Abstract: The management of COVID-19 patients based on chest imaging is emerging as an essential tool for evaluating the spread of the pandemic which has gripped the global community. It has already been used to monitor the situation of COVID-19 patients who have issues in respiratory status. There has been increase to use chest imaging for medical triage of patients who are showing moderate-severe clinical COVID-19 features, this is due to the fast dispersal of the pandemic to all continents and communities. This article demonstrates the development of machine learning techniques for the test of COVID-19 patients using Chest X-Ray (CXR) images in nearly real-time, to distinguish the COVID-19 infection with a significantly high level of accuracy. The testing performance has covered a combination of different datasets of CXR images of positive COVID-19 patients, patients with viral and bacterial infections, also, people with a clear chest. The proposed AI scheme successfully distinguishes CXR scans of COVID-19 infected patients from CXR scans of viral and bacterial based pneumonia as well as normal cases with an average accuracy of 94.43%, sensitivity 95%, and specificity 93.86%. Predicted decisions would be supported by visual evidence to help clinicians speed up the initial assessment process of new suspected cases, especially in a resource-constrained environment.
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.
Abstract: It is well known that cemented sand is one of the best approaches for soil stabilization. In some cases, a blend of sand, cement and other pozzolan materials such as zeolite, nano-particles and fiber can be widely (commercially) available and be effectively used in soil stabilization, especially in road construction. In this research, we investigate the effects of CaO which is based on the geotechnical characteristics of zeolite composition with sandy silt soil. Zeolites have low amount of CaO in their structures, that is, varying from 3% to 10%, and by removing the cement paste, we want to investigate the effect of zeolite pozzolan without any activator on soil samples strength. In this research, experiments are concentrated on various weight percentages of zeolite in the soil to examine the effect of the zeolite on drainage shear strength and California Bearing Ratio (CBR) both with and without curing. The study also investigates their liquid limit and plastic limit behavior and makes a comparative result by using Feng's and Wroth-Wood's methods in fall cone (cone penetrometer) device; in the final the SEM images have been presented. The results show that by increasing the percentage of zeolite in without-curing samples, the fine zeolite particles increase some soil's strength, but in the curing-state we can see a relatively higher strength toward without-curing state, since the zeolites have no plastic behavior, the pozzolanic property of zeolites plays a much higher role than cementing properties. Indeed, it is better to combine zeolite particle with activator material such as cement or lime to gain better results.
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.
Abstract: Strawberry is one of the most favored fruits all along the world. But due to its vulnerability to microbial contamination and short life storage, there are lots of problems in industrial production and transportation of this fruit. Therefore, lots of ideas have tried to increase the storage life of strawberries especially through proper packaging. This paper works on efficient packaging as well. The primary material used is produced through simple mixing of low-density polyethylene (LDPE) and silver nanoparticles in different weight fractions of 0.5 and 1% in presence of dicumyl peroxide as a cross-linking agent. Final packages were made in a twin-screw extruder. Then, their effect on the quality maintenance of strawberry is evaluated. The SEM images of nano-silver packages show the distribution of silver nanoparticles in the packages. Total bacteria count, mold, yeast and E. coli are measured for microbial evaluation of all samples. Texture, color, appearance, odor, taste and total acceptance of various samples are evaluated by trained panelists and based on 9-point hedonic scale method. The results show a decrease in total bacteria count and mold in nano-silver packages compared to the samples packed in polyethylene packages for the same storage time. The optimum concentration of silver nanoparticles for the lowest bacteria count and mold is predicted to be around 0.5% which has attained the most acceptance from the panelist as well. Moreover, organoleptic properties of strawberry are preserved for a longer period in nano-silver packages. It can be concluded that using nano-silver particles in strawberry packages has improved the storage life and quality maintenance of the fruit.
Abstract: The study has been carried out on the Saranda in Jharkhand and a part of Odisha state. Geospatial data of Hyperion, a remote sensing satellite, have been used. This study has used a wide variety of patterns related to image processing to enhance and extract the mining class of Fe and Mn ores.Landsat-8, OLI sensor data have also been used to correctly explore related minerals. In this way, various processes have been applied to increase the mineralogy class and comparative evaluation with related frequency done. The Hyperion dataset for hyperspectral remote sensing has been specifically verified as an effective tool for mineral or rock information extraction within the band range of shortwave infrared used. The abundant spatial and spectral information contained in hyperspectral images enables the differentiation of different objects of any object into targeted applications for exploration such as exploration detection, mining.
Abstract: Primary progressive aphasia (PPA) is a neurodegenerative disease similar to frontotemporal and semantic dementia, while having a different clinical image and anatomic pathology topography. Nonetheless, they are often included under an umbrella term: frontotemporal lobar degeneration (FTLD). In the study, examples of diagnosing PPA are presented through the multidisciplinary lens of specialists from different fields (neurologists, psychiatrists, clinical speech therapists, clinical neuropsychologists and others) using a variety of diagnostic tools such as MR, PET/CT, genetic screening and neuropsychological and logopedic methods. Thanks to that, specialists can get a better and clearer understanding of PPA diagnosis. The study summarizes the concrete procedures and results of different specialists while diagnosing PPA in a patient of younger middle age and illustrates the importance of multidisciplinary approach to differential diagnosis of PPA.
Abstract: Multimodal image registration is a profoundly complex
task which is why deep learning has been used widely to address it in
recent years. However, two main challenges remain: Firstly, the lack
of ground truth data calls for an unsupervised learning approach,
which leads to the second challenge of defining a feasible loss
function that can compare two images of different modalities to judge
their level of alignment. To avoid this issue altogether we implement a
generative adversarial network consisting of two registration networks
GAB, GBA and two discrimination networks DA, DB connected by
spatial transformation layers. GAB learns to generate a deformation
field which registers an image of the modality B to an image of the
modality A. To do that, it uses the feedback of the discriminator DB
which is learning to judge the quality of alignment of the registered
image B. GBA and DA learn a mapping from modality A to modality
B. Additionally, a cycle-consistency loss is implemented. For this,
both registration networks are employed twice, therefore resulting in
images ˆA, ˆB which were registered to ˜B, ˜A which were registered
to the initial image pair A, B. Thus the resulting and initial images
of the same modality can be easily compared. A dataset of liver
CT and MRI was used to evaluate the quality of our approach and
to compare it against learning and non-learning based registration
algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01
and is therefore comparable to and slightly more successful than
algorithms like SimpleElastix and VoxelMorph.
Abstract: Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.
Abstract: Based on the remote image data of land use in the four periods of 1980, 1995, 2005 and 2015, this study quantitatively analyzed the dynamic variation of landscape transfer and landscape pattern in the Fuxian Lake basin by constructing a land use dynamic variation model and using ArcGIS 10.5 and Fragstats 4.2. The results indicate that: (1) From the perspective of land use landscape transfer, the intensity of land use is slowly rising from 1980 to 2015, and the main reduction landscape type is farmland and its net amount of transfer-out is the most among all transfer-outs, which is to 788.85 hm2, the main added landscape type is construction land and its net amount of transfer-in is the most, which is to 475.23 hm2. Meanwhile, the land use landscape variation in the stage of 2005-2015 showed the most severe among three periods when compared with other two stages. (2) From the perspective of land use landscape variation, significant spatial differences are shown, the changes in the north of the basin are significantly higher than that in the south, the west coast are apparently higher than the east. (3) From the perspective of landscape pattern index, the number of plaques is on the increase in the periods of 35 years in the basin, and there is little mutual interference between landscape patterns because the plaques are relatively discrete. Cultivated land showed a trend of fragmentation but constructive land showed trend of relative concentration. The sustainable development and biodiversity in this basin are under threat for the fragmented landscape pattern and the poorer connectivity.
Abstract: Accurate segmentation of the optic disc is very
important for computer-aided diagnosis of several ocular diseases
such as glaucoma, diabetic retinopathy, and hypertensive retinopathy.
The paper presents an accurate and fast optic disc detection and
segmentation method using an attention based fully convolutional
network. The network is trained from scratch using the fundus images
of extended MESSIDOR database and the trained model is used for
segmentation of optic disc. The false positives are removed based on
morphological operation and shape features. The result is evaluated
using three-fold cross-validation on six public fundus image databases
such as DIARETDB0, DIARETDB1, DRIVE, AV-INSPIRE, CHASE
DB1 and MESSIDOR. The attention based fully convolutional
network is robust and effective for detection and segmentation of
optic disc in the images affected by diabetic retinopathy and it
outperforms existing techniques.
Abstract: In this paper, we report the development of a portable and inexpensive infrared lightbox for improving the detection limits of paper-based phosphate devices. Commercial paper-based devices utilize the molybdenum blue protocol to detect phosphate in the environment. Although these devices are easy to use and have a long shelf life, their main deficiency is their low sensitivity based on the qualitative results obtained via a color chart. To improve the results, we constructed a compact infrared lightbox that communicates wirelessly with a smartphone. The system measures the absorbance of radiation for the molybdenum blue reaction in the infrared region of the spectrum. It consists of a lightbox illuminated by four infrared light-emitting diodes, an infrared digital camera, a Raspberry Pi microcontroller, a mini-router, and an iPhone to control the microcontroller. An iPhone application was also developed to analyze images captured by the infrared camera in order to quantify phosphate concentrations. Additionally, the app connects to an online data center to present a highly scalable worldwide system for tracking and analyzing field measurements. In this study, the detection limits for two popular commercial devices were improved by a factor of 4 for the Quantofix devices (from 1.3 ppm using visible light to 300 ppb using infrared illumination) and a factor of 6 for the Indigo units (from 9.2 ppm to 1.4 ppm) with repeatability of less than or equal to 1.2% relative standard deviation (RSD). The system also provides more granular concentration information compared to the discrete color chart used by commercial devices and it can be easily adapted for use in other applications.
Abstract: Program synthesis is the task to automatically generate
programs based on user specification. In this paper, we present a
framework that synthesizes programs from flow charts that serve as
accurate and intuitive specification. In order doing so, we propose a
deep neural network called GRCNN that recognizes graph structure
from its image. GRCNN is trained end-to-end, which can predict edge
and node information of the flow chart simultaneously. Experiments
show that the accuracy rate to synthesize a program is 66.4%, and
the accuracy rates to recognize edge and node are 94.1% and 67.9%,
respectively. On average, it takes about 60 milliseconds to synthesize
a program.
Abstract: Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.
Abstract: This paper presents a method for single image dehazing based on dark channel prior (DCP). The property that the intensity of the dark channel gives an approximate thickness of the haze is used to estimate the transmission and atmospheric light. Instead of constant atmospheric light, the proposed method employs scene depth to estimate spatially varying atmospheric light as it truly occurs in nature. Haze imaging model together with the soft matting method has been used in this work to produce high quality haze free image. Experimental results demonstrate that the proposed approach produces better results than the classic DCP approach as color fidelity and contrast of haze free image are improved and no over-saturation in the sky region is observed. Further, lifting Haar wavelet transform is employed to reduce overall execution time by a factor of two to three as compared to the conventional approach.
Abstract: The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.
Abstract: The main objective of this study is to find a suitable approach to monitor the land infrastructure growth over a period of time using multispectral satellite images. Bi-temporal change detection method is unable to indicate the continuous change occurring over a long period of time. To achieve this objective, the approach used here estimates a statistical model from series of multispectral image data over a long period of time, assuming there is no considerable change during that time period and then compare it with the multispectral image data obtained at a later time. The change is estimated pixel-wise. Statistical composite hypothesis technique is used for estimating pixel based change detection in a defined region. The generalized likelihood ratio test (GLRT) is used to detect the changed pixel from probabilistic estimated model of the corresponding pixel. The changed pixel is detected assuming that the images have been co-registered prior to estimation. To minimize error due to co-registration, 8-neighborhood pixels around the pixel under test are also considered. The multispectral images from Sentinel-2 and Landsat-8 from 2015 to 2018 are used for this purpose. There are different challenges in this method. First and foremost challenge is to get quite a large number of datasets for multivariate distribution modelling. A large number of images are always discarded due to cloud coverage. Due to imperfect modelling there will be high probability of false alarm. Overall conclusion that can be drawn from this work is that the probabilistic method described in this paper has given some promising results, which need to be pursued further.
Abstract: In this study, an automated building and tree detection
method is proposed using DSM data and true orthophoto image. A
multiscale matched filtering is used on DSM data. Therefore, first
watershed transform is applied. Then, Otsu’s thresholding method
is used as an adaptive threshold to segment each watershed region.
Detected objects are masked with NDVI to separate buildings and
trees. The proposed method is able to detect buildings and trees
without entering any elevation threshold. We tested our method on
ISPRS semantic labeling dataset and obtained promising results.
Abstract: Absent Theaters is a project that virtually reconstructs three theaters that existed in the twentieth century, demolished in the city of Medellin, Colombia: Circo España, Bolívar, and Junín. Virtual reconstruction is used as an excuse to talk with those who lived in their childhood and youth cultural spaces that formed a whole generation. Around 100 people who witnessed these theaters were interviewed. The means used to perform the oral history work was the virtual reconstruction of the interior of the theaters that were presented to the interviewees through the Virtual Reality glasses. The voices of people between 60 and 103 years old were used to generate a transmission of knowledge to the new generations about the importance of theaters as essential places for the city, as spaces generating social relations and knowledge of other cultures. Oral stories about events, the historical and social context of the city, were mixed with archive images and animations of the architectural transformations of these places. Oral stories about events, the historical and social context of the city, were mixed with archive images and animations of the architectural transformations of these places, with the purpose of compiling a collective discourse around cultural activities, heritage, and memory of Medellin.
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%.