The Diagnosis of COVID-19 through X-ray Images via Transfer Learning and Fine-Tuned Dense Layer on Pipeline

X-ray is used in medical treatment as a method to diagnose the human body internally from diseases. Nevertheless, the development in machine learning technologies for pattern recognition have allowed machine learning of diagnosing diseases from chest X-ray images. One such diseases that are able to be detected by using X-ray is the COVID-19 coronavirus. This research investigates the diagnosis of COVID-19 through X-ray images by using transfer learning and fine-tuning of the fully connected layer. Next, hyperparameters such as dropout, p, number of neurons, and activation functions are investigated on which combinations of these hyperparameters will yield the highest classification accuracy model. InceptionV3 which is one of the common neural network is used for feature extraction from chest X-ray images. Subsequently, the loss and accuracy graphs are used to find the pipeline which performs the best in classification task. The findings in this research will open new possibilities in screening method for COVID-19.

Design and Analysis of a Lower Limb Exo-Skeleton Suit for Post Stroke Patient: Static and Ergonomic Analyses

This paper presents a study on the development of a lower limb exoskeleton suit (exo-suit) for post-stroke patients. The exo-suit is designed and developed for restoration of post-stroke patients' gait motion (ability to use their lower limb joints) and analysis on ergonomics and statics are also considered. The mechanical structure of the exo-suit is proposed according to the anatomy of Asian people with an average mass of eighty kilograms in order that it is fitted perfectly. The conceptual design is established and selected by a dedicated design matrix and compared using the matrix evaluation process, and then Computer-Aided Design (CAD) software CATIA is used to create the 3D model. The design has undergone an evaluation of static structural and ergonomic analysis via CATIA and ANSYS Finite Element Analysis (FEA) software. Two materials are used in the static structural analysis, one is aluminium alloy, the other is steel material. The result of equivalent stress for both materials is within the allowable range of 29.511MPa to 1168.4 MPa. For RULA (Rapid Upper Limb Assessment) Analysis, the results showed that all three postures (static, intermittent, and repeated) yield acceptable final score which is 1 for intermittent and 2 for static and repeated postures.

Time-Series Classification Vegetables in Detecting Growth Rate Using Machine Learning

IoT based innovative irrigation management systems can help in attaining optimum water-resource utilisation in the exactness farming landscape. This paper presents a clustering of unsupervised learning based innovative system to forecast the irrigation requirements of a field using the sensing of a ground parameter such as soil moisture, light intensity, temperature, and humidity. The entire system has been established and deployed. The sensor node data is gained through a serial monitor from Arduino IDE software collected directly and saved using the computer. Orange and MATLAB software is used to apply machine learning for the visualisation, and the decision support system delivers real-time information insights based on the analysis of sensors data. The plants organise either water or non-water includes weather conditions to gain various types of results. kNN reached 100.0%, SVM achieved 99.0% owhile Naïve Bayes achieved 87.40%.

Classification of Plant Health (Capsicum Frutescens) Normalize Differences Vegetation Index using Image Processing

The evolution of food manufacturer in global contribute in national income of the country. Agriculture has been a part of everyone’s life which result in providing food become the building block of every human being. Malaysia is only country experiencing deteriorating development contribute (25.9%) agriculture in Gross Deficient Domestics Product (GDP) while others are fishing (12%), rubber (3.0%) and forestry & logging (6.3%), livestock (15.3%). In line with the development of technology in present century, a lot of methods and technique introduced to upgrowth agriculture sector by focusing to the plant health. The aims of this study are to classify of agriculture plant health through NDVI using image processing. Image processing is a technique representing operations and observation on an image. The images of plant will be captured in this investigation to obtain a photo without (Infra-Red) IR imaging filter. Some of steps must be perform which also include of using multi-function software to gain NDVI values of plant. The main objective in this study is to classify plant health by performing the vegetation index of plant and identify the best machine learning to be applied.

Preventive Maintenance Data Logger Monitoring System

This research presents the Preventive Maintenance Data Logger (PMDL) Monitoring System and the process of how it has been manufactured. Preventive Maintenance Data Logger Monitoring System is a device which will collect the data from vehicle’s sensor for prevention maintenance and then save the data to other storage for future analysis. Preventive Maintenance Data Logger Monitoring System also can send notification to user for crash prevention. This project comprises of mechanical system, electronic system, and software system. The methodology of the Preventive Maintenance Data Logger system and prototype development is discussed in this paper on the manufacturing processes. The software is programmed using C language in Arduino software and the notification for preventive are develop using BLYNK application. Manufacturing processes involves in making this project, including additive manufacturing, welding and cutting. Several test case studies were conducted to verify the capability of the device in term of the vehicle speed, location, crash point data, distance between other vehicles detection and reliability.

The Analysis of Road Traffic Fatality Pattern for Selangor, Malaysia Case Study

Road traffic fatality is a burden towards low- and middle-income countries including Malaysia. Seeing that Selangor has the highest number of road traffic fatalities in Malaysia for the year 2019, therefore the state is selected as a case study. The aim of the article is 1) to understand the road traffic crash pattern and road traffic fatality pattern in Selangor 2) to determine the ability of 16 road traffic features in classifying road traffic fatality occurrence. The preliminary data screening shows that road traffic crash patterns and road traffic fatality patterns in Selangor have many similarities. However, both of them also have few dissimilarities such as crash time of occurrence, day of occurrence, number of vehicles involved in a crash, and type of vehicle first hit for the crash. Supervised machine learning algorithm in Orange data mining software was considered in this analysis. The analysed algorithms among others are neural network, random forest, decision tree, logistic regression, naïve Bayes, and support vector machine. Neural network was seen as the best algorithm to classify road traffic fatality occurrence with 97.0% classification accuracy outperform other algorithms. The result of the article can be used by the relevant traffic stakeholders to execute safety intervention in a more focused manner in Selangor to reduce the number of road traffic fatalities.

The Classification of Taekwondo Kicks Via Machine Learning: A feature selection investigation

Martial art strike classification by machine learning has drawn more attention over the past decade. The unique signal from each technique makes it harder to be recognized. Thus, this paper proposed an SVM, Random Forest, k-NN, and Naïve Bayes classification method applied to the time-domain signal to classify the three type of taekwondo technique. Data collected from the total of five participant and statistical features such as mean, median, minimum, maximum, standard deviation, variance, skewness, kurtosis, and standard error mean were extracted from the signal. After that, the data will be trained using selected rank features and hold-out method with k-fold cross-validation applied to the training and testing data. Therefore, with ANOVA test as features selection and 60:40 ratio of a hold-out method, Random Forest classifier score the highest accuracy of 86.7%..

Modified Particle Swarm Optimization with Chaotic Initialization Scheme for Unconstrained Optimization Problems

Different variants of particle swarm optimization (PSO) algorithms were introduced in recent years with various improvements to tackle different types of optimization problems more robustly. However, the conventional initialization scheme tends to generate an initial population with relatively inferior solution due to the random guess mechanism. In this paper, a PSO variant known as modified PSO with chaotic initialization scheme is introduced to solve unconstrained global optimization problems more effectively, by generating a more promising initial population. Experimental studies are conducted to assess and compare the optimization performance of the proposed algorithm with four existing well-establised PSO variants using seven test functions. The proposed algorithm is observed to outperform its competitors in solving the selected test problems.

The Classification of Covid-19 cases through the Employment of Transfer Learning on X-ray images

Covid-19 is a contagious disease that known to cause respirotary infection in humans. Almost 219 countries are effected by the outbreak of the latest coronavirus pandemic, exceed 100 millions of confirmed cases and about 2 million death recorded aound the world. This condition is alarming as some of the people who are infected with the virus show no symptoms of the disease. Due to the number of confirmed cases rapidly rising around the world, it is crucial find another method to diagnose the disease at the beginnings stage in order to control the spreading of the virus. Another alternative test from the main screening method is by using chest radiology image based detection which are X-ray or CT scan images. The aim of this research is to classify the Covid-19 cases by using the image classification technique.The dataset consist of 2000 images of chest X-ray images and have two classes which are Covid and Non-Covid. Each of the class consists of 1000 images.This research compare the performance of the various Transfer Learning models (VGG-16, VGG-19, and Inception V3) in extracting the feature from X-ray image combined with machine learning model (SVM, kNN, and Random Forest) as a classifier. The experiment result showed the VGG-19, VGG-16, and Inception V3 coupled with optimized SVM pipelines are comparably efficient in classifying the cases as compared to other pipelines evaluated in this reaseach and could archieved 99% acuuracy on the test datasets.

Implementation Study Of Field Programmable Gate Array (FPGA) And Complex Programmable Logic Device (CPLD) In Collision Avoidance System Using Vhsic Hardware Description Language (VHDL)

A collision avoidance system, also known as a pre-crash system, forward collision warning system, or collision mitigation system, is a sophisticated driver-assistance system that aims to avoid or mitigate the severity of a collision. For this research, collision avoidance system will be fabricating to show that this system can detect avoidance range before apply the braking action to prevent collision. The ultrasonic sensor will be used in this system to detect the avoidance range. In this collision avoidance system, there will be uses of Field Programmable Gate Array (FPGA) and Complex Programmable Logic Device (CPLD). This research will observe how to implement FPGA and CPLD in the collision avoidance system using VHSIC Hardware Description Language (VHDL). The VHDL will be done in Quartus II 15.0 Software. In this research, Terasic DE-10 Standard board has been used. It contains FPGA microcontroller model Cyclone V SoC 5CSXFC6D6F31C6N. Max II board is used because it contains CPLD microcontroller model EPM240T100C5.