Search results for: A recurrent neural network for solving nonlinear convex programs subject to linear constraints. IEEE Transactions on Neural Networks

Authors: Milagros Jaén-Vargas, Javier García Martínez, Karla Miriam Reyes Leiva, María Fernanda Trujillo-Guerrero, Francisco Fernandes, Sérgio Barroso Gonçalves, Miguel Tavares Silva, Daniel Simões Lopes, José Javier Serrano Olmedo

Abstract:

Human Activity Recognition (HAR) is having a growing impact in creating new applications and is responsible for emerging new technologies. Also, the use of wearable sensors is an important key to exploring the human body's behavior when performing activities. Hence, the use of these dispositive is less invasive and the person is more comfortable. In this study, a database that includes three activities is used. The activities were acquired from inertial measurement unit sensors (IMU) and motion capture systems (MOCAP). The main objective is differentiating the performance from four Deep Learning (DL) models: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and hybrid model Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), when considering acceleration, velocity and position and evaluate if integrating the IMU acceleration to obtain velocity and position represent an increment in performance when it works as input to the DL models. Moreover, compared with the same type of data provided by the MOCAP system. Despite the acceleration data is cleaned when integrating, results show a minimal increase in accuracy for the integrated signals.

Keywords: HAR, IMU, MOCAP, acceleration, velocity, position, feature maps

Procedia PDF Downloads 54

Authors: Kishore K. Pochampally

Abstract:

The success of a supply chain heavily relies on the efficiency of the suppliers involved. In this paper, we propose a neural network approach to evaluate the efficiency of a supplier, which is being considered for inclusion in a supply chain, using the available linguistic (fuzzy) data of suppliers that already exist in the supply chain. The approach is carried out in three phases, as follows: In phase one, we identify criteria for evaluation of the supplier of interest. Then, in phase two, we use performance measures of already existing suppliers to construct a neural network that gives weights (importance values) of criteria identified in phase one. Finally, in phase three, we calculate the overall rating of the supplier of interest. The following are the major findings of the research conducted for this paper: (i) linguistic (fuzzy) ratings of suppliers such as 'good', 'bad', etc., can be converted (defuzzified) to numerical ratings (1 – 10 scale) using fuzzy logic so that those ratings can be used for further quantitative analysis; (ii) it is possible to construct and train a multi-level neural network in order to determine the weights of the criteria that are used to evaluate a supplier; and (iii) Borda’s rule can be used to group the weighted ratings and calculate the overall efficiency of the supplier.

Keywords: fuzzy data, neural network, supplier, supply chain

Procedia PDF Downloads 85

Authors: Zahra Abdolkarimi, Naser Zourikalatehsamad,

Abstract:

Up to 40 years ago, after recognition of epilepsy, it was generally believed that these attacks occurred randomly and suddenly. However, thanks to the advance of mathematics and engineering, such attacks can be predicted within a few minutes or hours. In this way, various algorithms for long-term prediction of the time and frequency of the first attack are presented. In this paper, by considering the nonlinear nature of brain signals and dynamic recorded brain signals, ANFIS model is presented to predict the brain signals, since according to physiologic structure of the onset of attacks, more complex neural structures can better model the signal during attacks. Contribution of this work is the co-evolution algorithm for optimization of ANFIS network parameters. Our objective is to predict brain signals based on time series obtained from brain signals of the people suffering from epilepsy using ANFIS. Results reveal that compared to other methods, this method has less sensitivity to uncertainties such as presence of noise and interruption in recorded signals of the brain as well as more accuracy. Long-term prediction capacity of the model illustrates the usage of planted systems for warning medication and preventing brain signals.

Keywords: co-evolution algorithms, brain signals, time series, neural networks, ANFIS model, physiologic structure, time prediction, epilepsy suffering, illustrates model

Procedia PDF Downloads 246

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 247

Authors: Mohit Gupta, Chialing Wei, Thomas Czerniawski

Abstract:

In this paper, we have built a neural network that can detect walls on 2D sheets and subsequently create a 3D model in Revit using Dynamo. The training set includes 3500 labeled images, and the detection algorithm used is YOLO. Typically, engineers/designers make concentrated efforts to convert 2D cad drawings to 3D models. This costs a considerable amount of time and human effort. This paper makes a contribution in automating the task of 3D walls modeling. 1. Detecting Walls in 2D cad and generating 3D pop-ups in Revit. 2. Saving designer his/her modeling time in drafting elements like walls from 2D cad to 3D representation. An object detection algorithm YOLO is used for wall detection and localization. The neural network is trained over 3500 labeled images of size 256x256x3. Then, Dynamo is interfaced with the output of the neural network to pop-up 3D walls in Revit. The research uses modern technological tools like deep learning and artificial intelligence to automate the process of generating 3D walls without needing humans to manually model them. Thus, contributes to saving time, human effort, and money.

Keywords: neural networks, Yolo, 2D to 3D transformation, CAD object detection

Procedia PDF Downloads 109

Authors: Himanshu Payal, Sachin Maheshwari, Pushpendra S. Bharti

Abstract:

Electrical discharge machining (EDM), a non-conventional machining process, finds wide applications for shaping difficult-to-cut alloys. Process modeling of EDM is required to exploit the process to the fullest. Process modeling of EDM is a challenging task owing to involvement of so many electrical and non-electrical parameters. This work is an attempt to model the EDM process using artificial neural network (ANN). Experiments were carried out on die-sinking EDM taking Inconel 825 as work material. ANN modeling has been performed using experimental data. The prediction ability of trained network has been verified experimentally. Results indicate that ANN can predict the values of performance measures of EDM satisfactorily.

Keywords: artificial neural network, EDM, metal removal rate, modeling, surface roughness

Procedia PDF Downloads 380

Authors: Abdelhamid Louliej, Younes Jabrane

Abstract:

Satellites are becoming indispensable assets to fifth-generation (5G) new radio architecture, complementing wireless and terrestrial communication links. The combination of satellites and 5G architecture allows consumers to access all next-generation services anytime, anywhere, including scenarios, like traveling to remote areas (without coverage). Nevertheless, this solution faces several challenges, such as a significant propagation delay, Doppler frequency shift, and high Peak-to-Average Power Ratio (PAPR), causing signal distortion due to the non-linear saturation of the High-Power Amplifier (HPA). To compensate for HPA non-linearity in 5G satellite transmission, an efficient pre-distorter scheme using Neural Networks (NN) is proposed. To assess the proposed NN pre-distorter, two types of HPA were investigated: Travelling Wave Tube Amplifier (TWTA) and Solid-State Power Amplifier (SSPA). The results show that the NN pre-distorter design presents EVM improvement by 95.26%. NMSE and ACPR were reduced by -43,66 dB and 24.56 dBm, respectively. Moreover, the system suffers no degradation of the Bit Error Rate (BER) for TWTA and SSPA amplifiers.

Keywords: satellites, 5G, neural networks, HPA, TWTA, SSPA, EVM, NMSE, ACPR

Procedia PDF Downloads 58

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 174

Authors: Stylianos Kampakis

Abstract:

This paper presents a new algorithm for neural networks called “Input Dropout with Aggressive Re-weighting” (IDAR) aimed specifically at datasets with many useless features. IDAR combines two techniques (dropout of input neurons and aggressive re weighting) in order to eliminate the influence of noisy features. The technique can be seen as a generalization of dropout. The algorithm is tested on two different benchmark data sets: a noisy version of the iris dataset and the MADELON data set. Its performance is compared against three other popular techniques for dealing with useless features: L2 regularization, LASSO and random forests. The results demonstrate that IDAR can be an effective technique for handling data sets with many useless features.

Keywords: neural networks, feature selection, regularization, aggressive reweighting

Procedia PDF Downloads 424

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 348

Authors: Christopher Lama, Alix Rieser, Aleksandra Molchanova, Charles Thangaraj

Abstract:

New technologies like Tesla’s Dojo have made high-performance embedded computing more available. Although automobile computing has developed and benefited enormously from these more recent technologies, the costs are still high, prohibitively high in some cases for broader adaptation, particularly for the after-market and enthusiast markets. This project aims to implement a Raspberry Pi-based low-power (under one hundred Watts) highly mobile computing cluster for a neural network. The computing cluster built from off-the-shelf components is more affordable and, therefore, makes wider adoption possible. The paper describes the design of the neural network, Raspberry Pi-based cluster, and applications the cluster will run. The neural network will use input data from sensors and cameras to project a live view of the road state as the user drives. The neural network will be trained to predict traffic behavior and generate warnings when potentially dangerous situations are predicted. The significant outcomes of this study will be two folds, firstly, to implement and test the low-cost cluster, and secondly, to ascertain the effectiveness of the predictive AI implemented on the cluster.

Keywords: CS pedagogy, student research, cluster computing, machine learning

Procedia PDF Downloads 56

Authors: Said Benkaciali, Mourad Haddadi, Abdallah Khellaf, Kacem Gairaa, Mawloud Guermoui

Abstract:

In this study, many experiments were carried out to assess the influence of the input parameters on the performance of multilayer perceptron which is one the configuration of the artificial neural networks. To estimate the daily global solar radiation on the horizontal surface, we have developed some models by using seven combinations of twelve meteorological and geographical input parameters collected from a radiometric station installed at Ghardaïa city (southern of Algeria). For selecting of best combination which provides a good accuracy, six statistical formulas (or statistical indicators) have been evaluated, such as the root mean square errors, mean absolute errors, correlation coefficient, and determination coefficient. We noted that multilayer perceptron techniques have the best performance, except when the sunshine duration parameter is not included in the input variables. The maximum of determination coefficient and correlation coefficient are equal to 98.20 and 99.11%. On the other hand, some empirical models were developed to compare their performances with those of multilayer perceptron neural networks. Results obtained show that the neural networks techniques give the best performance compared to the empirical models.

Keywords: empirical models, multilayer perceptron neural network, solar radiation, statistical formulas

Procedia PDF Downloads 312

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 539

Authors: Ismail Abubakar, Hamid Mehrabi, Reg Morton

Abstract:

Currently, extensive signal analysis is performed in order to evaluate structural health of turbomachinery blades. This approach is affected by constraints of time and the availability of qualified personnel. Thus, new approaches to blade dynamics identification that provide faster and more accurate results are sought after. Generally, modal analysis is employed in acquiring dynamic properties of a vibrating turbomachinery blade and is widely adopted in condition monitoring of blades. The analysis provides useful information on the different modes of vibration and natural frequencies by exploring different shapes that can be taken up during vibration since all mode shapes have their corresponding natural frequencies. Experimental modal testing and finite element analysis are the traditional methods used to evaluate mode shapes with limited application to real live scenario to facilitate a robust condition monitoring scheme. For a real time mode shape evaluation, rapid evaluation and low computational cost is required and traditional techniques are unsuitable. In this study, artificial neural network is developed to evaluate the mode shape of a lab scale rotating blade assembly by using result from finite element modal analysis as training data. The network performance evaluation shows that artificial neural network (ANN) is capable of mapping the correlation between natural frequencies and mode shapes. This is achieved without the need of extensive signal analysis. The approach offers advantage from the perspective that the network is able to classify mode shapes and can be employed in real time including simplicity in implementation and accuracy of the prediction. The work paves the way for further development of robust condition monitoring system that incorporates real time mode shape evaluation.

Keywords: modal analysis, artificial neural network, mode shape, natural frequencies, pattern recognition

Procedia PDF Downloads 127

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 192

Authors: Nishant Parashar, Sawan S. Sinha, Balaji Srinivasan

Abstract:

We perform an investigation of the unclosed terms in the evolution equation of the velocity gradient tensor (VGT) in compressible decaying turbulent flow. Velocity gradients in a compressible turbulent flow field influence several important nonlinear turbulent processes like cascading and intermittency. In an attempt to understand the dynamics of the velocity gradients various researchers have tried to model the unclosed terms in the evolution equation of the VGT. The existing models proposed for these unclosed terms have limited applicability. This is mainly attributable to the complex structure of the higher order gradient terms appearing in the evolution equation of VGT. We investigate these higher order gradients using the data from direct numerical simulation (DNS) of compressible decaying isotropic turbulent flow. The gas kinetic method aided with weighted essentially non-oscillatory scheme (WENO) based flow- reconstruction is employed to generate DNS data. By applying neural-network to the DNS data, we map the structure of the unclosed higher order gradient terms in the evolution of the equation of the VGT with VGT itself. We validate our findings by performing alignment based study of the unclosed higher order gradient terms obtained using the neural network with the strain rate eigenvectors.

Keywords: compressible turbulence, neural network, velocity gradient tensor, direct numerical simulation

Procedia PDF Downloads 135

Authors: Zeina Merabi, Arij Dao

Abstract:

The temporal order of information processing in the brain is an important code in many acoustic signals, including speech, music, and animal vocalizations. Despite its significance, surprisingly little is known about its underlying cellular mechanisms and network manifestations. In the songbird telencephalic nucleus HVC, a subset of neurons shows temporal combination sensitivity (TCS). These neurons show a high temporal specificity, responding differently to distinct patterns of spectral elements and their combinations. HVC neuron types include basal-ganglia-projecting HVCX, forebrain-projecting HVCRA, and interneurons (HVC¬INT), each exhibiting distinct cellular, electrophysiological and functional properties. In this work, we develop conductance-based neural network models connecting the different classes of HVC neurons via different wiring scenarios, aiming to explore possible neural mechanisms that orchestrate the combination sensitivity property exhibited by HVCX, as well as replicating in vivo firing patterns observed when TCS neurons are presented with various auditory stimuli. The ionic and synaptic currents for each class of neurons that are presented in our networks and are based on pharmacological studies, rendering our networks biologically plausible. We present for the first time several realistic scenarios in which the different types of HVC neurons can interact to produce this behavior. The different networks highlight neural mechanisms that could potentially help to explain some aspects of combination sensitivity, including 1) interplay between inhibitory interneurons’ activity and the post inhibitory firing of the HVCX neurons enabled by T-type Ca2+ and H currents, 2) temporal summation of synaptic inputs at the TCS site of opposing signals that are time-and frequency- dependent, and 3) reciprocal inhibitory and excitatory loops as a potent mechanism to encode information over many milliseconds. The result is a plausible network model characterizing auditory processing in HVC. Our next step is to test the predictions of the model.

Keywords: combination sensitivity, songbirds, neural networks, spatiotemporal integration

Procedia PDF Downloads 35

Authors: Christoph Linse, Thomas Martinetz

Abstract:

Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets

Procedia PDF Downloads 55

Authors: Ulrike Dowie, Ralph Grothmann

Abstract:

Rational planning decisions are based upon forecasts. Precise forecasting has, therefore, a central role in business. The prediction of customer demand is a prime example. This paper introduces recurrent neural networks to model customer demand and combines the forecast with uncertainty measures to derive decision support of the demand planning department. It identifies and describes the keys to the successful implementation of an AI-based solution: bringing together data with business knowledge, AI methods, and user experience, and applying agile software development practices.

Keywords: agile software development, AI project success factors, deep learning, demand forecasting, forecast uncertainty, neural networks, supply chain management

Procedia PDF Downloads 142

Authors: M. K. Wijayarathna, S. M. Buddika Harshanath

Abstract:

Monitoring student engagement has become a crucial part of the educational process and a reliable indicator of the capacity to retain information. As online learning classrooms are now more common these days, students' attention levels have become increasingly important, making it more difficult to check each student's concentration level in an online classroom setting. To profile student attention to various gradients of engagement, a study is a plan to conduct using machine learning models. Using a convolutional neural network, the findings and confidence score of the high accuracy model are obtained. In this research, convolutional neural networks are using to help discover essential emotions that are critical in defining various levels of participation. Students' attention levels were shown to be influenced by emotions such as calm, enjoyment, surprise, and fear. An improved virtual learning system was created as a result of these data, which allowed teachers to focus their support and advise on those students who needed it. Student participation has formed as a crucial component of the learning technique and a consistent predictor of a student's capacity to retain material in the classroom. Convolutional neural networks have a plan to implement the platform. As a preliminary step, a video of the pupil would be taken. In the end, researchers used a convolutional neural network utilizing the Keras toolkit to take pictures of the recordings. Two convolutional neural network methods are planned to use to determine the pupils' attention level. Finally, those predicted student attention level results plan to display on the graphical user interface of the System.

Keywords: HTML5, JavaScript, Python flask framework, AI, graphical user

Procedia PDF Downloads 67

Authors: Constanza A. Barriga, Rafael Bernardi, Amokrane Berdja, Christian D. Guzman

Abstract:

Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariable in the image plane. However, this latter condition is not always satisfied with real optical systems. PSF angular variations cannot be evaluated directly from the observations, neither be corrected at a pixel resolution. We have developed a method for the restoration of images affected by static and anisotropic aberrations using deep neural networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T-80 telescope optical system, an 80 cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image, which has a constant and known PSF across its field-of-view. The method was tested with the T-80 telescope, achieving better results than with PSF deconvolution techniques. We present the method and results on this telescope.

Keywords: aberrations, deep neural networks, image restoration, variable point spread function, wide field images

Procedia PDF Downloads 105

Authors: Margarita Mayoral-Villa, J. Klapp, L. Di G. Sigalotti, J. E. V. Guzmán

Abstract:

Automated learning techniques are widely applied in the energy sector to address challenging problems from a practical point of view. To this end, we discuss the implementation of a Message Passing algorithm (MPNN)within a Graph Neural Network(GNN)to leverage the neighborhood of a set of nodes during the aggregation process. This approach enables the characterization of multiphase diffusion processes in the reservoir, such that the flow paths underlying the interconnections between multiple wells may be inferred from previously available data on flow rates and bottomhole pressures. The results thus obtained compare favorably with the predictions produced by the Reduced Order Capacitance-Resistance Models (CRM) and suggest the potential of MPNNs to enhance the robustness of the forecasts while improving the computational efficiency.

Keywords: multiphase diffusion, message passing neural network, well interconnection, interwell connectivity, graph neural network, capacitance-resistance models

Procedia PDF Downloads 115

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 96

Authors: Shoujia Fang, Guoqing Ding, Xin Chen

Abstract:

The quality of press-fit assembly is closely related to reliability and safety of product. The paper proposed a keypoint detection method based on convolutional neural network to improve the accuracy of keypoint detection in press-fit curve. It would provide an auxiliary basis for judging quality of press-fit assembly. The press-fit curve is a curve of press-fit force and displacement. Both force data and distance data are time-series data. Therefore, one-dimensional convolutional neural network is used to process the press-fit curve. After the obtained press-fit data is filtered, the multi-layer one-dimensional convolutional neural network is used to perform the automatic learning of press-fit curve features, and then sent to the multi-layer perceptron to finally output keypoint of the curve. We used the data of press-fit assembly equipment in the actual production process to train CNN model, and we used different data from the same equipment to evaluate the performance of detection. Compared with the existing research result, the performance of detection was significantly improved. This method can provide a reliable basis for the judgment of press-fit quality.

Keywords: keypoint detection, curve feature, convolutional neural network, press-fit assembly

Procedia PDF Downloads 184

Authors: Ying Han, Yuanxiang Chen, Yongtao Huang, Jia Fu, Kaile Li, Shangjing Lin, Jianguo Yu

Abstract:

In long-haul and high-speed optical transmission system, the orthogonal frequency division multiplexing (OFDM) signal suffers various linear and non-linear impairments. In recent years, researchers have proposed compensation schemes for specific impairment, and the effects are remarkable. However, different impairment compensation algorithms have caused an increase in transmission delay. With the widespread application of deep neural networks (DNN) in communication, multi-impairment compensation based on DNN will be a promising scheme. In this paper, we propose and apply DNN to compensate multi-impairment of 16-QAM coherent optical OFDM signal, thereby improving the performance of the transmission system. The trained DNN models are applied in the offline digital signal processing (DSP) module of the transmission system. The models can optimize the constellation mapping signals at the transmitter and compensate multi-impairment of the OFDM decoded signal at the receiver. Furthermore, the models reduce the peak to average power ratio (PAPR) of the transmitted OFDM signal and the bit error rate (BER) of the received signal. We verify the effectiveness of the proposed scheme for 16-QAM Coherent Optical OFDM signal and demonstrate and analyze transmission performance in different transmission scenarios. The experimental results show that the PAPR and BER of the transmission system are significantly reduced after using the trained DNN. It shows that the DNN with specific loss function and network structure can optimize the transmitted signal and learn the channel feature and compensate for multi-impairment in fiber transmission effectively.

Keywords: coherent optical OFDM, deep neural network, multi-impairment compensation, optical transmission

Procedia PDF Downloads 106

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 361

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 98

Authors: Yichao Ma, Chengsiong Chin, Wailok Woo

Abstract:

Since the last decade, there has been a rapid growth in digital multimedia, such as high-resolution media files and three-dimentional movies. Hence, there is a need for large digital storage such as Hard Disk Drive (HDD). As such, users expect to have a quieter HDD in their laptop. In this paper, a jury test has been conducted on a group of 34 people where 17 of them are students who is the potential consumer, and the remaining are engineers who know the HDD. A total 13 HDD sound samples have been selected from over hundred HDD noise recordings. These samples are selected based on an agreed subjective feeling. The samples are played to the participants using head acoustic playback system which enabled them to experience as similar as possible the same environment as have been recorded. Analysis has been conducted and the obtained results have indicated different group has different perception over the noises. Two neural network-based acoustic annoyance models are established based on back propagation neural network. Four psychoacoustic metrics, loudness, sharpness, roughness and fluctuation strength, are used as the input of the model, and the subjective evaluation results are taken as the output. The developed models are reasonably accurate in simulating both training and test samples.

Keywords: hdd noise, jury test, neural network model, psychoacoustic annoyance

Procedia PDF Downloads 394

Authors: A. Shebani, C. Pislaru

Abstract:

Wear of materials is an everyday experience and has been observed and studied for long time. The prediction of wear is a fundamental problem in the industrial field, mainly correlated to the planning of maintenance interventions and economy. Pin-on-disc test is the most common test which is used to study the wear behaviour. In this paper, the pin-on-disc (AEROTECH UNIDEX 11) is used for the investigation of the effects of normal load and hardness of material on the wear under dry and sliding conditions. In the pin-on-disc rig, two specimens were used; one, a pin which is made of steel with a tip, is positioned perpendicular to the disc, where the disc is made of aluminium. The pin wear and disc wear were measured by using the following instruments: The Talysurf instrument, a digital microscope, and the alicona instrument; where the Talysurf profilometer was used to measure the pin/disc wear scar depth, and the alicona was used to measure the volume loss for pin and disc. After that, the Archard model, American Society for Testing and Materials model (ASTM), and neural network model were used for pin/disc wear modelling and the simulation results are implemented by using the Matlab program. This paper focuses on how the alicona can be considered as a powerful tool for wear measurements and how the neural network is an effective algorithm for wear estimation.

Keywords: wear modelling, Archard Model, ASTM Model, Neural Networks Model, Pin-on-disc Test, Talysurf, digital microscope, Alicona

Procedia PDF Downloads 424

Authors: Tahir Nawaz Cheema, Dumitru Baleanu, Ali Raza

Abstract:

In this research work, we design intelligent computing through Bayesian Regularization artificial neural networks (BRANNs) introduced to solve the mathematical modeling of infectious diseases (Covid-19). The dynamical transmission is due to the interaction of people and its mathematical representation based on the system's nonlinear differential equations. The generation of the dataset of the Covid-19 model is exploited by the power of the explicit Runge Kutta method for different countries of the world like India, Pakistan, Italy, and many more. The generated dataset is approximately used for training, testing, and validation processes for every frequent update in Bayesian Regularization backpropagation for numerical behavior of the dynamics of the Covid-19 model. The performance and effectiveness of designed methodology BRANNs are checked through mean squared error, error histograms, numerical solutions, absolute error, and regression analysis.

Keywords: mathematical models, beysian regularization, bayesian-regularization backpropagation networks, regression analysis, numerical computing

Procedia PDF Downloads 110