Search results for: deep vein imaging

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 69

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 71

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 217

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 312

Authors: Harish Aryal

Abstract:

The safe and reliable operation of nuclear reactors has always been one of the topmost priorities in the nuclear industry. Transient testing allows us to understand the time-dependent behavior of the neutron population in response to either a planned change in the reactor conditions or unplanned circumstances. These unforeseen conditions might occur due to sudden reactivity insertions, feedback, power excursions, instabilities, and accidents. To study such behavior, we need transient testing, which is like car crash testing, to estimate the durability and strength of a car design. In nuclear designs, such transient testing can simulate a wide range of accidents due to sudden reactivity insertions and helps to study the feasibility and integrity of the fuel to be used in certain reactor types. This testing involves a high neutron flux environment and real-time imaging technology with advanced instrumentation with appropriate accuracy and resolution to study the fuel slumping behavior. With the aid of transient testing and adequate imaging tools, it is possible to test the safety basis for reactor and fuel designs that serves as a gateway in licensing advanced reactors in the future. To that end, it is crucial to fully understand advanced imaging techniques both analytically and via simulations. This paper presents an innovative method of supporting real-time imaging of fuel pins and other structures during transient testing. The major fuel-motion detection device that is studied in this dissertation is the Hodoscope which requires collimators. This paper provides 1) an MCNP model and simulation of a Transient Reactor Test (TREAT) core with a central fuel element replaced by a slotted fuel element that provides an open path between test samples and a hodoscope detector and 2) a choice of good filter to improve image resolution.

Keywords: hodoscope, transient testing, collimators, MCNP, TREAT, hodogram, filters

Procedia PDF Downloads 57

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 122

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 137

Authors: Maria Medeiros, Suren Surenthiran, Abitha Muralithar, Soushma Seeburuth, Mohammed Mohammed

Abstract:

Introduction: Appendicitis is the most common surgical emergency globally and can have devastating consequences. Diagnostic imaging in acute appendicitis has become increasingly common in aiding the diagnosis of acute appendicitis. Computerized tomography (CT) and ultrasound (US) are the most commonly used imaging modalities for diagnosing acute appendicitis. Pre-operative imaging has contributed to a reduction of negative appendicectomy rates from between 10-29% to 5%. Literature report CT scan has a diagnostic sensitivity of 94% in acute appendicitis. This clinical audit was conducted to establish if the CT scan's diagnostic yield for acute appendicitis matches the literature. CT scan has a high sensitivity and specificity for diagnosing acute appendicitis and its use can result in a lower negative appendicectomy rate. The aim of this study is to compare the pre-operative imaging findings from CT scans to the histopathology results post-operatively and establish the accuracy of CT scans in aiding the diagnosis of acute appendicitis. Methods: This was a retrospective study focusing on adult presentations to the general surgery department in a district general hospital in central London with an impression of acute appendicitis. We analyzed all patients from July 2022 to December 2022 who underwent a CT scan preceding appendicectomy. Pre-operative CT findings and post-operative histopathology findings were compared to establish the efficacy of CT scans in diagnosing acute appendicitis. Our results were also cross-referenced with pre-existing literature. Data was collected and anonymized using CERNER and analyzed in Microsoft Excel. Exclusion criteria: Children, age <16. Results: 65 patients had CT scans in which the report stated acute appendicitis. Of those 65 patients, 62 patients underwent diagnostic laparoscopies. 100% of patients who underwent an appendicectomy with a pre-operative CT scan showing acute appendicitis had acute appendicitis in histopathology analysis. 3 of the 65 patients who had a CT scan showing appendicitis received conservative treatment. Conclusion: CT scans positive for acute appendicitis had 100% sensitivity and a positive predictive value, which matches published research studies (sensitivity of 94%). The use of CT scans in the diagnostic work-up for acute appendicitis can be extremely helpful in a) confirming the diagnosis and b) reducing the rates of negative appendicectomies and consequently reducing unnecessary operative-associated risks for patients, reducing costs and reducing pressure on emergency theatre lists.

Keywords: acute apendicitis, CT scan, general surgery, imaging

Procedia PDF Downloads 70

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 104

Authors: M. Kowalski, M. Kastek, M. Szustakowski

Abstract:

Multispectral screening systems are becoming more popular because of their very interesting properties and applications. One of the most significant applications of multispectral screening systems is prevention of terrorist attacks. There are many kinds of threats and many methods of detection. Visual detection of objects hidden under clothing of a person is one of the most challenging problems of threats detection. There are various solutions of the problem; however, the most effective utilize multispectral surveillance imagers. The development of imaging devices and exploration of new spectral bands is a chance to introduce new equipment for assuring public safety. We investigate the possibility of long lasting detection of potentially dangerous objects covered with various types of clothing. In the article we present the results of comparative studies of passive imaging in three spectrums – visible, infrared and terahertz

Keywords: terahertz, infrared, object detection, screening camera, image processing

Procedia PDF Downloads 339

Authors: Sarai Guerrero, Lijia Liu

Abstract:

Zinc gallogermanate (ZGGO) is a persistent phosphor that can emit in the near infrared (NIR) range once dopped with Cr³⁺ enabling its use for in-vivo deep-tissue bio-imaging. Such a property also allows for its application in cancer diagnosis and therapy. Given this, work into developing a synthetic procedure that can be done using common laboratory instruments and equipment as well as understanding ZGGO overall, is in demand. However, the ZGGO nanoparticles must have a size compatible for cell intake to occur while still maintaining sufficient photoluminescence. The nanoparticle must also be made biocompatible by functionalizing the surface for hydrophilic solubility and for high particle uniformity in the final product. Additionally, most research is completed on doped ZGGO, leaving a gap in understanding the base form of ZGGO. It also leaves a gap in understanding how doping affects the synthesis of ZGGO. In this work, the first step of optimizing the particle size via the crystalline size of ZGGO was done with undoped ZGGO using the organic acid, oleic acid (OA) for organic ligand-assisted biphasic hydrothermal synthesis. The effects of this synthesis procedure on ZGGO’s crystallinity were evaluated using Powder X-Ray Diffraction (PXRD). OA was selected as the capping ligand as experiments have shown it beneficial in synthesizing sub-10 nm zinc gallate (ZGO) nanoparticles as well as palladium nanocrystals and magnetite (Fe₃O₄) nanoparticles. Later it is possible to substitute OA with a different ligand allowing for hydrophilic solubility. Attenuated Total Reflection Fourier-Transform Infrared (ATR-FTIR) was used to investigate the surface of the nanoparticle to investigate and verify that OA had capped the nanoparticle. PXRD results showed that using this procedure led to improved crystallinity, comparable to the high-purity reagents used on the ZGGO nanoparticles. There was also a change in the crystalline size of the ZGGO nanoparticles. ATR-FTIR showed that once capped ZGGO cannot be annealed as doing so will affect the OA. These results point to this new procedure positively affecting the crystallinity of ZGGO nanoparticles. There are also repeatable implying the procedure is a reliable source of highly crystalline ZGGO nanoparticles. With this completed, the next step will be working on substituting the OA with a hydrophilic ligand. As these ligands effect the solubility of the nanoparticle as well as the pH that the nanoparticles can dissolve in, further research is needed to verify which ligand is best suited for preparing ZGGO for bio-imaging.

Keywords: biphasic hydrothermal synthesis, crystallinity, oleic acid, zinc gallogermanate

Procedia PDF Downloads 116

Authors: Bijaya Kumar Sahoo

Abstract:

The effect of III-V nitride semiconductors on performance of a graphene-on-gold surface plasmon resonance (SPR) biosensor has been investigated theoretically. III-V nitrides (AlN, GaN and InN) have been grown between gold (Au) and graphene layers. The sensitivity and performance of the biosensor have been computed for with and without semiconductors. Due to superior electronic and optical properties, III-V nitrides demonstrate high sensitivity and performance over Si and Ge. The enhancement of evanescent electric field due to III-V nitrides have been computed and found highest for InN. The analysis shows that for a high-sensitive imaging biosensor the required optimal thickness of gold, InN and graphene are respectively 49 nm, 11 nm and 0.34 nm for the light of wavelength =633 nm (red He-Ne laser). This study suggests that InN would be a better choice for fabrication of new imaging SPR biosensors.

Keywords: SPR biosensor, optical properties, III-V nitrides, sensitivity, enhancement of electric field, performance of graphene gold SPR biosensor

Procedia PDF Downloads 529

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 277

Authors: Darshna Sharma, Suban K. Sahoo

Abstract:

The detection of intracellular fluoride in human cancer cell HeLa was achieved by chemosensors derived from vitamin B6 cofactors using fluorescence imaging technique. These sensors were first synthesized by condensation of pyridoxal/pyridoxal phosphate with 2-amino(thio)phenol. The anion recognition ability was explored by experimental (UV-VIS, fluorescence and 1H NMR) and theoretical DFT [(B3LYP/6-31G(d,p)] methods in DMSO and mixed DMSO-H2O system. All the developed sensors showed both naked-eye detectable color change and remarkable fluorescence enhancement in the presence of F- and AcO-. The anion recognition was occurred through the formation of hydrogen bonded complexes between these anions and sensor, followed by the partial deprotonation of sensor. The detection limit of these sensors were down to micro(nano) molar level of F- and AcO-.

Keywords: chemosensors, fluoride, acetate, turn-on, live cells imaging, DFT

Procedia PDF Downloads 383

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 73

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 69

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 91

Authors: Tugce Caliskan

Abstract:

The gentrification literature in Turkey provided important insights regarding the analysis of the socio-spatial change in İstanbul mostly through the existing gentrification theories which were produced in Anglo-American literature. Yet early researches focused on the classical gentrification while failing to notice other place-specific forms of the phenomena. It was only after the mid-2000s that scholarly attention shifted to the recent discussions in the mainstream such as the neoliberal urban policies, government involvement, and resistance. Although these studies have considerable potential to contribute to the geography of gentrification, it seems that copying the linear timeline of Anglo-American conceptualization limited the space to introduce contextually nuanced way of process in Turkey. More specifically, the gentrification literature in Turkey acknowledged the linear timeline of the process drawing on the mainstream studies, and, made the spontaneous classical gentrification as the starting point in İstanbul at the expense of contextually specific forms of the phenomenon that took place in the same years. This paper is an attempt to understand place-specific forms of gentrification through the abandonment of the linear understanding of time. In this vein, this paper approaches the process as moving both linear and cyclical rather than the waves succeeded each other. Maintaining a dialectical relationship between the cyclical and the linear time, this paper investigates how the components of gentrification have been taken place in the cyclical timeline while becoming bolder in the linear timeline. This paper argues that taking the (re)investment in the secondary circuit of capital and class transformation as the core characteristics of gentrification, and accordingly, searching for these components beyond the linear timeline provide strategic value to decenter the perspectives, not merely for Turkish studies. In this vein, this strategy revealed that Western experience of gentrification did not travel, adopted or copied in Turkey but gentrification -as an abstract and general concept- has emerged as a product of different contextual, historical and temporal forces which must be considered within the framework of state-led urbanization as early as 1980 differing from the Global North trajectories.

Keywords: comparative urbanism, geography of gentrification, linear and cyclical timeline, state-led gentrification

Procedia PDF Downloads 90

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 218

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 52

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 141

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 106

Authors: Jing Zhang, Yvonne Reinwald, Nick Poulson, Alicia El Haj, Chung See, Mike Somekh, Melissa Mather

Abstract:

Biomedical imaging of native tissue using light offers the potential to obtain excellent structural and functional information in a non-invasive manner with good temporal resolution. Image contrast can be derived from intrinsic absorption, fluorescence, or scatter, or through the use of extrinsic contrast. A major challenge in applying optical microscopy to in vivo tissue imaging is the effects of light attenuation which limits light penetration depth and achievable imaging resolution. Recently Selective Plane Illumination Microscopy (SPIM) has been used to map the 3D distribution of fluorophores dispersed in biological structures. In this approach, a focused sheet of light is used to illuminate the sample from the side to excite fluorophores within the sample of interest. Images are formed based on detection of fluorescence emission orthogonal to the illumination axis. By scanning the sample along the detection axis and acquiring a stack of images, 3D volumes can be obtained. The combination of rapid image acquisition speeds with the low photon dose to samples optical sectioning provides SPIM is an attractive approach for imaging biological samples in 3D. To date all implementations of SPIM rely on the use of fluorescence reporters be that endogenous or exogenous. This approach has the disadvantage that in the case of exogenous probes the specimens are altered from their native stage rendering them unsuitable for in vivo studies and in general fluorescence emission is weak and transient. Here we present for the first time to our knowledge a label-free implementation of SPIM that has downstream applications in the clinical setting. The experimental set up used in this work incorporates both label-free and fluorescent illumination arms in addition to a high specification camera that can be partitioned for simultaneous imaging of both fluorescent emission and scattered light from intrinsic sources of optical contrast in the sample being studied. This work first involved calibration of the imaging system and validation of the label-free method with well characterised fluorescent microbeads embedded in agarose gel. 3D constructs of mammalian cells cultured in agarose gel with varying cell concentrations were then imaged. A time course study to track cell proliferation in the 3D construct was also carried out and finally a native tissue sample was imaged. For each sample multiple images were obtained by scanning the sample along the axis of detection and 3D maps reconstructed. The results obtained validated label-free SPIM as a viable approach for imaging cells in a 3D gel construct and native tissue. This technique has the potential use in a near-patient environment that can provide results quickly and be implemented in an easy to use manner to provide more information with improved spatial resolution and depth penetration than current approaches.

Keywords: bioimaging, optics, selective plane illumination microscopy, tissue imaging

Procedia PDF Downloads 229

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 260

Authors: Seyedeh Sepideh Amini, Navideh Aghaei Amirkhizi, Seyedeh Paniz Amini, Seyed Soheil Sayyahi, Mohammad Reza Davar Panah

Abstract:

CT-Scan is one of the lateral and sectional imaging methods that produce 3D-images with use of rotational x-ray tube around central axis. This study is about evaluation and calculation of effective doses around heart organs such as breast, lung and liver with CT-Scan 128 dual sources with TLD_100 and RANDO Phantom by spiral, flash and conventional protocols. In results, it is showed that in spiral protocol organs have maximum effective dose and minimum in flash protocol. Thus flash protocol advised for children and risk persons.

Keywords: X-ray computed tomography, dosimetry, TLD-100, RANDO, phantom

Procedia PDF Downloads 453

Authors: Mina Dabirinezhad, Mohsen Bayat Pour, Amin Dabirinejad

Abstract:

This paper is intended to introduce the technology to solve some of the deficiencies of the direct digital radiology. Nowadays, digital radiology is the latest progression in dental imaging, which has become an essential part of dentistry. There are two main parts of the direct digital radiology comprised of an intraoral X-ray machine and a sensor (digital image receptor). The dentists and the dental nurses experience afflictions during the taking image process by the direct digital X-ray machine. For instance, sometimes they need to readjust the sensor in the mouth of the patient to take the X-ray image again due to the low quality of that. Another problem is, the position of the sensor may move in the mouth of the patient and it triggers off an inappropriate image for the dentists. It means that it is a time-consuming process for dentists or dental nurses. On the other hand, taking several the X-ray images brings some problems for the patient such as being harmful to their health and feeling pain in their mouth due to the pressure of the sensor to the jaw. The author provides a technology to solve the above-mentioned issues that is called “Self-Recognition Direct Digital Radiology” (SDDR). This technology is based on the principle that the intraoral X-ray machine is capable to diagnose the location of the sensor in the mouth of the patient automatically. In addition, to solve the aforementioned problems, SDDR technology brings out fewer environmental impacts in comparison to the previous version.

Keywords: Dental direct digital imaging, digital image receptor, digital x-ray machine, and environmental impacts

Procedia PDF Downloads 121

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 109

Authors: Ramin Ghasemi Shayan, Morteza Janebifam

Abstract:

Tumors are regularly inhomogeneous. Provincial varieties in death, metabolic action, multiplication and body part are watched. There’s expanding proof that strong tumors may contain subpopulations of cells with various genotypes and phenotypes. These unmistakable populaces of malignancy cells can connect during a serious way and may contrast in affectability to medications. Most tumors show organic heterogeneity1–3 remembering heterogeneity for genomic subtypes, varieties inside the statement of development variables and genius, and hostile to angiogenic factors4–9 and varieties inside the tumoural microenvironment. These can present as contrasts between tumors in a few people. for instance, O6-methylguanine-DNA methyltransferase, a DNA fix compound, is hushed by methylation of the quality advertiser in half of glioblastoma (GBM), adding to chemosensitivity, and improved endurance. From the outset, there includes been specific enthusiasm inside the usage of dissemination weighted imaging (DWI) and dynamic complexity upgraded MRI (DCE-MRI). DWI sharpens MRI to water dispersion inside the extravascular extracellular space (EES) and is wiped out with the size and setup of the cell populace. Additionally, DCE-MRI utilizes dynamic obtaining of pictures during and after the infusion of intravenous complexity operator. Signal changes are additionally changed to outright grouping of differentiation permitting examination utilizing pharmacokinetic models. PET scan modality gives one of a kind natural particularity, permitting dynamic or static imaging of organic atoms marked with positron emanating isotopes (for example, 15O, 18F, 11C). The strategy is explained to a colossal radiation portion, which points of confinement rehashed estimations, particularly when utilized together with PC tomography (CT). At long last, it's of incredible enthusiasm to quantify territorial hemoglobin state, which could be joined with DCE-CT vascular physiology estimation to create significant experiences for understanding tumor hypoxia.

Keywords: heterogeneity, computerized tomography scan, magnetic resonance imaging, PET

Procedia PDF Downloads 128

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 324

Authors: Pradeep Kumar Singh Chauhan, Gayatri Devi, Zamir Ahmad, Komal Chauhan, Abha Mittal

Abstract:

The application of geophysical methods to study the subsurface profile for site investigation is becoming popular globally. These methods are non-destructive and provide the image of subsurface at shallow depths. Seismic refraction method is one of the most common and efficient method being used for civil engineering site investigations particularly for knowing the seismic velocity of the subsurface layers. Resistivity imaging technique is a geo-electrical method used to image the subsurface, water bearing zone, bedrock and layer thickness. Integrated approach combining seismic refraction and 2-D resistivity imaging will provide a better and reliable picture of the subsurface. These are economical and less time-consuming field survey which provide high resolution image of the subsurface. Geophysical surveys carried out in this study include seismic refraction and 2D resistivity imaging method for delineation of sub-surface strata in different parts of Srinagar, Garhwal Himalaya, India. The aim of this survey was to map the shallow subsurface in terms of geological and geophysical properties mainly P-wave velocity, resistivity, layer thickness, and lithology of the area. Both sides of the river, Alaknanda which flows through the centre of the city, have been covered by taking two profiles on each side using both methods. Seismic and electrical surveys were carried out at the same locations to complement the results of each other. The seismic refraction survey was carried out using ABEM TeraLoc 24 channel Seismograph and 2D resistivity imaging was performed using ABEM Terrameter LS equipment. The results show three distinct layers on both sides of the river up to the depth of 20 m. The subsurface is divided into three distinct layers namely, alluvium extending up to, 3 m depth, conglomerate zone lying between the depth of 3 m to 15 m, and compacted pebbles and cobbles beyond 15 m. P-wave velocity in top layer is found in the range of 400 – 600 m/s, in second layer it varies from 700 – 1100 m/s and in the third layer it is 1500 – 3300 m/s. The resistivity results also show similar pattern and were in good agreement with seismic refraction results. The results obtained in this study were validated with an available exposed river scar at one site. The study established the efficacy of geophysical methods for subsurface investigations.

Keywords: 2D resistivity imaging, P-wave velocity, seismic refraction survey, subsurface

Procedia PDF Downloads 236