Search results for: deep learning model

Authors: Sakshi V. Tantak, Vishap K. Malik, Neelanjney Pilarisetty

Abstract:

A patent is an exclusive right granted for an invention. It can be a product or a process that provides an innovative method of doing something, or offers a new technical perspective or solution to a problem. A patent can be obtained by making the technical information and details about the invention publicly available. The patent owner has exclusive rights to prevent or stop anyone from using the patented invention for commercial uses. Any commercial usage, distribution, import or export of a patented invention or product requires the patent owner’s consent. It has been observed that the central and important parts of patents are scripted in idiosyncratic and complex linguistic structures that can be difficult to read, comprehend or interpret for the masses. The abstracts of these patents tend to obfuscate the precise nature of the patent instead of clarifying it via direct and simple linguistic constructs. This makes it necessary to have an efficient access to this knowledge via concise and transparent summaries. However, as mentioned above, due to complex and repetitive linguistic constructs and extremely long sentences, common extraction-oriented automatic text summarization methods should not be expected to show a remarkable performance when applied to patent documents. Other, more content-oriented or abstractive summarization techniques are able to perform much better and generate more concise summaries. This paper proposes an efficient summarization system for patents using artificial intelligence, natural language processing and deep learning techniques to condense the knowledge and essential information from a patent document into a single summary that is easier to understand without any redundant formatting and difficult jargon.

Keywords: abstractive summarization, deep learning, natural language Processing, patent document

Procedia PDF Downloads 110

Authors: Yuanchao Sang, Zhihao Gong, Longsheng Chen, Long Chen

Abstract:

Clothing fashion represents a human’s aesthetic appreciation towards everyday outfits and appetite for fashion, and it reflects the development of status in society, humanity, and economics. However, modelling fashion by machine is extremely challenging because fashion is too abstract to be efficiently described by machines. Even human beings can hardly reach a consensus about fashion. In this paper, we are dedicated to answering a fundamental fashion-related problem: what image feature best describes clothing fashion? To address this issue, we have designed and evaluated various image features, ranging from traditional low-level hand-crafted features to mid-level style awareness features to various current popular deep neural network-based features, which have shown state-of-the-art performance in various vision tasks. In summary, we tested the following 9 feature representations: color, texture, shape, style, convolutional neural networks (CNNs), CNNs with distance metric learning (CNNs&DML), AutoEncoder, CNNs with multiple layer combination (CNNs&MLC) and CNNs with dynamic feature clustering (CNNs&DFC). Finally, we validated the performance of these features on two publicly available datasets. Quantitative and qualitative experimental results on both intra-domain and inter-domain fashion clothing image retrieval showed that deep learning based feature representations far outweigh traditional hand-crafted feature representation. Additionally, among all deep learning based methods, CNNs with explicit feature clustering performs best, which shows feature clustering is essential for discriminative fashion feature representation.

Keywords: convolutional neural network, feature representation, image processing, machine modelling

Procedia PDF Downloads 123

Authors: Emanuel Koseos

Abstract:

Data-Driven Decision Making (DDDM) refers to making decisions that are based on historical data in order to inform practice, develop strategies and implement policies that benefit organizational settings. In educational technology, DDDM facilitates the implementation of differential educational learning approaches such as Educational Data Mining (EDM) and Competency-Based Education (CBE), which commonly target university classrooms. There is a current need for DDDM models applied to middle and secondary schools from a concern for assessing the needs, progress and performance of students and educators with respect to regional standards, policies and evolution of curriculums. To address these concerns, we propose a DDDM reference model developed using educational key process initiatives as inputs to a machine learning framework implemented with statistical software (SAS, R) to provide a best-practices, complex-free and automated approach for educators at their regional level. We assessed the efficiency of the model over a six-year period using data from 45 schools and grades K-12 in the Langley, BC, Canada regional school district. We concluded that the model has wider appeal, such as business learning systems.

Keywords: competency-based learning, data-driven decision making, machine learning, secondary schools

Procedia PDF Downloads 158

Authors: Ruqaya H. Aljabery

Abstract:

Reinforced Concrete (RC) deep beams are one of the main critical structural elements in terms of safety since significant loads are carried in a short span. The shear capacity of these sections cannot be predicted accurately by the current design codes like ACI and EC2; thus, they must be investigated. In this research, non-linear behavior of RC deep beams strengthened in shear with Fiber Reinforced Polymer (FRP) strips, and the efficiency of FRP in terms of enhancing the shear capacity in RC deep beams are examined using Finite Element Analysis (FEA), which is conducted using the software ABAQUS. The effect of several parameters on the shear capacity of the RC deep beam are studied in this paper as well including the effect of the cross-sectional area of the FRP strip and the shear reinforcement area to the spacing ratio (As/S), and it was found that FRP enhances the shear capacity significantly and can be a substitution of steel stirrups resulting in a more economical design.

Keywords: Abaqus, concrete, deep beam, finite element analysis, FRP, shear strengthening, strut-and-tie

Procedia PDF Downloads 131

Authors: Rong Wang, Sandra Hasanefendic, Elizabeth von Hauff, Bart Bossink

Abstract:

Technological learning and learning curve models have been continuously used to estimate the photovoltaics (PV) cost development over time for the climate mitigation targets. They can integrate a number of technological learning sources which influence the learning process. Yet the accuracy and realistic predictions for cost estimations of PV development are still difficult to achieve. This paper develops four hypothetical-alternative learning curve models by proposing different combinations of technological learning sources, including both local and global technology experience and the knowledge stock. This paper specifically focuses on the non-linear relationship between the costs and technological learning source and their dynamic interaction and uses the system dynamics approach to predict a more accurate PV cost estimation for future development. As the case study, the data from China is gathered and drawn to illustrate that the learning curve model that incorporates both the global and local experience is more accurate and realistic than the other three models for PV cost estimation. Further, absorbing and integrating the global experience into the local industry has a positive impact on PV cost reduction. Although the learning curve model incorporating knowledge stock is not realistic for current PV cost deployment in China, it still plays an effective positive role in future PV cost reduction.

Keywords: photovoltaic, system dynamics, technological learning, learning curve

Procedia PDF Downloads 81

Authors: Omar Alzeley, Sergey Utev

Abstract:

Minimizing a constrained multivariate function is the fundamental of Machine learning, and these algorithms are at the core of data mining and data visualization techniques. The decision function that maps input points to output points is based on the result of optimization. This optimization is the central of learning theory. One approach to complex systems where the dynamics of the system is inferred by a statistical analysis of the fluctuations in time of some associated observable is time series analysis. The purpose of this paper is a mathematical transition from the autoregressive model of classical time series to the matrix formalization of quantum theory. Firstly, we have proposed a quantum time series model (QTS). Although Hamiltonian technique becomes an established tool to detect a deterministic chaos, other approaches emerge. The quantum probabilistic technique is used to motivate the construction of our QTS model. The QTS model resembles the quantum dynamic model which was applied to financial data. Secondly, various statistical methods, including machine learning algorithms such as the Kalman filter algorithm, are applied to estimate and analyses the unknown parameters of the model. Finally, simulation techniques such as Markov chain Monte Carlo have been used to support our investigations. The proposed model has been examined by using real and simulated data. We establish the relation between quantum statistical machine and quantum time series via random matrix theory. It is interesting to note that the primary focus of the application of QTS in the field of quantum chaos was to find a model that explain chaotic behaviour. Maybe this model will reveal another insight into quantum chaos.

Keywords: machine learning, simulation techniques, quantum probability, tensor product, time series

Procedia PDF Downloads 451

Authors: Gyoomi Kim, Jiyoung Bae

Abstract:

The purpose of this study was to propose a framework that verifies the structural relationships among students’ use of digital English learning strategy (DELS), affective domains, and their individual variables. The study developed a hypothetical model based on previous studies on language learning strategy use as well as digital language learning. The participants were 720 Korean high school students and 430 university students. The instrument was a self-response questionnaire that contained 70 question items based on Oxford’s SILL (Strategy Inventory for Language Learning) as well as the previous studies on language learning strategies in digital learning environment in order to measure DELS and affective domains. The collected data were analyzed through structural equation modeling (SEM). This study used quantitative data analysis procedures: Explanatory factor analysis (EFA) and confirmatory factor analysis (CFA). Firstly, the EFA was conducted in order to verify the hypothetical model; the factor analysis was conducted preferentially to identify the underlying relationships between measured variables of DELS and the affective domain in the EFA process. The hypothetical model was established with six indicators of learning strategies (memory, cognitive, compensation, metacognitive, affective, and social strategies) under the latent variable of the use of DELS. In addition, the model included four indicators (self-confidence, interests, self-regulation, and attitude toward digital learning) under the latent variable of learners’ affective domain. Secondly, the CFA was used to determine the suitability of data and research models, so all data from the present study was used to assess model fits. Lastly, the model also included individual learner factors as covariates and five constructs selected were learners’ gender, the level of English proficiency, the duration of English learning, the period of using digital devices, and previous experience of digital English learning. The results verified from SEM analysis proposed a theoretical model that showed the structural relationships between Korean students’ use of DELS and their affective domains. Therefore, the results of this study help ESL/EFL teachers understand how learners use and develop appropriate learning strategies in digital learning contexts. The pedagogical implication and suggestions for the further study will be also presented.

Keywords: Digital English Learning Strategy, DELS, individual variables, learners' affective domains, Structural Equation Modeling, SEM

Procedia PDF Downloads 111

Authors: Abdulwakeel B. Raji

Abstract:

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

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

Procedia PDF Downloads 122

Authors: Chia-Yi Liu, Bo-Bin Xiao, Wen-Bin Lin, Hsiang-Ning Wu, Liang-Hsun Huang

Abstract:

In order to reduce the risk of radiation damage that personnel may suffer during operations in the radiation environment, the use of automated guided vehicles to assist or replace on-site personnel in the radiation environment has become a key technology and has become an important trend. In this paper, we demonstrate our proof of concept for autonomous self-learning radiation source searcher in an unknown environment without a map. The research uses GPU version of Asynchronous Advantage Actor-Critic network (GA3C) of deep reinforcement learning to search for radiation sources. The searcher network, based on GA3C architecture, has self-directed learned and improved how search the anomalous radiation source by training 1 million episodes under three simulation environments. In each episode of training, the radiation source position, the radiation source intensity, starting position, are all set randomly in one simulation environment. The input for searcher network is the fused data from a 2D laser scanner and a RGB-D camera as well as the value of the radiation detector. The output actions are the linear and angular velocities. The searcher network is trained in a simulation environment to accelerate the learning process. The well-performance searcher network is deployed to the real unmanned vehicle, Dashgo E2, which mounts LIDAR of YDLIDAR G4, RGB-D camera of Intel D455, and radiation detector made by Institute of Nuclear Energy Research. In the field experiment, the unmanned vehicle is enable to search out the radiation source of the 18.5MBq Na-22 by itself and avoid obstacles simultaneously without human interference.

Keywords: deep reinforcement learning, GA3C, source searching, source detection

Procedia PDF Downloads 97

Authors: Neerav Kumar, Naumaan Nayyar, Sharath Kashyap

Abstract:

Most companies see an increase in the adoption of machine learning (ML) applications across internal and external-facing use cases. ML applications vend output either in batch or real-time patterns. A complete batch ML pipeline architecture comprises data sourcing, feature engineering, model training, model deployment, model output vending into a data store for downstream application. Due to unclear role expectations, we have observed that scientists specializing in building and optimizing models are investing significant efforts into building the other components of the architecture, which we do not believe is the best use of scientists’ bandwidth. We propose a system architecture created using AWS services that bring industry best practices to managing the workflow and simplifies the process of model deployment and end-to-end data integration for an ML application. This narrows down the scope of scientists’ work to model building and refinement while specialized data engineers take over the deployment, pipeline orchestration, data quality, data permission system, etc. The pipeline infrastructure is built and deployed as code (using terraform, cdk, cloudformation, etc.) which makes it easy to replicate and/or extend the architecture to other models that are used in an organization.

Keywords: data pipeline, machine learning, AWS, architecture, batch machine learning

Procedia PDF Downloads 47

Authors: Jixiang Lei, Alexander Fuchs, Franz Pernkopf, Katrin Ellermann

Abstract:

Within the Space@Sea project, funded by the Horizon 2020 program, an island consisting of multiple platforms was designed. The platforms are connected by ropes and fenders. The connection is critical with respect to the safety of the whole system. Therefore, fault detection systems are investigated, which could detect early warning signs for a possible failure in the connection elements. Previously, a model-based method called Extended Kalman Filter was developed to detect the reduction of rope stiffness. This method detected several types of faults reliably, but some types of faults were much more difficult to detect. Furthermore, the model-based method is sensitive to environmental noise. When the wave height is low, a long time is needed to detect a fault and the accuracy is not always satisfactory. In this sense, it is necessary to develop a more accurate and robust technique that can detect all rope faults under a wide range of operational conditions. Inspired by this work on the Space at Sea design, we introduce a fault diagnosis method based on deep neural networks. Our method cannot only detect rope degradation by using the acceleration data from each platform but also estimate the contributions of the specific acceleration sensors using methods from explainable AI. In order to adapt to different operational conditions, the domain adaptation technique DANN is applied. The proposed model can accurately estimate rope degradation under a wide range of environmental conditions and help users understand the relationship between the output and the contributions of each acceleration sensor.

Keywords: fault diagnosis, deep learning, domain adaptation, explainable AI

Procedia PDF Downloads 161

Authors: Wanwadee Neamsakul

Abstract:

VARK learning style is an effective method of learning that could enhance all skills of the students like visual (V), auditory (A), read/write (R), and kinesthetic (K). This learning style benefits the students in terms of professional competencies, critical thinking and lifelong learning which are the desirable characteristics of the nursing students. This study aimed to develop a model of teaching and learning clinical practicum at postpartum ward for nursing students by using VARK learning styles, and evaluate the nursing students’ opinions about the developmental model. A methodology used for this study was research and development (R&D). The model was developed by focus group discussion with five obstetric nursing instructors who have experiences teaching Maternal Newborn and Midwifery I subject. The activities related to practices in the postpartum (PP) ward including all skills of VARK were assigned into the matrix table. The researcher asked the experts to supervise the model and adjusted the model following the supervision. Subsequently, it was brought to be tried out with the nursing students who practiced on the PP ward. Thirty third year nursing students from one of the northern Nursing Colleges, Academic year 2015 were purposive sampling. The opinions about the satisfaction of the model were collected using a questionnaire which was tested for its validity and reliability. Data were analyzed using descriptive statistics. The developed model composed of 27 activities. Seven activities were developed as enhancement of visual skills for the nursing students (25.93%), five activities as auditory skills (18.52%), six activities as read and write skills (22.22%), and nine activities as kinesthetic skills (33.33%). Overall opinions about the model were reported at the highest level of average satisfaction (mean=4.63, S.D=0.45). In the aspects of visual skill (mean=4.80, S.D=0.45) was reported at the highest level of average satisfaction followed by auditory skill (mean=4.62, S.D=0.43), read and write skill (mean=4.57, S.D=0.46), and kinesthetic skill (mean=4.53, S.D=0.45) which were reported at the highest level of average satisfaction, respectively. The nursing students reported that the model could help them employ all of their skills during practicing and taking care of the postpartum women and newborn babies. They could establish self-confidence while providing care and felt proud of themselves by the benefits of the model. It can be said that using VARK learning style to develop the model could enhance both nursing students’ competencies and positive attitude towards the nursing profession. Consequently, they could provide quality care for postpartum women and newborn babies effectively in the long run.

Keywords: model, nursing students, postpartum ward, teaching and learning clinical practicum

Procedia PDF Downloads 134

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 91

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 353

Authors: Damian Gordon, Paul Doyle, Anna Becevel, Júlia Vilafranca Molero, Cinta Gascon, Arianna Vitiello, Tina Baloh

Abstract:

It has long been recognized that the creation of any teaching content can be enhanced if the development process follows a pre-defined approach, which is often referred to as an instructional design methodology. These methodologies typically define a number of stages, or phases, that an educator should undertake to help ensure the quality of the final teaching content that is developed. In this paper, we present an instructional design methodology that is focused specifically on the introduction of blended resources into a heretofore bricks-and-mortar course. To achieve this, research was undertaken concerning a range of models of instructional design, as well as literature covering some of the key challenges and “pain points” of blending. Following this, our model, the BL-5D model, is presented, which incorporates some key questions at each stage of this five-stage methodology to guide the development process. Finally, a discussion of some of the key themes and issues that have been uncovered in this work is presented, as well as a template for a blended learning case study that emerged from this approach.

Keywords: blended learning, challenges of blended learning, design methodologies, instructional design

Procedia PDF Downloads 94

Authors: Hana' Al-Ghanim, Mu'tasim Abdel-Jaber, Maha Alqam

Abstract:

This experimental investigation deals with shear strengthening of reinforced concrete (RC) deep beams using the externally bonded carbon fiber-reinforced polymer (CFRP) composites. The current study, therefore, evaluates the effectiveness of four various configurations for shear strengthening of deep beams with two different types of CFRP materials including sheets and laminates. For this purpose, a total of 10 specimens of deep beams were cast and tested. The shear performance of the strengthened beams is assessed with respect to the cracks’ formation, modes of failure, ultimate strength and the overall stiffness. The obtained results demonstrate the effectiveness of using the CFRP technique on enhancing the shear capacity of deep beams; however, the efficiency varies depending on the material used and the strengthening scheme adopted. Among the four investigated schemes, the highest increase in the ultimate strength is recorded by using the continuous wrap of two layers of CFRP sheets, exceeding a value of 86%, whereas an enhancement of about 36% is achieved by the inclined CFRP laminates.

Keywords: deep beams, laminates, shear strengthening, sheets

Procedia PDF Downloads 342

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 60

Authors: Zhifeng Kong

Abstract:

Over-parameterized neural networks have attracted a great deal of attention in recent deep learning theory research, as they challenge the classic perspective of over-fitting when the model has excessive parameters and have gained empirical success in various settings. While a number of theoretical works have been presented to demystify properties of such models, the convergence properties of such models are still far from being thoroughly understood. In this work, we study the convergence properties of training two-hidden-layer partially over-parameterized fully connected networks with the Rectified Linear Unit activation via gradient descent. To our knowledge, this is the first theoretical work to understand convergence properties of deep over-parameterized networks without the equally-wide-hidden-layer assumption and other unrealistic assumptions. We provide a probabilistic lower bound of the widths of hidden layers and proved linear convergence rate of gradient descent. We also conducted experiments on synthetic and real-world datasets to validate our theory.

Keywords: over-parameterization, rectified linear units ReLU, convergence, gradient descent, neural networks

Procedia PDF Downloads 130

Authors: Gurukiran Veerapur, Nytik Birudavolu, Seetharam U. N., Chandravva Hebbi, R. Praneeth Reddy

Abstract:

This work presents a robust approach for the recognition of characters in Telugu and Kannada, two South Indian scripts with structural similarities in characters. To recognize the characters exhaustive datasets are required, but there are only a few publicly available datasets. As a result, we decided to create a dataset for one language (source language),train the model with it, and then test it with the target language.Telugu is the target language in this work, whereas Kannada is the source language. The suggested method makes use of Canny edge features to increase character identification accuracy on pictures with noise and different lighting. A dataset of 45,150 images containing printed Kannada characters was created. The Nudi software was used to automatically generate printed Kannada characters with different writing styles and variations. Manual labelling was employed to ensure the accuracy of the character labels. The deep learning models like CNN (Convolutional Neural Network) and Visual Attention neural network (VAN) are used to experiment with the dataset. A Visual Attention neural network (VAN) architecture was adopted, incorporating additional channels for Canny edge features as the results obtained were good with this approach. The model's accuracy on the combined Telugu and Kannada test dataset was an outstanding 97.3%. Performance was better with Canny edge characteristics applied than with a model that solely used the original grayscale images. The accuracy of the model was found to be 80.11% for Telugu characters and 98.01% for Kannada words when it was tested with these languages. This model, which makes use of cutting-edge machine learning techniques, shows excellent accuracy when identifying and categorizing characters from these scripts.

Keywords: base characters, modifiers, guninthalu, aksharas, vattakshara, VAN

Procedia PDF Downloads 37

Authors: Keyi Wang

Abstract:

Similar to the touchscreen, hand gesture based human-computer interaction (HCI) is a technology that could allow people to perform a variety of tasks faster and more conveniently. This paper proposes a training method of an image-based hand gesture image and video clip recognition system using a CNN (Convolutional Neural Network) with a dataset. A dataset containing 6 hand gesture images is used to train a 2D CNN model. ~98% accuracy is achieved. Furthermore, a 3D CNN model is trained on a dataset containing 4 hand gesture video clips resulting in ~83% accuracy. It is demonstrated that a Cozmo robot loaded with pre-trained models is able to recognize static and dynamic hand gestures.

Keywords: deep learning, hand gesture recognition, computer vision, image processing

Procedia PDF Downloads 119

Authors: Mafawez Alharbi, Mahdi Jemmali

Abstract:

E-learning is a developing area especially in education. E-learning can provide several benefits to learners. An intelligent system to collect all components satisfying user preferences is so important. This research presents an approach that it capable to personalize e-information and give the user their needs following their preferences. This proposal can make some knowledge after more evaluations made by the user. In addition, it can learn from the habit from the user. Finally, we show a walk-through to prove how intelligent process work.

Keywords: artificial intelligence, architecture, e-learning, software engineering, processing

Procedia PDF Downloads 174

Authors: Nathenal Thomas

Abstract:

In the food chain and in many other agricultural products, corn, also known as maize, which goes by the scientific name Zea mays subsp, is a widely produced agricultural product. Corn has the highest adaptability. It comes in many different types, is employed in many different industrial processes, and is more adaptable to different agro-climatic situations. In Ethiopia, maize is among the most widely grown crop. Small-scale corn farming may be a household's only source of food in developing nations like Ethiopia. The aforementioned data demonstrates that the country's requirement for this crop is excessively high, and conversely, the crop's productivity is very low for a variety of reasons. The most damaging disease that greatly contributes to this imbalance between the crop's supply and demand is the corn disease. The failure to diagnose diseases in maize plant until they are too late is one of the most important factors influencing crop output in Ethiopia. This study will aid in the early detection of such diseases and support farmers during the cultivation process, directly affecting the amount of maize produced. The diseases in maize plants, such as northern leaf blight and cercospora leaf spot, have distinct symptoms that are visible. This study aims to detect the most frequent and degrading maize diseases using the most efficiently used subset of machine learning technology, deep learning so, called Image Processing. Deep learning uses networks that can be trained from unlabeled data without supervision (unsupervised). It is a feature that simulates the exercises the human brain goes through when digesting data. Its applications include speech recognition, language translation, object classification, and decision-making. Convolutional Neural Network (CNN) for Image Processing, also known as convent, is a deep learning class that is widely used for image classification, image detection, face recognition, and other problems. it will also use this algorithm as the state-of-the-art for my research to detect maize diseases by photographing maize leaves using a mobile phone.

Keywords: CNN, zea mays subsp, leaf blight, cercospora leaf spot

Procedia PDF Downloads 61

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 58

Authors: Javad Abdi, Azam Famil Khalili

Abstract:

Modeling emotions have attracted much attention in recent years, both in cognitive psychology and design of artificial systems. However, it is a negative factor in decision-making; emotions have shown to be a strong faculty for making fast satisfying decisions. In this paper, we have adapted a computational model based on the limbic system in the mammalian brain for control engineering applications. Learning in this model based on Temporal Difference (TD) Learning, we applied the proposed controller (termed BELBIC) for a simple model of a submarine. The model was supposed to reach the desired depth underwater. Our results demonstrate excellent control action, disturbance handling, and system parameter robustness for TDBELBIC. The proposal method, regarding the present conditions, the system action in the part and the controlling aims, can control the system in a way that these objectives are attained in the least amount of time and the best way.

Keywords: artificial neural networks, temporal difference, brain emotional learning based intelligent controller, heating- ventilating and air conditioning

Procedia PDF Downloads 422

Authors: Xinyi Le

Abstract:

In this paper, 3D printing orientations were determined through our perceptual model. Some FDM (Fused Deposition Modeling) 3D printers, which are widely used in universities and industries, often require support structures during the additive manufacturing. After removing the residual material, some surface artifacts remain at the contact points. These artifacts will damage the function and visual effect of the model. To prevent the impact of these artifacts, we present a fuzzy extreme learning machine approach to find printing directions that avoid placing supports in perceptually significant regions. The proposed approach is able to solve the evaluation problem by combing both the subjective knowledge and objective information. Our method combines the advantages of fuzzy theory, auto-encoders, and extreme learning machine. Fuzzy set theory is applied for dealing with subjective preference information, and auto-encoder step is used to extract good features without supervised labels before extreme learning machine. An extreme learning machine method is then developed successfully for training and learning perceptual models. The performance of this perceptual model will be demonstrated on both natural and man-made objects. It is a good human-computer interaction practice which draws from supporting knowledge on both the machine side and the human side.

Keywords: 3d printing, perceptual model, fuzzy evaluation, data-driven approach

Procedia PDF Downloads 423

Authors: Vincent Liu

Abstract:

Machine learning algorithms (ML) can achieve high accuracy in predicting outcomes compared to classical models. Metaheuristic, nature-inspired algorithms can enhance traditional ML algorithms by optimizing them such as by performing feature selection. We compare ten ML algorithms to predict 30-day hospital readmission rates for diabetes patients in the US using a dataset from UCI Machine Learning Repository with feature selection performed by Greywolf nature-inspired algorithm. The baseline accuracy for the initial random forest model was 65%. After performing feature engineering, SMOTE for class balancing, and Greywolf optimization, the machine learning algorithms showed better metrics, including F1 scores, accuracy, and confusion matrix with improvements ranging in 10%-30%, and a best model of XGBoost with an accuracy of 95%. Applying machine learning this way can improve patient outcomes as unnecessary rehospitalizations can be prevented by focusing on patients that are at a higher risk of readmission.

Keywords: diabetes, machine learning, 30-day readmission, metaheuristic

Procedia PDF Downloads 38

Authors: Rabia Aslam

Abstract:

Overwhelming evidence from all around the world suggests that high-quality teacher professional development facilitates the improvement of teaching practices which in turn could improve student learning outcomes. The new Continuous Professional Development (CPD) model for primary school teachers in Punjab uses a blended approach in which pedagogical content knowledge is delivered through technology (high-quality instructional videos and lesson plans delivered to school tablets or mobile phones) with face-to-face support by Assistant Education Officers (AEOs). The model also develops Communities of Practice operationalized through formal meetings led by the AEOs and informal interactions through social media groups to provide opportunities for teachers to engage with each other and share their ideas, reflect on learning, and come up with solutions to issues they experience. Using Kirkpatrick’s 4 levels of the learning evaluation model, this paper investigates how school tablets and teacher mobile phones may act as transformational cultural tools to potentially expand perceptions and access to teaching and learning resources and explore some of the affordances of social media (Facebook, WhatsApp groups) in learning in an informal context. The results will be used to inform policy-level decisions on what shape could CPD of all teachers take in the context of a developing country like Pakistan.

Keywords: CPD, teaching & learning, blended learning, learning technologies

Procedia PDF Downloads 63

Authors: Badiossadat Hassanpour, Reza Sirjani, Nangkuala Utaberta

Abstract:

The avant-garde educational systems are striving to find a life long learning methods. Different fields and majors have test variety of proposed models, and found their difficulties and strengths. Architecture as a critical stage of education due to its characteristics which are learning by doing and critique based education and evaluation is out of this study procedure. Learning contracts is a new alternative form of evaluation of students’ achievements, while it acts as agreement about learning goals. Obtained results from studies in different fields which confirm its positive impact on students' learning in those fields and positively affected students' motivation and confidence in meeting their own learning needs, prompted us to implement this model in architecture design studio. In this implemented contract to the studio, students were asked to use the existing possibility of contract to have self assessment and examine their professional development to identify whether they are deficient or they would like to develop more expertise. The evidences of this research as well indicate that students feel positive about the learning contract and see it accommodating their individual learning needs.

Keywords: contract (LC), architecture design studio, education, student-centered learning

Procedia PDF Downloads 426

Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi

Abstract:

Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.

Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models

Procedia PDF Downloads 100

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 92