Selecting informative genes from microarray data by using hybrid methods for cancer classification

Gene expression technology, namely microarrays, offers the ability to measure the expression levels of thousands of genes simultaneously in biological organisms. Microarray data are expected to be of significant help in the development of an efficient cancer diagnosis and classification platform. A major problem in these data is that the number of genes greatly exceeds the number of tissue samples. These data also have noisy genes. It has been shown in literature reviews that selecting a small subset of informative genes can lead to improved classification accuracy. Therefore, this paper aims to select a small subset of informative genes that are most relevant for cancer classification. To achieve this aim, an approach using two hybrid methods has been proposed. This approach is assessed and evaluated on two well-known microarray data sets, showing competitive results. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Technology application in project-based learning

Project-based learning is a student-centered comprehensive instructional approach where students collectively engage themselves in complex learning tasks. Recent advances in educational technologies have made student-centered learning in a technology rich environment both possible and feasible. This paper will report part of a larger study carried out at a school in the United States of America on the use ofconstructivism and technology in project-based learning. Data collection techniques included those typically associated with qualitative field research. In this paper, the technological infrastructure of the school and how technology is used in one of the project-based learning classes will be provided. Based on this study, some suggestions are also provided on how technology can be used in the context of other countries including in Malaysia.     

BSLPSDN: Base station location privacy via software-defined networking (SDN) in wireless sensor networks

Base station's location privacy in a wireless sensor network (WSN) is critical for information security and operational availability of the network. A key part of securing the base station from potential compromise is to secure the information about its physical location. This paper proposes a technique called base station location privacy via software-defined networking (SDN) in wireless sensor networks (BSLPSDN). The inspiration comes from the architecture of SDN, where the control plane is separated from the data plane, and where control plane decides the policy for the data plane. BSLPSDN uses three categories of nodes, namely, a main controller to instruct the overall operations, a dedicated node to buffer and forward data, and lastly, a common node to sense and forward the packet. We employ three kinds of nodes to collaborate and achieve stealth for the base station and thus protecting it against the traffic-analysis attacks. Different traits of the WSN including energy status and traffic density can actively be monitored by BSLPSDN, which positively affects the energy goals, expected life of the network, load on common nodes, and the possibility of creating diversion in the wake of an attack on the base station. We incorporated multiple experiments to analyze and evaluate the performance of our proposed algorithm. We use single controller with multiple sensor nodes and multiple controllers with multiple sensor nodes to show the level of anonymity of BS. Experiments show that providing BS anonymity via multiple controllers is the best method both in terms of energy and privacy.     

Optimal Machine Learning Enabled Performance Monitoring for Learning Management Systems

Learning Management System (LMS) is an application software that is used in automation, delivery, administration, tracking, and reporting of courses and programs in educational sector. The LMS which exploits machine learning (ML) has the ability of accessing user data and exploit it for improving the learning experience. The recently developed artificial intelligence (AI) and ML models helps to accomplish effective performance monitoring for LMS. Among the different processes involved in ML based LMS, feature selection and classification processes find beneficial. In this motivation, this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring (GSO-MFWELM) technique for LMS. The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS. The proposed GSO-MFWELM technique involves GSO-based feature selection technique to select the optimal features. Besides, Weighted Extreme Learning Machine (WELM) model is applied for classification process whereas the parameters involved in WELM model are optimally fine-tuned with the help of Mayfly Optimization (MFO) algorithm. The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance. The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects. The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.     

Knowledge Diffusion of the Internet of Things (IoT): A Main Path Analysis

Wireless Personal Communications - The Internet of Things (IoT) is a concept that has attracted significant attention since the emergence of wireless technology. The knowledge diffusion of IoT...     

An efficient numerical algorithm for the study of time fractional Tricomi and Keldysh type equations

Engineering with Computers - This work addresses a hybrid scheme for the numerical solutions of time fractional Tricomi and Keldysh type equations. In proposed methodology, Haar wavelets are used...     

Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals

Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.     

Monitoring the Coefficient of Variation Using the Side Sensitive Group Runs Chart

Many quality characteristics have means and standard deviations that are not independent. Instead, the standard deviations of these quality characteristics are proportional to their corresponding means. Thus, monitoring the coefficient of variation (CV), for these quality characteristics, using a control chart has gained remarkable attention in recent years. This paper presents a side sensitive group runs chart for the CV (called the SSGR CV chart). The implementation and optimization procedures of the proposed chart are presented. Two optimization procedures are developed, i.e. (i) by minimizing the average run length (ARL) when the shift size is deterministic and (ii) by minimizing the expected average run length (EARL) when the shift size is unknown. An application of the SSGR CV chart using a real dataset is also demonstrated. Additionally, the SSGR CV chart is compared with the Shewhart CV, runs rules CV, synthetic CV and exponentially weighted moving average CV charts by means of ARLs and standard deviation of the run lengths. The performance comparison is also conducted using EARLs when the shift size is unknown. In general, the SSGR CV chart surpasses the other charts under comparison, for most upward and downward CV shifts. Copyright © 2015 John Wiley & Sons, Ltd.     

An Approach Method to Calibrate the Autocollimator with Small Angle Measurement Range

A new method to calibrate the autocollimator with small angle measurement range has been developed. This method used a system based on rotary encoder for angle measurements with self-calibration function (SelfA47). The SelfA47 has 18,000 graduation lines with angle interval of 0.02°, corresponds to 72 arcsec. Thereby this system cannot be used to calibrate the autocollimator with measurement range <72 arcsec. On the other hand, SelfA47 can be used to calibrate an electronic level. The deviation of electronic level shaped linear gradient. Therefore a small nominal gradient of electronic level can be approximated by interpolation. Since the gradient of a curve corresponds to the angle quantities, it is feasible to calibrate the autocollimator with nominal angle <72 arcsec using SelfA47 and an electronic level. In this proposed method, SelfA47 is placed horizontally on the same plane with electronic level and mirror reflector position. The electronic level value that have been corrected by SelfA47 is used as a reference. This reference value was converted to the angle, thus the angle deviation of autocollimator can be determined. The prominent uncertainty of angle measurement using this new technique derived from the uncertainty of electronic level and rotary encoder. Using this method, the expanded uncertainty of 0.36 arcsec is obtained from calibration of autocollimator with measuring range of ±20 arcsec and it is consistent statistically with the manufacturer calibration result shown by E _n value is <1. In conclusion, this approach method can be applied to calibrate the autocollimator with a resolution smaller than SelfA47 as standard, but it is not recommended for the calibration of highly accurate autocollimator.