Search results for: deep learning network

Authors: Manik Sharma, Ganapathy Krishnamurthi

Abstract:

The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.

Keywords: cellular images, genetic perturbations, deep-learning, explainability

Procedia PDF Downloads 103

Authors: Hichem Sassi

Abstract:

Pneumonia, being a respiratory infection, has garnered global attention due to its rapid transmission and relatively high mortality rates. Timely detection and treatment play a crucial role in significantly reducing mortality associated with pneumonia. Presently, X-ray diagnosis stands out as a reasonably effective method. However, the manual scrutiny of a patient's X-ray chest radiograph by a proficient practitioner usually requires 5 to 15 minutes. In situations where cases are concentrated, this places immense pressure on clinicians for timely diagnosis. Relying solely on the visual acumen of imaging doctors proves to be inefficient, particularly given the low speed of manual analysis. Therefore, the integration of artificial intelligence into the clinical image diagnosis of pneumonia becomes imperative. Additionally, AI recognition is notably rapid, with convolutional neural networks (CNNs) demonstrating superior performance compared to human counterparts in image identification tasks. To conduct our study, we utilized a dataset comprising chest X-ray images obtained from Kaggle, encompassing a total of 5216 training images and 624 test images, categorized into two classes: normal and pneumonia. Employing five mainstream network algorithms, we undertook a comprehensive analysis to classify these diseases within the dataset, subsequently comparing the results. The integration of artificial intelligence, particularly through improved network architectures, stands as a transformative step towards more efficient and accurate clinical diagnoses across various medical domains.

Keywords: deep learning, computer vision, pneumonia, models, comparative study

Procedia PDF Downloads 56

Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav

Abstract:

Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.

Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining

Procedia PDF Downloads 154

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 272

Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra

Abstract:

Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).

Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks

Procedia PDF Downloads 167

Authors: Arthur D. Wiedemann, Christopher Fuller, Kyle A. Pascioni

Abstract:

With the introduction of electric motors, small unmanned aerial vehicle designers have to consider trade-offs between acoustic noise and thrust generated. Currently, there are few low-computational tools available for predicting acoustic noise emitted by a propeller into the far-field. Artificial neural networks offer a highly non-linear and adaptive model for predicting isolated and interactive tonal noise. But neural networks require large data sets, exceeding practical considerations in modeling experimental results. A methodology known as physics guided machine learning has been applied in this study to reduce the required data set to train the network. After building and evaluating several neural networks, the best model is investigated to determine how the network successfully predicts the acoustic waveform. Lastly, a post-network transfer function is developed to remove discontinuity from the predicted waveform. Overall, methodologies from physics guided machine learning show a notable improvement in prediction performance, but additional loss functions are necessary for constructing predictive networks on small datasets.

Keywords: aeroacoustics, machine learning, propeller, rotor, neural network, physics guided machine learning

Procedia PDF Downloads 221

Authors: Hanlin Liu, Hua Li, Yintan AI

Abstract:

Network performance prediction (NPP) is essential for the management and optimization of software-defined networking (SDN) and contributes to improving the quality of service (QoS) in SDN to meet the requirements of users. Although current deep learning-based methods can achieve high effectiveness, they still suffer from some problems, such as difficulty in capturing global information of the network, inefficiency in modeling end-to-end network performance, and inadequate graph feature extraction. To cope with these issues, our proposed Graphormer-based architecture for NPP leverages the powerful graph representation ability of Graphormer to effectively model the graph structure data, and a node-edge transformation algorithm is designed to transfer the feature extraction object from nodes to edges, thereby effectively extracting the end-to-end performance characteristics of the network. Moreover, routing oriented centrality measure coefficient for nodes and edges is proposed respectively to assess their importance and influence within the graph. Based on this coefficient, an enhanced feature extraction method and an advanced centrality encoding strategy are derived to fully extract the structural information of the graph. Experimental results on three public datasets demonstrate that the proposed GraphNPP architecture can achieve state-of-the-art results compared to current NPP methods.

Keywords: software-defined networking, network performance prediction, Graphormer, graph neural network

Procedia PDF Downloads 38

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 164

Authors: Maria Amodeo, Pasquale Arpaia, Marco Buzio, Vincenzo Di Capua, Francesco Donnarumma

Abstract:

Different deep neural network architectures have been compared and tested to predict magnetic hysteresis in the context of pulsed electromagnets for experimental physics applications. Modelling quasi-static or dynamic major and especially minor hysteresis loops is one of the most challenging topics for computational magnetism. Recent attempts at mathematical prediction in this context using Preisach models could not attain better than percent-level accuracy. Hence, this work explores neural network approaches and shows that the architecture that best fits the measured magnetic field behaviour, including the effects of hysteresis and eddy currents, is the nonlinear autoregressive exogenous neural network (NARX) model. This architecture aims to achieve a relative RMSE of the order of a few 100 ppm for complex magnetic field cycling, including arbitrary sequences of pseudo-random high field and low field cycles. The NARX-based architecture is compared with the state-of-the-art, showing better performance than the classical operator-based and differential models, and is tested on a reference quadrupole magnetic lens used for CERN particle beams, chosen as a case study. The training and test datasets are a representative example of real-world magnet operation; this makes the good result obtained very promising for future applications in this context.

Keywords: deep neural network, magnetic modelling, measurement and empirical software engineering, NARX

Procedia PDF Downloads 128

Authors: Mehwish Asghar

Abstract:

Breast Cancer (BC) is a common type of cancer among women. Its screening is usually performed using different imaging modalities such as magnetic resonance imaging, mammogram, X-ray, CT, etc. Among these modalities’ mammogram is considered a powerful tool for diagnosis and screening of breast cancer. Sophisticated machine learning approaches have shown promising results in complementing human diagnosis. Generally, machine learning methods can be divided into two major classes: one is Radiomics analysis (RA), where image features are extracted manually; and the other one is the concept of convolutional neural networks (CNN), in which the computer learns to recognize image features on its own. This research aims to improve the incidence of early detection, thus reducing the mortality rate caused by breast cancer through the latest advancements in computer science, in general, and machine learning, in particular. It has also been aimed to ease the burden of doctors by improving and automating the process of breast cancer detection. This research is related to a relative analysis of different techniques for the implementation of different models for detecting and classifying breast cancer. The main goal of this research is to provide a detailed view of results and performances between different techniques. The purpose of this paper is to explore the potential of a convolutional neural network (CNN) w.r.t feature extractor and as a classifier. Also, in this research, it has been aimed to add the module of Radiomics for comparison of its results with deep learning techniques.

Keywords: breast cancer (BC), machine learning (ML), convolutional neural network (CNN), radionics, magnetic resonance imaging, artificial intelligence

Procedia PDF Downloads 220

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 31

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 152

Authors: Vinicius G. Goecks, Gregory M. Gremillion, William D. Nothwang

Abstract:

Modern approaches to train intelligent agents rely on prolonged training sessions, high amounts of input data, and multiple interactions with the environment. This restricts the application of these learning algorithms in robotics and real-world applications, in which there is low tolerance to inadequate actions, interactions are expensive, and real-time processing and action are required. This paper addresses this issue introducing CyberSteer, a novel approach to efficiently design intrinsic reward functions based on human intention to guide deep reinforcement learning agents with no environment-dependent rewards. CyberSteer uses non-expert human operators for initial demonstration of a given task or desired behavior. The trajectories collected are used to train a behavior cloning deep neural network that asynchronously runs in the background and suggests actions to the deep reinforcement learning module. An intrinsic reward is computed based on the similarity between actions suggested and taken by the deep reinforcement learning algorithm commanding the agent. This intrinsic reward can also be reshaped through additional human demonstration or critique. This approach removes the need for environment-dependent or hand-engineered rewards while still being able to safely shape the behavior of autonomous robotic agents, in this case, based on human intention. CyberSteer is tested in a high-fidelity unmanned aerial vehicle simulation environment, the Microsoft AirSim. The simulated aerial robot performs collision avoidance through a clustered forest environment using forward-looking depth sensing and roll, pitch, and yaw references angle commands to the flight controller. This approach shows that the behavior of robotic systems can be shaped in a reduced amount of time when guided by a non-expert human, who is only aware of the high-level goals of the task. Decreasing the amount of training time required and increasing safety during training maneuvers will allow for faster deployment of intelligent robotic agents in dynamic real-world applications.

Keywords: human-robot interaction, intelligent robots, robot learning, semisupervised learning, unmanned aerial vehicles

Procedia PDF Downloads 256

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 181

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 190

Authors: Tsega Asresa Mengistu, Getahun Tigistu

Abstract:

Computer vision is an artificial intelligence subfield that allows computers and systems to retrieve meaning from digital images. It is applied in various fields of study self-driving cars, video surveillance, agriculture, Quality control, Health care, construction, military, and everyday life. Aromatic and medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, and other natural health products for therapeutic and Aromatic culinary purposes. Herbal industries depend on these special plants. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs, and going to export not only industrial raw materials but also valuable foreign exchange. There is a lack of technologies for the classification and identification of Aromatic and medicinal plants in Ethiopia. The manual identification system of plants is a tedious, time-consuming, labor, and lengthy process. For farmers, industry personnel, academics, and pharmacists, it is still difficult to identify parts and usage of plants before ingredient extraction. In order to solve this problem, the researcher uses a deep learning approach for the efficient identification of aromatic and medicinal plants by using a convolutional neural network. The objective of the proposed study is to identify the aromatic and medicinal plant Parts and usages using computer vision technology. Therefore, this research initiated a model for the automatic classification of aromatic and medicinal plants by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides the root, flower and fruit, latex, and barks. The study was conducted on aromatic and medicinal plants available in the Ethiopian Institute of Agricultural Research center. An experimental research design is proposed for this study. This is conducted in Convolutional neural networks and Transfer learning. The Researcher employs sigmoid Activation as the last layer and Rectifier liner unit in the hidden layers. Finally, the researcher got a classification accuracy of 66.4 in convolutional neural networks and 67.3 in mobile networks, and 64 in the Visual Geometry Group.

Keywords: aromatic and medicinal plants, computer vision, deep convolutional neural network

Procedia PDF Downloads 429

Authors: Zhidong Zhang, Yingchen Yang

Abstract:

In this study, a diagnostic assessment model for Mastery Engineering Learning was established based on a group of undergraduate students who studied in an engineering course. A diagnostic assessment model can examine both students' learning process and report achievement results. One very unique characteristic is that the diagnostic assessment model can recognize the errors and anything blocking students in their learning processes. The feedback is provided to help students to know how to solve the learning problems with alternative strategies and help the instructor to find alternative pedagogical strategies in the instructional designs. Dynamics is a core course in which is a common course being shared by several engineering programs. This course is a very challenging for engineering students to solve the problems. Thus knowledge acquisition and problem-solving skills are crucial for student success. Therefore, developing an effective and valid assessment model for student learning are of great importance. Diagnostic assessment is such a model which can provide effective feedback for both students and instructor in the mastery of engineering learning.

Keywords: diagnostic assessment, mastery learning, engineering, bayesian network model, learning processes

Procedia PDF Downloads 149

Authors: Bo-Bin Xiaoa, Chia-Yi Liua

Abstract:

In the task of searching for anomalous radiation sources, personnel holding radiation detectors to search for radiation sources may be exposed to unnecessary radiation risk, and automated search using machines becomes a required project. The research uses various sophisticated algorithms, which are double Q learning, dueling network, and NoisyNet, of deep reinforcement learning to search for radiation sources. The simulation environment, which is a 10*10 grid and one shielding wall setting in it, improves the development of the AI model by training 1 million episodes. In each episode of training, the radiation source position, the radiation source intensity, agent position, shielding wall position, and shielding wall length are all set randomly. The three algorithms are applied to run AI model training in four environments where the training shielding wall is a full-shielding wall, a lead wall, a concrete wall, and a lead wall or a concrete wall appearing randomly. The 12 best performance AI models are selected by observing the reward value during the training period and are evaluated by comparing these AI models with the gradient search algorithm. The results show that the performance of the AI model, no matter which one algorithm, is far better than the gradient search algorithm. In addition, the simulation environment becomes more complex, the AI model which applied Double DQN combined Dueling and NosiyNet algorithm performs better.

Keywords: double Q learning, dueling network, NoisyNet, source searching

Procedia PDF Downloads 105

Authors: Saba Rahimi, Ozan Oktay, Javier Alvarez-Valle, Sujeeth Bharadwaj

Abstract:

Successful application of deep learning in medical image analysis necessitates unprecedented amounts of labeled training data. Unlike conventional 2D applications, radiological images can be three-dimensional (e.g., CT, MRI), consisting of many instances within each image. The problem is exacerbated when expert annotations are required for effective pixel-wise labeling, which incurs exorbitant labeling effort and cost. Active learning is an established research domain that aims to reduce labeling workload by prioritizing a subset of informative unlabeled examples to annotate. Our contribution is a cost-effective approach for U-Net 3D models that uses Monte Carlo sampling to analyze pixel-wise uncertainty. Experiments on the AAPM 2017 lung CT segmentation challenge dataset show that our proposed framework can achieve promising segmentation results by using only 42% of the training data.

Keywords: image segmentation, active learning, convolutional neural network, 3D U-Net

Procedia PDF Downloads 149

Authors: Guezouli Larbi, Belkacem Soundes

Abstract:

The automation of the text detection process can help the human in his driving task. Its application can be very useful to help drivers to have more information about their environment by facilitating the reading of road signs such as directional signs, events, stores, etc. In this paper, a system consisting of two stages has been proposed. In the first one, we used pseudo-Zernike moments to pinpoint areas of the image that may contain text. The architecture of this part is based on three main steps, region of interest (ROI) detection, text localization, and non-text region filtering. Then, in the second step, we present a convolutional neural network architecture (On-Road Text Detection Network - ORTDN) which is considered a classification phase. The results show that the proposed framework achieved ≈ 35 fps and an mAP of ≈ 90%, thus a low computational time with competitive accuracy.

Keywords: text detection, CNN, PZM, deep learning

Procedia PDF Downloads 79

Authors: Y. Heyrani Birak, R. Hizaji, J. Shahkarami

Abstract:

Reinforced Concrete (RC) deep beams are special structural elements because of their geometry and behavior under loads. For example, assumption of strain- stress distribution is not linear in the cross section. These types of beams may have simple supports or fixed supports. A lot of research works have been conducted on simply supported deep beams, but little study has been done in the fixed-end RC deep beams behavior. Recently, using of fixed-ended deep beams has been widely increased in structures. In this study, the behavior of fixed-ended deep beams is investigated, and the important parameters in capacity of this type of beams are mentioned.

Keywords: deep beam, capacity, reinforced concrete, fixed-ended

Procedia PDF Downloads 331

Authors: A. Aarabzadeh, R. Hizaji

Abstract:

Reinforced Concrete (RC) deep beams are a special type of beams due to their geometry, boundary conditions, and behavior compared to ordinary shallow beams. For example, assumption of a linear strain-stress distribution in the cross section is not valid. Little study has been dedicated to fixed-end RC deep beams. Also, most experimental studies are carried out on simply supported deep beams. Regarding recent tendency for application of deep beams, possibility of using fixed-ended deep beams has been widely increased in structures. Therefore, it seems necessary to investigate the aforementioned structural element in more details. In addition to experimental investigation of a concrete deep beam under cyclic load, different failure mechanisms of fixed-ended deep beams under this type of loading have been evaluated in the present study. The results show that failure mechanisms of deep beams under cyclic loads are quite different from monotonic loads.

Keywords: deep beam, cyclic load, reinforced concrete, fixed-ended

Procedia PDF Downloads 354

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 148

Authors: Ci Lin, Tet Yeap, Iluju Kiringa

Abstract:

This paper introduces the subspace rotation algorithm (SRA) to train the Restricted Hopfield Network (RHN) as an auto-associative memory. Subspace rotation algorithm is a gradient-free subspace tracking approach based on the singular value decomposition (SVD). In comparison with Backpropagation Through Time (BPTT) on training RHN, it is observed that SRA could always converge to the optimal solution and BPTT could not achieve the same performance when the model becomes complex, and the number of patterns is large. The AUTS case study showed that the RHN model trained by SRA could achieve a better structure of attraction basin with larger radius(in general) than the Hopfield Network(HNN) model trained by Hebbian learning rule. Through learning 10000 patterns from MNIST dataset with RHN models with different number of hidden nodes, it is observed that an several components could be adjusted to achieve a balance between recovery accuracy and noise resistance.

Keywords: hopfield neural network, restricted hopfield network, subspace rotation algorithm, hebbian learning rule

Procedia PDF Downloads 112

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

Abstract:

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

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

Procedia PDF Downloads 145

Authors: Mark Harmon, Abdolghani Ebrahimi, Patrick Lucey, Diego Klabjan

Abstract:

In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. Previous approaches to similar problems center on hand-crafting features to capture domain-specific knowledge. Although intuitive, recent work in deep learning has shown, this approach is prone to missing important predictive features. To circumvent this issue, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories, we use “fading.” We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFN+CNN is the best performing network with an error rate of 39%.

Keywords: basketball, computer vision, image processing, convolutional neural network

Procedia PDF Downloads 151

Authors: Kevin Fernagut, Olivier Flauzac, Erick M. G. Robledo, Florent Nolot

Abstract:

The adoption of modern lightweight virtualization often comes with new threats and network vulnerabilities. This paper seeks to assess this with a different approach studying the behavior of a testbed built with tools such as Kernel-Based Virtual Machine (KVM), Linux Containers (LXC) and Docker, by performing stress tests within a platform where students experiment simultaneously with cyber-attacks, and thus observe the impact on the campus network and also find the best solution for cyber-security learning. Interesting outcomes can be found in the literature comparing these technologies. It is, however, difficult to find results of the effects on the global network where experiments are carried out. Our work shows that other physical hosts and the faculty network were impacted while performing these trials. The problems found are discussed, as well as security solutions and the adoption of new network policies.

Keywords: containerization, containers, cybersecurity, cyberattacks, isolation, performance, virtualization, virtual machines

Procedia PDF Downloads 142

Authors: Bin Ji, Kai Xu, Shunyu Yao, Jingjing Liu, Ye Pan

Abstract:

Human pose estimation is a popular research area in computer vision for its important application in human-machine interface. In recent years, 2D human pose estimation based on convolution neural network has got great progress and development. However, in more and more practical applications, people often need to deal with tasks based on video. It’s not far-fetched for us to consider how to combine the spatial and temporal information together to achieve a balance between computing cost and accuracy. To address this issue, this study proposes a new spatiotemporal model, namely Spatiotemporal Net (STNet) to combine both temporal and spatial information more rationally. As a result, the predicted keypoints heatmap is potentially more accurate and spatially more precise. Under the condition of ensuring the recognition accuracy, the algorithm deal with spatiotemporal series in a decoupled way, which greatly reduces the computation of the model, thus reducing the resource consumption. This study demonstrate the effectiveness of our network over the Penn Action Dataset, and the results indicate superior performance of our network over the existing methods.

Keywords: convolutional long short-term memory, deep learning, human pose estimation, spatiotemporal series

Procedia PDF Downloads 143

Authors: Chien-Kuo Chang, Yu-Hsiang Lin, Yi-Yun Tang, Min-Chiu Wu

Abstract:

With the trend of technological advancement, the harm caused by power outages is substantial, mostly due to problems in the power grid. This highlights the necessity for further improvement in the reliability of the power system. In the power system, gas-insulated switches (GIS) and power cables play a crucial role. Long-term operation under high voltage can cause insulation materials in the equipment to crack, potentially leading to partial discharges. If these partial discharges (PD) can be analyzed, preventative maintenance and replacement of equipment can be carried out, there by improving the reliability of the power grid. This research will diagnose defects by identifying three different defects in GIS and three different defects in straight cable joints, for a total of six types of defects. The partial discharge data measured will be converted through phase analysis diagrams and pulse sequence analysis. Discharge features will be extracted using convolutional image processing, and three different deep learning models, CNN, ResNet18, and MobileNet, will be used for training and evaluation. Class Activation Mapping will be utilized to interpret the black-box problem of deep learning models, with each model achieving an accuracy rate of over 95%. Lastly, the overall model performance will be enhanced through an ensemble learning voting method.

Keywords: partial discharge, gas-insulated switches, straight cable joint, defect identification, deep learning, ensemble learning

Procedia PDF Downloads 73

Authors: Anastassis Kozanitis, Diane Leduc, Alain Stockless

Abstract:

This paper presents preliminary results from a two-year funded research program looking to analyze and understand the relationship between high cognitive engagement, higher order cognitive processes employed in situations of complex learning tasks, and the use of active learning pedagogies in engineering undergraduate programs. A mixed method approach was used to gauge student engagement and their cognitive processes when accomplishing complex tasks. Quantitative data collected from the self-report cognitive engagement scale shows that deep learning approach is positively correlated with high levels of complex learning tasks and the level of student engagement, in the context of classroom active learning pedagogies. Qualitative analyses of in depth face-to-face interviews reveal insights into the mechanisms influencing students’ cognitive processes when confronted with open-ended problem resolution. Findings also support evidence that students will adjust their level of cognitive engagement according to the specific didactic environment.

Keywords: cognitive engagement, deep and shallow strategies, engineering programs, higher order cognitive processes

Procedia PDF Downloads 319