A neural network combined with sliding mode controller for the two-wheel self-balancing robot

This article presents the sliding control method combined with the selfadjusting neural network to compensate for noise to improve the control system's quality for the two-wheel self-balancing robot. Firstly, the dynamic equations of the two-wheel self-balancing robot built by Euler–Lagrange is the basis for offering control laws with a neural network of noise compensation. After disturbance-compensating, the sliding mode controller is applied to control quickly the two-wheel self-balancing robot reached the desired position. The stability of the proposed system is proved based on the Lyapunov theory. Finally, the simulation results will confirm the effectiveness and correctness of the control method suggested by the authors.

Internet of things and fuzzy logic for smart street lighting prototypes

Internet of things (IoT) and fuzzy logic are very useful in increasing the efficiency and effectiveness of a system; this study applies both to the street lighting systems. The prototype of a street lighting control and monitoring system has been completed. The status of lights that are on or off and the value of the light intensity can be monitored by using IoT. The intensity of the light is fuzzy controlled by utilizing the presence of vehicles and pedestrians around the lights. The prototype is made with a scale against real conditions. Data is processed and transmitted using a microcontroller and Wi-Fi on the IoT module. Mobile applications have been used on smartphone interfaces to monitor and control lamps wherever they are connected to the Internet. Changes in the status of lights to turn on or off are done by the relay module. The fuzzy light intensity control system uses sensors and microcontrollers by utilizing the presence of vehicles and pedestrians around the lights. Performance evaluation has been carried out on a miniature street lighting with the results of monitoring and control following its function. An analysis of the resulting energy savings has been demonstrated.

Empirical Bayesian network to improve service delivery and performance dependability on a campus network

An effective systemic approach to task will lead to efficient communication and resource sharing within a network. This has become imperative as it aids alternative delivery. With communication properly etched into the fabrics of today’s society via effective integration of informatics and communication technology, the constant upgrades to existing network infrastructure are only a start to meeting with the ever-increasing challenges. There are various criteria responsible for network performance, scalability, and resilience. To ensure best practices, we analyze the network and select parameters required to improve performance irrespective of bottlenecks, potentials, and expansion capabilities of the network infrastructure. Study compute feats via Bayesian network design alongside upgrades implementation to result in a prototype design, capable of addressing users need(s). Thus, to ensure functionality, the experimental network uses known simulation kits such as riverbed modeler edition 17.5 and cisco packet tracer 6.0.1-to conduct standardized tests such as throughput test, application response-time test, and availability test.

Automatic cerebrovascular segmentation methods-a review

Cerebrovascular diseases are one of the serious causes for the increase in mortality rate in the world which affect the blood vessels and blood supply to the brain. In order, diagnose and study the abnormalities in the cerebrovascular system, accurate segmentation methods can be used. The shape, direction and distribution of blood vessels can be studied using automatic segmentation. This will help the doctors to envisage the cerebrovascular system. Due to the complex shape and topology, automatic segmentation is still a challenge to the clinicians. In this paper, some of the latest approaches used for segmentation of magnetic resonance angiography images are explained. Some of such methods are deep convolutional neural network (CNN), 3dimentional-CNN (3D-CNN) and 3D U-Net. Finally, these methods are compared for evaluating their performance. 3D U-Net is the better performer among the described methods.

Classification of adult autistic spectrum disorder using machine learning approach

Autism spectrum disorder (ASD) is a neurological-related disorder. Patients with ASD have poor social interaction and lack of communication that lead to restricted activities. Thus, early diagnosis with a reliable system is crucial as the symptoms may affect the patient’s entire lifetime. Machine learning approaches are an effective and efficient method for the prediction of ASD disease. The study mainly aims to achieve the accuracy of ASD classification using a variety of machine learning approaches. The dataset comprises 16 selected attributes that are inclusive of 703 patients and non-patients. The experiments are performed within the simulation environment and analyzed using the Waikato environment for knowledge analysis (WEKA) platform. Linear support vector machine (SVM), k-nearest neighbours (k-NN), J48, Bagging, Stacking, AdaBoost, and naïve bayes are the methods used to compute the prediction of ASD status on the subject using 3, 5, and 10-folds cross validation. The analysis is then computed to evaluate the accuracy, sensitivity, and specificity of the proposed methods. The comparative result between the machine learning approaches has shown that linear SVM, J48, Bagging, Stacking, and naïve bayes produce the highest accuracy at 100% with the lowest error rate.

Design of grip strength measuring system using FSR and flex sensors using SVM algorithm

This paper proposes a design of a complete system to identify weak grip strength that is caused by multiple factors like ageing, diseases, or accidents. This paper presents a grip measurement system that comprises of force sensing resistor and flex sensor to evaluate the condition of the hand. The system is tested by gripping a pencil and a cylindrical object using the glove, to determine the condition of the hand. Force sensitive resistor (FSR) evaluates the force applied by the different parts of the palm on the object being grasped. Flex sensor evaluates the bending of the fingers and thumb. The data from the sensors is then compared with existing data to evaluate the state of the hand. The data from the sensors is stored on the personal computer (PC) through serial communication. A model is trained using the data from the sensors, which determine if the grip strength of the user is weak or strong. The model is also trained to differentiate between two modes that are pen mode and object mode. The model achieved an accuracy of 90.8 percent using support vector machine (SVM) algorithm. This glove can be deployed in medical centers to assist in grip strength measurement.

Hybrid of convolutional neural network algorithm and autoregressive integrated moving average model for skin cancer classification among Malaysian

Skin cancer is a widely spreading cause of mortality among the people specifically living on or near the equatorial belt. Early detection of skin cancer significantly improves the recovery prevalence and the chance of surviving. Without the assist of computer-aided decision (CAD) system, skin cancer classification is the challenging task for the dermatologist to differentiate the type of skin cancer and provide the suitable treatment. Recently, the development of machine learning and pretrained deep neural network (DNN) shows the tremendous performance in image classification task which also provide the promising performance in medical field. However, these machine learning methods cannot get the deep features from network flow which resulting in low accuracy and the pretrained DNN has the complex network with a huge number of parameters causes the limited classification accuracy. This paper focuses on the classification of skin cancer to identify whether it is basal cell carcinoma, melanoma or squamous cell carcinoma by using the development of hybrid convolutional neural network algorithm and autoregressive integrated moving average model (CNN-ARIMA). The CNNARIMA model was trained and found to produce the best accuracy of 92.25%.

A framework to shape the recommender system features based on participatory design and artificial intelligence approaches

<span lang="EN-GB">A recommender system is an algorithm aiming at giving suggestions to users on relevant elements or items such as products to purchase, books to read, jobs to apply or anything else depending on industries or situations. Recently, there has been a surge in interest in developing a recommender system in a variety of areas. One of the most widely used approaches in recommender systems is collaborative filtering (CF). The CF is a strategy for automatically creating a filter based on a user's needs by extracting desires or recommendation information from a large number of users. The CF approach uses multiple correlation steps to do this. However, the occurrence of uncertainty in finding the best similarity measure is unavoidable. This paper outlines a method for improving the configuration of a recommender system that is tasked with recommending an appropriate study field and supervisor to a group of final-year project students. The framework we suggest is built on a participatory design methodology that allows students' individual opinions to be factored into the recommender system's design. The architecture of the recommender scheme was also illustrated using a real-world scenario, namely mapping the students' field of interest to a possible supervisor for the final year project.</span>

Deep ensemble learning for skin lesions classification with convolutional neural network

<span lang="EN-US">One type of skin cancer that is considered a malignant tumor is melanoma. Such a dangerous disease can cause a lot of death in the world. The early detection of skin lesions becomes an important task in the diagnosis of skin cancer. Recently, a machine learning paradigm emerged known as deep learning (DL) utilized for skin lesions classification. However, in some previous studies by using seven class images diagnostic of skin lesions classification based on a single DL approach with CNNs architecture does not produce a satisfying performance. The DL approach allows the development of a medical image analysis system for improving performance, such as the deep convolutional neural networks (DCNNs) method. In this study, we propose an ensemble learning approach that combines three DCNNs architectures such as Inception V3, Inception ResNet V2 and DenseNet 201 for improving the performance in terms of accuracy, sensitivity, specificity, precision, and F1-score. Seven classes of dermoscopy image categories of skin lesions are utilized with 10015 dermoscopy images from well-known the HAM10000 dataset. The proposed model produces good classification performance with 97.23% accuracy, 90.12% sensitivity, 97.73% specificity, 82.01% precision, and 85.01% F1-Score. This method gives promising results in classifying skin lesions for cancer diagnosis.</span>

Human behavior scoring in credit card fraud detection

<span lang="EN-US">Now days, the analysis of the behavior of cardholders is one of the important fields in electronic payment. This kind of analysis helps to extract behavioral and transaction profile patterns that can help financial systems to better protect their customers. In this paper, we propose an intelligent machine learning (ML) system for rules generation. It is based on a hybrid approach using rough set theory for feature selection, fuzzy logic and association rules for rules generation. A score function is defined and computed for each transaction based on the number of rules, that make this transaction suspicious. This score is kind of risk factor used to measure the level of awareness of the transaction and to improve a card fraud detection system in general. The behavior analysis level is a part of a whole financial fraud detection system where it is combined to intelligent classification to improve the fraud detection. In this work, we also propose an implementation of this system integrating the behavioral layer. The system results obtained are very convincing and the consumed time by our system, per transaction was 6 ms, which prove that our system is able to handle real time process.</span>