Search

Parkinson's disease (PD) is a neurological disease that has been reported to have affected most people worldwide. Recent research pointed out that about 90% of PD patients possess voice disorders. Motivated by this fact, many researchers proposed methods based on multiple types of speech data for PD prediction. However, these methods either face the problem of low rate of accuracy or lack generalization. To develop an approach that will be free of these issues, in this paper we propose a novel ensemble approach. These paper contributions are two folds. First, investigating feature selection integration with deep neural network (DNN) and validating its effectiveness by comparing its performance with conventional DNN and other similar integrated systems. Second, development of a novel ensemble model namely EOFSC (Ensemble model with Optimal Features and Sample Dependant Base Classifiers) that exploits the findings of recently published studies. Recent research pointed out that for different types of voice data, different optimal models are obtained which are sensitive to different types of samples and subsets of features. In this paper, we further consolidate the findings by utilizing the proposed integrated system and propose the development of EOFSC. For multiple types of vowel phonations, multiple base classifiers are obtained which are sensitive to different subsets of features. These features and sample-dependent base classifiers are integrated, and the proposed EOFSC model is constructed. To evaluate the final prediction of the EOFSC model, the majority voting methodology is adopted. Experimental results point out that feature selection integration with neural networks improves the performance of conventional neural networks. Additionally, feature selection integration with DNN outperforms feature selection integration with conventional machine learning models. Finally, the newly developed ensemble model is observed to improve PD detection accuracy by 6.5%. [ABSTRACT FROM AUTHOR]

For the purpose of usability feature extraction and prediction, an innovative metaheuristic algorithm is introduced. Generally, the term "usability" is defined by the several researchers with respect to the hierarchical-based software usability model and it has become one of the important methods in terms of software quality. In hierarchically based software, its usability factors, attributes, and its characteristics are combined. The paper presented an algorithm, i.e., modified crow search algorithm (MCSA) mainly for extraction of usability features from hierarchical model with the optimal solution under the search for useful features. MCSA is an extension of original crow search algorithm (CSA), which is a naturally inspired algorithm. The mechanism of this algorithm is based on the process of hiding food and prevents theft and hence introduced this CSA in the field of software engineering practices as an inspiration. The algorithm generates a particular number of selected features/attributes and is applied on software development life cycles models, finding out the best among them. The results of the presented algorithm are compared with the standard binary bat algorithm (BBA), original CSA, and modified whale optimization algorithm (MWOA). The outcomes conclude that the proposed MCSA performs well than the standard BBA and original CSA as the proposed algorithms generate fewer number of feature selection equal to 17 than 18 in BBA, 23 in CSA, and 19 in MWOA. [ABSTRACT FROM AUTHOR]

Among the numerous alternatives used in the world of risk balance, it highlights the provision of guarantees in the formalization of credit agreements. The objective of this paper is to compare the achievement of fuzzy sets with that of artificial neural network-based decision trees on credit scoring to predict the recovered value using a sample of 1890 borrowers. Comparing with fuzzy logic, the decision analytic approach can more easily present the outcomes of the analysis. On the other hand, fuzzy logic makes some implicit assumptions that may make it even harder for credit-grantors to follow the logical decision-making process. This paper leads an initial study of collateral as a variable in the calculation of the credit scoring. The study concludes that the two models make modelling of uncertainty in the credit scoring process possible. Although more difficult to implement, fuzzy logic is more accurate for modelling the uncertainty. However, the decision tree model is more favourable to the presentation of the problem. [ABSTRACT FROM AUTHOR]

Precision agriculture is the mechanism which controls the land productivity and maximizes the revinue and minimizes the impact on sorroundings by automating the complete agriculture processes. This projected work relies on independent internet of things (IoT) enabled wireless sensor network (WSN) framework consisting of soil moisture (MC) probe, soil temperature measuring device, environmental temperature sensor, environmental humidity sensing device, CO2 sensor, daylight intensity device (light dependent resistor) to acquire real-time farm information through multi-point measurement. The projected observance technique consists of all standalone IoT-enabled WSN nodes used for timely data acquisitions and storage of agriculture information. The farm history is additionally stored for generating necessary action throughout the whole course of farming. The work summarizes the optimum usage of irrigation by the precise management of water valve using neural network-based prediction of soil water requirement in 1 h ahead. Our proposed irrigation control scheme utilizes structural similarity (SSIM)-based water valve management mechanism which is used to locate farm regions having water deficiency. Moreover, a close comparative study of optimization techniques, like variable learning rate gradient descent, gradient descent for feedforward neural network-based pattern classification, is performed and the best practice is employed to forecast soil MC on hourly basis together with interpolation method for generating soil moisture content (MC) distribution map. Finally, SSIM index-based soil MC deficiency is calculated to manipulate the specified valves for maintaining uniform water requirement through the entire farm area. The valve control commands are again processed using fuzzy logic-based weather condition modeling system to manipulate control commands by considering different weather conditions. [ABSTRACT FROM AUTHOR]

Cancer is the major leading reason of death around the world. However, the early identification and prediction of a cancer type is very critical for patient’s health. Recently, microarray gene expression data was utilized for efficient and early diagnosis of cancer. Previous work shows that microarray data has two major issues which are high dimensionality and small sample size. Several researchers have analyzed and evaluated the cancer classification problem using different statistical and machine learning-based approaches but there are still some issues with these approaches that make cancer classification a nontrivial task. Such as, the inability of certain machine learning algorithms to use unstructured data has limited their utility in the cancer classification process. Convolutional neural networks are proven to very suitable to analyze variety of unstructured data. This ability allowed the deep learning algorithms to play a vibrant part in early detection of cancer through data classification. In this research, a hybrid deep learning model based on Laplacian Score-Convolutional Neural Network (LS-CNN) is employed for the classification of given cancer’s data. The performance of the proposed system was evaluated on 10 different benchmark datasets using various performance measurement metrics such as accuracy and confusion matrix. The experimental results conclude that proposed LS-CNN model outperformed compared to traditional machine learning and recently used deep learning approaches. [ABSTRACT FROM AUTHOR]