Search results for: deep supervision

Authors: Ziying Wu, Danfeng Yan

Abstract:

Multi-Access Edge Computing (MEC) is one of the key technologies of the future 5G network. By deploying edge computing centers at the edge of wireless access network, the computation tasks can be offloaded to edge servers rather than the remote cloud server to meet the requirements of 5G low-latency and high-reliability application scenarios. Meanwhile, with the development of IOV (Internet of Vehicles) technology, various delay-sensitive and compute-intensive in-vehicle applications continue to appear. Compared with traditional internet business, these computation tasks have higher processing priority and lower delay requirements. In this paper, we design a 5G-based Vehicle-Aware Multi-Access Edge Computing Network (VAMECN) and propose a joint optimization problem of minimizing total system cost. In view of the problem, a deep reinforcement learning-based joint computation offloading and task migration optimization (JCOTM) algorithm is proposed, considering the influences of multiple factors such as concurrent multiple computation tasks, system computing resources distribution, and network communication bandwidth. And, the mixed integer nonlinear programming problem is described as a Markov Decision Process. Experiments show that our proposed algorithm can effectively reduce task processing delay and equipment energy consumption, optimize computing offloading and resource allocation schemes, and improve system resource utilization, compared with other computing offloading policies.

Keywords: multi-access edge computing, computation offloading, 5th generation, vehicle-aware, deep reinforcement learning, deep q-network

Procedia PDF Downloads 118

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 150

Authors: Hy Dang, Bo Mei

Abstract:

The development of machine learning methods and techniques has opened doors for investigation in many areas such as medicines, economics, finance, etc. One active research area involving machine learning is stock market prediction. This research paper tries to consider multiple techniques and methods for stock movement prediction using historical price or price factors. The paper explores the effectiveness of some deep learning frameworks for forecasting stock. Moreover, an architecture (TimeStock) is proposed which takes the representation of time into account apart from the price information itself. Our model achieves a promising result that shows a potential approach for the stock movement prediction problem.

Keywords: classification, machine learning, time representation, stock prediction

Procedia PDF Downloads 147

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 143

Authors: Mohammad Mardi

Abstract:

Generally, the resistivity is high in oil layer and low in water layer. Yet there are intervals of oil-bearing zones showing low resistivity, high porosity, and low resistance. In the typical example, well A (depth: 4341.5-4372.0m), both Spectral Gamma Ray (SGR) and Corrected Gamma Ray (CGR) are relatively low; porosity varies from 12-22%. Above 4360 meters, the reservoir shows the conventional positive difference between deep and shallow resistivity with high resistance; below 4360m, the reservoir shows a negative difference with low resistance, especially at depths of 4362.4 meters and 4371 meters, deep resistivity is only 2Ω.m, and the CAST-V imaging map shows that there are low resistance substances contained in the pores or matrix in the reservoirs of this interval. The rock slice analysis data shows that the pyrite volume is 2-3% in the interval 4369.08m-4371.55m. A comprehensive analysis on the volume of shale (Vsh), porosity, invasion features of resistivity, mud logging, and mineral volume indicates that the possible causes for the negative difference between deep and shallow resistivities with relatively low resistance are erosional pores, caves, micritic texture and the presence of pyrite. Full-bore Drill Stem Test (DST) verified 4991.09 bbl/d in this interval. To identify and thoroughly characterize low resistivity intervals coring, Nuclear Magnetic Resonance (NMR) logging and further geological evaluation are needed.

Keywords: low resistivity pay, carbonates petrophysics, microporosity, porosity

Procedia PDF Downloads 167

Authors: Supriya H. S., Chandrakala B. M.

Abstract:

Deep learning based models have been recently successful adoption for network traffic prediction. However, training a deep learning model for various prediction tasks is considered one of the critical tasks due to various reasons. This research work develops Multi-Layer Hybrid Network (MLHN) for network traffic prediction and analysis; MLHN comprises the three distinctive networks for handling the different inputs for custom feature extraction. Furthermore, an optimized and efficient parameter-tuning algorithm is introduced to enhance parameter learning. MLHN is evaluated considering the “Big Data Challenge” dataset considering the Mean Absolute Error, Root Mean Square Error and R^2as metrics; furthermore, MLHN efficiency is proved through comparison with a state-of-art approach.

Keywords: MLHN, network traffic prediction

Procedia PDF Downloads 88

Authors: Bahareh Golchin, Nooshin Riahi

Abstract:

One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.

Keywords: emotion classification, sentiment analysis, social networks, deep neural networks

Procedia PDF Downloads 137

Authors: P. R. Prabhu, S. M. Kulkarni, S. S. Sharma, K. Jagannath, Achutha Kini U.

Abstract:

In the present study, response surface methodology has been used to optimize turn-assisted deep cold rolling process of AISI 4140 steel. A regression model is developed to predict surface hardness and surface roughness using response surface methodology and central composite design. In the development of predictive model, deep cold rolling force, ball diameter, initial roughness of the workpiece, and number of tool passes are considered as model variables. The rolling force and the ball diameter are the significant factors on the surface hardness and ball diameter and numbers of tool passes are found to be significant for surface roughness. The predicted surface hardness and surface roughness values and the subsequent verification experiments under the optimal operating conditions confirmed the validity of the predicted model. The absolute average error between the experimental and predicted values at the optimal combination of parameter settings for surface hardness and surface roughness is calculated as 0.16% and 1.58% respectively. Using the optimal processing parameters, the hardness is improved from 225 to 306 HV, which resulted in an increase in the near surface hardness by about 36% and the surface roughness is improved from 4.84µm to 0.252 µm, which resulted in decrease in the surface roughness by about 95%. The depth of compression is found to be more than 300µm from the microstructure analysis and this is in correlation with the results obtained from the microhardness measurements. Taylor Hobson Talysurf tester, micro Vickers hardness tester, optical microscopy and X-ray diffractometer are used to characterize the modified surface layer.

Keywords: hardness, response surface methodology, microstructure, central composite design, deep cold rolling, surface roughness

Procedia PDF Downloads 420

Authors: Xiaoyan Dai, Hsieh Yisan

Abstract:

Barcode processing of captured images is a huge challenge, as different shooting conditions can result in different barcode appearances. This paper proposes a deep learning-based barcode detection using synthetic-to-real data augmentation. We first augment barcodes themselves; we then augment images containing the barcodes to generate a large variety of data that is close to the actual shooting environments. Comparisons with previous works and evaluations with our original data show that this approach achieves state-of-the-art performance in various real images. In addition, the system uses hybrid resolution for barcode “scan” and is applicable to real-time applications.

Keywords: barcode detection, data augmentation, deep learning, image-based processing

Procedia PDF Downloads 168

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 74

Authors: Mehmet Karabekir

Abstract:

Attack helicopters (AHs) are usually deployed in conventional warfare to destroy armored and mechanized forces of enemy. In addition, AHs are able to perform various tasks in the deep, and close operations – intelligence, surveillance, reconnaissance, air assault operations, and search and rescue operations. Apache helicopters were properly employed in the Gulf Wars and contributed the success of campaign by destroying a large number of armored and mechanized vehicles of Iraq Army. The purpose of this article is to discuss the deployment of AHs in conventional warfare in the light of Gulf Wars. First, the employment of AHs in deep and close operations will be addressed regarding the doctrine. Second, the US armed forces AH-64 doctrinal and tactical usage will be argued in the 1st and 2nd Gulf Wars.

Keywords: attack helicopter, conventional warfare, gulf wars

Procedia PDF Downloads 473

Authors: Selim M. Khan

Abstract:

Indoor air quality is strongly influenced by the presence of radioactive radon (222Rn) gas. Indeed, exposure to high 222Rn concentrations is unequivocally linked to DNA damage and lung cancer and is a worsening issue in North American and European built environments, having increased over time within newer housing stocks as a function of as yet unclear variables. Indoor air radon concentration can be influenced by a wide range of environmental, structural, and behavioral factors. As some of these factors are quantitative while others are qualitative, no single statistical model can determine indoor radon level precisely while simultaneously considering all these variables across a complex and highly diverse dataset. The ability of AI- machine (deep) learning to simultaneously analyze multiple quantitative and qualitative features makes it suitable to predict radon with a high degree of precision. Using Canadian and Swedish long-term indoor air radon exposure data, we are using artificial deep neural network models with random weights and polynomial statistical models in MATLAB to assess and predict radon health risk to human as a function of geospatial, human behavioral, and built environmental metrics. Our initial artificial neural network with random weights model run by sigmoid activation tested different combinations of variables and showed the highest prediction accuracy (>96%) within the reasonable iterations. Here, we present details of these emerging methods and discuss strengths and weaknesses compared to the traditional artificial neural network and statistical methods commonly used to predict indoor air quality in different countries. We propose an artificial deep neural network with random weights as a highly effective method for assessing and predicting indoor radon.

Keywords: radon, radiation protection, lung cancer, aI-machine deep learnng, risk assessment, risk prediction, Europe, North America

Procedia PDF Downloads 96

Authors: Sushil Kumar Gupta, Atharva Joshi, Ayush Sonawale, Sachin Naik, Rajshree Khande

Abstract:

The usage of artificially created videos and audio by deep learning is a major problem of the current media landscape, as it pursues the goal of misinformation and distrust. In conclusion, the objective of this work targets generating a reliable deepfake detection model using deep learning that will help detect forged videos accurately. In this work, CelebDF v1, one of the largest deepfake benchmark datasets in the literature, is adopted to train and test the proposed models. The data includes authentic and synthetic videos of high quality, therefore allowing an assessment of the model’s performance against realistic distortions.

Keywords: deepfake detection, CelebDF v1, convolutional neural network (CNN), xception model, data augmentation, media manipulation

Procedia PDF Downloads 9

Authors: Li Hui, Riyadh Hindi

Abstract:

In the United States, bridge construction often employs overhang brackets to support the deck overhang, the weight of fresh concrete, and loads from construction equipment. This approach, however, can lead to significant torsional moments on the exterior girders, potentially causing excessive girder rotation. Such rotations can result in various safety and maintenance issues, including thinning of the deck, reduced concrete cover, and cracking during service. Traditionally, these issues are addressed by installing temporary lateral bracing systems and conducting comprehensive torsional analysis through detailed finite element analysis for the construction of bridge deck overhang. However, this process is often intricate and time-intensive, with the spacing between temporary lateral bracing systems usually relying on the field engineers’ expertise. In this study, a deep neural network model is introduced to limit exterior girder rotation during bridge deck construction. The model predicts the optimal spacing between temporary bracing systems. To train this model, over 10,000 finite element models were generated in SAP2000, incorporating varying parameters such as girder dimensions, span length, and types and spacing of lateral bracing systems. The findings demonstrate that the deep neural network provides an effective and efficient alternative for limiting the exterior girder rotation for bridge deck construction. By reducing dependence on extensive finite element analyses, this approach stands out as a significant advancement in improving safety and maintenance effectiveness in the construction of bridge decks.

Keywords: bridge deck construction, exterior girder rotation, deep learning, finite element analysis

Procedia PDF Downloads 62

Authors: J. Waita, S. Wamuhu, J. Makoyo, M. Rachel, T. Ngangari, W. Christine, M. Zipporah

Abstract:

Contraceptive use is one of the key global strategies to alleviate maternal mortality. Global efforts through advocating for contraceptive uptake and service provision has led improved contraceptive prevalence. In Kenya maternal mortality rate has remained a challenged despites efforts by government and non-governmental organizations. Objective: To describe the uptake of contraceptives among women in Tunza Clinics, Kenya. Design and Methods: Ps Kenya through health care marketing fund is implementing a family planning program among its 350 Tunza fractional franchise facilities. Through private partnership, private owned facilities in low socio-economic areas are recruited and trained on contraceptive technology update. The providers are supported through facilitative supervision through a mobile based application Health Network Quality Improvement System (HNQIS) and interpersonal communication through 150 community based volunteers. The data analyzed in this paper was collected between January to July 2017 to show the uptake of modern Contraceptives among women in the Tunza franchise, method mix, age and distribution among the age bracket. Further analysis compares two different service delivery strategies; outreach and walk ins. Supportive supervision HNQIS scores was analyzed. Results: During the time period, a total of 132121 family planning clients were attended in 350 facilities. The average age of clients was 29.6 years. The average number of clients attended in the facilities per month was 18874. 73.7 %( n=132121) of the clients attended in the Tunza facilities were aged above 25 years while 22.1% 20-24 years and 4.2% 15-19 years. On contraceptive method mix, intra uterine device insertions clients contributed to 7.5%, implant insertions 15.3%, pills 11.2%, injections 62.7% while condoms and emergency pills had 2.7% and 0.6% respectively. Analysis of service delivery strategy indicated more than 79% of the clients were walk ins while 21% were attended to during outreaches. Uptake of long term contraceptive methods during outreaches was 73% of the clients while short term modern methods were 27%. Health Network Quality Improvement system assessment scores indicated 51% of the facilities scored over 90%, 25% scoring 80-89% while 21% scored below 80%. Conclusion: Preference for short term methods by women is possibly associated to cost as they are cheaper and easy to administer. When the cost of intra uterine device Implants is meant affordable during outreaches, the uptake is observed to increase. Making intra uterine device and implants affordable to women is a key strategy in increasing contraceptive prevalence hence averting maternal mortality.

Keywords: contraceptives, contraceptive uptake, low socio economic, supportive supervision

Procedia PDF Downloads 168

Authors: H. Idmoussi, L. Somoue, O. Ettahiri, A. Makaoui, S. Charib, A. Agouzouk, A. Ben Mhamed, K. Hilmi, A. Errhif

Abstract:

The study on the composition, abundance, and distribution of phytoplankton was conducted along the Moroccan coast of the Mediterranean Sea (Saiidia - Three Forks Cape) in April 2018. Samples were collected at thirteen stations using Niskin bottles within two layers (surface and deep layers). The identification and enumeration of phytoplankton were carried out according to the Utermöhl method (1958). A total number of 54 phytoplankton species were identified over the entire survey area. Thirty-six species could be found both in the surface and the deep layers while eleven species were observed only in the surface layer and seven in the deep layer. The phytoplankton throughout the study area was dominated by diatoms represented mainly by Nitzschia sp., Pseudonitzschia sp., Chaetoceros sp., Cylindrotheca closterium, Leptocylindrus minimus, Leptocylindrus danicus, Dactyliosolen fragilissimus. Dinoflagellates were dominated by Gymnodinium sp., Scrippsiella sp., Gyrodinium spirale, Noctulica sp, Prorocentrum micans. Euglenophyceae, Silicoflagellates and Raphidophyceae were present in low numbers. Most of the phytoplankton were concentrated in the surface layer, particularly towards the Three Forks Cape (25200 cells·l⁻¹). Shannon species diversity (ranging from 2 and 4 Bits) and evenness index (broadly > 0.7) suggested that phytoplankton community is generally diversified and structured in the studied area.

Keywords: abundance, diversity, Mediterranean Sea, phytoplankton

Procedia PDF Downloads 158

Authors: Johan Loeckx, Joeri Bultheel

Abstract:

Recently, the application of deep learning to music has gained popularity. Its true potential, however, has been largely unexplored. In this paper, a new idea for representing the dynamic behavior of music is proposed. A ”forward” conditional RBM takes into account not only preceding but also future samples during training. Though this may sound controversial at first sight, it will be shown that it makes sense from a musical and neuro-cognitive perspective. The model is applied to reconstruct music based upon the first notes and to improvise in the musical style of a composer. Different to expectations, reconstruction accuracy with respect to a regular CRBM with the same order, was not significantly improved. More research is needed to test the performance on unseen data.

Keywords: deep learning, restricted boltzmann machine, music generation, conditional restricted boltzmann machine (CRBM)

Procedia PDF Downloads 522

Authors: Paulo Sérgio Ribeiro de Araújo Bogas

Abstract:

Although several studies have assumed (at least implicitly) that learners' approaches to learning develop into deeper approaches to higher education, there appears to be no clear theoretical basis for this assumption and no empirical evidence. As a scientific contribution to this discussion, a pedagogical intervention of a quasi-experimental nature was developed, with a mixed methodology, evaluating the intervention within a single curricular unit of Marketing, using cases based on real challenges of brands, business simulation, and customer projects. Primary and secondary experiences were incorporated in the intervention: the primary experiences are the experiential activities themselves; the secondary experiences result from the primary experience, such as reflection and discussion in work teams. A diversified learning relationship was encouraged through the various connections between the different members of the learning community. The present study concludes that in the same context, the student's responses can be described as students who reinforce the initial deep approach, students who maintain the initial deep approach level, and others who change from an emphasis on the deep approach to one closer to superficial. This typology did not always confirm studies reported in the literature, namely, whether the initial level of deep processing would influence the superficial and the opposite. The result of this investigation points to the inclusion of pedagogical and didactic activities that integrate different motivations and initial strategies, leading to the possible adoption of deep approaches to learning since it revealed statistically significant differences in the difference in the scores of the deep/superficial approach and the experiential level. In the case of real challenges, the categories of “attribution of meaning and meaning of studied” and the possibility of “contact with an aspirational context” for their future professional stand out. In this category, the dimensions of autonomy that will be required of them were also revealed when comparing the classroom context of real cases and the future professional context and the impact they may have on the world. Regarding the simulated practice, two categories of response stand out: on the one hand, the motivation associated with the possibility of measuring the results of the decisions taken, an awareness of oneself, and, on the other hand, the additional effort that this practice required for some of the students.

Keywords: experiential learning, higher education, mixed methods, reflective learning, marketing

Procedia PDF Downloads 83

Authors: Harish Kumar Sharma, Garima Sengar

Abstract:

Rice bran oil is considered comparatively nutritionally superior than different fats/oils. Therefore, model blends prepared from pure rice bran oil (RBO) and sunflower oil (SFO) were explored for changes in the different physicochemical parameters. Repeated deep fat frying process was carried out by using dried potato in order to study the thermal behaviour of pure rice bran oil, sunflower oil and their model blends. Pure rice bran oil and sunflower oil had shown good thermal stability during the repeated deep fat frying cycles. Although, the model blends constituting 60% RBO + 40% SFO showed better suitability during repeated deep fat frying than the remaining blended oils. The quantification of pure rice bran oil in the blended oils, physically refined rice bran oil (PRBO): SnF (sunflower oil) was carried by different methods. The study revealed that regression equations based on the oryzanol content, palmitic acid composition and iodine value can be used for the quantification. The rice bran oil can easily be quantified in the blended oils based on the oryzanol content by HPLC even at 1% level. The palmitic acid content in blended oils can also be used as an indicator to quantify rice bran oil at or above 20% level in blended oils whereas the method based on ultrasonic velocity, acoustic impedance and relative association showed initial promise in the quantification.

Keywords: rice bran oil, sunflower oil, frying, quantification

Procedia PDF Downloads 308

Authors: Ahmedou Moulaye Idriss, Tfeil Yahya, Tamas Ungi, Gabor Fichtinger

Abstract:

Image-guided therapy (IGT) plays a crucial role in minimally invasive procedures for liver interventions. Accurate segmentation of the liver and precise needle placement is essential for successful interventions such as needle aspiration. In this study, we propose a deep learning-based liver 3D slicer designed to enhance segmentation accuracy and facilitate needle aspiration procedures. The developed 3D slicer leverages state-of-the-art convolutional neural networks (CNNs) for automatic liver segmentation in medical images. The CNN model is trained on a diverse dataset of liver images obtained from various imaging modalities, including computed tomography (CT) and magnetic resonance imaging (MRI). The trained model demonstrates robust performance in accurately delineating liver boundaries, even in cases with anatomical variations and pathological conditions. Furthermore, the 3D slicer integrates advanced image registration techniques to ensure accurate alignment of preoperative images with real-time interventional imaging. This alignment enhances the precision of needle placement during aspiration procedures, minimizing the risk of complications and improving overall intervention outcomes. To validate the efficacy of the proposed deep learning-based 3D slicer, a comprehensive evaluation is conducted using a dataset of clinical cases. Quantitative metrics, including the Dice similarity coefficient and Hausdorff distance, are employed to assess the accuracy of liver segmentation. Additionally, the performance of the 3D slicer in guiding needle aspiration procedures is evaluated through simulated and clinical interventions. Preliminary results demonstrate the effectiveness of the developed 3D slicer in achieving accurate liver segmentation and guiding needle aspiration procedures with high precision. The integration of deep learning techniques into the IGT workflow shows great promise for enhancing the efficiency and safety of liver interventions, ultimately contributing to improved patient outcomes.

Keywords: deep learning, liver segmentation, 3D slicer, image guided therapy, needle aspiration

Procedia PDF Downloads 48

Authors: Xiaoqi Jia, Qing Zhu, Hao Zhang, Su Yang

Abstract:

A gender recognition system is able to tell the gender of the given person through a few of frontal facial images. An effective gender recognition approach enables to improve the performance of many other applications, including security monitoring, human-computer interaction, image or video retrieval and so on. In this paper, we present an effective method for gender classification task in frontal facial images based on deep belief networks (DBNs), which can pre-train model and improve accuracy a little bit. Our experiments have shown that the pre-training method with DBNs for gender classification task is feasible and achieves a little improvement of accuracy on FERET and CAS-PEAL-R1 facial datasets.

Keywords: gender recognition, beep belief net-works, semi-supervised learning, greedy-layer wise RBMs

Procedia PDF Downloads 453

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 93

Authors: Zhiguo Yang, Xiangan Yue, Minglu Shao, Yue Yang, Rongjie Yan

Abstract:

It is difficult to realize deep profile control because of the small pore-throats and easy water channeling in low-permeability heterogeneous reservoir, and the traditional polymer microspheres have the contradiction between injection and plugging. In order to solve this contradiction, the controllable self-aggregating colloidal particles (CSA) containing amide groups on the surface of microspheres was prepared based on emulsion polymerization of styrene and acrylamide. The dispersed solution of CSA colloidal particles, whose particle size is much smaller than the diameter of pore-throats, was injected into the reservoir. When the microspheres migrated to the deep part of reservoir, , these CSA colloidal particles could automatically self-aggregate into large particle clusters under the action of the shielding agent and the control agent, so as to realize the plugging of the water channels. In this paper, the morphology, temperature resistance and self-aggregation properties of CSA microspheres were studied by transmission electron microscopy (TEM) and bottle test. The results showed that CSA microspheres exhibited heterogeneous core-shell structure, good dispersion, and outstanding thermal stability. The microspheres remain regular and uniform spheres at 100℃ after aging for 35 days. With the increase of the concentration of the cations, the self-aggregation time of CSA was gradually shortened, and the influence of bivalent cations was greater than that of monovalent cations. Core flooding experiments showed that CSA polymer microspheres have good injection properties, CSA particle clusters can effective plug the water channels and migrate to the deep part of the reservoir for profile control.

Keywords: heterogeneous reservoir, deep profile control, emulsion polymerization, colloidal particles, plugging characteristic

Procedia PDF Downloads 241

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 178

Authors: Thrivikraman Aswathi, S. Advaith

Abstract:

As there can be cases where the use of real data is somehow limited, such as when it is hard to get access to a large volume of real data, we need to go for synthetic data generation. This produces high-quality synthetic data while maintaining the statistical properties of a specific dataset. In the present work, a generative adversarial network (GAN) is trained to produce multivariate time series (MTS) data since the MTS is now being gathered more often in various real-world systems. Furthermore, the GAN-generated MTS data is fed into a transformer-based deep learning architecture that carries out the data categorization into predefined classes. Further, the model is evaluated across various distinct domains by generating corresponding MTS data.

Keywords: GAN, transformer, classification, multivariate time series

Procedia PDF Downloads 130

Authors: Heewon Jeong, Seongpyo Kim, Joon Ha Kim

Abstract:

Over the last few tens of years, the coastal regions of Korea have experienced red tide algal blooms, which are harmful and toxic to both humans and marine organisms due to their potential threat. It was accelerated owing to eutrophication by human activities, certain oceanic processes, and climate change. Previous studies have tried to monitoring and predicting the algae concentration of the ocean with the bio-optical algorithms applied to color images of the satellite. However, the accurate estimation of algal blooms remains problems to challenges because of the complexity of coastal waters. Therefore, this study suggests a new method to identify the concentration of red tide algal bloom from images of geostationary ocean color imager (GOCI) which are representing the water environment of the sea in Korea. The method employed GOCI images, which took the water leaving radiances centered at 443nm, 490nm and 660nm respectively, as well as observed weather data (i.e., humidity, temperature and atmospheric pressure) for the database to apply optical characteristics of algae and train deep learning algorithm. Convolution neural network (CNN) was used to extract the significant features from the images. And then artificial neural network (ANN) was used to estimate the concentration of algae from the extracted features. For training of the deep learning model, backpropagation learning strategy is developed. The established methods were tested and compared with the performances of GOCI data processing system (GDPS), which is based on standard image processing algorithms and optical algorithms. The model had better performance to estimate algae concentration than the GDPS which is impossible to estimate greater than 5mg/m³. Thus, deep learning model trained successfully to assess algae concentration in spite of the complexity of water environment. Furthermore, the results of this system and methodology can be used to improve the performances of remote sensing. Acknowledgement: This work was supported by the 'Climate Technology Development and Application' research project (#K07731) through a grant provided by GIST in 2017.

Keywords: deep learning, algae concentration, remote sensing, satellite

Procedia PDF Downloads 183

Authors: Mudavath Raju, Bhaskar Gugulothu, B. Rajendra Naik

Abstract:

The rapid advances in Very Large Scale Integration (VLSI) technology has resulted in the reduction of minimum feature size to sub-quarter microns and switching time in tens of picoseconds or even less. As a result, the degradation of high-speed digital circuits due to signal integrity issues such as coupling effects, clock feedthrough, crosstalk noise and delay uncertainty noise. Crosstalk noise in VLSI interconnects is a major concern and reduction in VLSI interconnect has become more important for high-speed digital circuits. It is the most effectively considered in Deep Sub Micron (DSM) and Ultra Deep Sub Micron (UDSM) technology. Increasing spacing in-between aggressor and victim line is one of the technique to reduce the crosstalk. Guard trace or shield insertion in-between aggressor and victim is also one of the prominent options for the minimization of crosstalk. In this paper, far end crosstalk noise is estimated with mutual inductance and capacitance RLC interconnect model. Also investigated the extent of crosstalk in capacitive and inductively coupled interconnects to minimizes the same through shield insertion technique.

Keywords: VLSI, interconnects, signal integrity, crosstalk, shield insertion, guard trace, deep sub micron

Procedia PDF Downloads 185

Authors: Yooseo Pang, Jongwoong Choi, Yong Cho, Yongchae Jeong

Abstract:

Climate crisis, such as environmental problems related to energy supply, is getting emerged issues, so the use of renewable energy is essentially required to solve these problems, which are mainly managed by the Paris Agreement, the international treaty on climate change. The government of the Republic of Korea announced that the key long-term goal for a low-carbon strategy is “Carbon neutrality by 2050”. It is focused on the role of the internet data centers (IDC) in which large amounts of data, such as artificial intelligence (AI) and big data as an impact of the 4th industrial revolution, are managed. The demand for the cooling system market for IDC was about 9 billion US dollars in 2020, and 15.6% growth a year is expected in Korea. It is important to control the temperature in IDC with an efficient air conditioning system, so hydrothermal energy is one of the best options for saving energy in the cooling system. In order to save energy and optimize the operating conditions, it has been considered to apply ‘the dam deep water air conditioning system. Deep water at a specific level from the dam can supply constant water temperature year-round. It will be tested & analyzed the amount of energy saving with a pilot plant that has 100RT cooling capacity. Also, a target of this project is 1.2 PUE (Power Usage Effectiveness) which is the key parameter to check the efficiency of the cooling system.

Keywords: hydrothermal energy, HVAC, internet data center, free-cooling

Procedia PDF Downloads 81

Authors: Josua Sihotang

Abstract:

Jakarta Capital Special Region is the province that densely populated with rapidly growing infrastructure but less attention for the environmental condition. This makes some social problem happened like lack of clean water supply. Shallow groundwater and river water condition that has contaminated make the layer of deep water carrier (aquifer) should be done. This research aims to provide the people insight about deep groundwater potential and to determine the depth, location, and quality where the aquifer can be found in Jakarta’s area, particularly Kapuk-Cengkareng’s people. This research was conducted by geophysical method namely Well Logging Analysis. Well Logging is the geophysical method to know the subsurface lithology with the physical characteristic. The observation in this research area was conducted with several well devices that is Spontaneous Potential Log (SP Log), Resistivity Log, and Gamma Ray Log (GR Log). The first devices well is SP log which is work by comprising the electrical potential difference between the electrodes on the surface with the electrodes that is contained in the borehole and rock formations. The second is Resistivity Log, used to determine both the hydrocarbon and water zone based on their porosity and permeability properties. The last is GR Log, work by identifying radioactivity levels of rocks which is containing elements of thorium, uranium, or potassium. The observation result is curve-shaped which describes the type of lithological coating in subsurface. The result from the research can be interpreted that there are four of the deep groundwater layer zone with different quality. The good groundwater layer can be found in layers with good porosity and permeability. By analyzing the curves, it can be known that most of the layers which were found in this wellbore are clay stone with low resistivity and high gamma radiation. The resistivity value of the clay stone layers is about 2-4 ohm-meter with 65-80 Cps gamma radiation. There are several layers with high resistivity value and low gamma radiation (sand stone) that can be potential for being an aquifer. This is reinforced by the sand layer with a right-leaning SP log curve proving that this layer is permeable. These layers have 4-9 ohm-meter resistivity value with 40-65 Cps gamma radiation. These are mostly found as fresh water aquifer.

Keywords: aquifer, deep groundwater potential, well devices, well logging analysis

Procedia PDF Downloads 252

Authors: Bryan Crompton, Daniel Giger, Tanay Mehta, Apurva Mody

Abstract:

The task of classifying radio frequency (RF) signals has seen recent success in employing deep neural network models. In this work, we present a combined signal processing and machine learning approach to signal classification for cochannel anomalous signals. The power spectral density and cyclostationary signal processing features of a captured signal are computed and fed into a neural net to produce a classification decision. Our combined signal preprocessing and machine learning approach allows for simpler neural networks with fast training times and small computational resource requirements for inference with longer preprocessing time.

Keywords: signal processing, machine learning, cyclostationary signal processing, signal classification

Procedia PDF Downloads 107