Search results for: convolutional architectures

Authors: Ali Almadan, Anoop Krishnan, Ajita Rattani

Abstract:

Facial recognition is a widely adopted technology in surveillance, border control, healthcare, banking services, and lately, in mobile user authentication with Apple introducing “Face ID” moniker with iPhone X. A lot of research has been conducted in the area of face recognition on datasets captured by surveillance cameras, DSLR, and mobile devices. Recently, face recognition technology has also been deployed on body-worn cameras to keep officers safe, enabling situational awareness and providing evidence for trial. However, limited academic research has been conducted on this topic so far, without the availability of any publicly available datasets with a sufficient sample size. This paper aims to advance research in the area of face recognition using body-worn cameras. To this aim, the contribution of this work is two-fold: (1) collection of a dataset consisting of a total of 136,939 facial images of 102 subjects captured using body-worn cameras in in-door and daylight conditions and (2) evaluation of various deep-learning architectures for face identification on the collected dataset. Experimental results suggest a maximum True Positive Rate(TPR) of 99.86% at False Positive Rate(FPR) of 0.000 obtained by SphereFace based deep learning architecture in daylight condition. The collected dataset and the baseline algorithms will promote further research and development. A downloadable link of the dataset and the algorithms is available by contacting the authors.

Keywords: face recognition, body-worn cameras, deep learning, person identification

Procedia PDF Downloads 137

Authors: M. K. Benhaoua, A. K. Singh, A. E. Benyamina, P. Boulet

Abstract:

Mapping parallelized tasks of applications onto these MPSoCs can be done either at design time (static) or at run-time (dynamic). Static mapping strategies find the best placement of tasks at design-time, and hence, these are not suitable for dynamic workload and seem incapable of runtime resource management. The number of tasks or applications executing in MPSoC platform can exceed the available resources, requiring efficient run-time mapping strategies to meet these constraints. This paper describes a new Spiral Dynamic Task Mapping heuristic for mapping applications onto NoC-based Heterogeneous MPSoC. This heuristic is based on packing strategy and routing Algorithm proposed also in this paper. Heuristic try to map the tasks of an application in a clustering region to reduce the communication overhead between the communicating tasks. The heuristic proposed in this paper attempts to map the tasks of an application that are most related to each other in a spiral manner and to find the best possible path load that minimizes the communication overhead. In this context, we have realized a simulation environment for experimental evaluations to map applications with varying number of tasks onto an 8x8 NoC-based Heterogeneous MPSoCs platform, we demonstrate that the new mapping heuristics with the new modified dijkstra routing algorithm proposed are capable of reducing the total execution time and energy consumption of applications when compared to state-of-the-art run-time mapping heuristics reported in the literature.

Keywords: multiprocessor system on chip, MPSoC, network on chip, NoC, heterogeneous architectures, run-time mapping heuristics, routing algorithm

Procedia PDF Downloads 451

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 161

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 85

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 68

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

Abstract:

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

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

Procedia PDF Downloads 102

Authors: Khyamling Parane, B. M. Prabhu Prasad, Basavaraj Talawar

Abstract:

Fast simulations are critical in reducing time to market in CMPs and SoCs. Several simulators have been used to evaluate the performance and power consumed by Network-on-Chips. Researchers and designers rely upon these simulators for design space exploration of NoC architectures. Our experiments show that simulating large NoC topologies take hours to several days for completion. To speed up the simulations, it is necessary to investigate and optimize the hotspots in simulator source code. Among several simulators available, we choose Booksim2.0, as it is being extensively used in the NoC community. In this paper, we analyze the cache and memory system behaviour of Booksim2.0 to accurately monitor input dependent performance bottlenecks. Our measurements show that cache and memory usage patterns vary widely based on the input parameters given to Booksim2.0. Based on these measurements, the cache configuration having least misses has been identified. To further reduce the cache misses, we use software optimization techniques such as removal of unused functions, loop interchanging and replacing post-increment operator with pre-increment operator for non-primitive data types. The cache misses were reduced by 18.52%, 5.34% and 3.91% by employing above technology respectively. We also employ thread parallelization and vectorization to improve the overall performance of Booksim2.0. The OpenMP programming model and SIMD are used for parallelizing and vectorizing the more time-consuming portions of Booksim2.0. Speedups of 2.93x and 3.97x were observed for the Mesh topology with 30 × 30 network size by employing thread parallelization and vectorization respectively.

Keywords: cache behaviour, network-on-chip, performance profiling, vectorization

Procedia PDF Downloads 170

Authors: Huawei Bai, Jianguo Yao, Fellow, IEEE

Abstract:

Atrial fibrillation (AF) is the most common form of heart arrhythmia and is closely associated with mortality and morbidity in heart failure, stroke, and coronary artery disease. The development of single spot optical sensors enables widespread photoplethysmography (PPG) screening, especially for AF, since it represents a more convenient and noninvasive approach. To our knowledge, most existing studies based on public and unbalanced datasets can barely handle the multiple noises sources in the real world and, also, lack interpretability. In this paper, we construct a large- scale PPG dataset using measurements collected from PPG wrist- watch devices worn by volunteers and propose an attention-based two-stream heterogeneous neural network (TSHNN). The first stream is a hybrid neural network consisting of a three-layer one-dimensional convolutional neural network (1D-CNN) and two-layer attention- based bidirectional long short-term memory (Bi-LSTM) network to learn representations from temporally sampled signals. The second stream extracts latent representations from the PPG time-frequency spectrogram using a five-layer CNN. The outputs from both streams are fed into a fusion layer for the outcome. Visualization of the attention weights learned demonstrates the effectiveness of the attention mechanism against noise. The experimental results show that the TSHNN outperforms all the competitive baseline approaches and with 98.09% accuracy, achieves state-of-the-art performance.

Keywords: PPG wearables, atrial fibrillation, feature fusion, attention mechanism, hyber network

Procedia PDF Downloads 85

Authors: Riaan Kleyn

Abstract:

Mass wine production companies across the globe are provided with grapes from winegrowers that predominantly utilize mechanical harvesting machines to harvest wine grapes. Mechanical harvesting accelerates the rate at which grapes are harvested, allowing grapes to be delivered faster to meet the demands of wine cellars. The disadvantage of the mechanical harvesting method is the inclusion of material-other-than-grapes (MOG) in the harvested wine grape loads arriving at the cellar which degrades the quality of wine that can be produced. Currently, wine cellars do not have a method to determine the amount of MOG present within wine grape loads. This paper seeks to find an optimal computer vision method capable of detecting the amount of MOG within a wine grape load. A MOG detection method will encourage winegrowers to deliver MOG-free wine grape loads to avoid penalties which will indirectly enhance the quality of the wine to be produced. Traditional image segmentation methods were compared to deep learning segmentation methods based on images of wine grape loads that were captured at a wine cellar. The Mask R-CNN model with a ResNet-50 convolutional neural network backbone emerged as the optimal method for this study to determine the amount of MOG in an image of a wine grape load. Furthermore, a statistical analysis was conducted to determine how the MOG on the surface of a grape load relates to the mass of MOG within the corresponding grape load.

Keywords: computer vision, wine grapes, machine learning, machine harvested grapes

Procedia PDF Downloads 57

Authors: Tomas Trainys, Algimantas Venckauskas

Abstract:

Application of biometric features to the cryptography for human identification and authentication is widely studied and promising area of the development of high-reliability cryptosystems. Biometric cryptosystems typically are designed for patterns recognition, which allows biometric data acquisition from an individual, extracts feature sets, compares the feature set against the set stored in the vault and gives a result of the comparison. Preprocessing and fusion of biometric data are the most important phases in generating a feature vector for key generation or authentication. Fusion of biometric features is critical for achieving a higher level of security and prevents from possible spoofing attacks. The paper focuses on the tasks of initial processing and fusion of multiple representations of finger vein modality patterns. These tasks are solved by applying conventional image preprocessing methods and machine learning techniques, Convolutional Neural Network (SVM) method for image segmentation and feature extraction. An article presents a method for generating sets of biometric features from a finger vein network using several instances of the same modality. Extracted features sets were fused at the feature level. The proposed method was tested and compared with the performance and accuracy results of other authors.

Keywords: bio-cryptography, biometrics, cryptographic key generation, data fusion, information security, SVM, pattern recognition, finger vein method.

Procedia PDF Downloads 118

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 78

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 239

Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri

Abstract:

The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.

Keywords: deep learning, object detection, cnn, tomato, weeds

Procedia PDF Downloads 76

Authors: Omar Elharrouss, Youssef Hmamouche, Assia Kamal Idrissi, Btissam El Khamlichi, Amal El Fallah-Seghrouchni

Abstract:

Edge detection is represented as one of the most challenging tasks in computer vision, due to the complexity of detecting the edges or boundaries in real-world images that contains objects of different types and scales like trees, building as well as various backgrounds. Edge detection is represented also as a key task for many computer vision applications. Using a set of backbones as well as attention modules, deep-learning-based methods improved the detection of edges compared with the traditional methods like Sobel and Canny. However, images of complex scenes still represent a challenge for these methods. Also, the detected edges using the existing approaches suffer from non-refined results while the image output contains many erroneous edges. To overcome this, n this paper, by using the mechanism of residual learning, a refined edge detection network is proposed (RED-Net). By maintaining the high resolution of edges during the training process, and conserving the resolution of the edge image during the network stage, we make the pooling outputs at each stage connected with the output of the previous layer. Also, after each layer, we use an affined batch normalization layer as an erosion operation for the homogeneous region in the image. The proposed methods are evaluated using the most challenging datasets including BSDS500, NYUD, and Multicue. The obtained results outperform the designed edge detection networks in terms of performance metrics and quality of output images.

Keywords: edge detection, convolutional neural networks, deep learning, scale-representation, backbone

Procedia PDF Downloads 66

Authors: Bander Alzahrani

Abstract:

Information-centric networking (ICN) using architectures such as Publish-Subscribe Internet Routing Paradigm (PSIRP) is one of the promising candidates for a future Internet, has recently been under the spotlight by the research community to investigate the possibility of redesigning the current Internet architecture to solve many issues such as routing scalability, security, and quality of services issues.. The Bloom filter-based forwarding is a source-routing approach that is used in the PSIRP architecture. This mechanism is vulnerable to brute force attacks which may lead to denial-of-service (DoS) attacks. In this work, we present a new forwarding approach that keeps the advantages of Bloom filter-based forwarding while mitigates attacks on the forwarding mechanism. In practice, we introduce a special type of forwarding nodes called Edge-FW to be placed at the edge of the network. The role of these node is to add an extra security layer by validating and inspecting packets at the edge of the network against brute-force attacks and check whether the packet contains a legitimate forwarding identifier (FId) or not. We leverage Certificateless Aggregate Signature (CLAS) scheme with a small size of 64-bit which is used to sign the FId. Hence, this signature becomes bound to a specific FId. Therefore, malicious nodes that inject packets with random FIds will be easily detected and dropped at the Edge-FW node when the signature verification fails. Our preliminary security analysis suggests that with the proposed approach, the forwarding plane is able to resist attacks such as DoS with very high probability.

Keywords: bloom filter, certificateless aggregate signature, denial-of-service, information centric network

Procedia PDF Downloads 168

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 75

Authors: Nick Weir, Robert Stevens, Alan Hargreaves, Martin McGinnity, Chris Tinsley

Abstract:

Hydrophobic materials have previously demonstrated the ability to elevate cell-cell interactions and promote the formation of neural networks whilst aligned nanofibers demonstrate the ability to induce extensive neurite outgrowth in an aligned manner. Hydrophobic materials typically elicit an immune response upon implantation and thus materials used for implantation are typically hydrophilic. Poly-L-lactic acid (PLLA) is a hydrophobic, non-immunogenic, FDA approved material that can be electrospun to form aligned nanofibers. Primary rat cortical neurons cultured for 10 days on aligned PLLA nanofibers formed 3D cell clusters, approximately 800 microns in diameter. Neurites that extended from these clusters were highly aligned due to the alignment of the nanofibers they were cultured upon and fasciculation was also evident. Plasma treatment of the PLLA nanofibers prior to seeding of cells significantly reduced the hydrophobicity and abolished the cluster formation and neurite fasciculation, whilst reducing the extent and directionality of neurite outgrowth; it is proposed that hydrophobicity induces the changes to cellular behaviors. Aligned PLLA nanofibers induced the formation of a structure that mimics the grey-white matter compartmentalization that is observed in vivo and thus represents a step forward in generating organoids or biomaterial-based implants. Upon implantation into the brain, the biomaterial architectures described here may provide a useful platform for both brain repair and brain remodeling initiatives.

Keywords: hydrophobicity, nanofibers, neurite fasciculation, neurite outgrowth, PLLA

Procedia PDF Downloads 128

Authors: S. Jaramillo, Y. Montoya, W. Agudelo, J. Bustamante

Abstract:

Cardiovascular diseases (CVD) are related to affectations of the heart and blood vessels, within these are pathologies such as coronary or peripheral heart disease, caused by the narrowing of the vessel wall (atherosclerosis), which is related to the accumulation of Low-Density Lipoproteins (LDL) in the arterial walls that leads to a progressive reduction of the lumen of the vessel and alterations in blood perfusion. Currently, the main therapeutic strategy for this type of alteration is drug treatment with statins, which inhibit the enzyme 3-hydroxy-3-methyl-glutaryl-CoA reductase (HMG-CoA reductase), responsible for modulating the rate of cholesterol production and other isoprenoids in the mevalonate pathway. This enzyme induces the expression of LDL receptors in the liver, increasing their number on the surface of liver cells, reducing the plasma concentration of cholesterol. On the other hand, when the blood vessel presents stenosis, a surgical procedure with vascular implants is indicated, which are used to restore circulation in the arterial or venous bed. Among the materials used for the development of vascular implants are Dacron® and Teflon®, which perform the function of re-waterproofing the circulatory circuit, but due to their low biocompatibility, they do not have the ability to promote remodeling and tissue regeneration processes. Based on this, the present research proposes the development of a hydrolyzed collagen and polyethylene oxide electrospun membrane reinforced with medium and high-intensity statins, so that in future research it can favor tissue remodeling processes from its microarchitecture.

Keywords: atherosclerosis, medium and high-intensity statins, microarchitecture, electrospun membrane

Procedia PDF Downloads 100

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 44

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 105

Authors: Revoti Prasad Bora, Saurabh Yadav, Nikita Katyal

Abstract:

In the context of educational data mining, the use case of extracting information from images containing both text and diagrams is of high importance. Hence, document analysis requires the extraction of diagrams from such images and processes the text and diagrams separately. To the author’s best knowledge, none among plenty of approaches for extracting tables, figures, etc., suffice the need for real-time processing with high accuracy as needed in multiple applications. In the education domain, diagrams can be of varied characteristics viz. line-based i.e. geometric diagrams, chemical bonds, mathematical formulas, etc. There are two broad categories of approaches that try to solve similar problems viz. traditional computer vision based approaches and deep learning approaches. The traditional computer vision based approaches mainly leverage connected components and distance transform based processing and hence perform well in very limited scenarios. The existing deep learning approaches either leverage YOLO or faster-RCNN architectures. These approaches suffer from a performance-accuracy tradeoff. This paper proposes a U-Net based architecture that formulates the diagram extraction as a segmentation problem. The proposed method provides similar accuracy with a much faster extraction time as compared to the mentioned state-of-the-art approaches. Further, the segmentation mask in this approach allows the extraction of diagrams of irregular shapes.

Keywords: computer vision, deep-learning, educational data mining, faster-RCNN, figure extraction, image segmentation, real-time document analysis, text extraction, U-Net, YOLO

Procedia PDF Downloads 100

Authors: Sawsan Saridar masri, Hisham Arnaouty

Abstract:

Architecture both defines and is defined by social, cultural, political and financial constraints: this is where the discipline and the profession of architecture meet. This mutual sway evolves wherever interferences in the built environment are thought-out and can be strengthened or weakened by the many ways in which the practice of architecture can be undertaken. The more familiar we are about the concerns and factors that control what can be made, the greater the opportunities to propose and make appropriate architectures. Apparently, the criteria in any qualification policy should permit flexibility of approach and will – for reasons including cultural choice, political issues, and son on – vary significantly from country to country. However the weighting of the various criteria have to ensure adequate standards both in educational system as in the professional training. This paper develops, deepens and questions about the regulatory entry routes to the professional practice of architecture in the Arab world. It is also intended to provide an informed basis about strategies for conventional and unconventional models of practice in preparation for the next stages of architect’s work experience and professional experience. With the objective of promoting the implementation of adequate built environment in the practice of architecture, a comprehensive analysis of various pathways of access to the profession are selected as case studies, encompassing examples from across the world. The review of such case studies allows the creation of a comprehensive picture in relation to the conditions for qualification of practitioners of the built environment at the level of the Middle Eastern countries and the Arab World. Such investigation considers the following aspects: professional title and domain of practice, accreditation of courses, internship and professional training, professional examination and continuing professional development.

Keywords: architecture, internship, mobility, professional practice

Procedia PDF Downloads 517

Authors: Raymond Xu, Ashley Hua, Andrew Wang, Yuru Lin

Abstract:

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Keywords: artificial intelligence, COVID-19, depression detection, psychiatric disorder

Procedia PDF Downloads 99

Authors: P. Mirahmadpour, M. H. Banitaba, D. Nematollahi

Abstract:

The chemistry of coordination polymers in recent years has grown exponentially not only because of their interesting architectures but also due to their various technical applications in many fields including ion exchange, chemical catalysis, small molecule separations, and drug release. The use of bridging ligands for the controlled self-assembly of one, two or three dimensional metallo-supramolecular species is the subject of serious study in last decade. Numerous different synthetic methods have been offered for the preparation of coordination polymers such as (a) diffusion from the gas phase, (b) slow diffusion of the reactants into a polymeric matrix, (c) evaporation of the solvent at ambient or reduced temperatures, (d) temperature controlled cooling, (e) precipitation or recrystallisation from a mixture of solvents and (f) hydrothermal synthesis. The electrosynthetic process suggested several advantages over conventional approaches. A general advantage of electrochemical synthesis is that it allows synthesis under milder conditions than typical solvothermal or microwave synthesis. In this work we have introduced a simple electrochemical method for growing metal coordination polymers based on copper with a flexible 2,2’-thiodiacetic acid (TDA) and rigid 1,2,4,5-benzenetetracarboxylate (BTC) ligands. The structure of coordination polymers were characterized by scanning electron microscopy (SEM), X-ray powder diffraction (XRD), elemental analysis, thermal gravimetric (TG) and differential thermal analyses (DTA). The single-crystal X-ray diffraction analysis revealed that different conformations of the ligands and different coordination modes of the carboxylate group as well as different coordination geometries of the copper atoms. Electrochemical synthesis of coordination polymers has different advantages such as faster synthesis at lower temperature in compare with conventional chemical methods and crystallization of desired materials in a single synthetic step.

Keywords: 1, 2, 4, 5-benzenetetracarboxylate, coordination polymer, copper, 2, 2’-thiodiacetic acid

Procedia PDF Downloads 176

Authors: Aubry Martin, Nehed Amara, Jeff Nyalosaso, Audrey Potdevin, FrançOis ReVeret, Michel Langlet, Genevieve Chadeyron

Abstract:

Energy-saving lighting devices based on LightEmitting Diodes (LEDs) combine a semiconductor chip emitting in the ultraviolet or blue wavelength region to one or more phosphor(s) deposited in the form of coatings. The most common ones combine a blue LED with the yellow phosphor Y₃Al₅O₁₂:Ce³⁺ (YAG:Ce) and a red phosphor. Even if these devices are characterized by satisfying photometric parameters (Color Rendering Index, Color Temperature) and good luminous efficiencies, further improvements can be carried out to enhance light extraction efficiency (increase in phosphor forward emission). One of the possible strategies is to pattern the phosphor coatings. Here, we have worked on different ways to nanostructure the coating surface. On the one hand, we used the colloidal lithography combined with the Langmuir-Blodgett technique to directly pattern the surface of YAG:Tb³⁺ sol-gel derived coatings, YAG:Tb³⁺ being used as phosphor model. On the other hand, we achieved composite architectures combining YAG:Ce coatings and ZnO nanowires. Structural, morphological and optical properties of both systems have been studied and compared to flat YAG coatings. In both cases, nanostructuring brought a significative enhancement of photoluminescence properties under UV or blue radiations. In particular, angle-resolved photoluminescence measurements have shown that nanostructuring modifies photons path within the coatings, with a better extraction of the guided modes. These two strategies have the advantage of being versatile and applicable to any phosphor synthesizable by sol-gel technique. They then appear as promising ways to enhancement luminescence efficiencies of both phosphor coatings and the optical devices into which they are incorporated, such as LED-based lighting or safety devices.

Keywords: phosphor coatings, nanostructuring, light extraction, ZnO nanowires, colloidal lithography, LED devices

Procedia PDF Downloads 151

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 113

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 95

Authors: Kenan Morani, Esra Kaya Ayana

Abstract:

This study aimed to develop a novel pipeline for COVID-19 detection using a large and rigorously annotated database of computed tomography (CT) images. The pipeline consists of UNet-based segmentation, lung extraction, and a classification part, with the addition of optional slice removal techniques following the segmentation part. In this work, a batch normalization was added to the original UNet model to produce lighter and better localization, which is then utilized to build a full pipeline for COVID-19 diagnosis. To evaluate the effectiveness of the proposed pipeline, various segmentation methods were compared in terms of their performance and complexity. The proposed segmentation method with batch normalization outperformed traditional methods and other alternatives, resulting in a higher dice score on a publicly available dataset. Moreover, at the slice level, the proposed pipeline demonstrated high validation accuracy, indicating the efficiency of predicting 2D slices. At the patient level, the full approach exhibited higher validation accuracy and macro F1 score compared to other alternatives, surpassing the baseline. The classification component of the proposed pipeline utilizes a convolutional neural network (CNN) to make final diagnosis decisions. The COV19-CT-DB dataset, which contains a large number of CT scans with various types of slices and rigorously annotated for COVID-19 detection, was utilized for classification. The proposed pipeline outperformed many other alternatives on the dataset.

Keywords: classification, computed tomography, lung extraction, macro F1 score, UNet segmentation

Procedia PDF Downloads 97

Authors: Ilgoun Kim, Jongpil Jeong

Abstract:

Recently, a connected industrial parks (CIPs) architecture using new technologies such as RFID, cloud computing, CPS, Big Data, 5G 5G, IIOT, VR-AR, and ventral AI algorithms based on IoT has been proposed. This researcher noted the vehicle junction problem (VJP) as a more specific detail of the CIPs architectural models. The VJP noted by this researcher includes 'efficient AI physical connection challenges for vehicles' through ventilation, 'financial and financial issues with complex vehicle physical connections,' and 'welfare and working conditions of the performing personnel involved in complex vehicle physical connections.' In this paper, we propose a public solution architecture for the 'electronic financial problem of complex vehicle physical connections' as a detailed task during the vehicle junction problem (VJP). The researcher sought solutions to businesses, consumers, and Korean social problems through technological advancement. We studied how the beneficiaries of technological development can benefit from technological development with many consumers in Korean society and many small and small Korean company managers, not some specific companies. In order to more specifically implement the connected industrial parks (CIPs) architecture using the new technology, we noted the vehicle junction problem (VJP) within the smart factory industrial complex and noted the process of achieving the vehicle junction problem performance among several electronic processes. This researcher proposes a more detailed, integrated public finance enterprise architecture among the overall CIPs architectures. The main details of the public integrated financial enterprise architecture were largely organized into four main categories: 'business', 'data', 'technique', and 'finance'.

Keywords: enterprise architecture, IT Finance, smart logistics, CIPs

Procedia PDF Downloads 134

Authors: Debanjana Chatterjee

Abstract:

Vernacular settlements in India often take the form that is dictated by the climate they are in. India, with its vast cultural diversity and various climatic regions, offers a wide range of vernacular architecture. This paper focuses on two main geographical regions: Kashmir and Kerala. They bring together myriad challenges of climatic and social characteristics to incorporate into their vernacular architectures, which are still relevant despite the advent of globalization and modernization. Scholars like William Wurster and Catherine Bauer even claimed that all the traditional buildings in these places have the kind of urbanity, which is dignified and elegant but also lively and human that every architect would like to achieve if they knew how. With modernization, and with a greater ease of construction, a reduction in labor, and the apparent robustness of contemporary construction techniques, people have, however, become increasingly tentative in respect of vernacular architecture. And yet modern architecture has typically led to energize intensive structures without much consideration to the location and surroundings of the structure itself. In contrary, Laurie Baker, the British-born Indian architect, had shown us the way to integrate the knowledge of vernacular when he developed his designs based on the traditional architecture of Kerala, respecting the local climate and environment. This paper also explores his technical creativity in his design of Center for Development Studies (CDS) in Trivandrum. Hence, in order to protect and conserve our rich cultural and architectural heritage, the elements of vernacular should be incorporated into the contemporary planning and architecture for sustainable building design. The provision should be made to incorporate vernacular architecture and traditional knowledge in the policies. Ultimately, the policymakers, planners, and architects should consider this incorporation of traditional vernacular and contemporary sustainability in their work for the betterment of society now.

Keywords: vernacular, architecture, sustainable development, Kashmir and Kerala, climate, Laurie Baker

Procedia PDF Downloads 146