Search results for: Deep learning based segmentation

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 71

Authors: Edward Holupka, John Rossman, Tye Morancy, Joseph Aronovitz, Irving Kaplan

Abstract:

A common modality for the treatment of early stage prostate cancer is the implantation of radioactive seeds directly into the prostate. The radioactive seeds are positioned inside the prostate to achieve optimal radiation dose coverage to the prostate. These radioactive seeds are positioned inside the prostate using Transrectal ultrasound imaging. Once all of the planned seeds have been implanted, two dimensional transaxial transrectal ultrasound images separated by 2 mm are obtained through out the prostate, beginning at the base of the prostate up to and including the apex. A common deep neural network, called DetectNet was trained to automatically determine the position of the implanted radioactive seeds within the prostate under ultrasound imaging. The results of the training using 950 training ultrasound images and 90 validation ultrasound images. The commonly used metrics for successful training were used to evaluate the efficacy and accuracy of the trained deep neural network and resulted in an loss_bbox (train) = 0.00, loss_coverage (train) = 1.89e-8, loss_bbox (validation) = 11.84, loss_coverage (validation) = 9.70, mAP (validation) = 66.87%, precision (validation) = 81.07%, and a recall (validation) = 82.29%, where train and validation refers to the training image set and validation refers to the validation training set. On the hardware platform used, the training expended 12.8 seconds per epoch. The network was trained for over 10,000 epochs. In addition, the seed locations as determined by the Deep Neural Network were compared to the seed locations as determined by a commercial software based on a one to three months after implant CT. The Deep Learning approach was within \strikeout off\uuline off\uwave off2.29\uuline default\uwave default mm of the seed locations determined by the commercial software. The Deep Learning approach to the determination of radioactive seed locations is robust, accurate, and fast and well within spatial agreement with the gold standard of CT determined seed coordinates.

Keywords: prostate, deep neural network, seed implant, ultrasound

Procedia PDF Downloads 182

Authors: Ethan James

Abstract:

Over one billion people worldwide suffer from some level of vision loss or blindness as a result of progressive retinal diseases. Many patients, particularly in developing areas, are incorrectly diagnosed or undiagnosed whatsoever due to unconventional diagnostic tools and screening methods. Artificial intelligence (AI) based on deep learning (DL) convolutional neural networks (CNN) have recently gained a high interest in ophthalmology for its computer-imaging diagnosis, disease prognosis, and risk assessment. Optical coherence tomography (OCT) is a popular imaging technique used to capture high-resolution cross-sections of retinas. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography, and visual fields, achieving robust classification performance in the detection of various retinal diseases including macular degeneration, diabetic retinopathy, and retinitis pigmentosa. However, there is no complete diagnostic model to analyze these retinal images that provide a diagnostic accuracy above 90%. Thus, the purpose of this project was to develop an AI model that utilizes machine learning techniques to automatically diagnose specific retinal diseases from OCT scans. The algorithm consists of neural network architecture that was trained from a dataset of over 20,000 real-world OCT images to train the robust model to utilize residual neural networks with cyclic pooling. This DL model can ultimately aid ophthalmologists in diagnosing patients with these retinal diseases more quickly and more accurately, therefore facilitating earlier treatment, which results in improved post-treatment outcomes.

Keywords: artificial intelligence, deep learning, imaging, medical devices, ophthalmic devices, ophthalmology, retina

Procedia PDF Downloads 163

Authors: Wanchalerm Patanacharoenwong, Panaya Sudta, Prachya Bumrungkun

Abstract:

The paper focuses on the development of a system that combines Internet of Things (IoT) technologies and deep learning algorithms for anomaly detection in residential Electric Vehicle (EV) charging in smart cities. With the increasing number of EVs, ensuring efficient and reliable charging systems has become crucial. The aim of this research is to develop an integrated IoT and deep learning system for detecting anomalies in residential EV charging and enhancing EV load profiling and event detection in smart cities. This approach utilizes IoT devices equipped with infrared cameras to collect thermal images and household EV charging profiles from the database of Thailand utility, subsequently transmitting this data to a cloud database for comprehensive analysis. The methodology includes the use of advanced deep learning techniques such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) algorithms. IoT devices equipped with infrared cameras are used to collect thermal images and EV charging profiles. The data is transmitted to a cloud database for comprehensive analysis. The researchers also utilize feature-based Gaussian mixture models for EV load profiling and event detection. Moreover, the research findings demonstrate the effectiveness of the developed system in detecting anomalies and critical profiles in EV charging behavior. The system provides timely alarms to users regarding potential issues and categorizes the severity of detected problems based on a health index for each charging device. The system also outperforms existing models in event detection accuracy. This research contributes to the field by showcasing the potential of integrating IoT and deep learning techniques in managing residential EV charging in smart cities. The system ensures operational safety and efficiency while also promoting sustainable energy management. The data is collected using IoT devices equipped with infrared cameras and is stored in a cloud database for analysis. The collected data is then analyzed using RNN, LSTM, and feature-based Gaussian mixture models. The approach includes both EV load profiling and event detection, utilizing a feature-based Gaussian mixture model. This comprehensive method aids in identifying unique power consumption patterns among EV owners and outperforms existing models in event detection accuracy. In summary, the research concludes that integrating IoT and deep learning techniques can effectively detect anomalies in residential EV charging and enhance EV load profiling and event detection accuracy. The developed system ensures operational safety and efficiency, contributing to sustainable energy management in smart cities.

Keywords: cloud computing framework, recurrent neural networks, long short-term memory, Iot, EV charging, smart grids

Procedia PDF Downloads 49

Authors: Hae-Yeoun Lee

Abstract:

Quantification of cardiac function is performed by calculating blood volume and ejection fraction in routine clinical practice. However, these works have been performed by manual contouring,which requires computational costs and varies on the observer. In this paper, an automatic left ventricle segmentation algorithm on cardiac magnetic resonance images (MRI) is presented. Using knowledge on cardiac MRI, a K-mean clustering technique is applied to segment blood region on a coil-sensitivity corrected image. Then, a graph searching technique is used to correct segmentation errors from coil distortion and noises. Finally, blood volume and ejection fraction are calculated. Using cardiac MRI from 15 subjects, the presented algorithm is tested and compared with manual contouring by experts to show outstanding performance.

Keywords: cardiac MRI, graph searching, left ventricle segmentation, K-means clustering

Procedia PDF Downloads 390

Authors: Abder-Rahman Ali, Adélaïde Albouy-Kissi, Manuel Grand-Brochier, Viviane Ladan-Marcus, Christine Hoeffl, Claude Marcus, Antoine Vacavant, Jean-Yves Boire

Abstract:

In this paper, we present a new segmentation approach for focal liver lesions in contrast enhanced ultrasound imaging. This approach, based on a two-cluster Fuzzy C-Means methodology, considers type-II fuzzy sets to handle uncertainty due to the image modality (presence of speckle noise, low contrast, etc.), and to calculate the optimum inter-cluster threshold. Fine boundaries are detected by a local recursive merging of ambiguous pixels. The method has been tested on a representative database. Compared to both Otsu and type-I Fuzzy C-Means techniques, the proposed method significantly reduces the segmentation errors.

Keywords: defuzzification, fuzzy clustering, image segmentation, type-II fuzzy sets

Procedia PDF Downloads 468

Authors: Parveen Kumar

Abstract:

The cope the rapid change of technology and to control the ephemeral rate of information generation, librarians along with their professional colleagues need to equip themselves as per the requirement of the electronic information society. E-learning is purely based on computer and communication technologies. The terminologies like computer based learning. It is the delivery of content via all electronic media through internet, internet, Extranets television broadcast, CD-Rom documents, etc. E-learning poses lot of issues in the transformation of literature or knowledge from the conventional medium to ICT based format and web based services.

Keywords: e-learning, digital libraries, online learning, electronic information society

Procedia PDF Downloads 497

Authors: Vera G. Dianova, Lori P. Montross, Charles M. Burke

Abstract:

In the digital age, the widespread and frequently excessive use of mobile phones amongst university students is recognized as a significant distractor which interferes with their ability to enter a deep state of concentration during studies and diminishes their prospects of experiencing the enjoyable and instrumental state of flow, as defined and described by psychologist M. Csikszentmihalyi. This study has targeted 50 university students with the aim of teaching them to cultivate their ability to engage in deep work and to attain the state of flow, fostering more effective and enjoyable learning experiences. Prior to the start of the intervention, all participating students completed a comprehensive survey based on a variety of validated scales assessing their inclination toward lifelong learning, frequency of flow experiences during study, frustration tolerance, sense of agency, as well as their love of learning and daily time devoted to non-academic mobile phone activities. Several days after this initial assessment, students received a 90-minute lecture on the principles of flow and deep work, accompanied by a critical discourse on the detrimental effects of excessive mobile phone usage. They were encouraged to practice deep work and strive for frequent flow states throughout the semester. Subsequently, students submitted weekly surveys, including the 10-item CORE Dispositional Flow Scale, a 3-item agency scale and furthermore disclosed their average daily hours spent on non-academic mobile phone usage. As a final step, at the end of the semester students engaged in reflective report writing, sharing their experiences and evaluating the intervention's effectiveness. They considered alterations in their love of learning, reflected on the implications of their mobile phone usage, contemplated improvements in their tolerance for boredom and perseverance in complex tasks, and pondered the concept of lifelong learning. Additionally, students assessed whether they actively took steps towards managing their recreational phone usage and towards improving their commitment to becoming lifelong learners. Employing a mixed-methods approach our study offers insights into the dynamics of concentration, flow, mobile phone usage and attitudes towards learning among undergraduate and graduate university students. The findings of this study aim to promote profound contemplation, on the part of both students and instructors, on the rapidly evolving digital-age higher education environment. In an era defined by digital and AI advancements, the ability to concentrate, to experience the state of flow, and to love learning has never been more crucial. This study underscores the significance of addressing mobile phone distractions and providing strategies for cultivating deep concentration. The insights gained can guide educators in shaping effective learning strategies for the digital age. By nurturing a love for learning and encouraging lifelong learning, educational institutions can better prepare students for a rapidly changing labor market, where adaptability and continuous learning are paramount for success in a dynamic career landscape.

Keywords: deep work, flow, higher education, lifelong learning, love of learning

Procedia PDF Downloads 57

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

World-wide spread of coronavirus grows the concern about planning for the excess demand of hospital services in response to COVID-19 pandemic. The surge in the hospital services demand beyond the current capacity leads to shortage of ICU beds and ventilators in some parts of US. In this study, we forecast the required number of hospital beds and possible shortage of beds in US during COVID-19 pandemic to be used in the planning and hospitalization of new cases. In this paper, we used a data on COVID-19 deaths and patients’ hospitalization besides the data on hospital capacities and utilization in US from publicly available sources and national government websites. we used a novel ensemble modelling of deep learning networks, based on stacking different linear and non-linear layers to predict the shortage in hospital beds. The results showed that our proposed approach can predict the excess hospital beds demand very well and this can be helpful in developing strategies and plans to mitigate this gap.

Keywords: COVID-19, deep learning, ensembled models, hospital capacity planning

Procedia PDF Downloads 143

Authors: Clement Chimezie Aladi, Itamar Shabtai

Abstract:

A review of the literature in the last few years reveals that little attention has been paid to technological affordances in e-learning designs. However, affordances are key to engaging students and enabling teachers to actualize learning goals. E-learning systems (software and artifacts) need to be designed in such a way that the features facilitate perceptions of the affordances with minimal cognition. This study aimed to fill this gap in the literature and encourage further research in this area. It provides guidelines for facilitating the perception of affordances in e-learning design and advances Technology Affordance and Constraints Theory by incorporating the affordance-based design process, the principles of multimedia learning, e-learning design philosophy, and emotional and cognitive affordances.

Keywords: e-learning, technology affrodances, affordance based design, e-learning design

Procedia PDF Downloads 46

Authors: Selim M. Khan, Dustin D. Pearson, Tryggve Rönnqvist, Markus E. Nielsen, Joshua M. Taron, Aaron A. Goodarzi

Abstract:

Accumulation of radioactive radon gas in indoor air poses a serious risk to human health by increasing the lifetime risk of lung cancer and is classified by IARC as a category one carcinogen. Radon exposure risks are a function of geologic, geographic, design, and human behavioural variables and can change over time. Using time series and deep machine learning modelling, we analyzed long-term radon test outcomes as a function of building metrics from 25,489 Canadian and 38,596 Swedish residential properties constructed between 1945 to 2020. While Canadian and Swedish properties built between 1970 and 1980 are comparable (96–103 Bq/m³), innate radon risks subsequently diverge, rising in Canada and falling in Sweden such that 21st Century Canadian houses show 467% greater average radon (131 Bq/m³) relative to Swedish equivalents (28 Bq/m³). These trends are consistent across housing types and regions within each country. The introduction of energy efficiency measures within Canadian and Swedish building codes coincided with opposing radon level trajectories in each nation. Deep machine learning modelling predicts that, without intervention, average Canadian residential radon levels will increase to 176 Bq/m³ by 2050, emphasizing the importance and urgency of future building code intervention to achieve systemic radon reduction in Canada.

Keywords: radon health risk, time-series, deep machine learning, lung cancer, Canada, Sweden

Procedia PDF Downloads 75

Authors: Shafaq Rubab

Abstract:

The inclusion of special needs students in a classroom is prevailing gradually in developing countries. Digital game-based learning is one the most effective instructional methodology for special needs students. Digital game-based learning facilitates special needs students who actually face challenges and obstacles in their learning processes. This study aimed to evaluate the effectiveness of digital game-based learning on the educational progress of special needs students in developing countries. The quasi-experimental research was conducted by using purposively selected sample size of eight special needs students. Results of both experimental and control group showed that performance of the experimental group students was better than the control group students and there was a significant difference between both groups’ results. This research strongly recommended that digital game-based learning can help special needs students in an inclusive classroom. It also revealed that special needs students can learn efficiently by using pedagogically sound learning games and game-based learning helps a lot for the self-paced fast-track learning system.

Keywords: inclusive education, special needs, digital game-based learning, fast-track learning

Procedia PDF Downloads 281

Authors: Seynabou Toure, Oumar Diop, Kidiyo Kpalma, Amadou S. Maiga

Abstract:

Color and texture are the two most determinant elements for perception and recognition of the objects in an image. For this reason, color and texture analysis find a large field of application, for example in image classification and segmentation. But, the pioneering work in texture analysis was conducted on grayscale images, thus discarding color information. Many grey-level texture descriptors have been proposed and successfully used in numerous domains for image classification: face recognition, industrial inspections, food science medical imaging among others. Taking into account color in the definition of these descriptors makes it possible to better characterize images. Color texture is thus the subject of recent work, and the analysis of color texture images is increasingly attracting interest in the scientific community. In optical remote sensing systems, sensors measure separately different parts of the electromagnetic spectrum; the visible ones and even those that are invisible to the human eye. The amounts of light reflected by the earth in spectral bands are then transformed into grayscale images. The primary natural colors Red (R) Green (G) and Blue (B) are then used in mixtures of different spectral bands in order to produce RGB images. Thus, good color texture discrimination can be achieved using RGB under controlled illumination conditions. Some previous works investigate the effect of using different color space for color texture classification. However, the selection of the best performing color space in land-sea segmentation is an open question. Its resolution may bring considerable improvements in certain applications like coastline detection, where the detection result is strongly dependent on the performance of the land-sea segmentation. The aim of this paper is to present the results of a study conducted on different color spaces in order to show the best-performing color space for land-sea segmentation. In this sense, an experimental analysis is carried out using five different color spaces (RGB, XYZ, Lab, HSV, YCbCr). For each color space, the Haar wavelet decomposition is used to extract different color texture features. These color texture features are then used for Fusion of Over Segmentation (FOOS) based classification; this allows segmentation of the land part from the sea one. By analyzing the different results of this study, the HSV color space is found as the best classification performance while using color and texture features; which is perfectly coherent with the results presented in the literature.

Keywords: classification, coastline, color, sea-land segmentation

Procedia PDF Downloads 232

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 429

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 62

Authors: Konstantinos Sofianos, Michael Stefanidakis

Abstract:

Nowadays, advances in information and communication technologies offer a range of opportunities for new approaches, methods, and tools in the field of education and training. Teacher-centered learning has changed to student-centered learning. E-learning has now matured and enables the design and construction of intelligent learning systems. A smart learning system fully adapts to a student's needs and provides them with an education based on their preferences, learning styles, and learning backgrounds. It is a wise friend and available at any time, in any place, and with any digital device. In this paper, we propose an intelligent learning system, which includes an ontology with all elements of the learning process (learning objects, learning activities) and a massive open online course (MOOC) system. This intelligent learning system can be used in music education.

Keywords: intelligent learning systems, e-learning, music education, ontology, semantic web

Procedia PDF Downloads 300

Authors: Rui Wu

Abstract:

In the volatile modern manufacturing environment, new orders randomly occur at any time, while the pre-emptive methods are infeasible. This leads to a real-time scheduling method that can produce a reasonably good schedule quickly. The dynamic Flexible Job Shop problem is an NP-hard scheduling problem that hybrid the dynamic Job Shop problem with the Parallel Machine problem. A Flexible Job Shop contains different work centres. Each work centre contains parallel machines that can process certain operations. Many algorithms, such as genetic algorithms or simulated annealing, have been proposed to solve the static Flexible Job Shop problems. However, the time efficiency of these methods is low, and these methods are not feasible in a dynamic scheduling problem. Therefore, a dynamic rule selection scheduling system based on the reinforcement learning method is proposed in this research, in which the dynamic Flexible Job Shop problem is divided into several parallel machine problems to decrease the complexity of the dynamic Flexible Job Shop problem. Firstly, the features of jobs, machines, work centres, and flexible job shops are selected to describe the status of the dynamic Flexible Job Shop problem at each decision point in each work centre. Secondly, a framework of reinforcement learning algorithm using a double-layer deep Q-learning network is applied to select proper composite dispatching rules based on the status of each work centre. Then, based on the selected composite dispatching rule, an available operation is selected from the waiting buffer and assigned to an available machine in each work centre. Finally, the proposed algorithm will be compared with well-known dispatching rules on objectives of mean tardiness, mean flow time, mean waiting time, or mean percentage of waiting time in the real-time Flexible Job Shop problem. The result of the simulations proved that the proposed framework has reasonable performance and time efficiency.

Keywords: dynamic scheduling problem, flexible job shop, dispatching rules, deep reinforcement learning

Procedia PDF Downloads 91

Authors: Kian Jon Chua, Islam Md Raisul

Abstract:

Findings on a research study conducted for a group of year-2 engineering students participating in a flipped classroom (FC) experience that is judiciously incorporated into project-based learning (PBL) module are presented. The chief purpose of the research is to identify whether if the incorporation of flipped classroom approach to project-based learning indeed yields a positive learning experience for engineering students. Results are presented and compared from the two classes of students – one is subjected to a traditional PBL learning mode while the other undergoes a hybrid PBL-FC learning format. Some themes related to active learning, problem-solving ability, teacher as facilitator, and degree of self-efficacy are also discussed. This paper hopes to provide new knowledge and insights relating to the introduction of flipped classroom learning to a project-based engineering module. Some potential study limitations and future directions to address them are also presented.

Keywords: hybrid project-based learning, flipped classroom, problem-solving, active learning

Procedia PDF Downloads 125

Authors: A. B. Robert, Adam Pramadia, Calvin Andika

Abstract:

The main purpose of this study is to explore consumer loyalty characteristic of mobile phone category in Indonesia. Second, this research attempts to identify consumer segment and to explore their profile in each segment as the basis of marketing strategy formulation. This study used some tools of multivariate analysis such as discriminant analysis and cluster analysis. Discriminate analysis used to discriminate consumer loyal and not loyal by using particular variables. Cluster analysis used to reveal various segment in mobile phone category. In addition to having better customer understanding in each segment, this study used descriptive analysis and cross tab analysis in each segment defined by cluster analysis. This study expected several findings. First, consumer can be divided into two large group of loyal versus not loyal by set of variables. Second, this study identifies customer segment in mobile phone category. Third, exploring customer profile in each segment that has been identified. This study answer a call for additional empirical research into different product categories. Therefore, a replication research is advisable. By knowing the customer loyalty characteristic, and deep analysis of their consumption behavior and profile for each segment, this study is very advisable for high impact marketing strategy development. This study contributes body of knowledge by adding empirical study of consumer loyalty, segmentation analysis in mobile phone category by multiple brand analysis.

Keywords: customer loyalty, segmentation, marketing strategy, discriminant analysis, cluster analysis, mobile phone

Procedia PDF Downloads 585

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 146

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 63

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 139

Authors: Pitigalage Chamath Chandira Peiris

Abstract:

A widely researched domain in the field of image processing in recent times has been single image super-resolution, which tries to restore a high-resolution image from a single low-resolution image. Many more single image super-resolution efforts have been completed utilizing equally traditional and deep learning methodologies, as well as a variety of other methodologies. Deep learning-based super-resolution methods, in particular, have received significant interest. As of now, the most advanced image restoration approaches are based on convolutional neural networks; nevertheless, only a few efforts have been performed using Transformers, which have demonstrated excellent performance on high-level vision tasks. The effectiveness of CNN-based algorithms in image super-resolution has been impressive. However, these methods cannot completely capture the non-local features of the data. Enhancer is a simple yet powerful Transformer-based approach for enhancing the resolution of images. A method for single image super-resolution was developed in this study, which utilized an efficient and effective transformer design. This proposed architecture makes use of a locally enhanced window transformer block to alleviate the enormous computational load associated with non-overlapping window-based self-attention. Additionally, it incorporates depth-wise convolution in the feed-forward network to enhance its ability to capture local context. This study is assessed by comparing the results obtained for popular datasets to those obtained by other techniques in the domain.

Keywords: single image super resolution, computer vision, vision transformers, image restoration

Procedia PDF Downloads 92

Authors: Xuewei Li, Jingfeng Yuan, Jianliang Zhou

Abstract:

The 21st century has been called the century of human exploitation of underground space. Due to the characteristics of large quantity, tight schedule, low safety reserve and high uncertainty of deep foundation pit engineering, accidents frequently occur in deep foundation pit engineering, causing huge economic losses and casualties. With the successful application of information technology in the construction industry, building information modeling has become a research hotspot in the field of architectural engineering. Therefore, the application of building information modeling (BIM) and other information communication technologies (ICTs) in construction safety management is of great significance to improve the level of safety management. This research summed up the mechanism of the deep foundation pit engineering accident through the fault tree analysis to find the control factors of deep foundation pit engineering safety management, the deficiency existing in the traditional deep foundation pit construction site safety management. According to the accident cause mechanism and the specific process of deep foundation pit construction, the hazard information of deep foundation pit engineering construction site was identified, and the hazard list was obtained, including early warning information. After that, the system framework was constructed by analyzing the early warning information demand and early warning function demand of the safety management system of deep foundation pit. Finally, the safety management system of deep foundation pit construction site based on BIM through combing the database and Web-BIM technology was developed, so as to realize the three functions of real-time positioning of construction site personnel, automatic warning of entering a dangerous area, real-time monitoring of deep foundation pit structure deformation and automatic warning. This study can initially improve the current situation of safety management in the construction site of deep foundation pit. Additionally, the active control before the occurrence of deep foundation pit accidents and the whole process dynamic control in the construction process can be realized so as to prevent and control the occurrence of safety accidents in the construction of deep foundation pit engineering.

Keywords: Web-BIM, safety management, deep foundation pit, construction

Procedia PDF Downloads 142

Authors: Sirapop Nuannimnoi, Hojjat Baghban, Ching-Yao Huang

Abstract:

Over the past decade, with the fast development of blockchain technology since the birth of Bitcoin, there has been a massive increase in the usage of Cryptocurrencies. Cryptocurrencies are not seen as an investment opportunity due to the market’s erratic behavior and high price volatility. With the recent success of deep reinforcement learning (DRL), portfolio management can be modeled and automated. In this paper, we propose a novel DRL-based multi-agent system to automatically make proper trading decisions on multiple cryptocurrencies and gain profits in the highly volatile cryptocurrency market. We also extend this multi-agent system with horizontal federated transfer learning for better adapting to the inclusion of new cryptocurrencies in our portfolio; therefore, we can, through the concept of diversification, maximize our profits and minimize the trading risks. Experimental results through multiple simulation scenarios reveal that this proposed algorithmic trading system can offer three promising key advantages over other systems, including maximized profits, minimized risks, and adaptability.

Keywords: cryptocurrency portfolio management, algorithmic trading, federated learning, multi-agent reinforcement learning

Procedia PDF Downloads 107

Authors: Luther Ollier, Sylvie Thiria, Anastase Charantonis, Carlos E. Mejia, Michel Crépon

Abstract:

Sea Surface Height Anomaly (SLA) is a signature of the sub-mesoscale dynamics of the upper ocean. Sea Surface Temperature (SST) is driven by these dynamics and can be used to improve the spatial interpolation of SLA fields. In this study, we focused on the temporal evolution of SLA fields. We explored the capacity of deep learning (DL) methods to predict short-term SLA fields using SST fields. We used simulated daily SLA and SST data from the Mercator Global Analysis and Forecasting System, with a resolution of (1/12)◦ in the North Atlantic Ocean (26.5-44.42◦N, -64.25–41.83◦E), covering the period from 1993 to 2019. Using a slightly modified image-to-image convolutional DL architecture, we demonstrated that SST is a relevant variable for controlling the SLA prediction. With a learning process inspired by the teaching-forcing method, we managed to improve the SLA forecast at five days by using the SST fields as additional information. We obtained predictions of a 12 cm (20 cm) error of SLA evolution for scales smaller than mesoscales and at time scales of 5 days (20 days), respectively. Moreover, the information provided by the SST allows us to limit the SLA error to 16 cm at 20 days when learning the trajectory.

Keywords: deep-learning, altimetry, sea surface temperature, forecast

Procedia PDF Downloads 77

Authors: Edward W. Staley, Corban G. Rivera, Ashley J. Llorens

Abstract:

Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains. An emerging landscape of development environments is making powerful RL techniques more accessible for a growing community of researchers. However, most existing frameworks do not directly address the problem of learning in complex operating environments, such as dense urban settings or defense-related scenarios, that incorporate distributed, heterogeneous teams of agents. To help enable AI research for this important class of applications, we introduce the AI Arena: a scalable framework with flexible abstractions for distributed multi-agent reinforcement learning. The AI Arena extends the OpenAI Gym interface to allow greater flexibility in learning control policies across multiple agents with heterogeneous learning strategies and localized views of the environment. To illustrate the utility of our framework, we present experimental results that demonstrate performance gains due to a distributed multi-agent learning approach over commonly-used RL techniques in several different learning environments.

Keywords: reinforcement learning, multi-agent, deep learning, artificial intelligence

Procedia PDF Downloads 146

Authors: Abdulwakeel B. Raji

Abstract:

This paper introduces a concept of an intelligent virtual learning environment that involves communication between learners and an artificially intelligent teaching agent in an attempt to replicate classroom learning interactions. The benefits of this technology over current e-learning practices is that it creates a virtual classroom where real time adaptive learning interactions are made possible. This is a move away from the static learning practices currently being adopted by e-learning systems. Over the years, artificial intelligence has been applied to various fields, including and not limited to medicine, military applications, psychology, marketing etc. The purpose of e-learning applications is to ensure users are able to learn outside of the classroom, but a major limitation has been the inability to fully replicate classroom interactions between teacher and students. This study used comparative surveys to gain information and understanding of the current learning practices in Nigerian universities and how they compare to these practices compare to the use of a developed e-learning system. The study was conducted by attending several lectures and noting the interactions between lecturers and tutors and as an aftermath, a software has been developed that deploys the use of an artificial intelligent teaching-agent alongside an e-learning system to enhance user learning experience and attempt to create the similar learning interactions to those found in classroom and lecture hall settings. Dialogflow has been used to implement a teaching-agent, which has been developed using JSON, which serves as a virtual teacher. Course content has been created using HTML, CSS, PHP and JAVASCRIPT as a web-based application. This technology can run on handheld devices and Google based home technologies to give learners an access to the teaching agent at any time. This technology also implements the use of definite clause grammars and natural language processing to match user inputs and requests with defined rules to replicate learning interactions. This technology developed covers familiar classroom scenarios such as answering users’ questions, asking ‘do you understand’ at regular intervals and answering subsequent requests, taking advanced user queries to give feedbacks at other periods. This software technology uses deep learning techniques to learn user interactions and patterns to subsequently enhance user learning experience. A system testing has been undergone by undergraduate students in the UK and Nigeria on the course ‘Introduction to Database Development’. Test results and feedback from users shows that this study and developed software is a significant improvement on existing e-learning systems. Further experiments are to be run using the software with different students and more course contents.

Keywords: virtual learning, natural language processing, definite clause grammars, deep learning, artificial intelligence

Procedia PDF Downloads 124

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 178

Authors: Sushish Baral, Pratibha Joshi, Yaman Maharjan

Abstract:

Glaucoma is a chronic eye condition that causes vision loss that is irreversible. Early detection and treatment are critical to prevent vision loss because it can be asymptomatic. For the identification of glaucoma, multiple deep learning algorithms are used. Transformer-based architectures, which use the self-attention mechanism to encode long-range dependencies and acquire extremely expressive representations, have recently become popular. Convolutional architectures, on the other hand, lack knowledge of long-range dependencies in the image due to their intrinsic inductive biases. The aforementioned statements inspire this thesis to look at transformer-based solutions and investigate the viability of adopting transformer-based network designs for glaucoma detection. Using retinal fundus images of the optic nerve head to develop a viable algorithm to assess the severity of glaucoma necessitates a large number of well-curated images. Initially, data is generated by augmenting ocular pictures. After that, the ocular images are pre-processed to make them ready for further processing. The system is trained using pre-processed images, and it classifies the input images as normal or glaucoma based on the features retrieved during training. The Vision Transformer (ViT) architecture is well suited to this situation, as it allows the self-attention mechanism to utilise structural modeling. Extensive experiments are run on the common dataset, and the results are thoroughly validated and visualized.

Keywords: glaucoma, vision transformer, convolutional architectures, retinal fundus images, self-attention, deep learning

Procedia PDF Downloads 181