after evaluating the different parameters at long time performance, the concrete can be finalized to use for different purposes. This research work is carried out to solve the problem of time, cost and serviceability in the field of construction. In this research work, artificial neural network introduced to fix proportion of concrete ingredient with 50% waste replacement for M20, M25, M30, M35, M40, M45, M50, M55 and M60 grades of concrete. By using the neural network, mix design of high performance concrete was finalized, and the main basic mechanical properties were predicted at 3 days, 7 days and 28 days. The predicted strength was compared with the actual experimental mix design and concrete cube strength after 3 days, 7 days and 28 days. This experimentally and neural network based mix design can be used practically in field to give cost effective, time saving, feasible and sustainable high performance concrete for different types of structures.

Keywords: artificial neural network, high performance concrete, rebound hammer, strength prediction

Procedia PDF Downloads 132

Authors: R. Loukil, M. Chtourou, T. Damak

Abstract:

This paper investigates the training of multilayer neural network using the classic approach. Then, for estimation purposes, we suggest the use of a specific neural observer that we study its training algorithm which is the back-propagation one in the case of the disponibility of the state and in the case of an unmeasurable state. A MATLAB simulation example will be studied to highlight the usefulness of this kind of observer.

Keywords: training, estimation purposes, neural observer, back-propagation, unmeasurable state

Procedia PDF Downloads 541

Authors: Somayeh Komeylian

Abstract:

The direction of arrival (DoA) estimation is the crucial aspect of the radar technologies for detecting and dividing several signal sources. In this scenario, the antenna array output modeling involves numerous parameters including noise samples, signal waveform, signal directions, signal number, and signal to noise ratio (SNR), and thereby the methods of the DoA estimation rely heavily on the generalization characteristic for establishing a large number of the training data sets. Hence, we have analogously represented the two different optimization models of the DoA estimation; (1) the implementation of the decision directed acyclic graph (DDAG) for the multiclass least-squares support vector machine (LS-SVM), and (2) the optimization method of the deep neural network (DNN) radial basis function (RBF). We have rigorously verified that the LS-SVM DDAG algorithm is capable of accurately classifying DoAs for the three classes. However, the accuracy and robustness of the DoA estimation are still highly sensitive to technological imperfections of the antenna arrays such as non-ideal array design and manufacture, array implementation, mutual coupling effect, and background radiation and thereby the method may fail in representing high precision for the DoA estimation. Therefore, this work has a further contribution on developing the DNN-RBF model for the DoA estimation for overcoming the limitations of the non-parametric and data-driven methods in terms of array imperfection and generalization. The numerical results of implementing the DNN-RBF model have confirmed the better performance of the DoA estimation compared with the LS-SVM algorithm. Consequently, we have analogously evaluated the performance of utilizing the two aforementioned optimization methods for the DoA estimation using the concept of the mean squared error (MSE).

Keywords: DoA estimation, Adaptive antenna array, Deep Neural Network, LS-SVM optimization model, Radial basis function, and MSE

Procedia PDF Downloads 75

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 169

Authors: Hassan M. H. Mustafa

Abstract:

This piece of research addresses an interesting comparative analytical study. Which considers two concepts of diverse algorithmic computational intelligence approaches related tightly with Neural and Non-Neural Systems. The first algorithmic intelligent approach concerned with observed obtained practical results after three neural animal systems’ activities. Namely, they are Pavlov’s, and Thorndike’s experimental work. Besides a mouse’s trial during its movement inside figure of eight (8) maze, to reach an optimal solution for reconstruction problem. Conversely, second algorithmic intelligent approach originated from observed activities’ results for Non-Neural Ant Colony System (ACS). These results obtained after reaching an optimal solution while solving Traveling Sales-man Problem (TSP). Interestingly, the effect of increasing number of agents (either neurons or ants) on learning performance shown to be similar for both introduced systems. Finally, performance of both intelligent learning paradigms shown to be in agreement with learning convergence process searching for least mean square error LMS algorithm. While its application for training some Artificial Neural Network (ANN) models. Accordingly, adopted ANN modeling is a relevant and realistic tool to investigate observations and analyze performance for both selected computational intelligence (biological behavioral learning) systems.

Keywords: artificial neural network modeling, animal learning, ant colony system, traveling salesman problem, computational biology

Procedia PDF Downloads 445

Authors: Yike Lamu, Jieyu Tang, Jialin Wu, Jianyun Huang

Abstract:

With the development of economy and science and technology, the urban heat island effect becomes more and more serious. Taking Beijing city as an example, this paper divides the value of each influence index of heat island intensity and establishes a mathematical model – neural network system based on the fuzzy comprehensive evaluation index of heat island effect. After data preprocessing, the algorithm of weight of each factor affecting heat island effect is generated, and the data of sex indexes affecting heat island intensity of Shenyang City and Shanghai City, Beijing, and Hangzhou City are input, and the result is automatically output by the neural network system. It is of practical significance to show the intensity of heat island effect by visual method, which is simple, intuitive and can be dynamically monitored.

Keywords: heat island effect, neural network, comprehensive evaluation, visualization

Procedia PDF Downloads 111

Authors: Amel Ourici

Abstract:

An electrical machine failure that is not identified in an initial stage may become catastrophic and it may suffer severe damage. Thus, undetected machine faults may cascade in it failure, which in turn may cause production shutdowns. Such shutdowns are costly in terms of lost production time, maintenance costs, and wasted raw materials. Doubly fed induction generators are used mainly for wind energy conversion in MW power plants. This paper presents a detection of an inter turn stator fault in a doubly fed induction machine whose stator and rotor are supplied by two pulse width modulation (PWM) inverters. The method used in this article to detect this fault, is based on Park’s Vector Approach, using a neural network.

Keywords: doubly fed induction machine, PWM inverter, inter turn stator fault, Park’s vector approach, neural network

Procedia PDF Downloads 572

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 164

Authors: Dachuan Shi, M. Hecht, Y. Ye

Abstract:

With the trend of digitalization in railway freight transport, a large number of freight wagons in Germany have been equipped with telematics devices, commonly placed on the wagon body. A telematics device contains a GPS module for tracking and a 3-axis accelerometer for shock detection. Besides these basic functions, it is desired to use the integrated accelerometer for condition monitoring without any additional sensors. Wheel flats as a common type of failure on wheel tread cause large impacts on wagons and infrastructure as well as impulsive noise. A large wheel flat may even cause safety issues such as derailments. In this sense, this paper proposes a machine learning approach for wheel flat detection by using car body accelerations. Due to suspension systems, impulsive signals caused by wheel flats are damped significantly and thus could be buried in signal noise and disturbances. Therefore, it is very challenging to detect wheel flats using car body accelerations. The proposed algorithm considers the envelope spectrum of car body accelerations to eliminate the effect of noise and disturbances. Subsequently, a 1-D convolutional neural network (CNN), which is well known as a deep learning method, is constructed to automatically extract features in the envelope-frequency domain and conduct classification. The constructed CNN is trained and tested on field test data, which are measured on the underframe of a tank wagon with a wheel flat of 20 mm length in the operational condition. The test results demonstrate the good performance of the proposed algorithm for real-time fault detection.

Keywords: fault detection, wheel flat, convolutional neural network, machine learning

Procedia PDF Downloads 103

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 101

Authors: Tugce Talay, Kadir Erkan

Abstract:

In this study, the necessary steps for the design of axial flow permanent magnet motors are shown. The design and analysis of the engine were carried out based on ANSYS Maxwell program. The design parameters of the ANSYS Maxwell program and the artificial neural network system were established in MATLAB and the most efficient design parameters were found with the trained neural network. The results of the Maxwell program and the results of the artificial neural networks are compared and optimal working design parameters are found. The most efficient design parameters were submitted to the ANSYS Maxwell 3D design and the cogging torque was examined and design studies were carried out to reduce the cogging torque.

Keywords: AFPM, ANSYS Maxwell, cogging torque, design optimisation, efficiency, NNTOOL

Procedia PDF Downloads 192

Authors: Ali Reza Sattarzadeh, Ronny J. Kutadinata, Pubudu N. Pathirana, Van Thanh Huynh

Abstract:

Traffic congestion has become a severe worldwide problem, affecting everyday life, fuel consumption, time, and air pollution. The primary causes of these issues are inadequate transportation infrastructure, poor traffic signal management, and rising population. Traffic flow forecasting is one of the essential and effective methods in urban congestion and traffic management, which has attracted the attention of researchers. With the development of technology, undeniable progress has been achieved in existing methods. However, there is a possibility of improvement in the extraction of temporal and spatial features to determine the importance of traffic flow sequences and extraction features. In the proposed model, we implement the convolutional neural network (CNN) and long short-term memory (LSTM) deep learning models for mining nonlinear correlations and their effectiveness in increasing the accuracy of traffic flow prediction in the real dataset. According to the experiments, the results indicate that implementing Conv-LSTM networks increases the productivity and accuracy of deep learning models for traffic flow prediction.

Keywords: deep learning algorithms, intelligent transportation systems, spatiotemporal features, traffic flow prediction

Procedia PDF Downloads 138

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Cross-domain learning in the medical field is a research challenge as many conditions, like in oncology imaging, use different imaging modalities. Moreover, in most of the medical learning applications, the sample training size is relatively small. Although few-shot learning (FSL) through the use of a Siamese neural network was able to be trained on a small sample with remarkable accuracy, FSL fails to be effective for use in multiple domains as their convolution weights are set for task-specific applications. In this paper, we are addressing this problem by enabling FSL to possess the ability to shift across domains by designing a two-layer FSL network that can learn individually from each domain and produce a shared features map with extra modulation to be used at the second layer that can recognize important targets from mix domains. Our initial experimentations based on mixed medical datasets like the Medical-MNIST reveal promising results. We aim to continue this research to perform full-scale analytics for testing our cross-domain FSL learning.

Keywords: Siamese neural network, few-shot learning, meta-learning, metric-based learning, thick data transformation and analytics

Procedia PDF Downloads 25

Authors: Iwan Cony Setiadi, Aulia M. T. Nasution

Abstract:

The multispectral imaging (MSI) technique has been used for skin analysis, especially for distant mapping of in-vivo skin chromophores by analyzing spectral data at each reflected image pixel. For ergonomic purpose, our multispectral imaging system is decomposed in two parts: a light source compartment based on LED with 11 different wavelenghts and a monochromatic 8-Bit CCD camera with C-Mount Objective Lens. The software based on GUI MATLAB to control the system was also developed. Our system provides 11 monoband images and is coupled with a software reconstructing hyperspectral cubes from these multispectral images. In this paper, we proposed a new method to build a hyperspectral reflectance cube based on artificial neural network algorithm. After preliminary corrections, a neural network is trained using the 32 natural color from X-Rite Color Checker Passport. The learning procedure involves acquisition, by a spectrophotometer. This neural network is then used to retrieve a megapixel multispectral cube between 380 and 880 nm with a 5 nm resolution from a low-spectral-resolution multispectral acquisition. As hyperspectral cubes contain spectra for each pixel; comparison should be done between the theoretical values from the spectrophotometer and the reconstructed spectrum. To evaluate the performance of reconstruction, we used the Goodness of Fit Coefficient (GFC) and Root Mean Squared Error (RMSE). To validate reconstruction, the set of 8 colour patches reconstructed by our MSI system and the one recorded by the spectrophotometer were compared. The average GFC was 0.9990 (standard deviation = 0.0010) and the average RMSE is 0.2167 (standard deviation = 0.064).

Keywords: multispectral imaging, reflectance cube, spectral reconstruction, artificial neural network

Procedia PDF Downloads 298

Authors: Erick C. Valverde, Wansu Lim

Abstract:

Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.

Keywords: deep learning, face detection, facial emotion recognition, network optimization methods

Procedia PDF Downloads 92

Authors: Sonia Perez-Gamboa, Qingquan Sun, Yan Zhang

Abstract:

Non-intrusive sensor-based human activity recognition (HAR) is utilized in a spectrum of applications, including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short term memory (LSTM) recurrent neural networks (RNNs) provide a way to achieve HAR accurately and effectively. In this paper, we design a multi-layer hybrid architecture with CNN and LSTM and explore a variety of multi-layer combinations. Based on the exploration, we present a lightweight, hybrid, and multi-layer model, which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model, which can achieve a 94.7% activity recognition rate on a benchmark human activity dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between recognition rate and training time consumption.

Keywords: deep learning, LSTM, CNN, human activity recognition, inertial sensor

Procedia PDF Downloads 122

Authors: S. Nickolas, Shobha K.

Abstract:

The treatment of incomplete data is an important step in the data pre-processing. Missing values creates a noisy environment in all applications and it is an unavoidable problem in big data management and analysis. Numerous techniques likes discarding rows with missing values, mean imputation, expectation maximization, neural networks with evolutionary algorithms or optimized techniques and hot deck imputation have been introduced by researchers for handling missing data. Among these, imputation techniques plays a positive role in filling missing values when it is necessary to use all records in the data and not to discard records with missing values. In this paper we propose a novel artificial neural network based clustering algorithm, Adaptive Resonance Theory-2(ART2) for imputation of missing values in mixed attribute data sets. The process of ART2 can recognize learned models fast and be adapted to new objects rapidly. It carries out model-based clustering by using competitive learning and self-steady mechanism in dynamic environment without supervision. The proposed approach not only imputes the missing values but also provides information about handling the outliers.

Keywords: ART2, data imputation, clustering, missing data, neural network, pre-processing

Procedia PDF Downloads 250

Authors: Abdel Hadi N. Ebraheim, Eman Azomi, Nefisa A. Fahmy

Abstract:

This paper designs and implements a computer-aided system (CAS) to help detect and diagnose liver cirrhosis in patients with Chronic Hepatitis C. Our system reduces the required features (tests) the patient is asked to do to tests to their minimal best most informative subset of tests, with a diagnostic accuracy above 99%, and hence saving both time and costs. We use the Support Vector Machine (SVM) with cross-validation, a Multilayer Perceptron Neural Network (MLP), and a Generalized Regression Neural Network (GRNN) that employs a base of radial functions for functional approximation, as classifiers. Our system is tested on 199 subjects, of them 99 Chronic Hepatitis C.The subjects were selected from among the outpatient clinic in National Herpetology and Tropical Medicine Research Institute (NHTMRI).

Keywords: liver cirrhosis, artificial neural network, support vector machine, multi-layer perceptron, classification, accuracy

Procedia PDF Downloads 427