Search results for: deep plane

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 118

Authors: Hamdy M. Youssef, Eman A. Al-Lehaibi

Abstract:

Due to many applications and problems in the fields of plasma physics, geophysics, and other many topics, the interaction between the strain field and the magnetic field has to be considered. Adomian introduced the decomposition method for solving linear and nonlinear functional equations. This method leads to accurate, computable, approximately convergent solutions of linear and nonlinear partial and ordinary differential equations even the equations with variable coefficients. This paper is dealing with a mathematical model of generalized thermoelasticity of a half-space conducting medium. A magnetic field with constant intensity acts normal to the bounding plane has been assumed. Adomian’s decomposition method has been used to solve the model when the bounding plane is taken to be traction free and thermally loaded by harmonic heating. The numerical results for the temperature increment, the stress, the strain, the displacement, the induced magnetic, and the electric fields have been represented in figures. The magnetic field, the relaxation time, and the angular thermal load have significant effects on all the studied fields.

Keywords: Adomian’s decomposition method, magneto-thermoelasticity, finite conductivity, iteration method, thermal load

Procedia PDF Downloads 128

Authors: Nazish Iftikhar, Adil Jhangeer, Tayyaba Naz

Abstract:

The universe is expanding at an accelerated rate. Symmetries are useful in understanding universe’s behavior. Emmy Noether reported the relation between symmetries and conservation laws. These symmetries are known as Noether symmetries which correspond to a conserved quantity. In differential equations, conservation laws play an important role. Noether symmetries are helpful in modified theories of gravity. Time independent plane symmetric spacetime was classified by Noether`s theorem. By using Noether`s theorem, set of linear partial differential equations was obtained having A(r), B(r) and F(r) as unknown radial functions. The Lagrangian corresponding to considered spacetime in the Noether equation was used to get Noether operators. Different possibilities of radial functions were considered. Firstly, all functions were same. All the functions were considered as non-zero constant, linear, reciprocal and exponential respectively. Secondly, two functions were proportional to each other keeping third function different. Second case has four subcases in which four different relationships between A(r), B(r) and F(r) were discussed. In all cases, we obtained nontrivial Noether operators including gauge term. Conserved quantities for each Noether operators were also presented.

Keywords: Noether gauge symmetries, radial function, Noether operator, conserved quantities

Procedia PDF Downloads 206

Authors: Takashi Mitsuishi

Abstract:

Fuzzy logic has gained acceptance in the recent years in the fields of social sciences and humanities such as psychology and linguistics because it can manage the fuzziness of words and human subjectivity in a logical manner. However, the major field of application of the fuzzy logic is control engineering as it is a part of the set theory and mathematical logic. Mamdani method, which is the most popular technique for approximate reasoning in the field of fuzzy control, is one of the ways to numerically represent the control afforded by human language and sensitivity and has been applied in various practical control plants. Fuzzy logic has been gradually developing as an artificial intelligence in different applications such as neural networks, expert systems, and operations research. The objects of inference vary for different application fields. Some of these include time, angle, color, symptom and medical condition whose fuzzy membership function is a periodic function. In the defuzzification stage, the domain of the membership function should be unique to obtain uniqueness its defuzzified value. However, if the domain of the periodic membership function is determined as unique, an unintuitive defuzzified value may be obtained as the inference result using the center of gravity method. Therefore, the authors propose a method of circular-polar-coordinates transformation and defuzzification of the periodic membership functions in this study. The transformation to circular polar coordinates simplifies the domain of the periodic membership function. Defuzzified value in circular polar coordinates is an argument. Furthermore, it is required that the argument is calculated from a closed plane figure which is a periodic membership function on the circular polar coordinates. If the closed plane figure is continuous with the continuity of the membership function, a significant amount of computation is required. Therefore, to simplify the practice example and significantly reduce the computational complexity, we have discretized the continuous interval and the membership function in this study. In this study, the following three methods are proposed to decide the argument from the discrete polygon which the continuous plane figure is transformed into. The first method provides an argument of a straight line passing through the origin and through the coordinate of the arithmetic mean of each coordinate of the polygon (physical center of gravity). The second one provides an argument of a straight line passing through the origin and the coordinate of the geometric center of gravity of the polygon. The third one provides an argument of a straight line passing through the origin bisecting the perimeter of the polygon (or the closed continuous plane figure).

Keywords: defuzzification, fuzzy membership function, periodic function, polar coordinates transformation

Procedia PDF Downloads 335

Authors: Modreck Gomo

Abstract:

The evolution of groundwater chemistry and its quality is largely controlled by hydrogeochemical processes and their understanding is therefore important for groundwater quality assessments and protection of the water resources. A study was conducted in Bloemfontein town of South Africa to assess and compare the groundwater chemistry and quality characteristics in an alluvial aquifer and single-plane fractured-rock aquifers. 9 groundwater samples were collected from monitoring boreholes drilled into the two aquifer systems during a once-off sampling exercise. Samples were collected through low-flow purging technique and analysed for major ions and trace elements. In order to describe the hydrochemical facies and identify dominant hydrogeochemical processes, the groundwater chemistry data are interpreted using stiff diagrams and principal component analysis (PCA), as complimentary tools. The fitness of the groundwater quality for domestic and irrigation uses is also assessed. Results show that the alluvial aquifer is characterised by a Na-HCO₃ hydrochemical facie while fractured-rock aquifer has a Ca-HCO₃ facie. The groundwater in both aquifers originally evolved from the dissolution of calcite rocks that are common on land surface environments. However the groundwater in the alluvial aquifer further goes through another evolution as driven by cation exchange process in which Na in the sediments exchanges with Ca²⁺ in the Ca-HCO₃ hydrochemical type to result in the Na-HCO₃ hydrochemical type. Despite the difference in the hydrogeochemical processes between the alluvial aquifer and single-plane fractured-rock aquifer, this did not influence the groundwater quality. The groundwater in the two aquifers is very hard as influenced by the elevated magnesium and calcium ions that evolve from dissolution of carbonate minerals which typically occurs in surface environments. Based on total dissolved levels (600-900 mg/L), groundwater quality of the two aquifer systems is classified to be of fair quality. The negative potential impacts of the groundwater quality for domestic uses are highlighted.

Keywords: alluvial aquifer, fractured-rock aquifer, groundwater quality, hydrogeochemical processes

Procedia PDF Downloads 175

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 135

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 101

Authors: Vladimir Veremey

Abstract:

The paper describes the design and simulation of dual-polarization antennas that use the resonance and radiating properties of the H₀₀ mode of metal open waveguides. The proposed antennas are formed by two orthogonal slots in a finite conducting ground plane. The slots are backed by metal screens connected to the ground plane forming open waveguides. It has been shown that the antenna designs can be efficiently used in mm-wave bands. The antenna single mode operational bandwidth is higher than 10%. The antenna designs are very simple and low-cost. They allow flush installation and can be efficiently used in various communication and remote sensing devices on fast moving carriers. Mutual coupling between antennas of the proposed design is very low. Thus, multiple antenna structures with proposed antennas can be efficiently employed in multi-band and in multiple-input-multiple-output (MIMO) systems.

Keywords: antenna, antenna arrays, Multiple-Input-Multiple-Output (MIMO), millimeter wave bands, slot antenna, flush installation, directivity, open waveguide, conformal antennas

Procedia PDF Downloads 150

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization

Procedia PDF Downloads 275

Authors: Ju-Hong Lee, Chong-Jia Ciou

Abstract:

This paper deals with the problem of two-dimensional (2-D) recursive two-channel quincunx quadrature mirror filter (QQMF) banks design. The analysis and synthesis filters of the 2-D recursive QQMF bank are composed of 2-D recursive digital allpass lattice filters (DALFs) with symmetric half-plane (SHP) support regions. Using the 2-D doubly complementary half-band (DC-HB) property possessed by the analysis and synthesis filters, we facilitate the design of the proposed QQMF bank. For finding the coefficients of the 2-D recursive SHP DALFs, we present a structure of 2-D recursive digital allpass filters by using 2-D SHP recursive digital all-pass lattice filters (DALFs). The novelty of using 2-D SHP recursive DALFs to construct a 2-D recursive QQMF bank is that the resulting 2-D recursive QQMF bank provides better performance than the existing 2-D recursive QQMF banks. Simulation results are also presented for illustration and comparison.

Keywords: all-pass digital filter, lattice structure, quincunx QMF bank, symmetric half-plane digital filter

Procedia PDF Downloads 338

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.

Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation

Procedia PDF Downloads 72

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 68

Authors: Kashika P. H.

Abstract:

The development of computer vision systems has been greatly aided by the efficient and precise detection of images and videos. Although the ability to recognize and comprehend images is a strength of the human brain, employing technology to tackle this issue is exceedingly challenging. In the past few years, the use of Deep Learning algorithms to treat object detection has dramatically expanded. One of the key issues in the realm of image recognition is the recognition and detection of certain notable people from randomly acquired photographs. Face recognition uses a way to identify, assess, and compare faces for a variety of purposes, including user identification, user counting, and classification. With the aid of an accessible deep learning-based API, this article intends to recognize various faces of people and their facial descriptors more accurately. The purpose of this study is to locate suitable individuals and deliver accurate information about them by using the Amazon Rekognition system to identify a specific human from a vast image dataset. We have chosen the Amazon Rekognition system, which allows for more accurate face analysis, face comparison, and face search, to tackle this difficulty.

Keywords: Amazon rekognition, API, deep learning, computer vision, face detection, text detection

Procedia PDF Downloads 87

Authors: Chih-Chia Lin, Ching-Ying Huang, Cheng-Hong Liu, Wen-Lin Wang

Abstract:

A complete fuel cell stack comprises several single cells with end plates, bipolar plates, gaskets and membrane electrode assembly (MEA) components. Electrons generated from cells are conducted through bipolar plates. The amount of cells' components increases as the stack voltage increases, complicating the fuel cell assembly process and mass production. Stack assembly error influence cell performance. PEM fuel cell stack importing laser welding technique could eliminate transverse deformation between bipolar plates to promote stress uniformity of cell components as bipolar plates and MEA. Simultaneously, bipolar plates were melted together using laser welding to decrease interface resistance. A series of experiments as through-plan and in-plan resistance measurement test was conducted to observe the laser welding effect. The result showed that the through-plane resistance with laser welding was a drop of 97.5-97.6% when the contact pressure was about 1MPa to 3 MPa, and the in-plane resistance was not significantly different for laser welding.

Keywords: PEM fuel cell, laser welding, through-plan, in-plan, resistance

Procedia PDF Downloads 486

Authors: Avalloy McCarthy-Curvin

Abstract:

For over fifty years there has been widespread dissatisfaction with the teaching of Mathematics in Jamaica. Studies, done in the Jamaican context highlight that teachers at the end of training do not have a deep understanding of the mathematics content they teach. Little research has been done in the Jamaican context that targets the advancement of contextual knowledge on the problem to ultimately provide a solution. The aim of the study is to identify what influences this outcome of teacher education in Jamaica so as to remedy the problem. This study formatively evaluated the curriculum documents, assessments and the delivery of the curriculum that are being used in teacher training institutions in Jamaica to determine their rigor -the extent to which written document, instruction, and the assessments focused on enabling pre-service teachers to develop deep understanding of mathematics and relevance- the extent to which the curriculum document, instruction, and the assessments are focus on developing the requisite knowledge for teaching mathematics. The findings show that neither the curriculum document, instruction nor assessments ensure rigor and enable pre-service teachers to develop the knowledge and skills they need to teach mathematics effectively.

Keywords: relevance, rigor, deep understanding, formative evaluation

Procedia PDF Downloads 214

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 51

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 139

Authors: Satoko Fujiwara, Kiyotaka Obunai, Kazuya Okubo

Abstract:

A skew is one of important problems for designing the conveyor and transmission with frictional flat belt, in which running belt is deviated in width direction due to the transverse force applied to the belt. The skew often not only degrades the stability of the path of belt but also causes some damages of the belt and auxiliary machines. However, the transverse behavior such as the skew has not been discussed quantitatively in detail for frictional belts. The objective of this study is to clarify the transverse behavior of frictional flat belt driven by tapered pulley. Commercially available rubber flat belt reinforced by polyamide film was prepared as the test belt where the thickness and length were 1.25 mm and 630 mm, respectively. Test belt was driven between two pulleys made of aluminum alloy, where diameter and inter-axial length were 50 mm and 150 mm, respectively. Some tapered pulleys were applied where tapered angles were 0 deg (for comparison), 2 deg, 4 deg, and 6 deg. In order to alternatively investigate the transverse behavior, the transverse force applied to the belt was measured when the skew was constrained at the string under driving state. The transverse force was measured by a load cell having free rollers contacting on the side surface of the belt when the displacement in the belt width direction was constrained. The conditions of observed bending stiffness in-plane of the belt were changed by preparing three types of belts (the width of the belt was 20, 30, and 40 mm) where their observed stiffnesses were changed. The contributions of the bending stiffness in-plane of belt and initial inter-axial force to the transverse were discussed in experiments. The inter-axial force was also changed by setting a distance (about 240 mm) between the two pulleys. Influence of observed bending stiffness in-plane of the belt and initial inter-axial force on the transverse force were investigated. The experimental results showed that the transverse force was increased with an increase of observed bending stiffness in-plane of the belt and initial inter-axial force. The transverse force acting on the belt running on the tapered pulley was classified into multiple components. Those were components of forces applied with the deflection of the inter-axial force according to the change of taper angle, the resultant force by the bending moment applied on the belt winding around the tapered pulley, and the reaction force applied due to the shearing deformation. The calculation result of the transverse force was almost agreed with experimental data when those components were formulated. It was also shown that the most contribution was specified to be the shearing deformation, regardless of the test conditions. This study found that transverse behavior of frictional flat belt driven by tapered pulley was explained by the summation of those components of forces.

Keywords: skew, frictional flat belt, transverse force, tapered pulley

Procedia PDF Downloads 133

Authors: Rajan Goyal, S. Lamba, S. Annapoorni

Abstract:

The indirect exchange coupled system consists of two ferromagnetic layers separated by non-magnetic spacer layer. The type of exchange coupling may be either ferro or anti-ferro depending on the thickness of the spacer layer. In the present work, the strength of exchange coupling in FePt/Al₂O₃/Fe₃Pt has been investigated by varying the thickness of the spacer layer Al₂O₃. The FePt/Al₂O₃/Fe₃Pt trilayer structure is fabricated on Si <100> single crystal substrate using sputtering technique. The thickness of FePt and Fe₃Pt is fixed at 60 nm and 2 nm respectively. The thickness of spacer layer Al₂O₃ was varied from 0 to 16 nm. The normalized hysteresis loops recorded at room temperature both in the in-plane and out of plane configuration reveals that the orientation of easy axis lies along the plane of the film. It is observed that the hysteresis loop for ts=0 nm does not exhibit any knee around H=0 indicating that the hard FePt layer and soft Fe₃Pt layer are strongly exchange coupled. However, the insertion of Al₂O₃ spacer layer of thickness ts = 0.7 nm results in appearance of a minor knee around H=0 suggesting the weakening of exchange coupling between FePt and Fe₃Pt. The disappearance of knee in hysteresis loop with further increase in thickness of the spacer layer up to 8 nm predicts the co-existence of ferromagnetic (FM) and antiferromagnetic (AFM) exchange interaction between FePt and Fe₃Pt. In addition to this, the out of plane hysteresis loop also shows an asymmetry around H=0. The exchange field Hex = (Hc↑-HC↓)/2, where Hc↑ and Hc↓ are the coercivity estimated from lower and upper branch of hysteresis loop, increases from ~ 150 Oe to ~ 700 Oe respectively. This behavior may be attributed to the uncompensated moments in the hard FePt layer and soft Fe₃Pt layer at the interface. A better insight into the variation in indirect exchange coupling has been investigated using recoil curves. It is observed that the almost closed recoil curves are obtained for ts= 0 nm up to a reverse field of ~ 5 kOe. On the other hand, the appearance of appreciable open recoil curves at lower reverse field ~ 4 kOe for ts = 0.7 nm indicates that uncoupled soft phase undergoes irreversible magnetization reversal at lower reverse field suggesting the weakening of exchange coupling. The openness of recoil curves decreases with increase in thickness of the spacer layer up to 8 nm. This behavior may be attributed to the competition between FM and AFM exchange interactions. The FM exchange coupling between FePt and Fe₃Pt due to porous nature of Al₂O₃ decreases much slower than the weak AFM coupling due to interaction between Fe ions of FePt and Fe₃Pt via O ions of Al₂O₃. The hysteresis loop has been simulated using Monte Carlo based on Metropolis algorithm to investigate the variation in strength of exchange coupling in FePt/Al₂O₃/Fe₃Pt trilayer system.

Keywords: indirect exchange coupling, MH loop, Monte Carlo simulation, recoil curve

Procedia PDF Downloads 171

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

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

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

Procedia PDF Downloads 103

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 257

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 108

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 321

Authors: Ting Gao, Mingyue He

Abstract:

Reconfigurable intelligent surfaces (RISs) are expected to be an important part of next-generation wireless communication networks due to their potential to reduce the hardware cost and energy consumption of millimeter Wave (mmWave) massive multiple-input multiple-output (MIMO) technology. However, owing to the lack of signal processing abilities of the RIS, the perfect channel state information (CSI) in RIS-assisted communication systems is difficult to acquire. In this paper, the uplink channel estimation for mmWave systems with a hybrid active/passive RIS architecture is studied. Specifically, a deep learning-based estimation scheme is proposed to estimate the channel between the RIS and the user. In particular, the sparse structure of the mmWave channel is exploited to formulate the channel estimation as a sparse reconstruction problem. To this end, the proposed approach is derived to obtain the distribution of non-zero entries in a sparse channel. After that, the channel is reconstructed by utilizing the least-squares (LS) algorithm and compressed sensing (CS) theory. The simulation results demonstrate that the proposed channel estimation scheme is superior to existing solutions even in low signal-to-noise ratio (SNR) environments.

Keywords: channel estimation, reconfigurable intelligent surface, wireless communication, deep learning

Procedia PDF Downloads 120

Authors: Francisco Alvarado, Luz Ramírez

Abstract:

Corneal diseases are one of the main causes of visual impairment and affect almost 4 million, and this study assesses the effects of deep anterior lamellar keratoplasty (DALK) with porcine corneal stroma and postoperative topical treatment with tacrolimus in patients with infectious keratitis. No patient was observed with clinical graft rejection. Among the cases: 2 were positive to fungal culture, 2 with Aspergillus and the other 8 cases were confirmed by bacteriological culture. Corneal diseases are one of the main causes of visual impairment and affect almost 4 million. This study assesses the effects of deep anterior lamellar keratoplasty (DALK) with porcine corneal stroma and postoperative topical treatment with tacrolimus in patients with infectious keratitis. Receiver bed diameters ranged from 7.00 to 9.00 mm. No incidents of Descemet's membrane perforation were observed during surgery. During the follow-up period, no corneal graft splitting, IOP increase, or intolerance to tacrolimus were observed. Deep anterior lamellar keratoplasty seems to be the best option to avoid xenograft rejection, and it could help new surgical techniques in humans.

Keywords: ophthalmology, cornea, corneal transplant, xenografts, surgical innovations

Procedia PDF Downloads 65

Authors: Pranav Ajmera, Amit Kharat, Tanveer Gupte, Richa Pant, Viraj Kulkarni, Vinay Duddalwar, Purnachandra Lamghare

Abstract:

The cardiothoracic ratio (CTR) is the ratio of the diameter of the heart to the diameter of the thorax. An abnormal CTR, that is, a value greater than 0.55, is often an indicator of an underlying pathological condition. The accurate prediction of an abnormal CTR from chest X-rays (CXRs) aids in the early diagnosis of clinical conditions. We propose a deep learning-based model for automatic CTR calculation that can assist the radiologist with the diagnosis of cardiomegaly and optimize the radiology flow. The study population included 1012 posteroanterior (PA) CXRs from a single institution. The Attention U-Net deep learning (DL) architecture was used for the automatic calculation of CTR. A CTR of 0.55 was used as a cut-off to categorize the condition as cardiomegaly present or absent. An observer performance test was conducted to assess the radiologist's performance in diagnosing cardiomegaly with and without artificial intelligence (AI) assistance. The Attention U-Net model was highly specific in calculating the CTR. The model exhibited a sensitivity of 0.80 [95% CI: 0.75, 0.85], precision of 0.99 [95% CI: 0.98, 1], and a F1 score of 0.88 [95% CI: 0.85, 0.91]. During the analysis, we observed that 51 out of 1012 samples were misclassified by the model when compared to annotations made by the expert radiologist. We further observed that the sensitivity of the reviewing radiologist in identifying cardiomegaly increased from 40.50% to 88.4% when aided by the AI-generated CTR. Our segmentation-based AI model demonstrated high specificity and sensitivity for CTR calculation. The performance of the radiologist on the observer performance test improved significantly with AI assistance. A DL-based segmentation model for rapid quantification of CTR can therefore have significant potential to be used in clinical workflows.

Keywords: cardiomegaly, deep learning, chest radiograph, artificial intelligence, cardiothoracic ratio

Procedia PDF Downloads 72

Authors: Arefeh Arabaninezhad, Ali Fakher

Abstract:

Since the deterministic analysis methods fail to take system uncertainties into account, probabilistic and non-probabilistic methods are suggested. Geotechnical analyses are used to determine the stress and deformation caused by construction; accordingly, many input variables which depend on ground behavior are required for geotechnical analyses. The Random Set approach is an applicable reliability analysis method when comprehensive sources of information are not available. Using Random Set method, with relatively small number of simulations compared to fully probabilistic methods, smooth extremes on system responses are obtained. Therefore random set approach has been proposed for reliability analysis in geotechnical problems. In the present study, the application of random set method in reliability analysis of deep excavations is investigated through three deep excavation projects which were monitored during the excavating process. A finite element code is utilized for numerical modeling. Two expected ranges, from different sources of information, are established for each input variable, and a specific probability assignment is defined for each range. To determine the most influential input variables and subsequently reducing the number of required finite element calculations, sensitivity analysis is carried out. Input data for finite element model are obtained by combining the upper and lower bounds of the input variables. The relevant probability share of each finite element calculation is determined considering the probability assigned to input variables present in these combinations. Horizontal displacement of the top point of excavation is considered as the main response of the system. The result of reliability analysis for each intended deep excavation is presented by constructing the Belief and Plausibility distribution function (i.e. lower and upper bounds) of system response obtained from deterministic finite element calculations. To evaluate the quality of input variables as well as applied reliability analysis method, the range of displacements extracted from models has been compared to the in situ measurements and good agreement is observed. The comparison also showed that Random Set Finite Element Method applies to estimate the horizontal displacement of the top point of deep excavation. Finally, the probability of failure or unsatisfactory performance of the system is evaluated by comparing the threshold displacement with reliability analysis results.

Keywords: deep excavation, random set finite element method, reliability analysis, uncertainty

Procedia PDF Downloads 247

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

Abstract:

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

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

Procedia PDF Downloads 64

Authors: Abdelrahim Hamadelnil

Abstract:

Padeye design and analysis plays important roles during the lifting, load out and installation of heavy structures. This paper explains the disadvantages of limiting the effective thickness of the cheek plate to 75% of the main plate thickness. In addition, a sensitivity study about the impact of the out of plane force on the padeye design is discussed. This study also explains the fabrication requirements to ensure that the designed strength is achieved. The objective of this study is to elaborate and discuss the philosophy of padeye design and to propose the suitable effective cheek plate thickness to be considered in the analysis of padeye. A finite element analysis using London University Structure Analysis System (LUSAS), is conducted and compared with the hand calculation. The benefits and advantage of using FE analysis is addressed in this paper. At the end of this paper, a guideline elaborating the philosophy of the design of the padeye is developed and the suitable effective thickness of cheek plate to be considered in the design is recommended. In addition, a comparison between the finite element result and the hand calculation using beam theory is discussed as well.

Keywords: cheek plate, effective thickness, out of plane force, Padeye

Procedia PDF Downloads 301

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 214