Automatic Heart Disease Classification Using Ensemble Features Extraction Mechanism from ECG Signals

The heart disease detection and classification using the cost-effective tool electrocardiogram (ECG) becomes interesting research considering smart healthcare applications. Automation, accuracy, and robustness are vital demands for an ECG-based heart disease prediction system. Deep learning brings automation to the applications like Computer-Aided Diagnosis (CAD) systems with accuracy improvement compromising robustness. We propose the novel ECG-based heart disease prediction system using the hybrid mechanism to satisfy the automation, accuracy, and robustness requirements. We design the model via the steps of pre-processing, hybrid features formation, and classification. The ECG pre-processing is aiming at suppressing the baseline and powerline interference without loss of heartbeats. We propose a hybrid mechanism that consists of handcrafted and automatic Convolutional Neural Network (CNN) lightweight features for efficient classification. The hybrid feature vector is fed to the deep learning classifier Long Term Short Memory (LSTM) sequentially to predict the disease. The simulation results show that the proposed model reduces the diagnosis errors and time compare to state-of-art methods.

Differentially Private Kernel Support Vector Machines Based on the Exponential and Laplace Hybrid Mechanism

Support vector machines (SVMs) are among the most robust and accurate methods in all well-known machine learning algorithms, especially for classification. The SVMs train a classification model by solving an optimization problem to decide which instances in the training datasets are the support vectors (SVs). However, SVs are intact instances taken from the training datasets and directly releasing the classification model of the SVMs will carry significant risk to the privacy of individuals, when the training datasets contain sensitive information. In this paper, we study the problem of how to release the classification model of kernel SVMs while preventing privacy leakage of the SVs and satisfying the requirement of privacy protection. We propose a new differentially private algorithm for the kernel SVMs based on the exponential and Laplace hybrid mechanism named DPKSVMEL. The DPKSVMEL algorithm has two major advantages compared with existing private SVM algorithms. One is that it protects the privacy of the SVs by postprocessing and the training process of the non-private kernel SVMs does not change. Another is that the scoring function values are directly derived from the symmetric kernel matrix generated during the training process and does not require additional storage space and complex sensitivity analysis. In the DPKSVMEL algorithm, we define a similarity parameter to denote the correlation or distance between the non-SVs and every SV. And then, every non-SV is divided into a group with one of the SVs according to the maximal value of the similarity. Under some certain similarity parameter value, we replace every SV with a mean value of the top-k randomly selected most similar non-SVs within the group by the exponential mechanism if the number of non-SVs is greater than k. Otherwise, we add random noise to the SVs by the Laplace mechanism. We theoretically prove that the DPKSVMEL algorithm satisfies differential privacy. The extensive experiments show the effectiveness of the DPKSVMEL algorithm for kernel SVMs on real datasets; meanwhile, it achieves higher classification accuracy than existing private SVM algorithms.

Development of sago drying with environmentally friendly techniques

One of the drying machines that is commonly used by in industry is a rack-type dryer. However, the rack-type drying machine has generally fairly low efficiency. A rack-type dryer has been designed which was equipped with a hybrid mechanism, but is its performance not yet known when it is controlled by an expert control system. The purpose of this research was to produce an expert control system that can be applied to a rack-type dryer with a hybrid system mechanism which can improve the performance of the dryer. The research includes the development of expert rules applied to the control system and a series of tests was carried out using 10 kg of fresh sago starch. The test results show that the drying air temperature did not show any overshoot and short settling time, drying temperature is relatively stable and there was no steady state error. The drying rate of fresh sago starch can be increased by using the hybrid system. The use of electric power with the hybrid system was lower (5.78 kWh) compared to that of non-hybrid (6.88 kWh) or a reduction of about 16% compared to the non-hybrid system. Thermal efficiency of the rack-type dryer with the expert control system was about 36%.

Improved influential nodes identification in complex networks

Influential node identification plays an important role in optimizing network structure. Many measures and identification methods are proposed for this purpose. However, the current network system is more complex, the existing methods are difficult to deal with these networks. In this paper, several basic measures are introduced and discussed and we propose an improved influential nodes identification method that adopts the hybrid mechanism of information entropy and weighted degree of edge to improve the accuracy of identification (Hm-shell). Our proposed method is evaluated by comparing with nine algorithms in nine datasets. Theoretical analysis and experimental results on real datasets show that our method outperforms other methods on performance.