Search results for: deep graphical model

Authors: S. Sharan Sundar, Nithish B. Moudhgalya, Nidhi Bhandari, Vineeth Vijayaraghavan

Abstract:

Automatic Short Answer Grading is one of the prime applications of artificial intelligence in education. Several approaches involving the utilization of selective handcrafted features, graphical matching techniques, concept identification and mapping, complex deep frameworks, sentence embeddings, etc. have been explored over the years. However, keeping in mind the real-world application of the task, these solutions present a slight overhead in terms of computations and resources in achieving high performances. In this work, a simple and effective solution making use of elemental features based on statistical, linguistic properties, and word-based similarity measures in conjunction with tree-based classifiers and regressors is proposed. The results for classification tasks show improvements ranging from 1%-30%, while the regression task shows a stark improvement of 35%. The authors attribute these improvements to the addition of multiple similarity scores to provide ensemble of scoring criteria to the models. The authors also believe the work could reinstate that classical natural language processing techniques and simple machine learning models can be used to achieve high results for short answer grading.

Keywords: artificial intelligence, intelligent systems, natural language processing, text mining

Procedia PDF Downloads 124

Authors: Adeep Hande, Shubham Agarwal

Abstract:

This paper presents a study on identifying sexism in online texts using various state-of-the-art deep learning models based on BERT. We experimented with different feature sets and model architectures and evaluated their performance using precision, recall, F1 score, and accuracy metrics. We also explored the use of pseudolabeling technique to improve model performance. Our experiments show that the best-performing models were based on BERT, and their multilingual model achieved an F1 score of 0.83. Furthermore, the use of pseudolabeling significantly improved the performance of the BERT-based models, with the best results achieved using the pseudolabeling technique. Our findings suggest that BERT-based models with pseudolabeling hold great promise for identifying sexism in online texts with high accuracy.

Keywords: large language models, semi-supervised learning, sexism detection, data sparsity

Procedia PDF Downloads 57

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 169

Authors: Jiaxin Shi, Kaifeng Hao, Qingfan An, Zeng Peng

Abstract:

Due to a lack of data sources and data processing techniques, it has always been difficult to quantify public space quality, which includes urban construction quality and how it is perceived by people, especially in large urban areas. This study proposes a quantitative research method based on the consideration of emotional health and physical health of the built environment. It highlights the low quality of public areas in Tianjin, China, where there are many negative elements. Deep learning technology is then used to measure how effectively people perceive urban areas. First, this work suggests a deep learning model that might simulate how people can perceive the quality of urban construction. Second, we perform semantic segmentation on street images to identify visual elements influencing scene perception. Finally, this study correlated the scene perception score with the proportion of visual elements to determine the surrounding environmental elements that influence scene perception. Using a small-scale labeled Tianjin street view data set based on transfer learning, this study trains five negative spatial discriminant models in order to explore the negative space distribution and quality improvement of urban streets. Then it uses all Tianjin street-level imagery to make predictions and calculate the proportion of negative space. Visualizing the spatial distribution of negative space along the Tianjin Inner Ring Road reveals that the negative elements are mainly found close to the five key districts. The map of Tianjin was combined with the experimental data to perform the visual analysis. Based on the emotional assessment, the distribution of negative materials, and the direction of street guidelines, we suggest guidance content and design strategy points of the negative phenomena in Tianjin street space in the two dimensions of perception and substance. This work demonstrates the utilization of deep learning techniques to understand how people appreciate high-quality urban construction, and it complements both theory and practice in urban planning. It illustrates the connection between human perception and the actual physical public space environment, allowing researchers to make urban interventions.

Keywords: human perception, public space quality, deep learning, negative elements, street images

Procedia PDF Downloads 99

Authors: Atara Shriki, Ilana Lavy

Abstract:

In a rapidly changing technological society, creativity is considered as an engine of economic and social progress. No doubt the education system has a central role in nurturing all students’ creativity, however, it is normally not encouraged at school. The causes of this reality are related to a variety of circumstances, among them: external pressures to cover the curriculum and succeed in standardized tests that mostly require algorithmic thinking and implementation of rules; teachers’ tendency to teach similarly to the way they themselves were taught as school students; relating creativity to giftedness, and therefore avoid nurturing all students' creativity; lack of adequate learning materials and accessible tools for following and evaluating the development of students’ creativity; and more. Since success in academic studies requires, among other things, creativity, lecturers in higher education institutions should consider appropriate ways to nurture students’ creative thinking and assess its development. Obviously, creativity has a multifaceted nature, numerous definitions, various perspectives for studying its essence (e.g., process, personality, environment, and product), and several approaches aimed at evaluating and assessing creative expressions (e.g., cognitive, social-personal, and psychometric). In this framework, we suggest nurturing students’ creativity through engaging them in problem posing activities that are part of inquiry assignments. In order to assess the development of their creativity, we propose to employ a model that was designed for this purpose, based on the psychometric approach, viewing the posed problems as the “creative product”. The model considers four measurable aspects- fluency, flexibility, originality, and organization, as well as a total score of creativity that reflects the relative weights of each aspect. The scores given to learners are of two types: (1) Total scores- the absolute number of posed problems with respect to each of the four aspects, and a final score of creativity; (2) Relative scores- each absolute number is transformed into a number that relates to the relative infrequency of the posed problems in student’s reference group. Through converting the scores received over time into a graphical display, students can assess their progress both with respect to themselves and relative to their reference group. Course lecturers can get a picture of the strengths and weaknesses of each student as well as the class as a whole, and to track changes that occur over time in response to the learning environment they had generated. Such tracking may assist lecturers in making pedagogical decisions about emphases that should be put on one or more aspects of creativity, and about the students that should be given a special attention. Our experience indicates that schoolteachers and lecturers in higher education institutes find the combination of engaging learners in problem posing along with self-assessment of their progress through utilizing the graphical display of accumulating total and relative scores has the potential to realize most learners’ creative potential.

Keywords: creativity, problem posing, psychometric model, self-assessment

Procedia PDF Downloads 305

Authors: Pranjal Srivastava, Piyali Sengupta

Abstract:

The performance of marine drilling risers is crucial in the offshore oil and gas industry to ensure safe drilling operation with minimum downtime. Experimental investigations on marine drilling risers are limited in the literature owing to the expensive and exhaustive test setup required to replicate the realistic riser model and ocean environment in the laboratory. Therefore, this study presents an analytical model of marine drilling riser for determining its fragility under ocean environmental loading. In this study, the marine drilling riser is idealized as a continuous beam having a concentric circular cross-section. Hydrodynamic loading acting on the marine drilling riser is determined by Morison’s equations. By considering the equilibrium of forces on the marine drilling riser for the connected and normal drilling conditions, the governing partial differential equations in terms of independent variables z (depth) and t (time) are derived. Subsequently, the Runge Kutta method and Finite Difference Method are employed for solving the partial differential equations arising from the analytical model. The proposed analytical approach is successfully validated with respect to the experimental results from the literature. From the dynamic analysis results of the proposed analytical approach, the critical design parameters peak displacements, upper and lower flex joint rotations and von Mises stresses of marine drilling risers are determined. An extensive parametric study is conducted to explore the effects of top tension, drilling depth, ocean current speed and platform drift on the critical design parameters of the marine drilling riser. Thereafter, incremental dynamic analysis is performed to derive the fragility functions of shallow water and deep-water marine drilling risers under ocean environmental loading. The proposed methodology can also be adopted for downtime estimation of marine drilling risers incorporating the ranges of uncertainties associated with the ocean environment, especially at deep and ultra-deepwater.

Keywords: drilling riser, marine, analytical model, fragility

Procedia PDF Downloads 132

Authors: Shanxiong Chen, Xu Han, Xiaolong Wang, Hui Ma

Abstract:

Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.

Keywords: recognition, CNN, Yi character, divergence

Procedia PDF Downloads 153

Authors: Lizhi Ma, Chengcheng Hu, Fuxian Wong

Abstract:

Partial reduce (P-Reduce) has set a state-of-the-art performance on distributed machine learning in the heterogeneous environment over the All-Reduce architecture. The dynamic P-Reduce based on the exponential moving average (EMA) approach predicts all the intermediate model parameters, which raises unreliability. It is noticed that the approximation trick leads the wrong way to obtaining model parameters in all the nodes. In this paper, SAP-Reduce is proposed, which is a variant of the All-Reduce distributed training model with staleness-aware dynamic P-Reduce. SAP-Reduce directly utilizes the EMA-like algorithm to generate the normalized weights. To demonstrate the effectiveness of the algorithm, the experiments are set based on a number of deep learning models, comparing the single-step training acceleration ratio and convergence time. It is found that SAP-Reduce simplifying dynamic P-Reduce outperforms the intermediate approximation one. The empirical results show SAP-Reduce is 1.3× −2.1× faster than existing baselines.

Keywords: collective communication, decentralized distributed training, machine learning, P-Reduce

Procedia PDF Downloads 12

Authors: Hee-Chang Lim

Abstract:

The study aims to understand the surface pressure distribution around the bodies such as the suction pressure in the leading edge on the top and side-face when the aspect ratio of bodies and the wind direction are changed, respectively. We carried out the wind tunnel measurement and numerical simulation around a series of rectangular bodies (40^d×80^w×80^h, 80^d×80^w×80^h, 160^d×80^w×80^h, 80^d×40^w×80^h and 80^d×160^w×80^h in mm³) placed in a deep turbulent boundary layer. Based on a modern numerical platform, the Navier-Stokes equation with the typical 2-equation (k-ε model) and the DES (Detached Eddy Simulation) turbulence model has been calculated, and they are both compared with the measurement data. Regarding the turbulence model, the DES model makes a better prediction comparing with the k-ε model, especially when calculating the separated turbulent flow around a bluff body with sharp edged corner. In order to observe the effect of wind direction on the pressure variation around the cube (e.g., 80^d×80^w×80^h in mm), it rotates at 0º, 10º, 20º, 30º, and 45º, which stands for the salient wind directions in the tunnel. The result shows that the surface pressure variation is highly dependent upon the approaching wind direction, especially on the top and the side-face of the cube. In addition, the transverse width has a substantial effect on the variation of surface pressure around the bodies, while the longitudinal length has little or no influence.

Keywords: rectangular bodies, wind direction, aspect ratio, surface pressure distribution, wind-tunnel measurement, k-ε model, DES model, CFD

Procedia PDF Downloads 222

Authors: Riddhi Jangid, Gajendra Pratap Singh

Abstract:

Petri nets, a mathematical tool, is used for modeling in different areas of computer sciences, biological networks, chemical systems and many other disciplines. A Petri net model of a given system is created by the graphical representation that describes the properties and behavior of the system. While looking for the behavior of any system, 1-safe Petri nets are of particular interest to many in the application part. Boolean Petri nets correspond to those class in 1- safe Petri nets that generate all the binary n-vectors in their reachability analysis. We study the class by changing different parameters like the token counts in the places and how the structure of the tree changes in the reachability analysis. We discuss here an extended class of Boolean Petri nets that generates n-ary trees in their reachability-based analysis.

Keywords: marking vector, n-vector, petri nets, reachability

Procedia PDF Downloads 70

Authors: Davide Fuscà, Kanan Rahimli, Roberto Leuzzi

Abstract:

Preventing abuse and illegal activities in a given area of the sea is a very difficult and expensive task. Artificial intelligence offers the possibility to implement new methods to identify the vessel class type from the kinematic features of the vessel itself. The task strictly depends on the quality of the data. This paper explores the application of a deep, long short-term memory model by using AIS flow only with a relatively low quality. The proposed model reaches high accuracy on detecting nine vessel classes representing the most common vessel types in the Ionian-Adriatic Sea. The model has been applied during the Adriatic-Ionian trial period of the international EU ANDROMEDA H2020 project to identify vessels performing behaviors far from the expected one depending on the declared type.

Keywords: maritime surveillance, artificial intelligence, behavior analysis, LSTM

Procedia PDF Downloads 220

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 84

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 108

Authors: A. M. Gsiea, J. P. Goss, P. R. Briddon, Ramadan. M. Al-habashi, K. M. Etmimi, Khaled. A. S. Marghani

Abstract:

Using first-principles methods based on density functional theory and pseudopotentials, we have performed a details study of native defects in ZnO. Native point defects are unlikely to be cause of the unintentional n-type conductivity. Oxygen vacancies, which considered most often been invoked as shallow donors, have high formation energies in n-type ZnO, in edition are a deep donors. Zinc interstitials are shallow donors, with high formation energies in n-type ZnO, and thus unlikely to be responsible on their own for unintentional n-type conductivity under equilibrium conditions, as well as Zn antisites which have higher formation energies than zinc interstitials. Zinc vacancies are deep acceptors with low formation energies for n-type and in which case they will not play role in p-type coductivity of ZnO. Oxygen interstitials are stable in the form of electrically inactive split interstitials as well as deep acceptors at the octahedral interstitial site under n-type conditions. Our results may provide a guide to experimental studies of point defects in ZnO.

Keywords: DFT, native, n-type, ZnO

Procedia PDF Downloads 578

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 113

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

Abstract:

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

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

Procedia PDF Downloads 182

Authors: Avatharam Ganivada, Krishna Shah

Abstract:

The Mask R-CNN is recently introduced by the team of Facebook AI Research (FAIR), which is mainly concerned with instance segmentation in images. Here, the Mask R-CNN is based on ResNet and feature pyramid network (FPN), where a single dropout method is employed. This paper provides a modified Mask R-CNN by adding multiple dropout methods into the Mask R-CNN. The proposed model has also utilized the concepts of Resnet and FPN to extract stage-wise network feature maps, wherein a top-down network path having lateral connections is used to obtain semantically strong features. The proposed model produces three outputs for each object in the image: class label, bounding box coordinates, and object mask. The performance of the proposed network is evaluated in the segmentation of every instance in images using COCO and cityscape datasets. The proposed model achieves better performance than the state-of-the-networks for the datasets.

Keywords: instance segmentation, object detection, convolutional neural networks, deep learning, computer vision

Procedia PDF Downloads 64

Authors: Chinlun Lai, Lunjyh Jiang

Abstract:

Due to the heavy burden and pressure of caring for infants, an integrated automatic baby watching system based on IoT smart sensing and deep learning machine vision techniques is proposed in this paper. By monitoring infant body conditions such as heartbeat, breathing, body temperature, sleeping posture, as well as the surrounding conditions such as dangerous/sharp objects, light, noise, humidity and temperature, the proposed system can analyze and predict the obvious/potential dangerous conditions according to observed data and then adopt suitable actions in real time to protect the infant from harm. Thus, reducing the burden of the caregiver and improving safety efficiency of the caring work. The experimental results show that the proposed system works successfully for the infant care work and thus can be implemented in various life fields practically.

Keywords: baby care system, Internet of Things, deep learning, machine vision

Procedia PDF Downloads 219

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

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 131

Authors: Djarot B. Darmadi

Abstract:

The wider growing Finite Element Method (FEM) application is caused by its benefits of cost saving and environment friendly. Also, by using FEM a deep understanding of certain phenomenon can be achieved. This paper observed the role of material properties and volumetric change when Solid State Phase Transformation (SSPT) takes place in residual stress formation due to a welding process of ferritic steels through coupled Thermo-Metallurgy-Mechanical (TMM) analysis. The correctness of FEM residual stress prediction was validated by experiment. From parametric study of the FEM model, it can be concluded that the material properties change tend to over-predicts residual stress in the weld center whilst volumetric change tend to underestimates it. The best final result is the compromise of both by incorporates them in the model which has a better result compared to a model without SSPT.

Keywords: residual stress, ferritic steels, SSPT, coupled-TMM

Procedia PDF Downloads 260

Authors: M. J. Davidson, N. Selvaraj, L. Venugopal

Abstract:

The elevated temperature forming studies on the expansion of thin walled tubes have been studied in the present work. The influence of process parameters namely the die angle, the die ratio and the operating temperatures on the expansion of tube ends at elevated temperatures is carried out. The range of operating parameters have been identified by perfoming extensive simulation studies. The hot forming parameters have been evaluated for AA2014 alloy for performing the simulation studies. Experimental matrix has been developed from the feasible range got from the simulation results. The design of experiments is used for the optimization of process parameters. Response Surface Method’s (RSM) and Box-Behenken design (BBD) is used for developing the mathematical model for expansion. Analysis of variance (ANOVA) is used to analyze the influence of process parameters on the expansion of tube ends. The effect of various process combinations of expansion are analyzed through graphical representations. The developed model is found to be appropriate as the coefficient of determination value is very high and is equal to 0.9726. The predicted values are found to coincide well with the experimental results, within acceptable error limits.

Keywords: expansion, optimization, Response Surface Method (RSM), ANOVA, bbd, residuals, regression, tube

Procedia PDF Downloads 495

Authors: Hongmei Wang, Ziyun Xiang, Ying liu, Li Yu, Dongsheng Yue

Abstract:

Intro: The COVID-19 (Corona Virus Disease 2019) has greatly changed the global economic, political and financial ecology. The mutation of the coronavirus in the UK in December 2020 has brought new panic to the world. Deep learning was performed on Chest Computed tomography (CT) of COVID-19 and Influenza and describes their characteristics. The predominant features of COVID-19 pneumonia was ground-glass opacification, followed by consolidation. Lesion density: most lesions appear as ground-glass shadows, and some lesions coexist with solid lesions. Lesion distribution: the focus is mainly on the dorsal side of the periphery of the lung, with the lower lobe of the lungs as the focus, and it is often close to the pleura. Other features it has are grid-like shadows in ground glass lesions, thickening signs of diseased vessels, air bronchi signs and halo signs. The severe disease involves whole bilateral lungs, showing white lung signs, air bronchograms can be seen, and there can be a small amount of pleural effusion in the bilateral chest cavity. At the same time, this year's flu season could be near its peak after surging throughout the United States for months. Chest CT for Influenza infection is characterized by focal ground glass shadows in the lungs, with or without patchy consolidation, and bronchiole air bronchograms are visible in the concentration. There are patchy ground-glass shadows, consolidation, air bronchus signs, mosaic lung perfusion, etc. The lesions are mostly fused, which is prominent near the hilar and two lungs. Grid-like shadows and small patchy ground-glass shadows are visible. Deep neural networks have great potential in image analysis and diagnosis that traditional machine learning algorithms do not. Method: Aiming at the two major infectious diseases COVID-19 and influenza, which are currently circulating in the world, the chest CT of patients with two infectious diseases is classified and diagnosed using deep learning algorithms. The residual network is proposed to solve the problem of network degradation when there are too many hidden layers in a deep neural network (DNN). The proposed deep residual system (ResNet) is a milestone in the history of the Convolutional neural network (CNN) images, which solves the problem of difficult training of deep CNN models. Many visual tasks can get excellent results through fine-tuning ResNet. The pre-trained convolutional neural network ResNet is introduced as a feature extractor, eliminating the need to design complex models and time-consuming training. Fastai is based on Pytorch, packaging best practices for in-depth learning strategies, and finding the best way to handle diagnoses issues. Based on the one-cycle approach of the Fastai algorithm, the classification diagnosis of lung CT for two infectious diseases is realized, and a higher recognition rate is obtained. Results: A deep learning model was developed to efficiently identify the differences between COVID-19 and influenza using chest CT.

Keywords: COVID-19, Fastai, influenza, transfer network

Procedia PDF Downloads 130

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 81

Authors: Nur Mohammad Ali, Md. Shafiqul Alam, Jayanta Bhusan Deb, Nowrin Sharmin

Abstract:

The past ten years have seen significant expansion in the aviation sector, which during the previous five years has steadily pushed emerging countries closer to economic independence. It is crucial to accurately forecast the potential demand for air travel to make long-term financial plans. To forecast market demand for low-cost passenger carriers, this study suggests working with low-cost airlines, airports, consultancies, and governmental institutions' strategic planning divisions. The study aims to develop an artificial intelligence-based methods, notably fuzzy inference systems (FIS), to determine the most accurate forecasting technique for domestic low-cost carrier demand in Bangladesh. To give end users real-world applications, the study includes nine variables, two sub-FIS, and one final Mamdani Fuzzy Inference System utilizing a graphical user interface (GUI) made with the app designer tool. The evaluation criteria used in this inquiry included mean square error (MSE), accuracy, precision, sensitivity, and specificity. The effectiveness of the developed air passenger demand prediction FIS is assessed using 240 data sets, and the accuracy, precision, sensitivity, specificity, and MSE values are 90.83%, 91.09%, 90.77%, and 2.09%, respectively.

Keywords: aviation industry, fuzzy inference system, membership function, graphical user interference

Procedia PDF Downloads 56

Authors: Nishank Raisinghani

Abstract:

Efficiently predicting drug response remains a challenge in the realm of drug discovery. To address this issue, we propose four model architectures that combine graphical representation with varying positions of multiheaded self-attention mechanisms. By leveraging two types of multi-omics data, transcriptomics and genomics, we create a comprehensive representation of target cells and enable drug response prediction in precision medicine. A majority of our architectures utilize multiple transformer models, one with a graph attention mechanism and the other with a multiheaded self-attention mechanism, to generate latent representations of both drug and omics data, respectively. Our model architectures apply an attention mechanism to both drug and multiomics data, with the goal of procuring more comprehensive latent representations. The latent representations are then concatenated and input into a fully connected network to predict the IC-50 score, a measure of cell drug response. We experiment with all four of these architectures and extract results from all of them. Our study greatly contributes to the future of drug discovery and precision medicine by looking to optimize the time and accuracy of drug response prediction.

Keywords: drug discovery, transformers, graph neural networks, multiomics

Procedia PDF Downloads 130

Authors: Kong Ngai Pei

Abstract:

The argument scheme approach to argumentation has two components. One is to identify the recurrent patterns of inferences used in everyday discourse. The second is to devise critical questions to evaluate the inferences in these patterns. Although this approach is intuitive and contains many insightful ideas, it has been noted to be not free of problems. One is that due to its disavowing the probability calculus, it cannot give the exact strength of an inference. In order to tackle this problem, thereby paving the way to a more complete normative account of argument strength, it has been proposed, the most promising way is to combine the scheme-based approach with Bayesian networks (BNs). This paper pursues this line of thought, attempting to combine three common schemes, Appeal to Ignorance, Composition, and Division, with BNs. In the first part, it is argued that most (if not all) formulations of the critical questions corresponding to these schemes in the current argumentation literature are incomplete and not very informative. To remedy these flaws, more thorough and precise formulations of these questions are provided. In the second part, how to use graphical idioms (e.g. measurement and synthesis idioms) to translate the schemes as well as their corresponding critical questions to graphical structure of BNs, and how to define probability tables of the nodes using functions of various sorts are shown. In the final part, it is argued that many misuses of these schemes, traditionally called fallacies with the same names as the schemes, can indeed be adequately accounted for by the BN models proposed in this paper.

Keywords: appeal to ignorance, argument schemes, Bayesian networks, composition, division

Procedia PDF Downloads 270

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 128

Authors: Shaik Ayesha Fathima, Shaik Noor Jahan, Duvvada Rajeswara Rao

Abstract:

Earth's environment and its evolution can be seen through satellite images in near real-time. Through satellite imagery, remote sensing data provide crucial information that can be used for a variety of applications, including image fusion, change detection, land cover classification, agriculture, mining, disaster mitigation, and monitoring climate change. The objective of this project is to propose a method for classifying satellite images according to multiple predefined land cover classes. The proposed approach involves collecting data in image format. The data is then pre-processed using data pre-processing techniques. The processed data is fed into the proposed algorithm and the obtained result is analyzed. Some of the algorithms used in satellite imagery classification are U-Net, Random Forest, Deep Labv3, CNN, ANN, Resnet etc. In this project, we are using the DeepLabv3 (Atrous convolution) algorithm for land cover classification. The dataset used is the deep globe land cover classification dataset. DeepLabv3 is a semantic segmentation system that uses atrous convolution to capture multi-scale context by adopting multiple atrous rates in cascade or in parallel to determine the scale of segments.

Keywords: area calculation, atrous convolution, deep globe land cover classification, deepLabv3, land cover classification, resnet 50

Procedia PDF Downloads 131

Authors: Teja Sai Puligadda

Abstract:

Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.

Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss

Procedia PDF Downloads 144