Search results for: deep supervision

Authors: Jamison Duckworth, Shankarachary Ragi

Abstract:

Detection and segmentation of wildfire smoke plumes from remote sensing imagery are being pursued as a solution for early fire detection and response. Smoke plume detection can be automated and made robust by the application of artificial intelligence methods. Specifically, in this study, the deep learning approach Mask Region-based Convolutional Neural Network (RCNN) is being proposed to learn smoke patterns across different spectral bands. This method is proposed to separate the smoke regions from the background and return masks placed over the smoke plumes. Multispectral data was acquired using NASA’s Earthdata and WorldView and services and satellite imagery. Due to the use of multispectral bands along with the three visual bands, we show that Mask R-CNN can be applied to distinguish smoke plumes from clouds and other landscape features that resemble smoke.

Keywords: deep learning, mask-RCNN, smoke plumes, spectral bands

Procedia PDF Downloads 127

Authors: Sahar Tabarroki, Ahad Nazari

Abstract:

The design process is one of the most key project processes in the construction industry. Although architects have the responsibility to produce complete, accurate, and coordinated documents, architectural design is accompanied by many errors. A design error occurs when the constraints and requirements of the design are not satisfied. Errors are potentially costly and time-consuming to correct if not caught early during the design phase, and they become expensive in either construction documents or in the construction phase. The aim of this research is to identify the risk factors of architectural design errors, so identification of risks is necessary. First, a literature review in the design process was conducted and then a questionnaire was designed to identify the risks and risk factors. The questions in the form of the questionnaire were based on the “similar service description of study and supervision of architectural works” published by “Vice Presidency of Strategic Planning & Supervision of I.R. Iran” as the base of architects’ tasks. Second, the top 10 risks of architectural activities were identified. To determine the positions of possible causes of risks with respect to architectural activities, these activities were located in a design process modeled by the IDEF0 technique. The research was carried out by choosing a case study, checking the design drawings, interviewing its architect and client, and providing a checklist in order to identify the concrete examples of architectural design errors. The results revealed that activities such as “defining the current and future requirements of the project”, “studies and space planning,” and “time and cost estimation of suggested solution” has a higher error risk than others. Moreover, the most important causes include “unclear goals of a client”, “time force by a client”, and “lack of knowledge of architects about the requirements of end-users”. For error detecting in the case study, lack of criteria, standards and design criteria, and lack of coordination among them, was a barrier, anyway, “lack of coordination between architectural design and electrical and mechanical facility”, “violation of the standard dimensions and sizes in space designing”, “design omissions” were identified as the most important design errors.

Keywords: architectural design, design error, risk management, risk factor

Procedia PDF Downloads 130

Authors: Shri Krishna Mishra

Abstract:

In an educational context, technology can prompt interactive plight only when it is used in conjunction with interactive plight methods. This study, therefore, examines the relationships among components that contribute to higher levels of interactive plight and execution, such as interactive Plight methods, technology, intrinsic motivation and deep learning. 526 students participated in this study. With structural equation modelling, the authors test the conceptual model and identify satisfactory model fit. The results indicate that interactive Plight methods, technology and intrinsic motivation have significant relationship with interactive Plight; deep learning mediates the relationships of the other variables with Execution.

Keywords: searching the relationship among components, contribute to interactive plight, educational execution, intrinsic motivation

Procedia PDF Downloads 454

Authors: Prathiksha Kamath, Pratibha Jamkhandi, Prateek Ghanti, Priyanshu Gupta, M. Lakshmi Neelima

Abstract:

Combining Image Captioning and Visual Question Answering (VQA) tasks have emerged as a new and exciting research area. The image captioning task involves generating a textual description that summarizes the content of the image. VQA aims to answer a natural language question about the image. Both these tasks include computer vision and natural language processing (NLP) and require a deep understanding of the content of the image and semantic relationship within the image and the ability to generate a response in natural language. There has been remarkable growth in both these tasks with rapid advancement in deep learning. In this paper, we present a comprehensive review of recent progress in combining image captioning and visual question-answering (VQA) tasks. We first discuss both image captioning and VQA tasks individually and then the various ways in which both these tasks can be integrated. We also analyze the challenges associated with these tasks and ways to overcome them. We finally discuss the various datasets and evaluation metrics used in these tasks. This paper concludes with the need for generating captions based on the context and captions that are able to answer the most likely asked questions about the image so as to aid the VQA task. Overall, this review highlights the significant progress made in combining image captioning and VQA, as well as the ongoing challenges and opportunities for further research in this exciting and rapidly evolving field, which has the potential to improve the performance of real-world applications such as autonomous vehicles, robotics, and image search.

Keywords: image captioning, visual question answering, deep learning, natural language processing

Procedia PDF Downloads 73

Authors: Edward K. Boahen, Brunel E. Bouya-Moko, Changda Wang

Abstract:

The major threat to online social network (OSN) users is account compromisation. Spammers now spread malicious messages by exploiting the trust relationship established between account owners and their friends. The challenge in detecting a compromised account by service providers is validating the trusted relationship established between the account owners, their friends, and the spammers. Another challenge is the increase in required human interaction with the feature selection. Research available on supervised learning (machine learning) has limitations with the feature selection and accounts that cannot be profiled, like application programming interface (API). Therefore, this paper discusses the various behaviours of the OSN users and the current approaches in detecting a compromised OSN account, emphasizing its limitations and challenges. We propose a deep learning approach that addresses and resolve the constraints faced by the previous schemes. We detailed our proposed optimized nonsymmetric deep auto-encoder (OPT_NDAE) for unsupervised feature learning, which reduces the required human interaction levels in the selection and extraction of features. We evaluated our proposed classifier using the NSL-KDD and KDDCUP'99 datasets in a graphical user interface enabled Weka application. The results obtained indicate that our proposed approach outperformed most of the traditional schemes in OSN compromised account detection with an accuracy rate of 99.86%.

Keywords: computer security, network security, online social network, account compromisation

Procedia PDF Downloads 119

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 89

Authors: Diego Aguirre, Olac Fuentes

Abstract:

In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 135

Authors: Mohammadjavad Yaghoubi, Arul Arulrajah, Mahdi M. Disfani, Suksun Horpibulsuk, Myint W. Bo, Stephen P. Darmawan

Abstract:

Utilising waste materials, such as fly ash (FA) and slag (S) stockpiled in landfills, has drawn the attention of researchers and engineers in the recent years. There is a great potential for usage of these wastes in ground improvement projects, especially where deep deposits of soft compressible soils exist. This paper investigates the changes in the strength development of a high water content soft soil stabilised with alkaline activated FA and S, termed as geopolymer binder, to use in deep soil mixing technology. The strength improvement and the changes in the microstructure of the mixtures have been studied. The results show that using FA and S-based geopolymers can increases the strength significantly. Furthermore, utilising FA and S in ground improvement projects, where large amounts of binders are required, can be a solution to the disposal of these wastes.

Keywords: alkaline activation, fly ash, geopolymer, slag, strength development

Procedia PDF Downloads 267

Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas

Abstract:

This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).

Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems

Procedia PDF Downloads 134

Authors: Karissa Graham, Andrew Campbell-Lloyd

Abstract:

The deep inferior epigastric artery perforator flap (DIEP) is used to reconstruct large volumes of tissue. The DIEP flap is based on the deep inferior epigastric artery (DIEA) and vein. Accurate knowledge of the anatomy of these vessels allows for efficient dissection of the flap, minimal damage to surrounding tissue, and a well vascularized flap. A 54 year old lady was assessed for bilateral delayed autologous reconstruction with DIEP free flaps. The right DIEA was consistent with the described anatomy. The left DIEA had a vessel branching shortly after leaving the external iliac artery and before entering the muscle. This independent branch entered the muscle and had a long intramuscular course to the largest perforator. The main DIEA vessel demonstrated a type II branching pattern but had perforators that were too small to have a viable DIEP flap. There were no communicating arterial branches between the independent vessel and DIEA, however, there was one venous communication between them. A muscle sparing transverse rectus abdominis muscle flap was raised using the main periumbilical perforator from the independent vessel. Our case report demonstrated an unreported anatomical variant of the DIEA. A few anatomical variants have been described in the literature, including a unilateral absent DIEA and peritoneal-cutaneous perforators that had no connection to the DIEA. Doing a pre-operative CTA helps to identify these rare anatomical variations, which leads to safer, more efficient, and effective operating.

Keywords: aberrant anatomy, CT angiography, DIEP anatomy, free flap

Procedia PDF Downloads 134

Authors: Kwangmin Joo

Abstract:

Automatic detection of lumbar vertebrae and classification method is proposed for evaluating the degree of disc narrowing. Prior to classification, deep learning based segmentation is applied to detect individual lumbar vertebra. M-net is applied to segment five lumbar vertebrae and fine-tuning segmentation is employed to improve the accuracy of segmentation. Using the features extracted from previous step, clustering technique, k-means clustering, is applied to estimate the degree of disc space narrowing under four grade scoring system. As preliminary study, techniques proposed in this research could help building an automatic scoring system to diagnose the severity of disc narrowing from X-ray images.

Keywords: Disc space narrowing, Degenerative disc disorders, Deep learning based segmentation, Clustering technique

Procedia PDF Downloads 125

Authors: Ghazala Hcini, Imen Jdey, Hela Ltifi

Abstract:

Malaria disease should be considered and handled as a potential restorative catastrophe. One of the most challenging tasks in the field of microscopy image processing is due to differences in test design and vulnerability of cell classifications. In this article, we focused on applying deep learning to classify patients by identifying images of infected and uninfected cells. We performed multiple forms, counting a classification approach using the Hue, Saturation, Value (HSV) color space. HSV is used since of its superior ability to speak to image brightness; at long last, for classification, a convolutional neural network (CNN) architecture is created. Clusters of focus were used to deliver the classification. The highlights got to be forbidden, and a few more clamor sorts are included in the information. The suggested method has a precision of 99.79%, a recall value of 99.55%, and provides 99.96% accuracy.

Keywords: deep learning, convolutional neural network, image classification, color transformation, HSV color, malaria diagnosis, malaria cells images

Procedia PDF Downloads 88

Authors: Ashish Kumar, Tejendra Dixit, I. A. Palani, Vipul Singh

Abstract:

Zinc oxide, with its interesting properties such as large band gap (3.37eV), high exciton binding energy (60 meV) and intense UV absorption has been studied in literature for various applications viz. optoelectronics, biosensors, UV-photodetectors etc. The performance of ZnO devices is highly influenced by morphologies, size, crystallinity of the ZnO active layer and processing conditions. Recently, our group has shown the influence of the in situ addition of KMnO4 in the precursor solution during the hydrothermal growth of ZnO nanorods (NRs) on their near band edge (NBE) emission. In this paper, we have investigated the effect of post-growth annealing on the variations in NBE and deep level (DL) emissions of as grown ZnO nanorods. These observed results have been explained on the basis of X-ray Diffraction (XRD) and Raman spectroscopic analysis, which clearly show that improved crystalinity and quantum confinement in ZnO nanorods.

Keywords: ZnO, nanorods, hydrothermal, KMnO4

Procedia PDF Downloads 400

Authors: Zahra Khoshnood, Mehdi Kazaie, Sajedeh Neisi

Abstract:

In 2013, 24 fish samples were taken from two fishery regions in the north of Persian Gulf near the Iranian coastal lines. The two flatfishes were Yellofin seabream (Acanthopagrus latus) and Longtail tuna (Thannus tonggol). We analyzed total Hg concentration of liver and muscle tissues by Mercury Analyzer (model LECO AMA 254). The average concentration of total Hg in edible Muscle tissue of deep-Flounder was measured in Bandar-Abbas and was found to be 18.92 and it was 10.19 µg.g-1 in Bandar-Lengeh. The corresponding values for Oriental sole were 8.47 and 0.08 µg.g-1. The average concentration of Hg in liver tissue of deep-Flounder, in Bandar-Abbas was 25.49 and that in Bandar-Lengeh was 12.52 µg.g-1.the values for Oriental sole were 11.88 and 3.2 µg.g-1 in Bandar-Abbas and Bandar-Lengeh, respectively.

Keywords: mercury, Acanthopagrus latus, Thannus tonggol, Persian Gulf

Procedia PDF Downloads 603

Authors: Khadija Bouzaachane, El Mahdi El Guarmah

Abstract:

The classification of low-resolution satellite images has been a worthwhile and fertile field that attracts plenty of researchers due to its importance in monitoring geographical areas. It could be used for several purposes such as disaster management, military surveillance, agricultural monitoring. The main objective of this work is to classify efficiently and accurately low-resolution satellite images by using novel technics of deep learning and reinforcement learning. The images include roads, residential areas, industrial areas, rivers, sea lakes, and vegetation. To achieve that goal, we carried out experiments on the sentinel-2 images considering both high accuracy and efficiency classification. Our proposed model achieved a 91% accuracy on the testing dataset besides a good classification for land cover. Focus on the parameter precision; we have obtained 93% for the river, 92% for residential, 97% for residential, 96% for the forest, 87% for annual crop, 84% for herbaceous vegetation, 85% for pasture, 78% highway and 100% for Sea Lake.

Keywords: classification, deep learning, reinforcement learning, satellite imagery

Procedia PDF Downloads 213

Authors: Girlie D. Leopoldo, Myrna S. Ceniza, Ronnie L. Besagas, Antonio Y. Asoy, Noel T. Dael, Romeo M. Del Rosario

Abstract:

The quality of groundwater from main deep well sources of seven (7) municipalities in Western Misamis Oriental, Philippines was examined. The study looks at the well waters’ physicochemical properties (temperture, pH, turbidity, conductivity, TDS, salinity, chlorides, TOC, and total hardness), the heavy metals and other metals (Pb, Cd, Al, As, Hg, Sb, Zn, Cu, Fe) and their microbiological (total coliform and E. coli) characteristics. The physicochemical properties of groundwater samples were found to be within the Philippine National Standards for Drinking Water (PNSDW)/US-EPA except for the TDS, chlorides, and hardness of some sources. Well waters from both Initao and Gitagum municipalities have TDS values of 643.2 mg/L and 578.4 mg/L, respectively, as compared to PNSDW/US-EPA standard limit of 500 mg/L. These same two municipalities Initao and Gitagum as well as the municipality of Libertad also have chloride levels beyond the 250 mg/L limit of PNSDW/US-EPA/EU with values at 360, 318 and 277 mg/L respectively. The Libertad sample also registered a total hardness of 407.5 mg/L CaCO3 as compared to the 300 mg/L PNSDW limit. These mentioned three (3) municipalities are noticed to have similar geologic structures. Although metal analyses revealed the presence of Zn, Cu and Fe in almost all well water sources, their concentrations are below allowable limit. All well waters from the seven municipalities failed in total coliform count. Escherichia coli were also found in well waters from four (4) municipalities including Laguindingan, Lugait, Gitagum, and Libertad. The presence of these pathogens in the well waters needs to be addressed to make the waters suitable for human consumption.

Keywords: groundwater, deep well, physico-chemical, heavy metal, microbiological

Procedia PDF Downloads 593

Authors: Mohamed Ahmed Khali

Abstract:

Numbers of deep well anode ground beds (GBs) have been retrieved due to un operated anode chains. New identical magnetite anode chains(MAC) have been installed at Raslanuf complex impressed current Cathodic protection(ICCP) system, distributed at different plants(Utility, ethylene and polyethylene). All problems associated with retrieving and installation of MACs have been discussed, rectified and presented. All GB associated severely corroded wellhead casings were well maintained and/ or replaced by new fabricated and modified ones. The main cause of wellhead casings internal corrosion was discussed, and the conducted remedy action to overcome future corrosion problem is presented. All GB connected anode junction boxes (AJBs) and shunts were closely inspected, maintained, and necessary replacement/and or modification were carried out on shunts. All damaged GB concrete foundations (CF) have been inspected and completely replaced. All GB associated Transformer-Rectifiers units (TRUs) were subjected to through inspection, and necessary maintenance has been performed on each individual TRU. After completion of all MACs and TRU maintenance activities, each cathodic protection station (CPS) has been re-operated. An alternative current (AC), direct current (DC), voltage and structure to soil potential (S/P) measurements have been conducted, recorded, and all obtained test results are presented. DC current outputs has been adjusted, and DC current outputs of each MAC has been recorded for each GB AJB.

Keywords: magnatite anode, deep well, ground bed, cathodic protection, transformer rectifies, impreced current, junction box

Procedia PDF Downloads 112

Authors: Muhammad Nawaz, Sandeep N. Kundu, Farha Sattar

Abstract:

Augmented reality sandbox adds new dimensions to education and learning process. It can be a core component of geoscience teaching and learning to understand the geographic contexts and landform processes. Augmented reality sandbox is a useful tool not only to create an interactive learning environment through spatial visualization but also it can provide an active learning experience to students and enhances the cognition process of learning. Augmented reality sandbox can be used as an interactive learning tool to teach geomorphic and landform processes. This article explains the augmented reality sandbox and the constructivism approach for geoscience teaching and learning, and endeavours to explore the ways to teach the geographic processes using the three-dimensional digital environment for the deep learning of the geoscience concepts interactively.

Keywords: augmented reality sandbox, constructivism, deep learning, geoscience

Procedia PDF Downloads 402

Authors: Victor Manuel Alcántara Alza

Abstract:

The way in which the application of the deep cryogenic treatment DCT(-196°C) affects, applied with subsequent aging, was investigated, regarding the mechanical properties of hardness, toughness and microstructure, applied to martensitic stainless steels, with the aim of establishing a different methodology compared to the traditional DCT cryogenic treatment with subsequent tempering. For this experimental study, a muffle furnace was used, first subjecting the specimens to deep cryogenization in a liquid Nitrogen bath/4h, after being previously austenitized at the following temperatures: 1020-1030-1040-1050 (°C) / 1 hour; and then tempered in oil. A first group of cryogenic samples were subjected to subsequent aging at 150°C, with immersion times: 2.5 -5- 10 - 20 - 50 – 100 (h). The next group was subjected to subsequent tempering at temperatures: 480-500-510-520-530-540 (°C)/ 2h. The hardness tests were carried out under standards, using a Universal Durometer, and the readings were made on the HRC scale. The Impact Resistance tests were carried out in a Charpy machine following the ASTM E 23 – 93ª standard. Measurements were taken in joules. Microscopy was performed at the optical level using a 1000X microscope. It was found: For the entire aging interval, the samples austenitized at 1050°C present greater hardness than austenitized at 1040°C, with the maximum peak aged being at 30h. In all cases, the aged samples exceed the hardness of the tempered samples, even in their minimum values. In post-tempered samples, the tempering temperature hardly have effect on the impact strength of material. In the Cryogenic Treatment: DCT + subsequent aging, the maximum hardness value (58.7 HRC) is linked to an impact toughness value (54J) obtained with aging time of 39h, which is considered an optimal condition. The higher hardness of steel after the DCT treatment is attributed to the transformation of retained austenite into martensite. The microstructure is composed mainly of lath martensite; and the original grain size of the austenite can be appreciated. The choice of the combination: Hardness-toughness, is subject to the required service conditions of steel.

Keywords: deep cryogenic treatment; aged precipitation; martensitic steels;, mechanical properties; martensitic steels, hardness, carbides precipitaion

Procedia PDF Downloads 74

Authors: Paola Comella, Vincenzo Francani, Paola Gattinoni

Abstract:

This paper presents the Colzate-Vertova landslide, a Deep Seated Gravitational Slope Deformation (DSGSD) located in the Seriana Valley, Northern Italy. The paper aims at describing the development as well as evaluating the factors that influence the evolution of the landslide. After defining the conceptual model of the landslide, numerical simulations were developed using a finite element numerical model, first with a two-dimensional domain, and later with a three-dimensional one. The results of the 2-D model showed a displacement field typical of a sackung, as a consequence of the erosion along the Seriana Valley. The analysis also showed that the groundwater flow could locally affect the slope stability, bringing about a reduction in the safety factor, but without reaching failure conditions. The sensitivity analysis carried out on the strength parameters pointed out that slope failures could be reached only for relevant reduction of the geotechnical characteristics. Such a result does not fit the real conditions observed on site, where a number of small failures often develop all along the hillslope. The 3-D model gave a more comprehensive analysis of the evolution of the DSGSD, also considering the border effects. The results showed that the convex profile of the slope favors the development of displacements along the lateral valley, with a relevant reduction in the safety factor, justifying the existing landslides.

Keywords: deep seated gravitational slope deformation, Italy, landslide, numerical modeling

Procedia PDF Downloads 365

Authors: Simon Espigolé, Igor Shalyminov, Helen Hastie

Abstract:

Deep machine learning techniques including deep neural networks (DNN) have been used to model language and dialogue for conversational agents to perform tasks, such as giving technical support and also for general chit-chat. They have been shown to be capable of generating long, diverse and coherent sentences in end-to-end dialogue systems and natural language generation. However, these systems tend to imitate the training data and will only generate the concepts and language within the scope of what they have been trained on. This work explores how deep neural networks can be used in a task that would normally require human creativity, whereby the human would read the movie description and/or watch the movie and come up with a compelling, interesting movie title. This task differs from simple summarization in that the movie title may not necessarily be derivable from the content or semantics of the movie description. Here, we train a type of DNN called a sequence-to-sequence model (seq2seq) that takes as input a short textual movie description and some information on e.g. genre of the movie. It then learns to output a movie title. The idea is that the DNN will learn certain techniques and approaches that the human movie titler may deploy that may not be immediately obvious to the human-eye. To give an example of a generated movie title, for the movie synopsis: ‘A hitman concludes his legacy with one more job, only to discover he may be the one getting hit.’; the original, true title is ‘The Driver’ and the one generated by the model is ‘The Masquerade’. A human evaluation was conducted where the DNN output was compared to the true human-generated title, as well as a number of baselines, on three 5-point Likert scales: ‘creativity’, ‘naturalness’ and ‘suitability’. Subjects were also asked which of the two systems they preferred. The scores of the DNN model were comparable to the scores of the human-generated movie title, with means m=3.11, m=3.12, respectively. There is room for improvement in these models as they were rated significantly less ‘natural’ and ‘suitable’ when compared to the human title. In addition, the human-generated title was preferred overall 58% of the time when pitted against the DNN model. These results, however, are encouraging given the comparison with a highly-considered, well-crafted human-generated movie title. Movie titles go through a rigorous process of assessment by experts and focus groups, who have watched the movie. This process is in place due to the large amount of money at stake and the importance of creating an effective title that captures the audiences’ attention. Our work shows progress towards automating this process, which in turn may lead to a better understanding of creativity itself.

Keywords: creativity, deep machine learning, natural language generation, movies

Procedia PDF Downloads 326

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 76

Authors: Lee Bih Ni

Abstract:

This paper discusses that good learning involves all academic groups in the school. Blended learning is learning outside the classroom. Google Classroom is a free service learning app for schools, non-profit organizations and anyone with a personal Google account. Facilities accessed through computers and mobile phones are very useful for school teachers and students. Blended learning classrooms using both traditional and technology-based methods for teaching have become the norm for many educators. Using Google Classroom gives students access to online learning. Even if the teacher is not in the classroom, the teacher can provide learning. This is the supervision of the form of the teacher when the student is outside the school.

Keywords: blended learning, learning app, google classroom, schools

Procedia PDF Downloads 146

Authors: Sheldon McCall, Miao Yu, Liyun Gong, Shigang Yue, Stefanos Kollias

Abstract:

Falls are a significant health concern for older adults globally, and prompt identification is critical to providing necessary healthcare support. Our study proposes a new fall detection method using computer vision based on modern deep learning techniques. Our approach involves training a trans- former model on a large 2D pose dataset for general action recognition, followed by transfer learning. Specifically, we freeze the first few layers of the trained transformer model and train only the last two layers for fall detection. Our experimental results demonstrate that our proposed method outperforms both classical machine learning and deep learning approaches in fall/non-fall classification. Overall, our study suggests that our proposed methodology could be a valuable tool for identifying falls.

Keywords: healthcare, fall detection, transformer, transfer learning

Procedia PDF Downloads 146

Authors: Dayo Samuel Banjo, Connice Trimmingham, Niloofar Yousefi, Nitin Agarwal

Abstract:

Technological advancement and its omnipresent connection have pushed humans past the boundaries and limitations of a computer screen, physical state, or geographical location. It has provided a depth of avenues that facilitate human-computer interaction that was once inconceivable such as audio and body language detection. Given the complex modularities of emotions, it becomes vital to study human-computer interaction, as it is the commencement of a thorough understanding of the emotional state of users and, in the context of social networks, the producers of multimodal information. This study first acknowledges the accuracy of classification found within multimodal emotion detection systems compared to unimodal solutions. Second, it explores the characterization of multimedia content produced based on their emotions and the coherence of emotion in different modalities by utilizing deep learning models to classify emotion across different modalities.

Keywords: affective computing, deep learning, emotion recognition, multimodal

Procedia PDF Downloads 156

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 130

Authors: Chaitanya Chawla, Divya Panwar, Gurneesh Singh Anand, M. P. S Bhatia

Abstract:

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Keywords: image forensics, computer graphics, classification, deep learning, convolutional neural networks

Procedia PDF Downloads 336

Authors: Rui Mao, Heming Ji, Xiaoyu Wang

Abstract:

Keystroke dynamics are widely used in identity recognition. It has the advantage that the individual typing rhythm is difficult to imitate. It also supports continuous authentication through the keyboard without extra devices. The existing keystroke dynamics authentication methods based on machine learning have a drawback in supporting relatively complex scenarios with massive data. There are drawbacks to both feature extraction and model optimization in these methods. To overcome the above weakness, an authentication model of keystroke dynamics based on deep learning is proposed. The model uses feature vectors formed by keystroke content and keystroke time. It ensures efficient continuous authentication by cooperating attention mechanisms with the combination of CNN and Bi-LSTM. The model has been tested with Open Data Buffalo dataset, and the result shows that the FRR is 3.09%, FAR is 3.03%, and EER is 4.23%. This proves that the model is efficient and accurate on continuous authentication.

Keywords: keystroke dynamics, identity authentication, deep learning, CNN, LSTM

Procedia PDF Downloads 155

Authors: Bekkem Chakradhar Reddy, Y. Soni Priya, Mathivanan G., L. K. Joshila Grace, N. Srinivasan, Asha P.

Abstract:

Currently, there are a lot of problems related to marking attendance in schools, offices, or other places. Organizations tasked with collecting daily attendance data have numerous concerns. There are different ways to mark attendance. The most commonly used method is collecting data manually by calling each student. It is a longer process and problematic. Now, there are a lot of new technologies that help to mark attendance automatically. It reduces work and records the data. We have proposed to implement attendance marking using the latest technologies. We have implemented a system based on face identification and analyzing faces. The project is developed by gathering faces and analyzing data, using deep learning algorithms to recognize faces effectively. The data is recorded and forwarded to the host through mail. The project was implemented in Python and Python libraries used are CV2, Face Recognition, and Smtplib.

Keywords: python, deep learning, face recognition, CV2, smtplib, Dlib.

Procedia PDF Downloads 58

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 155