Search results for: deep plane

Authors: Nurhak Altın, Ayhan Kucukmanisa, Oguzhan Urhan

Abstract:

It is important that highways are in good condition for traffic safety. Road crashes (road cracks, erosion of lane markings, etc.) can cause accidents by affecting driving. Image processing based methods for detecting road cracks are available in the literature. In this paper, a deep learning based road crack detection approach is proposed. YOLO (You Look Only Once) is adopted as core component of the road crack detection approach presented. The YOLO network structure, which is developed for object detection, is trained with road crack images as a new class that is not previously used in YOLO. The performance of the proposed method is compared using different training methods: using randomly generated weights and training their own pre-trained weights (transfer learning). A similar training approach is applied to the simplified version of the YOLO network model (tiny yolo) and the results of the performance are examined. The developed system is able to process 8 fps on NVIDIA Jetson TX1 development kit.

Keywords: deep learning, embedded platform, real-time processing, road crack detection

Procedia PDF Downloads 320

Authors: Gautier Girard, Marion Martiny, Sebastien Mercier, Mohamad Jrad, Mohamed-Slim Bahi, Laurent Bodin, Francois Lechleiter, David Nevo, Sophie Dareys

Abstract:

Reliability of electronic devices has always been of highest interest for Aero-MIL and space applications. In any electronic device, Printed Circuit Board (PCB), providing interconnection between components, is a key for reliability. During the last decades, PCB technologies evolved to sustain and/or fulfill increased original equipment manufacturers requirements and specifications, higher densities and better performances, faster time to market and longer lifetime, newer material and mixed buildups. From the very beginning of the PCB industry up to recently, qualification, experiments and trials, and errors were the most popular methods to assess system (PCB) reliability. Nowadays OEM, PCB manufacturers and scientists are working together in a close relationship in order to develop predictive models for PCB reliability and lifetime. To achieve that goal, it is fundamental to characterize precisely base materials (laminates, electrolytic copper, …), in order to understand failure mechanisms and simulate PCB aging under environmental constraints by means of finite element method for example. The laminates are woven composites and have thus an orthotropic behaviour. The in-plane properties can be measured by combining classical uniaxial testing and digital image correlation. Nevertheless, the out-of-plane properties cannot be evaluated due to the thickness of the laminate (a few hundred of microns). It has to be noted that the knowledge of the out-of-plane properties is fundamental to investigate the lifetime of high density printed circuit boards. A homogenization method combining analytical and numerical approaches has been developed in order to obtain the complete elastic orthotropic behaviour of a woven composite from its precise 3D internal structure and its experimentally measured in-plane elastic properties. Since the mechanical properties of the resin surrounding the fibres are unknown, an inverse method is proposed to estimate it. The methodology has been applied to one laminate used in hyperfrequency spatial applications in order to get its elastic orthotropic behaviour at different temperatures in the range [-55°C; +125°C]. Next; numerical simulations of a plated through hole in a double sided PCB are performed. Results show the major importance of the out-of-plane properties and the temperature dependency of these properties on the lifetime of a printed circuit board. Acknowledgements—The support of the French ANR agency through the Labcom program ANR-14-LAB7-0003-01, support of CNES, Thales Alenia Space and Cimulec is acknowledged.

Keywords: homogenization, orthotropic behaviour, printed circuit board, woven composites

Procedia PDF Downloads 174

Authors: Ariel Barel, Rotem Manor, Alfred M. Bruckstein

Abstract:

We present a probabilistic gathering algorithm for agents that can only detect the presence of other agents in front of or behind them. The agents act in the plane and are identical and indistinguishable, oblivious, and lack any means of direct communication. They do not have a common frame of reference in the plane and choose their orientation (direction of possible motion) at random. The analysis of the gathering process assumes that the agents act synchronously in selecting random orientations that remain fixed during each unit time-interval. Two algorithms are discussed. The first one assumes discrete jumps based on the sensing results given the randomly selected motion direction, and in this case, extensive experimental results exhibit probabilistic clustering into a circular region with radius equal to the step-size in time proportional to the number of agents. The second algorithm assumes agents with continuous sensing and motion, and in this case, we can prove gathering into a very small circular region in finite expected time.

Keywords: control, decentralized, gathering, multi-agent, simple sensors

Procedia PDF Downloads 143

Authors: Elsyed Fath Khalifa, Samer Mohamed Daghash

Abstract:

The present study was carried out to investigate the structure of the masseter muscle of camel and its attachments to the skull as well as the relationships with its arterial blood supply. Fourteen heads of clinically healthy camels of different ages and sexes were used in the present investigation. The both common carotid arteries of six specimens were cannulated and flushed with warm normal saline solution (0.9%) then injected with red colored neoprine (60%) latex in order to study the pattern of the blood supply to the masseter muscle. Two heads were injected with an eventually mixture of 75gm red lead oxide in 150cc latex and preserved in a cold room for 3-4 days then divided sagittaly along the median plane to avoid super imposition of the arteries. The arteries of the masseter muscle of each half were radiographed. Four heads were used in manual dissection to describe the laminar arrangement of the masseter muscle. The masseter muscle of the camel was very tendinous and was situated far caudally, which enable the camel to open its jaw very wide. In the camel, the masseter muscle was recognized into proper and improper masseter groups. The proper group included the first, second superficial, intermediate and deep masseter layers. The improper group consisted of maxillo-mandibularis and zygomatico-mandibularis. The remaining two heads were used for clearance.

Keywords: anatomy, camel, masseter, lamination, blood supply

Procedia PDF Downloads 296

Authors: Kazuaki Shiraishi, Narumitsu Asai, Tsukasa Kitahara, Sosuke Mieno, Takaharu Kameoka

Abstract:

The purpose of this research is to facilitate productivity advances in agriculture. To accomplish this, we developed an automatic three-dimensional (3D) recording system for growth of field crops that consists of a number of inexpensive modules: a very low-cost stereo camera, a couple of ZigBee wireless modules, a Raspberry Pi single-board computer, and a third generation (3G) wireless communication module. Our system uses an inexpensive Web stereo camera in order to keep total costs low. However, inexpensive video cameras record low-resolution images that are very noisy. Accordingly, in order to resolve these problems, we adopted a deep learning method. Based on the results of extended period of time operation test conducted without the use of an external power supply, we found that by using Super-Resolution Convolutional Neural Network method, our system could achieve a balance between the competing goals of low-cost and superior performance. Our experimental results showed the effectiveness of our system.

Keywords: 3D plant data, automatic recording, stereo camera, deep learning, image processing

Procedia PDF Downloads 253

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 193

Authors: Muhammad Naseem Baig, Abdul Qudoos Khan, Jamal Ali

Abstract:

Ground deformations in deep excavations are affected by wall stiffness and pile embedment ratio. This paper presents the findings of a parametric study of 64ft deep excavation in mixed stiff soil conditions supported by a cantilever pile wall. A series of finite element analyses have been carried out in Plaxis 2D by varying pile embedment ratio and wall stiffness. It has been observed that maximum wall deflections decrease by increasing the embedment ratio up to 1.50; however, any further increase in pile length does not improve the performance of wall. Similarly, increasing wall stiffness reduces the wall deformations and affects the deflection patterns of wall. The finite element analysis results are compared with field data of 25 case studies of cantilever walls. Analysis results fall within the range of normalized wall deflections of 25 case studies. It has been concluded that deep excavations can be supported by cantilever walls provided the system stiffness is increased significantly.

Keywords: excavations, support systems, wall stiffness, cantilever walls

Procedia PDF Downloads 184

Authors: Elif Kalkanli, Constantinos Soutis

Abstract:

The use of textile preform in the advanced fields including aerospace, automotive and marine has exponentially grown in recent years. These preforms offer excellent advantages such as being lightweight and low-cost, and also, their suitability for creating different fiber architectures with different materials whilst improved mechanical properties in certain aspects. In this study, a novel honeycomb core is developed by a 3Dweaving process. The assembly of the layers is achieved thanks to innovative weaving design. Polyester yarn is selected for the 3D woven honeycomb core (3DWHC). The core is used to manufacture a sandwich panel with 2x2 twill glass fiber composite face sheets. These 3DWHC sandwich panels will be tested in three-point bending. The in-plane and out-of-plane (through-the-thickness) mechanical response of the core will be examined as a function of cell size in addition to the flexural response of the sandwich panel. The failure mechanisms of the core and the sandwich skins will be reported in addition to flexural strength and stiffness. Possible engineering applications will be identified.

Keywords: 3D woven, assembly, failure modes, honeycomb sandwich panel

Procedia PDF Downloads 182

Authors: Mario Isaza-Ruget, Claudia C. Colmenares-Mejia, Nancy Yomayusa, Camilo A. González, Andres Cely, Jossie Murcia

Abstract:

Quantification of risks associated with complications development from chronic kidney disease (CKD) through accurate survival models can help with patient management. A retrospective cohort that included patients diagnosed with CKD from a primary care program and followed up between 2013 and 2018 was carried out. Time-dependent and static covariates associated with demographic, clinical, and laboratory factors were included. Deep Learning (DL) survival analyzes were developed for three CKD outcomes: CKD stage progression, >25% decrease in Estimated Glomerular Filtration Rate (eGFR), and Renal Replacement Therapy (RRT). Models were evaluated and compared with Random Survival Forest (RSF) based on concordance index (C-index) metric. 2.143 patients were included. Two models were developed for each outcome, Deep Neural Network (DNN) model reported C-index=0.9867 for CKD stage progression; C-index=0.9905 for reduction in eGFR; C-index=0.9867 for RRT. Regarding the RSF model, C-index=0.6650 was reached for CKD stage progression; decreased eGFR C-index=0.6759; RRT C-index=0.8926. DNN models applied in survival analysis context with considerations of longitudinal covariates at the start of follow-up can predict renal stage progression, a significant decrease in eGFR and RRT. The success of these survival models lies in the appropriate definition of survival times and the analysis of covariates, especially those that vary over time.

Keywords: artificial intelligence, chronic kidney disease, deep neural networks, survival analysis

Procedia PDF Downloads 110

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 142

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 100

Authors: William Li

Abstract:

Lane-change path planning is a crucial and yet complex task in autonomous driving. The traditional path planning approach based on a system of carefully-crafted rules to cover various driving scenarios becomes unwieldy as more and more rules are added to deal with exceptions and corner cases. This paper proposes to divide the entire path planning to two stages. In the first stage the ego vehicle travels longitudinally in the source lane to reach a safe state. In the second stage the ego vehicle makes lateral lane-change maneuver to the target lane. The paper derives the safe state conditions based on lateral lane-change maneuver calculation to ensure collision free in the second stage. To determine the acceleration sequence that minimizes the time to reach a safe state in the first stage, the paper proposes three schemes, namely, kinetic model based optimization, deep reinforcement learning, and 5G vehicle-to-vehicle (V2V) communications. The paper investigates these schemes via simulation. The model-based optimization is sensitive to the model assumptions. The deep reinforcement learning is more flexible in handling scenarios beyond the model assumed by the optimization. The 5G V2V eliminates uncertainty in predicting future behaviors of surrounding vehicles by sharing driving intents and enabling cooperative driving.

Keywords: lane change, path planning, autonomous driving, deep reinforcement learning, 5G, V2V communications, connected vehicles

Procedia PDF Downloads 185

Authors: Snowie Jane Galgo, Victor Asio

Abstract:

Geochemical composition of soils provides vital information about their origin and development. Highly weathered soils are widespread in the islands of Leyte and Samar but limited data have been published in terms of their nature, characteristics and nutrient status. This study evaluated the total elemental composition, properties and nutrient status of eight (8) deep and highly weathered soils in various parts of Leyte and Samar. Sampling was done down to 3 to 4 meters deep. Total amounts of Al₂O₃, As₂O₃, CaO, CdO, Cr₂O₃, CuO, Fe₂O₃, K₂O, MgO, MnO, Na₂O, NiO, P₂O₅, PbO, SO₃, SiO₂, TiO₂, ZnO and ZrO₂ were analyzed using an X-ray analytical microscope for eight soil profiles. Most of the deep and highly weathered soils have probably developed from homogenous parent materials based on the regular distribution with depth of TiO₂ and ZrO₂. Two of the soils indicated high variability with depth of TiO₂ and ZrO₂ suggesting that these soils developed from heterogeneous parent material. Most soils have K₂O and CaO values below those of MgO and Na₂O. This suggests more losses of K₂O and CaO have occurred since they are more mobile in the weathering environment. Most of the soils contain low amounts of other elements such as CuO, ZnO, PbO, NiO, CrO and SO₂. Basic elements such as K₂O and CaO are more mobile in the weathering environment than MgO and Na₂O resulting in higher losses of the former than the latter. Other elements also show small amounts in all soil profile. Thus, this study is very useful for sustainable crop production and environmental conservation in the study area specifically for highly weathered soils which are widespread in the Philippines.

Keywords: depth function, geochemical composition, highly weathered soils, total elemental composition

Procedia PDF Downloads 237

Authors: Youji Miyake

Abstract:

In aircraft assembly, a large number of preparatory holes are required for screw and rivet joints. Currently, many holes are drilled manually because it is difficult to machine the holes using conventional computerized numerical control(CNC) machines. The application of industrial robots to drill the hole has been considered as an alternative to the CNC machines. However, the rigidity of robot arms is so low that vibration is likely to occur during drilling. In this study, it is proposed constant-load feed machining as a method to perform high-precision drilling while minimizing the thrust force, which is considered to be the cause of vibration. In this method, the drill feed is realized by a constant load applied onto the tool so that the thrust force is theoretically kept below the applied load. The performance of the proposed method was experimentally examined through the deep hole drilling of plastic and simultaneous drilling of metal/plastic stack plates. It was confirmed that the deep hole drilling and simultaneous drilling could be performed without generating vibration by controlling the tool feed rate in the appropriate range.

Keywords: constant load feed machining, robotic drilling, deep hole, simultaneous drilling

Procedia PDF Downloads 170

Authors: Nirjhar Dhang, S. Vinay Kumar

Abstract:

Concrete is a non-homogeneous mix of coarse aggregates, sand, cement, air-voids and interfacial transition zone (ITZ) around aggregates. Adoption of these complex structures and material properties in numerical simulation would lead us to better understanding and design of concrete. In this work, the mesoscale model of concrete has been prepared from X-ray computerized tomography (CT) image. These images are converted into computer model and numerically simulated using commercially available finite element software. The mesoscale models are simulated under the influence of compressive displacement. The effect of shape and distribution of aggregates, continuous and discrete ITZ thickness, voids, and variation of mortar strength has been investigated. The CT scan of concrete cube consists of series of two dimensional slices. Total 49 slices are obtained from a cube of 150mm and the interval of slices comes approximately 3mm. In CT scan images, the same cube can be CT scanned in a non-destructive manner and later the compression test can be carried out in a universal testing machine (UTM) for finding its strength. The image processing and extraction of mortar and aggregates from CT scan slices are performed by programming in Python. The digital colour image consists of red, green and blue (RGB) pixels. The conversion of RGB image to black and white image (BW) is carried out, and identification of mesoscale constituents is made by putting value between 0-255. The pixel matrix is created for modeling of mortar, aggregates, and ITZ. Pixels are normalized to 0-9 scale considering the relative strength. Here, zero is assigned to voids, 4-6 for mortar and 7-9 for aggregates. The value between 1-3 identifies boundary between aggregates and mortar. In the next step, triangular and quadrilateral elements for plane stress and plane strain models are generated depending on option given. Properties of materials, boundary conditions, and analysis scheme are specified in this module. The responses like displacement, stresses, and damages are evaluated by ABAQUS importing the input file. This simulation evaluates compressive strengths of 49 slices of the cube. The model is meshed with more than sixty thousand elements. The effect of shape and distribution of aggregates, inclusion of voids and variation of thickness of ITZ layer with relation to load carrying capacity, stress-strain response and strain localizations of concrete have been studied. The plane strain condition carried more load than plane stress condition due to confinement. The CT scan technique can be used to get slices from concrete cores taken from the actual structure, and the digital image processing can be used for finding the shape and contents of aggregates in concrete. This may be further compared with test results of concrete cores and can be used as an important tool for strength evaluation of concrete.

Keywords: concrete, image processing, plane strain, interfacial transition zone

Procedia PDF Downloads 222

Authors: Atakan Aral Ormancı, Tuğçe Arslantaş, Murat Özcü

Abstract:

This study presents the design and implementation of an experimental chassis-level system for various control applications. Specifically, the height level of the chassis is controlled using proportional integrated derivative, fuzzy logic, and deep learning control methods. Real-time data obtained from height and pressure sensors installed in a 6x2 truck chassis, in combination with pulse-width modulation signal values, are utilized during the tests. A prototype pneumatic system of a 6x2 truck is added to the setup, which enables the Smart Pneumatic Actuators to function as if they were in a real-world setting. To obtain real-time signal data from height sensors, an Arduino Nano is utilized, while a Raspberry Pi processes the data using Matlab/Simulink and provides the correct output signals to control the Smart Pneumatic Actuator in the truck chassis. The objective of this research is to optimize the time it takes for the chassis to level down and up under various loads. To achieve this, proportional integrated derivative control, fuzzy logic control, and deep learning techniques are applied to the system. The results show that the deep learning method is superior in optimizing time for a non-linear system. Fuzzy logic control with a triangular membership function as the rule base achieves better outcomes than proportional integrated derivative control. Traditional proportional integrated derivative control improves the time it takes to level the chassis down and up compared to an uncontrolled system. The findings highlight the superiority of deep learning techniques in optimizing the time for a non-linear system, and the potential of fuzzy logic control. The proposed approach and the experimental results provide a valuable contribution to the field of control, automation, and systems engineering.

Keywords: automotive, chassis level control, control systems, pneumatic system control

Procedia PDF Downloads 56

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 137

Authors: Yuan Yan Tang, Lina Yang, Hong Li

Abstract:

Harmonic model is a very important approximation for the image transform. The harmanic model converts an image into arbitrary shape; however, this mode cannot be described by any fixed functions in mathematics. In fact, it is represented by partial differential equation (PDE) with boundary conditions. Therefore, to develop an efficient method to solve such a PDE is extremely significant in the image transform. In this paper, a novel Integral Equation-Wavelet based method is presented, which consists of three steps: (1) The partial differential equation is converted into boundary integral equation and representation by an indirect method. (2) The boundary integral equation and representation are changed to plane integral equation and representation by boundary measure formula. (3) The plane integral equation and representation are then solved by a method we call wavelet collocation. Our approach has two main advantages, the shape of an image is arbitrary and the program code is independent of the boundary. The performance of our method is evaluated by numerical experiments.

Keywords: harmonic model, partial differential equation (PDE), integral equation, integral representation, boundary measure formula, wavelet collocation

Procedia PDF Downloads 528

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 121

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 239

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 245

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 71

Authors: Abhijith Asok

Abstract:

This paper presents a generalized approach for the simple linear data transformation, Y=bX, through an integration of multidimensional coordinate geometry, vector space theory and polygonal geometry. The scaling is performed by adding an additional ’Dummy Dimension’ to the n-dimensional data, which helps plot two dimensional component-wise straight lines on pairs of dimensions. The end result is a set of scaled extensions of observations in any of the 2n spatial divisions, where n is the total number of applicable dimensions/dataset variables, created by shifting the n-dimensional plane along the ’Dummy Axis’. The derived scaling factor was found to be dependent on the coordinates of the common point of origin for diverging straight lines and the plane of extension, chosen on and perpendicular to the ’Dummy Axis’, respectively. This result indicates the geometrical interpretation of a linear data transformation and hence, opportunities for a more informed choice of the factor ’b’, based on a better choice of these coordinate values. The paper follows on to identify the effect of this transformation on certain popular distance metrics, wherein for many, the distance metric retained the same scaling factor as that of the features.

Keywords: data transformation, dummy dimension, linear transformation, scaling

Procedia PDF Downloads 282

Authors: Asmau Mukhtar Ahmed, Olga Duran

Abstract:

Hydrocarbon (HC) spills constitute a significant problem that causes great concern to the environment. With the latest technology (hyperspectral images) and state of the earth techniques (image processing tools), hydrocarbon spills can easily be detected at an early stage to mitigate the effects caused by such menace. In this study; a controlled laboratory experiment was used, and clay soil was mixed and homogenized with different hydrocarbon types (diesel, bio-diesel, and petrol). The different mixtures were scanned with HYSPEX hyperspectral camera under constant illumination to generate the hypersectral datasets used for this experiment. So far, the Short Wave Infrared Region (SWIR) has been exploited in detecting HC spills with excellent accuracy. However, the Near-Infrared Region (NIR) is somewhat unexplored with regards to HC contamination and how it affects the spectrum of soils. In this study, Deep Neural Network (DNN) was applied to the controlled datasets to detect and quantify the amount of HC spills in soils in the Near-Infrared Region. The initial results are extremely encouraging because it indicates that the DNN was able to identify features of HC in the Near-Infrared Region with a good level of accuracy.

Keywords: hydrocarbon, Deep Neural Network, short wave infrared region, near-infrared region, hyperspectral image

Procedia PDF Downloads 91

Authors: Balogun R. Ayodeji, Adefisan E. Adesanya, Adeyewa Z. Debo, E. C. Okogbue

Abstract:

Deep convective systems during active periods of the West African monsoon season have not been properly investigated over better temporal and spatial resolution in West Africa. Deep convective systems are investigated over seven climatic zones of the West African sub-region, which are; west-coast rainforest, dry rainforest, Nigeria-Cameroon rainforest, Nigeria savannah, Central African and South Sudan (CASS) Savannah, Sudano-Sahel, and Sahel, using data from Tropical Rainfall Measurement Mission (TRMM) Precipitation Feature (PF) database. The vertical structure of the convective systems indicated by the presence of at least one 40 dBZ and reaching (attaining) at least 1km in the atmosphere showed strong core (highest frequency (%)) of reflectivity values around 2 km which is below the freezing level (4-5km) for all the zones. Echoes are detected above the 15km altitude much more frequently in the rainforest and Savannah zones than the Sudano and Sahel zones during active periods in March-May (MAM), whereas during active periods in June-September (JJAS) the savannahs, Sudano and Sahel zones convections tend to reach higher altitude more frequently than the rainforest zones. The percentage frequencies of deep convection indicated that the occurrences of the systems are within the range of 2.3-2.8% during both March-May (MAM) and June-September (JJAS) active periods in the rainforest and savannah zones. On the contrary, the percentage frequencies were found to be less than 2% in the Sudano and Sahel zones, except during the active-JJAS period in the Sudano zone.

Keywords: active periods, convective system, frequency, reflectivity

Procedia PDF Downloads 126

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 61

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 215

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 309

Authors: Marcin Jakiel, Maria Kurek, Karolina Gutkowska, Sylwia Sanakiewicz, Dominika Stolarczyk, Jakub Batko, Rafał Jakiel, Mateusz K. Hołda

Abstract:

The geometry of RVOT is extremely complicated. It is an irregular block with an ellipsoidal cross-section, whose dimensions decrease toward the pulmonary valve and measure 33.82 (IQR 30,51-39,36), 28.82 (IQR 26,11-32,22), 27.95 ± 4,11 for width [mm] and 33.41 ± 6,14, 26.99 ± 4,41, 26.91 ± 4,00 [mm] for depth, in the basal, middle and subpulmonary parts, respectively. In a sagittal section view, the RVOT heads upward and slightly backward. Its anterior perimeter has an average length of 41.96 mm and inclines to the transverse plane at an angle of 50.77° (IQR 46,53°-58,70°). In the posterior region, the RVOT is shorter (18.17mm) and flexes anteriorly. Therefore, the slope of the upper part of the rear wall to the transverse plane is an acute angle (open toward the rear) of 44,58° (IQR 37,30°-51,25°), while in the lower part it is an angle close to a right angle of 94,30°±15,44°. In addition, the thickness of the RVOT wall in the diastolic phase, at the posterior perimeter at the base, in the middle of the length and subpulmonary measure 3,80 mm ± 0,88 mm, 3,56 mm ± 0,73 mm, 3,56 mm ± 0,65 mm, respectively. In frontal cross-section, the RVOT rises on the interventricular septum, which makes it possible to distinguish the septal and supraseptal parts on its left periphery. The angles (facing the vertices to the right) of the inclination of these parts to the transverse plane are 75.5° (IQR 66,44°-81,11°) and 107.01° (IQR 99,09 – 115,23°), respectively, which allows us to conclude that the direction of the RVOT long axis changes from left to right. The above analysis shows that there is no single RVOT axis. Two axes can be distinguished, the one for the upper RVOT being more backward and leftward. The aforementioned forward deflection of the posterior wall and the RVOT's elevation over the interventricular septum, suggest that access to the subpulmonary region may be difficult. It should be emphasized that this area is often the target for ablation of ventricular arrhythmias. The small thickness of the RVOT posterior wall, with its difficult geometry, may favor its perforation into the pericardium or ascending aorta.

Keywords: angle, geometry, operation access, position, RVOT, shape

Procedia PDF Downloads 89

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 116