Your search

Design of the Proportional-Integral-Derivative (PID) controller for an industrial process represents a challenge due to process complexity and non-linearity. Traditional methods such as Ziegler-Nichols (ZN) for PID controller tuning do not provide an optimal gain; thus, might leave the system with potential instability condition and cause significant losses and damages to the system. This paper investigates the merits of evolutionary and swarm-based optimization algorithms in fine-tuning the parameters of a PID controller. Here, Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) algorithm were utilized to optimize the PID controller for a DC motor system. Various fitness functions were provided for the presented algorithms to compute the performance of the controller. A new fitness function was proposed to achieve an outstanding control response for the DC motor system. Results demonstrate the efficacy of the proposed methods in improving closed loop system response.

SESSION TITLE: Clinical Prediction and Diagnosis of OSA

Robotic systems have been evolving since decades and touching almost all aspects of life, either for leisure or critical applications. Most of traditional robotic systems operate in well-defined environments utilizing pre-configured on-board processing units. However, modern and foreseen robotic applications ask for complex processing requirements that exceed the limits of on-board computing power. Cloud computing and the related technologies have high potential to overcome on-board hardware restrictions and can improve the performance efficiency. This research highlights the advancements in robotic systems with focus on cloud robotics as an emerging trend. There exists an extensive amount of effort to leverage the potentials of robotic systems and to handle arising shortcomings. Moreover, there are promising insights for future breed of intelligent, flexible, and autonomous robotic systems in the Internet of Things era.

This work proposes a new evolutionary multilayer perceptron neural networks using the recently proposed Bird Swarm Algorithm. The problem of finding the optimal connection weights and neuron biases is first formulated as a minimization problem with mean square error as the objective function. The BSA is then used to estimate the global optimum for this problem. A comprehensive comparative study is conducted using 13 classification datasets, three function approximation datasets, and one real-world case study (Tennessee Eastman chemical reactor problem) to benchmark the performance of the proposed evolutionary neural network. The results are compared with well-regarded conventional and evolutionary trainers and show that the proposed method provides very competitive results. The paper also considers a deep analysis of the results, revealing the flexibility, robustness, and reliability of the proposed trainer when applied to different datasets.

SESSION TITLE: Clinical Prediction and Diagnosis of OSA

AbstractThe autonomous navigation of robots in unknown environments is a challenge since it needs the integration of a several subsystems to implement different functionality. It needs drawing a map of the environment, robot map localization, motion planning or path following, implementing the path in real-world, and many others; all have to be implemented simultaneously. Thus, the development of autonomous robot navigation (ARN) problem is essential for the growth of the robotics field of research. In this paper, we present a simulation of a swarm intelligence method is known as Particle Swarm Optimization (PSO) to develop an ARN system that can navigate in an unknown environment, reaching a pre-defined goal and become collision-free. The proposed system is built such that each subsystem manipulates a specific task which integrated to achieve the robot mission. PSO is used to optimize the robot path by providing several waypoints that minimize the robot traveling distance. The Gazebo simulator was used to test the response of the system under various envirvector representing a solution to the optimization problem.onmental conditions. The proposed ARN system maintained robust navigation and avoided the obstacles in different unknown environments. vector representing a solution to the optimization problem.

SESSION TITLE: Clinical Prediction and Diagnosis of OSA

Promoter regions of long non-coding RNA (lncRNA) genes are crucial to understand their transcriptional regulatory pattern. LncRNA genes, being more cryptic than protein-coding genes in terms of their functionality and biogenesis divergence, are lacking in number of existing studies to elucidate the roles of their promoters compared to their counterparts. Based on the overlap between epigenetic marks and transcription start sites, human lncRNAs were categorized into two broad categories: enhancer-originated lncRNAs (e-lncRNAs) and promoter-originated lncRNAs (p-lncRNAs) and hence these two groups are subject to distinct transcriptional regulatory programs. To understand the difference in the transcriptional regulatory mechanisms that governs p- and e-lncRNAs, we studied the promoter sequences of these two groups of lncRNAs including distinct transcription factor (TF) proteins that favor p-over e-lncRNA (and vice versa). In addition, we developed a convolution neural network (CNN) based deep learning (DL) framework DeePEL (deep p-, e-lncRNA promoter recognizer), to classify the promoter of p- and e-lncRNAs. To the best of our knowledge, this is the first attempt to classify these two groups of lncRNA promoters, using sequence and TF information, based on DL framework. We report several sequence specific signatures in the promoter regions as well as several distinct TFs specific to groups of lncRNAs that will help in understanding the promoter-proximal transcriptional regulation of p-lncRNAs and e-lncRNAs. © 2019 IEEE.

Deep learning is a promising approach for fine- grained disease severity classification for smart agriculture, as it avoids the labor-intensive feature engineering and segmentation-based threshold. In this work, we first propose a Densely Connected Convolutional Networks (DenseNet) based transfer learning method to detect the plant diseases, which expects to run on edge servers with augmented computing resources. Then, we propose a lightweight Deep Neural Networks (DNN) approach that can run on Internet of Things (IoT) devices with constrained resources. To reduce the size and computation cost of the model, we further simplify the DNN model and reduce the size of input sizes. The proposed models are trained with different image sizes to find the appropriate size of the input images. Experiment results are provided to evaluate the performance of the proposed models based on real- world dataset, which demonstrate the proposed models can accurately detect plant disease using low computational resources. © 2019 IEEE.

This paper presents highly robust, novel approaches to solving the forward and inverse problems of an Electrical Capacitance Tomography (ECT) system for imaging conductive materials. ECT is one of the standard tomography techniques for industrial imaging. An ECT technique is nonintrusive and rapid and requires a low burden cost. However, the ECT system still suffers from a soft-field problem which adversely affects the quality of the reconstructed images. Although many image reconstruction algorithms have been developed, still the generated images are inaccurate and poor. In this work, the Capacitance Artificial Neural Network (CANN) system is presented as a solver for the forward problem to calculate the estimated capacitance measurements. Moreover, the Metal Filled Fuzzy System (MFFS) is proposed as a solver for the inverse problem to construct the metal images. To assess the proposed approaches, we conducted extensive experiments on image metal distributions in the lost foam casting (LFC) process to light the reliability of the system and its efficiency. The experimental results showed that the system is sensible and superior. © 2019 Wael Deabes et al.

In this paper, we present a Neighborhood Search Genetic Algorithms (NSGAs) for mobile robot path planning. GAs have been used successfully in a variety of path planning problem because they can search the space of all possible paths and provide the optimal one. The convergence process of GAs might be lengthy compared to traditional search techniques that depend on local search methods. We propose a hybrid approach that allows GAs to combine both the advantages of GAs and local search algorithms. GAs will create a multiple waypoint path allowing a mobile robot to navigate through static obstacles and finding the optimal path in order to approach the target location without collision. The proposed NSGAs has been examined over four different path planning case studies with varying complexity. The performance of the enhanced GA has been compared with A-star algorithm (A∗) standard GA, particle swarm optimization (PSO) algorithm. The obtained results show that the proposed approach is able to get good results compared to other algorithms. © 2019 ACM.

With the growing access to technology in the medical domain, an increased volume of medical data is recorded. The size and complexity of these data make the process of analysis of meaningful discoveries of beneficial patterns more challenging. This problem has attracted numerous researchers around the world. Statistical methods have been employed to handle medical data for diagnosis purposes. Unfortunately, these methods were less capable of dealing with these massive and complex datasets. To solve this problem, we suggest a process to classify medical data which includes feature selection and classification using a number of supervised learning techniques. Binary Brain Storm Optimization (BBSO) is used for feature selection, which is a population search approach that simulates the process of electing the best idea (solution), among others. We simulated six different classifiers: Naive-Bayes, K-Nearest Neighbor, Support Vector Machine, Linear Discriminant Analysis, Decision Tree and Random Forest. Five datasets adopted from the UCI Machine Learning Repository, (Breast Cancer, Diabetes, Heart Disease, Chronic Kidney, and SPECT), are employed as a benchmark test data. The performance of BBSO is evaluated using accuracy on the datasets using the various classifiers. Experimental results show that the proposed approach improves the classification performance for better medical diagnosis. © 2019 ACM.

Keystroke dynamics has been used as a form of one-time user authentication and continuous verification especially when it comes to securing the cyberspace. In this paper, we present the idea of using keystroke dynamics as a form of second layer authentication in web applications. We showed that this method can authenticate a user with high accuracy and can be used as an alternate to CAPTCHA tests, security questions and image selections that are being used today. We have developed a working web-based platform in a browser environment that enforces the proposed second-layer security. We performed penetration test experiments by launching a total of 598,500 impostor and genuine authentication attempts and found the Equal Error Rate (EER) as 10.5%. © 2019 IEEE.

The growth in using various smart wireless devices in the last few decades has given rise to indoor localization service (ILS). Indoor localization is defined as the process of locating a user location in an indoor environment. Indoor device localization has been widely studied due to its popular applications in public settlement planning, health care zones, disaster management, the implementation of location-based services (LBS) and the Internet of Things (IoT). The ILS problem can be formulated as a learning problem utilizing Wi-Fi technology. The measured Wi-Fi signal strength can be used as an indication of the distribution of users in a various indoor location. Developing a classification model with high accuracy can be achieved using a machine learning approach. Artificial Neural Network is one of the most successful trends in machine learning. In this article, we provide our initial idea of using Cascaded Layered Recurrent Neural Network (L-RNN) for the classification of user localization in an indoor environment. Several neural network models were trained, with the best performance attainment is reported. The experimental results marked that the presented L-RNN model is highly accurate for indoor localization and can be utilized for many applications. © 2019 IEEE.

Promoter region of protein-coding genes are gradually being well understood, yet no comparable studies exist for the promoter of long non-coding RNA (lncRNA) genes which has emerged as a global potential regulator in multiple cellular process and different diseases for human. To understand the difference in the transcriptional regulation pattern of these genes, previously, we proposed a machine learning based model to classify the promoter of protein-coding genes and lncRNA genes. In this study, we are presenting DeepCNPP (deep coding non-coding promoter predictor), an improved model based on deep learning (DL) framework to classify the promoter of lncRNA genes and protein-coding genes. We used convolution neural network (CNN) based deep network to classify the promoter of these two broad categories of human genes. Our computational model, built upon the sequence information only, was able to classify these two groups of promoters from human at a rate of 83.34% accuracy and outperformed the existing model. Further analysis and interpretation of the output from DeepCNPP architecture will enable us to understand the difference in transcription regulatory pattern for these two groups of genes.

Human genes often, through alternative splicing of pre-messenger RNAs, produce multiple mRNAs and protein isoforms that may have similar or completely different functions. Identification of splice sites is, therefore, crucial to understand the gene structure and variants of mRNA and protein isoforms produced by the primary RNA transcripts. Although many computational methods have been developed to detect the splice sites in humans, this is still substantially a challenging problem and further improvement of the computational model is still foreseeable. Accordingly, we developed DeepDSSR (deep donor splice site recognizer), a novel deep learning based architecture, for predicting human donor splice sites. The proposed method, built upon publicly available and highly imbalanced benchmark dataset, is comparable with the leading deep learning based methods for detecting human donor splice sites. Performance evaluation metrics show that DeepDSSR outperformed the existing deep learning based methods. Future work will improve the predictive capabilities of our model, and we will build a model for the prediction of acceptor splice sites.