Search results for: tensorflow

Authors: Carlos Tarmeño Noriega, Igor Aguilar Alonso

Abstract:

Fungal diseases are common in vineyards; they cause a decrease in the quality of the products that can be sold, generating distrust of the customer towards the seller when buying fruit. Currently, technology allows the classification of fruits according to their characteristics thanks to artificial intelligence. This study proposes the implementation of a control system that allows the identification of the main fungal diseases present in the Italia grape, making use of a convolutional neural network (CNN), OpenCV, and TensorFlow. The methodology used was based on a collection of 20 articles referring to the proposed research on quality control, classification, and recognition of fruits through artificial vision techniques.

Keywords: computer vision, convolutional neural networks, quality control, fruit market, OpenCV, TensorFlow

Procedia PDF Downloads 38

Authors: Ratun Rahman, Rafid Islam, Akin Ahmed, Kamrul Hasan, Hasan Mahmud

Abstract:

Malware is becoming more prevalent, and several threat categories have risen dramatically in recent years. This paper provides a bird's-eye view of the world of malware analysis. The efficiency of five different machine learning methods (Naive Bayes, K-Nearest Neighbor, Decision Tree, Random Forest, and TensorFlow Decision Forest) combined with features picked from the retrieval of Android permissions to categorize applications as harmful or benign is investigated in this study. The test set consists of 1,168 samples (among these android applications, 602 are malware and 566 are benign applications), each consisting of 948 features (permissions). Using the permission-based dataset, the machine learning algorithms then produce accuracy rates above 80%, except the Naive Bayes Algorithm with 65% accuracy. Of the considered algorithms TensorFlow Decision Forest performed the best with an accuracy of 90%.

Keywords: android malware detection, machine learning, malware, malware analysis

Procedia PDF Downloads 113

Authors: Khalak Bin Khair, Saqib Jahir, Mohammed Ibrahim, Fahad Bin, Debajyoti Karmaker

Abstract:

Object detection is a computer technology that deals with searching through digital images and videos for occurrences of semantic elements of a particular class. It is associated with image processing and computer vision. On top of object detection, we detect camouflage objects within an image using Deep Learning techniques. Deep learning may be a subset of machine learning that's essentially a three-layer neural network Over 6500 images that possess camouflage properties are gathered from various internet sources and divided into 4 categories to compare the result. Those images are labeled and then trained and tested using vgg16 architecture on the jupyter notebook using the TensorFlow platform. The architecture is further customized using Transfer Learning. Methods for transferring information from one or more of these source tasks to increase learning in a related target task are created through transfer learning. The purpose of this transfer of learning methodologies is to aid in the evolution of machine learning to the point where it is as efficient as human learning.

Keywords: deep learning, transfer learning, TensorFlow, camouflage, object detection, architecture, accuracy, model, VGG16

Procedia PDF Downloads 95

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 202

Authors: Ramin Vafadary, Maryam Khanbaghi

Abstract:

Forecasting electricity load is important for various purposes like planning, operation, and control. Forecasts can save operating and maintenance costs, increase the reliability of power supply and delivery systems, and correct decisions for future development. This paper compares various time series methods to forecast 24 hours ahead of electricity load. The methods considered are the Holt-Winters smoothing, SARIMA Modeling, LSTM Network, Fbprophet, and Tensorflow probability. The performance of each method is evaluated by using the forecasting accuracy criteria, namely, the mean absolute error and root mean square error. The National Renewable Energy Laboratory (NREL) residential energy consumption data is used to train the models. The results of this study show that the SARIMA model is superior to the others for 24 hours ahead forecasts. Furthermore, a Bagging technique is used to make the predictions more robust. The obtained results show that by Bagging multiple time-series forecasts, we can improve the robustness of the models for 24 hours ahead of electricity load forecasting.

Keywords: bagging, Fbprophet, Holt-Winters, LSTM, load forecast, SARIMA, TensorFlow probability, time series

Procedia PDF Downloads 53

Authors: Selvavinayagan Babiharan

Abstract:

This research aims to develop a deep learning platform to enhance mathematics education for secondary students in Sri Lanka. The platform will be designed to incorporate interactive and user-friendly features to engage students in active learning and promote their mathematical skills. The proposed platform will be developed using TensorFlow and Keras, two widely used deep learning frameworks. The system will be trained on a large dataset of math problems, which will be collected from Sri Lankan school curricula. The results of this research will contribute to the improvement of mathematics education in Sri Lanka and provide a valuable tool for teachers to enhance the learning experience of their students.

Keywords: information technology, education, machine learning, mathematics

Procedia PDF Downloads 45

Authors: Zan Azma Nasruddin, Irwan Mazlin, Nor Aziah Daud, Fauziah Redzuan, Fariza Hanis Abdul Razak

Abstract:

This paper focuses on a machine learning that learn the correct pronunciation of Makhraj Huroofs. Usually, people need to find an expert to pronounce the Huroof accurately. In this study, the researchers have developed a system that is able to learn the selected Huroofs which are ha, tsa, zho, and dza using the Convolutional Neural Network. The researchers present the chosen type of the CNN architecture to make the system that is able to learn the data (Huroofs) as quick as possible and produces high accuracy during the prediction. The researchers have experimented the system to measure the accuracy and the cross entropy in the training process.

Keywords: convolutional neural network, Makhraj recognition, speech recognition, signal processing, tensorflow

Procedia PDF Downloads 291

Authors: Almagul Assainova , Dariya Abykenova, Liudmila Goncharenko, Sergey Sybachin, Saule Rakhimova, Abay Aman

Abstract:

The recognition of a handwritten Kazakh text is a relevant objective today for the digitization of materials. The study presents a model of a hybrid neural network for handwriting recognition, which includes a convolutional neural network and a multi-layer perceptron. Each network includes 1024 input neurons and 42 output neurons. The model is implemented in the program, written in the Python programming language using the EMNIST database, NumPy, Keras, and Tensorflow modules. The neural network training of such specific letters of the Kazakh alphabet as ә, ғ, қ, ң, ө, ұ, ү, h, і was conducted. The neural network model and the program created on its basis can be used in electronic document management systems to digitize the Kazakh text.

Keywords: handwriting recognition system, image recognition, Kazakh font, machine learning, neural networks

Procedia PDF Downloads 218

Authors: Mayank Raj, V. G. Narendra

Abstract:

Ever since the DARPA challenge on autonomous vehicles in 2005, there has been a lot of buzz about ‘Autonomous Vehicles’ amongst the major tech giants such as Google, Uber, and Tesla. Numerous approaches have been adopted to solve this problem, which can have a long-lasting impact on mankind. In this paper, we have used Deep Learning techniques and TensorFlow framework with the goal of building a neural network model to predict (speed, acceleration, steering angle, and brake) features needed for navigation of autonomous vehicles. The Deep Neural Network has been trained on images and sensor data obtained from the comma.ai dataset. A heatmap was used to check for correlation among the features, and finally, four important features were selected. This was a multivariate regression problem. The final model had five convolutional layers, followed by five dense layers. Finally, the calculated values were tested against the labeled data, where the mean squared error was used as a performance metric.

Keywords: autonomous vehicles, deep learning, computer vision, artificial intelligence

Procedia PDF Downloads 119

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 50

Authors: Teja Koduru

Abstract:

Untreated Lyme disease can lead to neurological, cardiac, and dermatological complications. Rapid diagnosis of the erythema migrans (EM) rash, a characteristic symptom of Lyme disease is therefore crucial to early diagnosis and treatment. In this study, we aim to utilize deep learning frameworks including Tensorflow and Keras to create deep convolutional neural networks (DCNN) to detect images of acute Lyme Disease from images of erythema migrans. This study uses a custom database of erythema migrans images of varying quality to train a DCNN capable of classifying images of EM rashes vs. non-EM rashes. Images from publicly available sources were mined to create an initial database. Machine-based removal of duplicate images was then performed, followed by a thorough examination of all images by a clinician. The resulting database was combined with images of confounding rashes and regular skin, resulting in a total of 683 images. This database was then used to create a DCNN with an accuracy of 93% when classifying images of rashes as EM vs. non EM. Finally, this model was converted into a web and mobile application to allow for rapid diagnosis of EM rashes by both patients and clinicians. This tool could be used for patient prescreening prior to treatment and lead to a lower mortality rate from Lyme disease.

Keywords: Lyme, untreated Lyme, erythema migrans rash, EM rash

Procedia PDF Downloads 198

Authors: Tong He, Long Chen, Irag Mantegh, Wen-Fang Xie

Abstract:

This paper proposes an image-based obstacle avoidance and tracking target identification strategy in GPS-degraded or GPS-denied environment for an Unmanned Aerial Vehicle (UAV). The traditional force algorithm for obstacle avoidance could produce local minima area, in which UAV cannot get away obstacle effectively. In order to eliminate it, an artificial potential approach based on harmonic potential is proposed to guide the UAV to avoid the obstacle by using the vision system. And image-based visual servoing scheme (IBVS) has been adopted to implement the proposed obstacle avoidance approach. In IBVS, the pixel accuracy is a key factor to realize the obstacle avoidance. In this paper, the deep reinforcement learning framework has been applied by reducing pixel errors through constant interaction between the environment and the agent. In addition, the combination of OpenTLD and Tensorflow based on neural network is used to identify the type of tracking target. Numerical simulation in Matlab and ROS GAZEBO show the satisfactory result in target identification and obstacle avoidance.

Keywords: image-based visual servoing, obstacle avoidance, tracking target identification, deep reinforcement learning, artificial potential approach, neural network

Procedia PDF Downloads 98

Authors: Yong Wee Foo, Lai Meng Tang

Abstract:

Artificial Intelligence (AI), particularly the usage of deep neural networks for hierarchical representations from data, has found numerous complex applications across various domains, including computer vision, robotics, autonomous vehicles, and other scientific fields. However, their inherent “black box” nature can sometimes make it challenging for early researchers or school students of various levels to comprehend and trust the results they produce. Consequently, there has been a growing demand for reliable visualization tools in engineering and science education to help learners understand, trust, and explain a deep learning network. This has led to a notable emphasis on the visualization of AI in the research community in recent years. AI visualization tools are increasingly being adopted to significantly improve the comprehension of complex topics in deep learning. This paper proposes a novel approach to empower students to actively explore the inner workings of deep neural networks by combining the student-centered learning approach of flipped classroom models with the investigative power of AI visualization tools, namely, the TensorFlow Playground, the Local Interpretable Model-agnostic Explanations (LIME), and the SHapley Additive exPlanations (SHAP), for delivering an AI education curriculum. Combining the two factors is vital in fostering ownership, responsibility, and critical thinking skills in the age of AI.

Keywords: deep learning, explainable AI, AI visualization, representation learning

Procedia PDF Downloads 24

Authors: Theodoros Tziolas, Konstantinos Papageorgiou, Theodosios Theodosiou, Sebastian Pantoja, Nikos Dimitriou Dimosthenis, Elpiniki Papageorgiou

Abstract:

Assembly processes involve disparate materials that possess dissimilar resiliencies and, therefore, are prone to generating defective products. Manually performed quality inspection of such products is a time-consuming and susceptible to error process. The emerging computer vision techniques in smart manufacturing can alleviate the need for thorough, manually performed quality control. Object detection techniques provide crucial localization abilities, thus helping the operators further validate the identified defect with ease. In this work, several state-of-the-art object detection models are assessed in a real industrial imagery dataset and with the use of transfer learning. EfficientDet D2 is proposed for the identification and localization of antenna defects that are generated during the assembly process. To further enhance the dataset, heavy on-the-fly data augmentation was employed, along with synthetic samples generated with the use of image processing software. The proposed approach utilizing EfficientDet D2 can increase the Average Precision from 0.90 (at IoU 0.5) to 0.97 (at IoU 0.3). The overall performance is further evaluated by applying the F1-Score at each confidence score. For conducting the experiments, the TensorFlow object detection API is employed.

Keywords: defect detection, EfficientDet, deep learning, smart manufacturing, classification

Procedia PDF Downloads 6

Authors: Nurul Bin Ibrahim

Abstract:

Advancements in neural networks have offered valuable insights into Fluid Dynamics, notably in addressing turbulence-related challenges. In this research, we introduce multiple applications of models of neural networks, namely Feed-Forward and Recurrent Neural Networks, to explore the relationship between jet formations and stratified turbulence within stochastically excited Boussinesq systems. Using machine learning tools like TensorFlow and PyTorch, the study has created models that effectively mimic and show the underlying features of the complex patterns of jet formation and stratified turbulence. These models do more than just help us understand these patterns; they also offer a faster way to solve problems in stochastic systems, improving upon traditional numerical techniques to solve stochastic differential equations such as the Euler-Maruyama method. In addition, the research includes a thorough comparison with the Statistical State Dynamics (SSD) approach, which is a well-established method for studying chaotic systems. This comparison helps evaluate how well neural networks can help us understand the complex relationship between jet formations and stratified turbulence. The results of this study underscore the potential of neural networks in computational physics and fluid dynamics, opening up new possibilities for more efficient and accurate simulations in these fields.

Keywords: neural networks, machine learning, computational fluid dynamics, stochastic systems, simulation, stratified turbulence

Procedia PDF Downloads 33

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

Abstract:

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

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

Procedia PDF Downloads 73

Authors: Susan Diamond

Abstract:

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

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

Procedia PDF Downloads 171

Authors: Gholba Niranjan Dilip, Anil Kumar

Abstract:

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

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

Procedia PDF Downloads 124

Authors: Zafer Yüce, Paşa Yayla, Alev Taşkın

Abstract:

There are heaps of analytical methods to estimate the crack growth life of a component. Soft computing methods have an increasing trend in predicting fatigue life. Their ability to build complex relationships and capability to handle huge amounts of data are motivating researchers and industry professionals to employ them for challenging problems. This study focuses on soft computing methods, especially random forest regressors and artificial neural networks with hyperparameter optimization algorithms such as grid search and random grid search, to estimate the crack growth life of an aircraft wing splice joint under variable amplitude loading. TensorFlow and Scikit-learn libraries of Python are used to build the machine learning models for this study. The material considered in this work is 7050-T7451 aluminum, which is commonly preferred as a structural element in the aerospace industry, and regarding the crack type; corner crack is used. A finite element model is built for the joint to calculate fastener loads and stresses on the structure. Since finite element model results are validated with analytical calculations, findings of the finite element model are fed to AFGROW software to calculate analytical crack growth lives. Based on Fighter Aircraft Loading Standard for Fatigue (FALSTAFF), 90 unique fatigue loading spectra are developed for various load levels, and then, these spectrums are utilized as inputs to the artificial neural network and random forest regression models for predicting crack growth life. Finally, the crack growth life predictions of the machine learning models are compared with analytical calculations. According to the findings, a good correlation is observed between analytical and predicted crack growth lives.

Keywords: aircraft, fatigue, joint, life, optimization, prediction.

Procedia PDF Downloads 129

Authors: Tesfaye Mengistu

Abstract:

Power cables play a crucial role in the transmission and distribution of electrical energy. As the electricity generation, transmission, distribution, and storage systems become smarter, there is a growing emphasis on incorporating intelligent approaches to ensure the reliability of power cables. Various types of electrical cables are employed for transmitting and distributing electrical energy, with cross-linked polyethylene (XLPE) cables being widely utilized due to their exceptional electrical and mechanical properties. However, insulation defects can occur in XLPE cables due to subpar manufacturing techniques during production and cable joint installation. To address this issue, experts have proposed different methods for monitoring XLPE cables. Some suggest the use of interdigital capacitive (IDC) technology for online monitoring, while others propose employing continuous wave (CW) terahertz (THz) imaging systems to detect internal defects in XLPE plates used for power cable insulation. In this study, we have developed models that employ a custom dataset collected locally to classify the physical safety status of individual power cables. Our models aim to replace physical inspections with computer vision and image processing techniques to classify defective power cables from non-defective ones. The implementation of our project utilized the Python programming language along with the TensorFlow package and a convolutional neural network (CNN). The CNN-based algorithm was specifically chosen for power cable defect classification. The results of our project demonstrate the effectiveness of CNNs in accurately classifying power cable defects. We recommend the utilization of similar or additional datasets to further enhance and refine our models. Additionally, we believe that our models could be used to develop methodologies for detecting power cable defects from live video feeds. We firmly believe that our work makes a significant contribution to the field of power cable inspection and maintenance. Our models offer a more efficient and cost-effective approach to detecting power cable defects, thereby improving the reliability and safety of power grids.

Keywords: artificial intelligence, computer vision, defect detection, convolutional neural net

Procedia PDF Downloads 55

Authors: Hany Elsaid Fawaz Abdallah

Abstract:

This study presents a new artificial neural network(ANN) model to predict the Nusselt Number and pressure drop for the turbulent flow in a triangular corrugated plate heat exchanger for forced air and turbulent water flow. An experimental investigation was performed to create a new dataset for the Nusselt Number and pressure drop values in the following range of dimensionless parameters: The plate corrugation angles (from 0° to 60°), the Reynolds number (from 10000 to 40000), pitch to height ratio (from 1 to 4), and Prandtl number (from 0.7 to 200). Based on the ANN performance graph, the three-layer structure with {12-8-6} hidden neurons has been chosen. The training procedure includes back-propagation with the biases and weight adjustment, the evaluation of the loss function for the training and validation dataset and feed-forward propagation of the input parameters. The linear function was used at the output layer as the activation function, while for the hidden layers, the rectified linear unit activation function was utilized. In order to accelerate the ANN training, the loss function minimization may be achieved by the adaptive moment estimation algorithm (ADAM). The ‘‘MinMax’’ normalization approach was utilized to avoid the increase in the training time due to drastic differences in the loss function gradients with respect to the values of weights. Since the test dataset is not being used for the ANN training, a cross-validation technique is applied to the ANN network using the new data. Such procedure was repeated until loss function convergence was achieved or for 4000 epochs with a batch size of 200 points. The program code was written in Python 3.0 using open-source ANN libraries such as Scikit learn, TensorFlow and Keras libraries. The mean average percent error values of 9.4% for the Nusselt number and 8.2% for pressure drop for the ANN model have been achieved. Therefore, higher accuracy compared to the generalized correlations was achieved. The performance validation of the obtained model was based on a comparison of predicted data with the experimental results yielding excellent accuracy.

Keywords: artificial neural networks, corrugated channel, heat transfer enhancement, Nusselt number, pressure drop, generalized correlations

Procedia PDF Downloads 47

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 54

Authors: Andrew N. Saylor, James R. Peters

Abstract:

Scoliosis is a complex 3D deformity of the thoracic and lumbar spines, clinically diagnosed by measurement of a Cobb angle of 10 degrees or more on a coronal X-ray. The Cobb angle is the angle made by the lines drawn along the proximal and distal endplates of the respective proximal and distal vertebrae comprising the curve. Traditionally, Cobb angles are measured manually using either a marker, straight edge, and protractor or image measurement software. The task of measuring the Cobb angle can also be represented by a function taking the spine geometry rendered using X-ray imaging as input and returning the approximate angle. Although the form of such a function may be unknown, it can be approximated using artificial neural networks (ANNs). The performance of ANNs is affected by many factors, including the choice of activation function and network architecture; however, the effects of these parameters on the accuracy of scoliotic deformity measurements are poorly understood. Therefore, the objective of this study was to systematically investigate the effect of ANN architecture and activation function on Cobb angle measurement from the coronal X-rays of scoliotic subjects. The data set for this study consisted of 609 coronal chest X-rays of scoliotic subjects divided into 481 training images and 128 test images. These data, which included labeled Cobb angle measurements, were obtained from the SpineWeb online database. In order to normalize the input data, each image was resized using bi-linear interpolation to a size of 500 × 187 pixels, and the pixel intensities were scaled to be between 0 and 1. A fully connected (dense) ANN with a fixed cost function (mean squared error), batch size (10), and learning rate (0.01) was developed using Python Version 3.7.3 and TensorFlow 1.13.1. The activation functions (sigmoid, hyperbolic tangent [tanh], or rectified linear units [ReLU]), number of hidden layers (1, 3, 5, or 10), and number of neurons per layer (10, 100, or 1000) were varied systematically to generate a total of 36 network conditions. Stochastic gradient descent with early stopping was used to train each network. Three trials were run per condition, and the final mean squared errors and mean absolute errors were averaged to quantify the network response for each condition. The network that performed the best used ReLU neurons had three hidden layers, and 100 neurons per layer. The average mean squared error of this network was 222.28 ± 30 degrees2, and the average mean absolute error was 11.96 ± 0.64 degrees. It is also notable that while most of the networks performed similarly, the networks using ReLU neurons, 10 hidden layers, and 1000 neurons per layer, and those using Tanh neurons, one hidden layer, and 10 neurons per layer performed markedly worse with average mean squared errors greater than 400 degrees2 and average mean absolute errors greater than 16 degrees. From the results of this study, it can be seen that the choice of ANN architecture and activation function has a clear impact on Cobb angle inference from coronal X-rays of scoliotic subjects.

Keywords: scoliosis, artificial neural networks, cobb angle, medical imaging

Procedia PDF Downloads 90