Search results for: star image

Authors: Morgan Johansson, Joosef Leppanen, Mathias Flansbjer, Fabio Lozano, Josef Makdesi

Abstract:

Concrete is commonly used for protective structures and how impact loading affects different types of concrete structures is an important issue. Often the knowledge gained from static loading is also used in the design of impulse loaded structures. A large plastic deformation capacity is essential to obtain a large energy absorption in an impulse loaded structure. However, the structural response of an impact loaded concrete beam may be very different compared to a statically loaded beam. Consequently, the plastic deformation capacity and failure modes of the concrete structure can be different when subjected to dynamic loads; and hence it is not sure that the observations obtained from static loading are also valid for dynamic loading. The aim of this paper is to investigate the residual plastic deformation capacity in reinforced concrete beams subjected to drop weight impact tests. A test-series consisting of 18 simply supported beams (0.1 x 0.1 x 1.18 m, ρs = 0.7%) with a span length of 1.0 m and subjected to a point load in the beam mid-point, was carried out. 2x6 beams were first subjected to drop weight impact tests, and thereafter statically tested until failure. The drop in weight had a mass of 10 kg and was dropped from 2.5 m or 5.0 m. During the impact tests, a high-speed camera was used with 5 000 fps and for the static tests, a camera was used with 0.5 fps. Digital image correlation (DIC) analyses were conducted and from these the velocities of the beam and the drop weight, as well as the deformations and crack propagation of the beam, were effectively measured. Additionally, for the static tests, the applied load and midspan deformation were measured. The load-deformation relations for the beams subjected to an impact load were compared with 6 reference beams that were subjected to static loading only. The crack pattern obtained were compared using DIC, and it was concluded that the resulting crack formation depended much on the test method used. For the static tests, only bending cracks occurred. For the impact loaded beams, though, distinctive diagonal shear cracks also formed below the zone of impact and less wide shear cracks were observed in the region half-way to the support. Furthermore, due to wave propagation effects, bending cracks developed in the upper part of the beam during initial loading. The results showed that the plastic deformation capacity increased for beams subjected to drop weight impact tests from a high drop height of 5.0 m. For beams subjected to an impact from a low drop height of 2.5 m, though, the plastic deformation capacity was in the same order of magnitude as for the statically loaded reference beams. The beams tested were designed to fail due to bending when subjected to a static load. However, for the impact tested beams, one beam exhibited a shear failure at a significantly reduced load level when it was tested statically; indicating that there might be a risk of reduced residual load capacity for impact loaded structures.

Keywords: digital image correlation (DIC), drop weight impact, experiments, plastic deformation capacity, reinforced concrete

Procedia PDF Downloads 142

Authors: S. Hatamikia, A. Biguri, H. Furtado, G. Kronreif, J. Kettenbach, W. Birkfellner

Abstract:

Nowadays, three dimensional Cone Beam CT (CBCT) has turned into a widespread clinical routine imaging modality for interventional radiology. In conventional CBCT, a circular sourcedetector trajectory is used to acquire a high number of 2D projections in order to reconstruct a 3D volume. However, the accumulated radiation dose due to the repetitive use of CBCT needed for the intraoperative procedure as well as daily pretreatment patient alignment for radiotherapy has become a concern. It is of great importance for both health care providers and patients to decrease the amount of radiation dose required for these interventional images. Thus, it is desirable to find some optimized source-detector trajectories with the reduced number of projections which could therefore lead to dose reduction. In this study we investigate some source-detector trajectories with the optimal arbitrary orientation in the way to maximize performance of the reconstructed image at particular regions of interest. To achieve this approach, we developed a box phantom consisting several small target polytetrafluoroethylene spheres at regular distances through the entire phantom. Each of these spheres serves as a target inside a particular region of interest. We use the 3D Point Spread Function (PSF) as a measure to evaluate the performance of the reconstructed image. We measured the spatial variance in terms of Full-Width-Half-Maximum (FWHM) of the local PSFs each related to a particular target. The lower value of FWHM shows the better spatial resolution of reconstruction results at the target area. One important feature of interventional radiology is that we have very well-known imaging targets as a prior knowledge of patient anatomy (e.g. preoperative CT) is usually available for interventional imaging. Therefore, we use a CT scan from the box phantom as the prior knowledge and consider that as the digital phantom in our simulations to find the optimal trajectory for a specific target. Based on the simulation phase we have the optimal trajectory which can be then applied on the device in real situation. We consider a Philips Allura FD20 Xper C-arm geometry to perform the simulations and real data acquisition. Our experimental results based on both simulation and real data show our proposed optimization scheme has the capacity to find optimized trajectories with minimal number of projections in order to localize the targets. Our results show the proposed optimized trajectories are able to localize the targets as good as a standard circular trajectory while using just 1/3 number of projections. Conclusion: We demonstrate that applying a minimal dedicated set of projections with optimized orientations is sufficient to localize targets, may minimize radiation.

Keywords: CBCT, C-arm, reconstruction, trajectory optimization

Procedia PDF Downloads 131

Authors: Zellagui Rahima, Chaumont Denis, Boughelout Abderrahman, Adnane Mohamed

Abstract:

Thin films of CdxZn1-xS were deposed by chemical bath deposition on glass substrates for photovoltaic applications. The thin films CdZnS were synthesized by chemical bath (CBD) with different deposition protocols for optimized the parameter of deposition as the temperature, time of deposition, concentrations of ion and pH. Surface morphology, optical and chemical composition properties of thin film CdZnS were investigated by SEM, EDAX, spectrophotometer. The transmittance is 80% in visible region 300 nm – 1000 nm; it has been observed in that films the grain size is between 50nm and 100nm measured by SEM image and we also note that the shape of particle is changing with the change in concentration. This result favors of application these films in solar cells; the chemical analysis with EDAX gives information about the presence of Cd, Zn and S elements and investigates the stoichiometry.

Keywords: thin film, solar cells, transmition, cdzns

Procedia PDF Downloads 258

Authors: Najam Aziz, Nasru Minallah, Ahmad Junaid, Kashaf Gul

Abstract:

Landcover classification using automated classification techniques, while employing remotely sensed multi-spectral imagery, is one of the promising areas of research. Different land conditions at different time are captured through satellite and monitored by applying different classification algorithms in specific environment. In this paper, a SPOT-5 image provided by SUPARCO has been studied and classified in Environment for Visual Interpretation (ENVI), a tool widely used in remote sensing. Then, Artificial Neural Network (ANN) classification technique is used to detect the land cover changes in Abbottabad district. Obtained results are compared with a pixel based Distance classifier. The results show that ANN gives the better overall accuracy of 99.20% and Kappa coefficient value of 0.98 over the Mahalanobis Distance Classifier.

Keywords: landcover classification, artificial neural network, remote sensing, SPOT 5

Procedia PDF Downloads 544

Authors: Oğuzhan Urhan

Abstract:

In this paper, an improved motion estimation (ME) approach based on weighted constrained one-bit transform is proposed for block-based ME employed in video encoders. Binary ME approaches utilize low bit-depth representation of the original image frames with a Boolean exclusive-OR based hardware efficient matching criterion to decrease computational burden of the ME stage. Weighted constrained one-bit transform (WC‑1BT) based approach improves the performance of conventional C-1BT based ME employing 2-bit depth constraint mask instead of a 1-bit depth mask. In this work, the range of constraint mask is further extended to increase ME performance of WC-1BT approach. Experiments reveal that the proposed method provides better ME accuracy compared existing similar ME methods in the literature.

Keywords: fast motion estimation; low-complexity motion estimation, video coding

Procedia PDF Downloads 314

Authors: Nareenad Panbun

Abstract:

The objective is to study the knowledge utilization from the participants of the announcer training program by National Broadcasting and Telecommunications Commission (NBTC). This study is a quantitative research based on surveys and self-answering questionnaires. The population of this study is 100 participants randomly chosen by non-probability sampling method. The results have shown that most of the participants were satisfied with the topics of general knowledge about the broadcasting and television business for 37 people representing 37%, followed by the topics of broadcasting techniques. The legal issues, consumer rights, television business ethics, and credibility of the media are, in addition to the media's role and responsibilities in society, the use of language for successful communication. Therefore, the communication language skills are the most important for all of the trainees and will also build up the image of the broadcasting center.

Keywords: announcer training program, participant, requirements announced, theory of utilization

Procedia PDF Downloads 222

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinie

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. That is why the need for automation of this task is urgent. A lot of studies have investigated the subject using different standard image processing descriptors and sometimes hand-crafted ones.In this work, we make a comparative study between classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN, Autoencoders, Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches

Keywords: pollens identification, features extraction, pollens classification, automated palynology

Procedia PDF Downloads 135

Authors: Ayalew Yimam Ali

Abstract:

The T-shaped microchannel is used to mix both miscible or immiscible fluids with different viscosities. However, mixing at the entrance of the T-junction microchannel can be difficult mixing phenomena due to micro-scale laminar flow aspects with the two miscible high-viscosity water-glycerol fluids. One of the most promising methods to improve mixing performance and diffusion mass transfer in laminar flow phenomena is acoustic streaming (AS), which is a time-averaged, second-order steady streaming that can produce rolling motion in the microchannel by oscillating a low-frequency range acoustic transducer and inducing an acoustic wave in the flow field. The newly developed 3D trapezoidal, triangular structure spine used in this study was created using sophisticated CNC machine cutting tools used to create microchannel mold with a 3D trapezoidal triangular structure spine alone the T-junction longitudinal mixing region. In order to create the molds for the 3D trapezoidal structure with the 3D sharp edge tip angles of 30° and 0.3mm trapezoidal, triangular sharp edge tip depth from PMMA glass (Polymethylmethacrylate) with advanced CNC machine and the channel manufactured using PDMS (Polydimethylsiloxane) which is grown up longitudinally on the top surface of the Y-junction microchannel using soft lithography nanofabrication strategies. Flow visualization of 3D rolling steady acoustic streaming and mixing enhancement with high-viscosity miscible fluids with different trapezoidal, triangular structure longitudinal length, channel width, high volume flow rate, oscillation frequency, and amplitude using micro-particle image velocimetry (μPIV) techniques were used to study the 3D acoustic streaming flow patterns and mixing enhancement. The streaming velocity fields and vorticity flow fields show 16 times more high vorticity maps than in the absence of acoustic streaming, and mixing performance has been evaluated at various amplitudes, flow rates, and frequencies using the grayscale value of pixel intensity with MATLAB software. Mixing experiments were performed using fluorescent green dye solution with de-ionized water in one inlet side of the channel, and the de-ionized water-glycerol mixture on the other inlet side of the T-channel and degree of mixing was found to have greatly improved from 67.42% without acoustic streaming to 0.96.83% with acoustic streaming. The results show that the creation of a new 3D steady streaming rolling motion with a high volume flowrate around the entrance was enhanced by the formation of a new, three-dimensional, intense streaming rolling motion with a high-volume flowrate around the entrance junction mixing zone with the two miscible high-viscous fluids which are influenced by laminar flow fluid transport phenomena.

Keywords: micro fabrication, 3d acoustic streaming flow visualization, micro-particle image velocimetry, mixing enhancement.

Procedia PDF Downloads 19

Authors: Rahma Abed, Sahbi Bahroun, Ezzeddine Zagrouba

Abstract:

Due to the huge amount of data in videos, extracting the relevant frames became a necessity and an essential step prior to performing face recognition. In this context, we propose a method for extracting keyframes from videos based on face quality and deep learning for a face recognition task. This method has two steps. We start by generating face quality scores for each face image based on the use of three face feature extractors, including Gabor, LBP, and HOG. The second step consists in training a Deep Convolutional Neural Network in a supervised manner in order to select the frames that have the best face quality. The obtained results show the effectiveness of the proposed method compared to the methods of the state of the art.

Keywords: keyframe extraction, face quality assessment, face in video recognition, convolution neural network

Procedia PDF Downloads 229

Authors: Revytia Tanera

Abstract:

This research is a pilot study to examine the rise of selfie trend in dealing with individual self representation and identity building in social media. The symbolic interactionism theory is used as the concept of the desired self image, and Cooley’s looking glass-self concept is used to analyze the mechanical reflection of ourselves; how do people perform their “digital self” in social media. In-depth interviews were conducted in the study with a non-random sample who owns a smartphone with a front camera feature and are active in social media. This research is trying to find out whether the selfie trend brings any influence on identity building on each individual. Through analysis of interview results, it can be concluded that people take selfie photos in order to express themselves and to boost their confidence. This study suggests a follow up and more in depth analysis on identity and self representation from various age groups.

Keywords: self representation, selfie, social media, symbolic interaction, looking glass-self

Procedia PDF Downloads 297

Authors: Lam Hong Lan

Abstract:

The textile industry is said to be the second-largest polluter, responsible for 92 million tonnes of waste annually. There is an urgent need to practice the circular economy to increase the use and reuse around the world. By its nature, the pre-owned fashion business is considered part of the circular economy as it helps to eliminate waste and circulate products. Second-hand clothes and accessories used to be associated with a ‘cheap image’ that carried ‘old energy’ in Vietnam. This perception has been shifted, especially amongst the younger generation. Vietnamese consumer is spending more on products and services that increase self-esteem. The same consumer is moving away from a collectivist social identity towards a ‘me, not we’ outlook as they look for a way to express their individual identity. And pre-owned fashion is one of their solutions as it values money, can create a unique personal style for the wearer and links with sustainability. The design of this study is based on the second-hand shopping motivation theory. A semi-structured online survey with 100 consumers from one pre-owned clothing community and one pre-owned e-commerce site in Vietnam. The findings show that in contrast with Vietnamese older consumers (55+yo) who, in the previous study, generally associated pre-owned fashion with ‘low-cost’, ‘cheap image’ that carried ‘old energy’, young customers (20-30 yo) were actively promoted their pre-owned fashion items to the public via outlet’s social platforms and their social media. This cultural shift comes from the impact of global and local discourse around sustainable fashion and the growth of digital platforms in the pre-owned fashion business in the last five years, which has generally supported wider interest in pre-owned fashion in Vietnam. It can be summarised in three areas: (1) global and local celebrity influencers. A number of celebrities have been photographed wearing vintage items in music videos, photoshoots or at red carpet events. (2) E-commerce and intermediaries. International e-commerce sites – e.g., Vinted, TheRealReal – and/or local apps – e.g., Re.Loved – can influence attitudes and behaviors towards pre-owned consumption. (3) Eco-awareness. The increased online coverage of climate change and environmental pollution has encouraged customers to adopt a more eco-friendly approach to their wardrobes. While sustainable biomaterials and designs are still navigating their way into sustainability, sustainable consumerism via pre-owned fashion seems to be an immediate solution to lengthen the clothes lifecycle. This study has found that young consumers are primarily seeking value for money and/or a unique personal style from pre-owned/vintage fashion while using these purchases to promote their own “eco-awareness” via their social media networks. This is a good indication for fashion designers to keep in mind in their design process and for fashion enterprises in their business model’s choice to not overproduce fashion items.

Keywords: cultural shift, pre-owned fashion, sustainable consumption, sustainable fashion.

Procedia PDF Downloads 83

Authors: Martin K. Steiger, Lukas Heisler, Hans-Georg Brachtendorf

Abstract:

Deep neural networks and their variants form the backbone of many AI applications. Based on the so-called residual networks, a continuous formulation of such models as ordinary differential equations (ODEs) has proven advantageous since different techniques may be applied that significantly increase the learning speed and enable controlled trade-offs with the resulting error at the same time. For the evaluation of such models, high-performance numerical differential equation solvers are used, which also provide the gradients required for training. However, whether classical gradient-based methods are even applicable or which one yields the best results has not been discussed yet. This paper aims to redeem this situation by providing empirical results for different applications.

Keywords: deep neural networks, gradient-based learning, image processing, ordinary differential equation networks

Procedia PDF Downloads 167

Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi

Abstract:

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.

Keywords: ANPR, CS, CNN, deep learning, NPL

Procedia PDF Downloads 304

Authors: Rokeshia Renné Ashley

Abstract:

The purpose of this study is to understand the perception of historical figure Saartjie 'Sara/Sarah' Baartman from a cross cultural perspective of black women in the United States and black women in South Africa. Semi-structured interviews (n = 30) uncover that many women in both countries did not have an accurate representation, recollection, or have been exposed to the story of Baartman. Nonetheless, those who were familiar with Baartman’s story, those participants compared her to modern examples of black women who are showcased in a contemporary familiarity. The women are described by participants as women who reveal their bodies in a sexualized manner and have the curves that are similar to Baartman’s historic figure. This comparison emphasized a connection to popular images of black women who represent the curvaceous ideal. Findings contribute to social comparison theory by providing a lens for examining black women’s body image.

Keywords: black women, body modification, media, South Africa

Procedia PDF Downloads 318

Authors: Mahdi Bazarganigilani

Abstract:

Computer-aided diagnosis (CAD) systems can play crucial roles in diagnosing crucial diseases such as breast cancer at the earliest. In this paper, a CAD system for the diagnosis of breast cancer was introduced and evaluated. This CAD system was developed by using spatio-temporal analysis of data on a set of consecutive thermographic images by employing wavelet transformation. By using this analysis, a very accurate machine learning model using random forest was obtained. The final results showed a promising accuracy of 91% in terms of the F1 measure indicator among 200 patients' sample data. The CAD system was further extended to obtain a detailed analysis of the effect of smaller sub-areas of each breast on the occurrence of cancer.

Keywords: computer-aided diagnosis systems, thermographic analysis, spatio-temporal analysis, image processing, machine learning

Procedia PDF Downloads 209

Authors: Shiyin He, Zheng Huang

Abstract:

In this paper, deep learning methods are applied in bio-medical field to detect and count different types of cells in an automatic way instead of manual work in medical practice, specifically in bone marrow examination. The process is mainly composed of two steps, detection and recognition. Mask-Region-Convolutional Neural Networks (Mask-RCNN) was used for detection and image segmentation to extract cells and then Convolutional Neural Networks (CNN), as well as Deep Residual Network (ResNet) was used to classify. Result of cell detection network shows high efficiency to meet application requirements. For the cell recognition network, two networks are compared and the final system is fully applicable.

Keywords: cell detection, cell recognition, deep learning, Mask-RCNN, ResNet

Procedia PDF Downloads 186

Authors: Ayalew Yimam Ali

Abstract:

The Y-shaped microchannel is used to mix both miscible or immiscible fluids with different viscosities. However, mixing at the entrance of the Y-junction microchannel can be a difficult mixing phenomena due to micro-scale laminar flow aspects with the two miscible high-viscosity water-glycerol fluids. One of the most promising methods to improve mixing performance and diffusion mass transfer in laminar flow phenomena is acoustic streaming (AS), which is a time-averaged, second-order steady streaming that can produce rolling motion in the microchannel by oscillating a low-frequency range acoustic transducer and inducing an acoustic wave in the flow field. The developed 3D trapezoidal, triangular structure spine used in this study was created using sophisticated CNC machine cutting tools used to create microchannel mold with a 3D trapezoidal triangular structure spine alone the Y-junction longitudinal mixing region. In order to create the molds for the 3D trapezoidal structure with the 3D sharp edge tip angles of 30° and 0.3mm trapezoidal triangular sharp edge tip depth from PMMA glass (Polymethylmethacrylate) with advanced CNC machine and the channel manufactured using PDMS (Polydimethylsiloxane) which is grown up longitudinally on top surface of the Y-junction microchannel using soft lithography nanofabrication strategies. Flow visualization of 3D rolling steady acoustic streaming and mixing enhancement with high-viscosity miscible fluids with different trapezoidal, triangular structure longitudinal length, channel width, high volume flow rate, oscillation frequency, and amplitude using micro-particle image velocimetry (μPIV) techniques were used to study the 3D acoustic streaming flow patterns and mixing enhancement. The streaming velocity fields and vorticity flow fields show 16 times more high vorticity maps than in the absence of acoustic streaming, and mixing performance has been evaluated at various amplitudes, flow rates, and frequencies using the grayscale value of pixel intensity with MATLAB software. Mixing experiments were performed using fluorescent green dye solution with de-ionized water in one inlet side of the channel, and the de-ionized water-glycerol mixture on the other inlet side of the Y-channel and degree of mixing was found to have greatly improved from 67.42% without acoustic streaming to 0.96.83% with acoustic streaming. The results show that the creation of a new 3D steady streaming rolling motion with a high volume flowrate around the entrance was enhanced by the formation of a new, three-dimensional, intense streaming rolling motion with a high-volume flowrate around the entrance junction mixing zone with the two miscible high-viscous fluids which are influenced by laminar flow fluid transport phenomena.

Keywords: micro fabrication, 3d acoustic streaming flow visualization, micro-particle image velocimetry, mixing enhancement

Procedia PDF Downloads 20

Authors: Sello Mokwena, Monyepao Thabang

Abstract:

In this study, we propose a comprehensive approach to address the challenges in person re-identification models. By combining a centroid tracking algorithm with a Siamese convolutional neural network model, our method excels in detecting, tracking, and capturing robust person features across non-overlapping camera views. The algorithm efficiently identifies individuals in the camera network, while the neural network extracts fine-grained global features for precise cross-image comparisons. The approach's effectiveness is further accentuated by leveraging the camera network topology for guidance. Our empirical analysis on benchmark datasets highlights its competitive performance, particularly evident when background subtraction techniques are selectively applied, underscoring its potential in advancing person re-identification techniques.

Keywords: camera network, convolutional neural network topology, person tracking, person re-identification, siamese

Procedia PDF Downloads 70

Authors: Shrikaant Kulkarni, Akshata Naik Nimbalkar

Abstract:

In this worki a method protocol has been developed for the synthesis of innovative Co3O4 material by using a method of chemical synthesis followed by calcination. The effect of calcination temperature on the morphology, structure and catalytic performance on material in question is investigated by using characterization tools like scanning electron microscopy (SEM), X-ray diffraction (XRD) spectroscopy and electrochemical techniques. The SEM images reveal that the morphology of the Co3O4 material undergoes a change from the rod to a beadlike shape on calcination at temperature of 700 °C. The XRD image shows that although the morphology of synthesized Co3O4 material exhibits a cubic phase but it differs in crystallinity depending upon morphology. Similarly spherical beadlike Co3O4 material has exhibited better activity than its rodlike counterpart which is reflected from electrochemical findings. Further, its performance in terms of bifunctional nature and hlods a lot much of promise as a excellent electrode material in the next generation batteries and fuel cells.

Keywords: bifunctional, next generation material, Co3O4, XRD

Procedia PDF Downloads 376

Authors: Asil Zureigat, Ayat Odat

Abstract:

Analyzing the old and bringing in the new is an ever ongoing process in driving innovations in architecture. This paper looks at the excessive use of stone in apartment buildings in Amman and speculates on the existing possibilities of changing the cladding material. By looking at architectural exceptions present in Amman the paper seeks to make the exception, the rule by adding new materials to the architectural library of Amman and in turn, project a series of possible new identities to the existing stone scape. Through distributing a survey, conducting a photographic study on exceptional buildings and shedding light on the historical narrative of stone, the paper highlights the ways in which new finishing materials such as plaster, paint and stone variations could be introduced in an attempt to project a new architectural identity to Amman.

Keywords: architectural city identity, cladding materials, façade architecture, image of the city

Procedia PDF Downloads 223

Authors: Almagul Assainova , Dariya Abykenova, Liudmila Goncharenko, Sergey Sybachin, Saule Rakhimova, Abay Aman

Abstract:

The recognition of a handwritten Kazakh text is a relevant objective today for the digitization of materials. The study presents a model of a hybrid neural network for handwriting recognition, which includes a convolutional neural network and a multi-layer perceptron. Each network includes 1024 input neurons and 42 output neurons. The model is implemented in the program, written in the Python programming language using the EMNIST database, NumPy, Keras, and Tensorflow modules. The neural network training of such specific letters of the Kazakh alphabet as ә, ғ, қ, ң, ө, ұ, ү, h, і was conducted. The neural network model and the program created on its basis can be used in electronic document management systems to digitize the Kazakh text.

Keywords: handwriting recognition system, image recognition, Kazakh font, machine learning, neural networks

Procedia PDF Downloads 260

Authors: Josef Uher, Jana Boháčová, Richard Kadeřábek

Abstract:

In this paper, we present a multi-robot imaging and irradiation research platform referred to as Irradion, with full capabilities of portable arbitrary path computed tomography (CT). Irradion is an imaging and irradiation unit entirely based on robotic arms for research on cancer treatment with ion beams on small animals (mice or rats). The platform comprises two subsystems that combine several imaging modalities, such as 2D X-ray imaging, CT, and particle tracking, with precise positioning of a small animal for imaging and irradiation. Computed Tomography: The CT subsystem of the Irradion platform is equipped with two 6-joint robotic arms that position a photon counting detector and an X-ray tube independently and freely around the scanned specimen and allow image acquisition utilizing computed tomography. Irradiation measures nearly all conventional 2D and 3D trajectories of X-ray imaging with precisely calibrated and repeatable geometrical accuracy leading to a spatial resolution of up to 50 µm. In addition, the photon counting detectors allow X-ray photon energy discrimination, which can suppress scattered radiation, thus improving image contrast. It can also measure absorption spectra and recognize different materials (tissue) types. X-ray video recording and real-time imaging options can be applied for studies of dynamic processes, including in vivo specimens. Moreover, Irradion opens the door to exploring new 2D and 3D X-ray imaging approaches. We demonstrate in this publication various novel scan trajectories and their benefits. Proton Imaging and Particle Tracking: The Irradion platform allows combining several imaging modules with any required number of robots. The proton tracking module comprises another two robots, each holding particle tracking detectors with position, energy, and time-sensitive sensors Timepix3. Timepix3 detectors can track particles entering and exiting the specimen and allow accurate guiding of photon/ion beams for irradiation. In addition, quantifying the energy losses before and after the specimen brings essential information for precise irradiation planning and verification. Work on the small animal research platform Irradion involved advanced software and hardware development that will offer researchers a novel way to investigate new approaches in (i) radiotherapy, (ii) spectral CT, (iii) arbitrary path CT, (iv) particle tracking. The robotic platform for imaging and radiation research developed for the project is an entirely new product on the market. Preclinical research systems with precision robotic irradiation with photon/ion beams combined with multimodality high-resolution imaging do not exist currently. The researched technology can potentially cause a significant leap forward compared to the current, first-generation primary devices.

Keywords: arbitrary path CT, robotic CT, modular, multi-robot, small animal imaging

Procedia PDF Downloads 87

Authors: Zohra Aziz Ali Manjiyani, Renju Thomas Jacob, Keerthan Kumar

Abstract:

This project develops a hand movement monitoring system, which feeds the data into the computer and gives the 3D image rotation according to the direction of the tilt and hence monitoring the movement of the hand in context to its tilt. Advancement of MEMS Technology has enabled us to get very small and low-cost accelerometer ICs which is based on capacitive principle. Accelerometer based Tilt sensor ADXL335 is used in this paper, based on MEMS technology and the project emphasis on the development of the MEMS-based accelerometer to measure the tilt, interfacing the hardware with the LabVIEW and showing the 3D rotation to the user, which is in his understandable form and tilt data can be saved in the computer. It provides an experience of working on emerging technologies like MEMS and design software like LabVIEW.

Keywords: MEMS accelerometer, tilt sensor ADXL335, LabVIEW simulation, 3D animation

Procedia PDF Downloads 514

Authors: Ulysse Lecomte, Maryline Thenot

Abstract:

For a long time, disabled people lived in isolation within the family environment, with little interaction with the outside world and a high risk of social exclusion. However, in a number of countries, progress has been made thanks to changes in legislation on the social integration of disabled people, a significant change in attitudes, and the development of CSR. But the problem of their social, economic, and professional exclusion persists and has been further exacerbated by the COVID-19 pandemic. This societal phenomenon is sufficiently important to be the subject of management science research. We have therefore focused our work on society's current perception of people with disabilities and their possible integration. Our aim is to find out what levers could be put in place to bring about positive change in the situation. We have chosen to focus on the perception of young people in France, who are the new generation responsible for the future of our society and from whom tomorrow's decisionmakers, future employers, and stakeholders who can influence the living conditions of disabled people will be drawn. Our study sample corresponds to the 18-30 age group, which is the population of young adults likely to have sufficient experience and maturity. The aim of this study is not only to find out how this population currently perceives disability but also to identify the factors influencing this perception and the most effective levers for action to act positively on this phenomenon and thus promote better social integration of people with disabilities in the future. The methodology is based on theoretical and empirical research. The literature review includes a historical and etymological approach to disability, a definition of the different concepts of disability, an approach to disability as a vector of social exclusion, and the role of perception and representations in defining the social image of disability. This literature review is followed by an empirical part carried out by means of a questionnaire administered to 110 young people aged 18 to 30. Analysis of our results suggests that, despite a recent improvement, disabled people are still perceived as vulnerable and socially marginalised. The following factors stand out as having a significant influence (positive or negative) on the perception of disability: the individual's familiarity with the 'world of disability', cultural factors, the degree of 'visibility' of the disability and the empathy level of the disabled person him/herself. Others, on the other hand, such as socio-political and economic factors, have little impact on this perception. In addition, it is possible to classify the various levers of action likely to improve the social perception of disability according to their degree of effectiveness. Our study population prioritised training initiatives for the various players and stakeholders (teachers, students, disabled people themselves, companies, sports clubs, etc.). This was followed by communication, ecommunication and media campaigns in favour of disability. Lastly, the sample was judged as 'less effective' positive discrimination actions such as setting a minimum percentage for the representation of disabled people in various fields (studies, employment, politics ...).

Keywords: disability, perception, social image, young people, influencing factors, levers for action

Procedia PDF Downloads 32

Authors: Manaranjan Pradhan, Shailaja Grover, U. Dinesh Kumar

Abstract:

Farming community in India, as well as other parts of the world, is one of the highly stressed communities due to reasons such as increasing input costs (cost of seeds, fertilizers, pesticide), droughts, reduced revenue leading to farmer suicides. Lack of integrated farm advisory system in India adds to the farmers problems. Farmers need right information during the early stages of crop’s lifecycle to prevent damage and loss in revenue. In this paper, we use deep learning techniques to develop an early warning system for detection of crop diseases using images taken by farmers using their smart phone. The research work leads to building a smart assistant using analytics and big data which could help the farmers with early diagnosis of the crop diseases and corrective actions. The classical approach for crop disease management has been to identify diseases at crop level. Recently, ImageNet Classification using the convolutional neural network (CNN) has been successfully used to identify diseases at individual plant level. Our model uses convolution filters, max pooling, dense layers and dropouts (to avoid overfitting). The models are built for binary classification (healthy or not healthy) and multi class classification (identifying which disease). Transfer learning is used to modify the weights of parameters learnt through ImageNet dataset and apply them on crop diseases, which reduces number of epochs to learn. One shot learning is used to learn from very few images, while data augmentation techniques are used to improve accuracy with images taken from farms by using techniques such as rotation, zoom, shift and blurred images. Models built using combination of these techniques are more robust for deploying in the real world. Our model is validated using tomato crop. In India, tomato is affected by 10 different diseases. Our model achieves an accuracy of more than 95% in correctly classifying the diseases. The main contribution of our research is to create a personal assistant for farmers for managing plant disease, although the model was validated using tomato crop, it can be easily extended to other crops. The advancement of technology in computing and availability of large data has made possible the success of deep learning applications in computer vision, natural language processing, image recognition, etc. With these robust models and huge smartphone penetration, feasibility of implementation of these models is high resulting in timely advise to the farmers and thus increasing the farmers' income and reducing the input costs.

Keywords: analytics in agriculture, CNN, crop disease detection, data augmentation, image recognition, one shot learning, transfer learning

Procedia PDF Downloads 117

Authors: Lumindu Dilumka, Ranaweera I. D., Sudusinghe S. P., Sanduni Kanchana A. M. K.

Abstract:

This study was motivated by the challenges experienced by parents and guardians in ensuring the safety of children in cyberspace. In the last two or three years, online education has become very popular all over the world due to the Covid 19 pandemic. Therefore, parents, guardians and teachers must ensure the safety of children in cyberspace. Children are more likely to go astray and there are plenty of online programs are waiting to get them on the wrong track and also, children who are engaging in the online education can be distracted at any moment. Therefore, parents should keep a close check on their children's online activity. Apart from that, due to the unawareness of children, they tempt to share their sensitive information, causing a chance of being a victim of phishing attacks from outsiders. These problems can be overcome through the proposed web-based system. We use feature extraction, web tracking and analysis mechanisms, image processing and name entity recognition to implement this web-based system.

Keywords: online education, cyber bullying, social media, face recognition, web tracker, privacy data

Procedia PDF Downloads 86

Authors: Jaeyoung Lee

Abstract:

Autonomous driving systems require high reliability to provide people with a safe and comfortable driving experience. However, despite the development of a number of vehicle sensors, it is difficult to always provide high perceived performance in driving environments that vary from time to season. The image segmentation method using deep learning, which has recently evolved rapidly, provides high recognition performance in various road environments stably. However, since the system controls a vehicle in real time, a highly complex deep learning network cannot be used due to time and memory constraints. Moreover, efficient networks are optimized for GPU environments, which degrade performance in embedded processor environments equipped simple hardware accelerators. In this paper, a semantic segmentation network, matrix multiplication accelerator network (MMANet), optimized for matrix multiplication accelerator (MMA) on Texas instrument digital signal processors (TI DSP) is proposed to improve the recognition performance of autonomous driving system. The proposed method is designed to maximize the number of layers that can be performed in a limited time to provide reliable driving environment information in real time. First, the number of channels in the activation map is fixed to fit the structure of MMA. By increasing the number of parallel branches, the lack of information caused by fixing the number of channels is resolved. Second, an efficient convolution is selected depending on the size of the activation. Since MMA is a fixed, it may be more efficient for normal convolution than depthwise separable convolution depending on memory access overhead. Thus, a convolution type is decided according to output stride to increase network depth. In addition, memory access time is minimized by processing operations only in L3 cache. Lastly, reliable contexts are extracted using the extended atrous spatial pyramid pooling (ASPP). The suggested method gets stable features from an extended path by increasing the kernel size and accessing consecutive data. In addition, it consists of two ASPPs to obtain high quality contexts using the restored shape without global average pooling paths since the layer uses MMA as a simple adder. To verify the proposed method, an experiment is conducted using perfsim, a timing simulator, and the Cityscapes validation sets. The proposed network can process an image with 640 x 480 resolution for 6.67 ms, so six cameras can be used to identify the surroundings of the vehicle as 20 frame per second (FPS). In addition, it achieves 73.1% mean intersection over union (mIoU) which is the highest recognition rate among embedded networks on the Cityscapes validation set.

Keywords: edge network, embedded network, MMA, matrix multiplication accelerator, semantic segmentation network

Procedia PDF Downloads 128

Authors: Ihsane Modhaffar

Abstract:

Fiber orientation is essential for the physical properties of composite materials. The theoretical parameters of a given reinforcement are usually known and widely used to predict the behavior of the material. In this work, we propose an image processing approach to estimate true principal directions and fiber orientation during injection molding processes of short fiber reinforced thermoplastics. Generally, a group of fibers are described in terms of probability distribution function or orientation tensor. Numerical techniques for the prediction of fiber orientation are also considered for concentrated situations. The flow was considered to be incompressible, and behave as Newtonian fluid containing suspensions of short-fibers. The governing equations, of this problem are: the continuity, the momentum and the energy. The obtained results were compared to available experimental findings. A good agreement between the numerical results and the experimental data was achieved.

Keywords: injection, composites, short-fiber reinforced thermoplastics, fiber orientation, incompressible fluid, numerical simulation

Procedia PDF Downloads 530

Authors: I. Gkolfinopoulos, N. Chijiwa

Abstract:

To evaluate the remaining capacity in concrete tensioned members, it is important to accurately estimate damage in precast concrete tendons. In this research Johnson-Cook model and damage parameters of high-strength steel material were calculated by static and dynamic uniaxial tensile tests. Replication of experimental results was achieved through finite element analysis for both single 8-noded three-dimensional element as well as the full-scale dob-bone shaped model and relevant model parameters are proposed. Finally, simulation results in terms of strain and deformation were verified using digital image correlation analysis.

Keywords: DIC analysis, Johnson-Cook, quasi-static, dynamic, rupture, tendon

Procedia PDF Downloads 145

Authors: Rakkrit Duangsoithong, Jermphiphut Jaruenpunyasak, Alba Garcia

Abstract:

The use of foot recognition can be applied in many medical fields such as the gait pattern analysis and the knee exercises of patients in rehabilitation. Generally, a camera-based foot recognition system is intended to capture a patient image in a controlled room and background to recognize the foot in the limited views. However, this system can be inconvenient to monitor the knee exercises at home. In order to overcome these problems, this paper proposes to use the deep learning method using Convolutional Neural Networks (CNNs) for foot recognition. The results are compared with the traditional classification method using LBP and HOG features with kNN and SVM classifiers. According to the results, deep learning method provides better accuracy but with higher complexity to recognize the foot images from online databases than the traditional classification method.

Keywords: foot recognition, deep learning, knee rehabilitation, convolutional neural network

Procedia PDF Downloads 160