Search results for: deep q-network

Authors: Xueming Xu, Jiahao Liu, Jichao Li, Kewei Yang, Minghao Li, Bingfeng Ge

Abstract:

A combat system-of-systems (CSoS) comprises various types of functional combat entities that interact to meet corresponding task requirements in the present and future. Enhancing the resilience of CSoS holds significant military value in optimizing the operational planning process, improving military survivability, and ensuring the successful completion of operational tasks. Accordingly, this research proposes an integrated framework called CSoS resilience enhancement (CSoSRE) to enhance the resilience of CSoS from a recovery perspective. Specifically, this research presents a two-phase resilience optimization model to define a resilience optimization objective for CSoS. This model considers not only task baseline, recovery cost, and recovery time limit but also the characteristics of emergency recovery and comprehensive recovery. Moreover, the research extends it from the deterministic case to the stochastic case to describe the uncertainty in the recovery process. Based on this, a resilience-oriented recovery optimization method based on deep reinforcement learning (RRODRL) is proposed to determine a set of entities requiring restoration and their recovery sequence, thereby enhancing the resilience of CSoS. This method improves the deep Q-learning algorithm by designing a discount factor that adapts to changes in CSoS state at different phases, simultaneously considering the network’s structural and functional characteristics within CSoS. Finally, extensive experiments are conducted to test the feasibility, effectiveness and superiority of the proposed framework. The obtained results offer useful insights for guiding operational recovery activity and designing a more resilient CSoS.

Keywords: combat system-of-systems, resilience optimization model, recovery optimization method, deep reinforcement learning, certainty and uncertainty

Procedia PDF Downloads 16

Authors: Beatriz Lafuente Alcázar, Yash Wani, Amit J. Nimunkar

Abstract:

Cardiovascular Diseases (CVDs) are the leading cause of death globally, and around 80% of sudden cardiac deaths are due to arrhythmias or irregular heartbeats. The majority of these pathologies are revealed by either short-term or long-term alterations in the electrocardiogram (ECG) morphology. The ECG is the main diagnostic tool in cardiology. It is a non-invasive, pain free procedure that measures the heart’s electrical activity and that allows the detecting of abnormal rhythms and underlying conditions. A cardiologist can diagnose a wide range of pathologies based on ECG’s form alterations, but the human interpretation is subjective and it is contingent to error. Moreover, ECG records can be quite prolonged in time, which can further complicate visual diagnosis, and deeply retard disease detection. In this context, deep learning methods have risen as a promising strategy to extract relevant features and eliminate individual subjectivity in ECG analysis. They facilitate the computation of large sets of data and can provide early and precise diagnoses. Therefore, the cardiology field is one of the areas that can most benefit from the implementation of deep learning algorithms. In the present study, a deep learning algorithm is trained following a novel approach, using a combination of different databases as the training set. The goal of the algorithm is to achieve the detection of R-peaks in ECG signals. Its performance is further evaluated in ECG signals with different origins and features to test the model’s ability to generalize its outcomes. Performance of the model for detection of R-peaks for clean and noisy ECGs is presented. The model is able to detect R-peaks in the presence of various types of noise, and when presented with data, it has not been trained. It is expected that this approach will increase the effectiveness and capacity of cardiologists to detect divergences in the normal cardiac activity of their patients.

Keywords: arrhythmia, deep learning, electrocardiogram, machine learning, R-peaks

Procedia PDF Downloads 186

Authors: Nan Deng, Zhenqiu Liu

Abstract:

Thousands of patients with metastatic tumors were diagnosed with cancers of unknown primary sites each year. The inability to identify the primary cancer site may lead to inappropriate treatment and unexpected prognosis. Nowadays, a large amount of genomics and transcriptomics cancer data has been generated by next-generation sequencing (NGS) technologies, and The Cancer Genome Atlas (TCGA) database has accrued thousands of human cancer tumors and healthy controls, which provides an abundance of resource to differentiate cancer types. Meanwhile, deep convolutional neural networks (CNNs) have shown high accuracy on classification among a large number of image object categories. Here, we utilize 25 cancer primary tumors and 3 normal tissues from TCGA and convert their RNA-Seq gene expression profiling to color images; train, validate and test a CNN classifier directly from these images. The performance result shows that our CNN classifier can archive >80% test accuracy on most of the tumors and normal tissues. Since the gene expression pattern of distant metastases is similar to their primary tumors, the CNN classifier may provide a potential computational strategy on identifying the unknown primary origin of metastatic cancer in order to plan appropriate treatment for patients.

Keywords: bioinformatics, cancer, convolutional neural network, deep leaning, gene expression pattern

Procedia PDF Downloads 299

Authors: Barham J. Nareeman, Ilham I. Mohammed

Abstract:

Excavations in urban developed area are generally supported by deep excavation walls such as; diaphragm wall, bored piles, soldier piles and sheet piles. In some cases, these walls may be braced by internal braces or tie back anchors. Tie back anchors are by far the predominant method for wall support, the large working space inside the excavation provided by a tieback anchor system has a significant construction advantage. This paper aims to analyze a deep excavation bracing system of contiguous pile wall braced by pre-stressed tie back anchors, which is a part of a huge residential building project, located in Turkey/Gaziantep province. The contiguous pile wall will be constructed with a length of 270 m that consists of 285 piles, each having a diameter of 80 cm, and a center to center spacing of 95 cm. The deformation analysis was carried out by a finite element analysis tool using PLAXIS. In the analysis, beam element method together with an elastic perfect plastic soil model and Soil Hardening Model was used to design the contiguous pile wall, the tieback anchor system, and the soil. The two soil clusters which are limestone and a filled soil were modelled with both Hardening soil and Mohr Coulomb models. According to the basic design, both soil clusters are modelled as drained condition. The simulation results show that the maximum horizontal movement of the walls and the maximum settlement of the ground are convenient with 300 individual case histories which are ranging between 1.2mm and 2.3mm for walls, and 15mm and 6.5mm for the settlements. It was concluded that tied-back contiguous pile wall can be satisfactorily modelled using Hardening soil model.

Keywords: deep excavation, finite element, pre-stressed tie back anchors, contiguous pile wall, PLAXIS, horizontal deflection, ground settlement

Procedia PDF Downloads 255

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 268

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 154

Authors: S. Khurram, N. Mubashar

Abstract:

The paper examines, through the lens of Postcolonial Theory, how natives resist and react in Derrek Walcott’s “Dream on Monkey Mountain”. It aims at how natives, for being ‘recognized and reformed’, mimic and adapt the white’s ways of living. It also focuses how Walcott expresses natives’ reaction when they cannot construct their identity. Moreover, the paper exploits the Homi. K Bhaba’s concept of Mimicry and Berry’s concepts of Hybridity to explain Caribbean native’s plight. Furthermore, it bring forth Walcott’s deep insight into the psychology of the Caribbean natives. He digs deep into the colonial discourse to reconstruct post-colonial identity and he, as a post-colonial writer, does so by deconstructing colonial ideology of racism by resisting against it.

Keywords: postcolonial theory, mimicry, hybridity, reaction

Procedia PDF Downloads 182

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 114

Authors: Khoi A. Nguyen, Rodney A. Stewart, Hong Zhang

Abstract:

‘Water-related energy’ is energy use which is directly or indirectly influenced by changes to water use. Informatics applying a range of mathematical, statistical and rule-based approaches can be used to reveal important information on demand from the available data provided at second, minute or hourly intervals. This study aims to combine these two concepts to improve the current water end use disaggregation problem through applying a wide range of most advanced pattern recognition techniques to analyse the concurrent high-resolution water-energy consumption data. The obtained results have shown that recognition accuracies of all end-uses have significantly increased, especially for mechanised categories, including clothes washer, dishwasher and evaporative air cooler where over 95% of events were correctly classified.

Keywords: deep learning network, smart metering, water end use, water-energy data

Procedia PDF Downloads 306

Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang

Abstract:

Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.

Keywords: CNN, classification, deep learning, GAN, Resnet50

Procedia PDF Downloads 88

Authors: Bambang Antoro, Lasito Soebari, Geoffrey de Jong, Fernandy Meiriyanto, Michael Siahaan, Eko Wibowo, Pormando Silalahi, Ruswanto, Adi Budirumantyo

Abstract:

The Ertsberg East Skarn System (EESS) is located in the Ertsberg Mining District, Papua, Indonesia. EESS is a sub-vertical zone of copper-gold mineralization hosted in both diorite (vein-style mineralization) and skarn (disseminated and vein style mineralization). Deep Mill Level Zone (DMLZ) is a mining zone in the lower part of East Ertsberg Skarn System (EESS) that product copper and gold. The Deep Mill Level Zone deposit is located below the Deep Ore Zone deposit between the 3125m to 2590m elevation, measures roughly 1,200m in length and is between 350 and 500m in width. DMLZ planned start mined on Q2-2015, being mined at an ore extraction rate about 60,000 tpd by the block cave mine method (the block cave contain 516 Mt). Mineralization and associated hydrothermal alteration in the DMLZ is hosted and enclosed by a large stock (The Main Ertsberg Intrusion) that is barren on all sides and above the DMLZ. Late porphyry dikes that cut through the Main Ertsberg Intrusion are spatially associated with the center of the DMLZ hydrothermal system. DMLZ orebody hosted in diorite and skarn, both dominantly by vein style mineralization. Percentage Material Mined at DMLZ compare with current Reserves are diorite 46% (with 0.46% Cu; 0.56 ppm Au; and 0.83% EqCu); Skarn is 39% (with 1.4% Cu; 0.95 ppm Au; and 2.05% EqCu); Hornfels is 8% (with 0.84% Cu; 0.82 ppm Au; and 1.39% EqCu); and Marble 7 % possible mined waste. Correlation between Ertsberg intrusion, major structure, and vein style mineralization is important to determine characteristic orebody in DMLZ Mine. Generally Deep Mill Level Zone has 2 type of vein filling mineralization from both hosted (diorite and skarn), in diorite hosted the vein system filled by chalcopyrite-bornite-quartz and pyrite, in skarn hosted the vein filled by chalcopyrite-bornite-pyrite and magnetite without quartz. Based on orientation the stockwork vein at diorite hosted and shallow vein in skarn hosted was generally NW-SE trending and NE-SW trending with shallow-moderate dipping. Deep Mill Level Zone control by two main major faults, geologist founded and verified local structure between major structure with NW-SE trending and NE-SW trending with characteristics slickenside, shearing, gauge, water-gas channel, and some has been re-healed.

Keywords: copper-gold, DMLZ, skarn, structure

Procedia PDF Downloads 501

Authors: Tesfaw Belayneh Abebe

Abstract:

Integrating low-altitude earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN) with the assistance of reconfigurable intelligent surfaces (RIS), we investigate the problem of how to enhance throughput through integrated LEO satellites and UAVs with the assistance of RIS. We propose a method to jointly optimize the associations with the LEO satellite, the 3D trajectory of the UAV, and the phase shifts of the RIS to maximize communication throughput for RIS-assisted integrated LEO satellite and UAV-enabled wireless communications, which is challenging due to the time-varying changes in the position of the LEO satellite, the high mobility of UAVs, an enormous number of possible control actions, and also the large number of RIS elements. Utilizing a multi-agent double deep Q-network (MADDQN), our approach dynamically adjusts LEO satellite association, UAV positioning, and RIS phase shifts. Simulation results demonstrate that our method significantly outperforms baseline strategies in maximizing throughput. Lastly, thanks to the integrated network and the RIS, the proposed scheme achieves up to 65.66x higher peak throughput and 25.09x higher worst-case throughput.

Keywords: integrating low-altitude earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN), reconfigurable intelligent surfaces (RIS), multi-agent double deep Q-network (MADDQN)

Procedia PDF Downloads 48

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 78

Authors: Chien-kuo Chang, Bo-wei Wu, Yi-yun Tang, Min-chiu Wu

Abstract:

This paper proposes a power equipment diagnosis system based on partial discharge (PD), which is characterized by increasing the readability of experimental data and the convenience of operation. This system integrates a variety of analysis programs of different data formats and different programming languages and then establishes a set of interfaces that can follow and expand the structure, which is also helpful for subsequent maintenance and innovation. This study shows a case of using the developed Convolutional Neural Networks (CNN) to integrate with this system, using the designed model architecture to simplify the complex training process. It is expected that the simplified training process can be used to establish an adaptive deep learning experimental structure. By selecting different test data for repeated training, the accuracy of the identification system can be enhanced. On this platform, the measurement status and partial discharge pattern of each equipment can be checked in real time, and the function of real-time identification can be set, and various training models can be used to carry out real-time partial discharge insulation defect identification and insulation state diagnosis. When the electric power equipment entering the dangerous period, replace equipment early to avoid unexpected electrical accidents.

Keywords: partial discharge, convolutional neural network, partial discharge analysis platform, adaptive deep learning

Procedia PDF Downloads 78

Authors: Christopher Baiyegunhi, Oswald Gwavava

Abstract:

The location/source of the Beattie magnetic anomaly (BMA) and interconnectivity of geologic structures at depth have been a topic of investigation for over 30 years. Up to now, no relationship between geological structures (interconnectivity of dolerite intrusions) at depth has been established. Therefore, the environmental impact of fracking the Karoo for shale gas could not be assessed despite the fact that dolerite dykes are groundwater localizers in the Karoo. In this paper, we shed more light to the unanswered questions concerning the possible location of the source of the BMA, the connectivity of geologic structures like dolerite dykes and sills at depth and this relationship needs to be established before the tectonic evolution of the Karoo basin can be fully understood and related to fracking of the Karoo for shale gas. The result of the magnetic investigation and modelling of four gravity profiles that crosses the BMA in the study area reveals that the anomaly, which is part of the Beattie magnetic anomaly tends to divide into two anomalies and continue to trend in an NE-SW direction, the dominant gravity signatures is of long wavelength that is due to a deep source/interface inland and shallows towards the coast, the average depth to the top of the shallow and deep magnetic sources was estimated to be approximately 0.6 km and 15 km, respectively. The BMA become stronger with depth which could be an indication that the source(s) is deep possibly a buried body in the basement. The bean-shaped anomaly also behaves in a similar manner like the BMA thus it could possibly share the same source(s) with the BMA.

Keywords: Beattie magnetic anomaly, magnetic sources, modelling, Karoo Basin

Procedia PDF Downloads 554

Authors: Hasan Yalcin, Tugba Dursun Capar

Abstract:

Deep-fat frying causes desirable as well as undesirable changes in oil and potato, and changes the quality of the oil by hydrolysis, oxidation, and polymerization. The main objective of the present study was to investigate the pre-drying effects on the quality of both frying oil and potatoes. Prior to frying, potato slices (10 mm x10 mm x 30 mm) were air- dried at 60°C for 15, 30, 45, 60, 90, and 120 mins., respectively. Potato slices without the pre-drying treatment were considered as the control variable. Potato slices were fried in sunflower oil at 180°C for 5, 10, and 13 mins. The deep-frying experiments were repeated five times using the new potato slices in the same oil without oil replenishment. Samples of the fresh oil, together with those sampled at the end of successive frying operations (1th, 3th and 5th) were removed and analysed. Moisture content, colour and oil intake of the potato and colour, peroxide value (PV), free fatty acid (FFA), fatty acid composition and viscosity of the used oil were evaluated. The effect of frying time was also examined. Results show that pre-drying treatment had a significant effect on physicochemical properties and colour parameters of potato slices and frying oil. Pre-drying considerably decreased the oil absorption. The lowest oil absorption was found for the treatment that was pre-dried for 120, and fried for 5 min. The FFA levels decreased permanently for each pre-treatment throughout the frying period. All the pre-drying treatments had reached their maximum levels of FFA by the end of the frying procedures. The PV of the control and 60 min pre-dried sample decreased after the third frying. However, the PV of other samples increased constantly throughout the frying periods. Lastly, pre-drying did not affect the fatty acid composition of frying oil considerably when compared against previously unused oil.

Keywords: air-drying, deep-fat frying, moisture content oil uptake, quality

Procedia PDF Downloads 308

Authors: A. Sekhar, N. Ramakrishna Raju

Abstract:

This paper is a result of ground improvement using deep vibro techniques with combination of sand and stone columns performed on a highly liquefaction susceptible site (70 to 80% sand strata and balance silt) with low bearing capacities due to high settlements located (earth quake zone V as per IS code) at Madhepura, Bihar state in northern part of India. Initially, it was envisaged with bored cast in-situ/precast piles, stone/sand columns. However, after detail analysis to address both liquefaction and improve bearing capacities simultaneously, it was analyzed the deep vibro techniques with combination of sand and stone columns is excellent solution for given site condition which may be first time in India. First after detail soil investigation, pre eCPT test was conducted to evaluate the potential depth of liquefaction to densify silty sandy soils to improve factor of safety against liquefaction. Then trail test were being carried out at site by deep vibro compaction technique with sand and stone columns combination with different spacings of columns in triangular shape with different timings during each lift of vibro up to ground level. Different spacings and timing was done to obtain the most effective spacing and timing with vibro compaction technique to achieve maximum densification of saturated loose silty sandy soils uniformly for complete treated area. Then again, post eCPT test and plate load tests were conducted at all trail locations of different spacings and timing of sand and stone columns to evaluate the best results for obtaining the required factor of safety against liquefaction and the desired bearing capacities with reduced settlements for construction of industrial structures. After reviewing these results, it was noticed that the ground layers are densified more than the expected with improved factor of safety against liquefaction and achieved good bearing capacities for a given settlements as per IS codal provisions. It was also worked out for cost-effectiveness of lightly loaded single storied structures by using deep vibro technique with sand column avoiding stone. The results were observed satisfactory for resting the lightly loaded foundations. In this technique, the most important is to mitigating liquefaction with improved bearing capacities and reduced settlements to acceptable limits as per IS: 1904-1986 simultaneously up to a depth of 19M. To our best knowledge it was executed first time in India.

Keywords: ground improvement, deep vibro techniques, liquefaction, bearing capacity, settlement

Procedia PDF Downloads 197

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Parisa Mansour

Abstract:

The coronavirus disease 2019 (COVID-19) was discovered and rapidly spread to various countries around the world since the end of 2019. Computed tomography (CT) images have been used as an important alternative to the time-consuming RT. PCR test. However, manual segmentation of CT images alone is a major challenge as the number of suspected cases increases. Thus, accurate and automatic segmentation of COVID-19 infections is urgently needed. Because the imaging features of the COVID-19 infection are different and similar to the background, existing medical image segmentation methods cannot achieve satisfactory performance. In this work, we try to build a deep convolutional neural network adapted for the segmentation of chest CT images with COVID-19 infections. First, we maintain a large and novel chest CT image database containing 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of an infected lung can be improved by global intensity adjustment, we introduce a feature variable block into the proposed deep CNN, which adjusts the global features of features to segment the COVID-19 infection. The proposed PV array can effectively and adaptively improve the performance of functions in different cases. We combine features of different scales by proposing a progressive atrocious space pyramid fusion scheme to deal with advanced infection regions with various aspects and shapes. We conducted experiments on data collected in China and Germany and showed that the proposed deep CNN can effectively produce impressive performance.

Keywords: chest, COVID-19, chest Image, coronavirus, CT image, chest CT

Procedia PDF Downloads 57

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 87

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 142

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 195

Authors: Mojebullah Wahidy, Murat Olgun

Abstract:

In this study, four different types of cement are used to investigate the permeability of DMC (Deep Mixing Column) in the clay. The clay used in this research is in the kaolin group, and the types of cement are; CEM I 42.5.R. normal portland cement, CEM II/A-M (P-L) pozzolan doped cement, CEM III/A 42.5 N blast furnace slag cement and DMFC-800 fine-grained portland cement. Firstly, some rheological tests are done on every cement, and a 0.9 water/cement ratio is selected as the appropriate ratio. This ratio is used to prepare the small-scale DMCs for all types of cement with %6, %9, %12, and %15, which are determined as the dry weight of the clay. For all the types of cement, three samples were prepared in every percentage and were kept on curing for 7, 14, and 28 days for permeability tests. As a result of the small-scale DMCs, permeability tests, a %12 selected for big-scale DMCs. A total of five big scales DMC were prepared by using a %12-cement and were kept for 28 days curing for permeability tests. The results of the permeability tests show that by increasing the cement percentage and curing time of all DMCs, the permeability coefficient (k) is decreased. Despite variable results in different cement ratios and curing time in general, samples treated by DMFC-800 fine-grained cement have the lowest permeability coefficient. Samples treated with CEM II and CEM I cement types were the second and third lowest permeable samples. The highest permeability coefficient belongs to the samples that were treated with CEM III cement type.

Keywords: deep mixing column, rheological test, DMFC-800, permeability test

Procedia PDF Downloads 78

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 114

Authors: Swapnil A. Padvi, Dipak S. Dalal

Abstract:

The chemistry of tetrazoles has been grown tremendously in the past few years because tetrazoles are important and useful class of heterocyclic compounds which have a widespread application such as anticancer, antimicrobial, analgesics, antibacterial, antifungal, antihypertensive, and anti-allergic drugs in medicinal chemistry. Furthermore, tetrazoles have application in material sciences as explosives, rocket propellants, and in information recording systems. In addition to this, they have a wide range of application in coordination chemistry as a ligand. Deep eutectic solvents (DES) have emerged over the current decade as a novel class of green reaction media and applied in various fields of sciences because of their unique physical and chemical properties similar to the ionic liquids such as low vapor pressure, non-volatility, high thermal stability and recyclability. In addition, the reactants of DES are cheaply available, low-toxic, and biodegradable, which makes them predominantly required for large-scale applications effectively in industrial production. Herein we report the [2+3] cycloaddition reaction of organic nitriles with sodium azide affords the corresponding 5-substituted 1H-tetrazoles in six different types of choline chloride based deep eutectic solvents under mild reaction condition. Choline chloride: ZnCl2 (1:2) showed the best results for the synthesis of 5-substituted 1 H-tetrazoles. This method reduces the disadvantages such as: the use of toxic metals and expensive reagents, drastic reaction conditions and the presence of dangerous hydrazoic acid. The approach provides environment-friendly, short reaction times, good to excellent yields; safe process and simple workup make this method an attractive and useful contribution to present green organic synthesis of 5-substituted-1H-tetrazoles. All synthesized compounds were characterized by IR, 1H NMR, 13C NMR and Mass spectroscopy. DES can be recovered and reused three times with very little loss in activity.

Keywords: click chemistry, choline chloride, green chemistry, deep eutectic solvent, tetrazoles

Procedia PDF Downloads 231

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 11

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 104

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 66

Authors: Yong Chen

Abstract:

To understand the detailed molecular mechanisms of memory formation in engram cells is one of the most fundamental questions in neuroscience. Recent single-cell RNA-seq (scRNA-seq) and single-nucleus RNA-seq (snRNA-seq) techniques have allowed us to explore the sparsely activated engram ensembles, enabling access to the molecular mechanisms that underlie experience-dependent memory formation and consolidation. However, the absence of specific and powerful computational methods to detect memory-related genes (modules) and their regulatory relationships in the sc/snRNA-seq datasets has strictly limited the analysis of underlying mechanisms and memory coding principles in mammalian brains. Here, we present a deep-learning method named SCENTBOX, to detect memory-related gene modules and causal regulatory relationships among themfromsc/snRNA-seq datasets. SCENTBOX first constructs codifferential expression gene network (CEGN) from case versus control sc/snRNA-seq datasets. It then detects the highly correlated modules of differential expression genes (DEGs) in CEGN. The deep network embedding and attention-based convolutional neural network strategies are employed to precisely detect regulatory relationships among DEG genes in a module. We applied them on scRNA-seq datasets of TRAP; Ai14 mouse neurons with fear memory and detected not only known memory-related genes, but also the modules and potential causal regulations. Our results provided novel regulations within an interesting module, including Arc, Bdnf, Creb, Dusp1, Rgs4, and Btg2. Overall, our methods provide a general computational tool for processing sc/snRNA-seq data from case versus control studie and a systematic investigation of fear-memory-related gene modules.

Keywords: sc/snRNA-seq, memory formation, deep learning, gene module, causal inference

Procedia PDF Downloads 120

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 170