Malaria is a life-threatening disease causing by an infection of the protozoan parasite Plasmodium. Plasmodium falciparum is the deadliest and most common human infected parasites hosted by anopheles mosquito vector. To cure a malaria infected patient and prevent further spreading, malaria diagnosis using microscopy to visualize Giemsa-stained parasites is commonly done. The microscopy diagnosis is somewhat time consuming and requires well-trained malaria experts to interpret what they see under the microscope. To address this limitation, an automated malaria infected diagnosis is needed. This work proposed a computer-aided automated diagnosis system that can perform remote field diagnosis with high accuracy while requiring less computational demands. The proposed framework consists of two main parts that are red blood cell counting and parasite life-cycle stage classification. The counting process is performed by computer vision techniques, namely Hough transform. Different machine learning techniques, i.e., Multilayer Perceptron, Linear Discriminant Analysis, Support Vector Machine, and Weighted Similarity Extreme Learning Machine, are employed in the classification task. We also demonstrated that combining hand-crafted and deep-learned features can enhance the overall performance of the framework. The experimental results showed that the proposed methods could correctly count and classify at 97.94% and 98.12% accuracy, respectively. The overall proposal system can achieve at 96.18% accuracy. This is achieved by WELM in conjunction with deep-learned (AlexNet_FC7) and the hand-crafted (color) features. INDEX TERMS Combining features, Giemsa-stained thin film, malaria.

Machine learning techniques are becoming popular in virtual screening tasks. One of the powerful machine learning algorithms is Extreme Learning Machine (ELM) which has been applied to many applications and has recently been applied to virtual screening. We propose the Weighted Similarity ELM (WS-ELM) which is based on a single layer feed-forward neural network in a conjunction of 16 different similarity coefficients as activation function in the hidden layer. It is known that the performance of conventional ELM is not robust due to random weight selection in the hidden layer. Thus, we propose a Clustering-based WS-ELM (CWS-ELM) that deterministically assigns weights by utilising clustering algorithms i.e. k-means clustering and support vector clustering. The experiments were conducted on one of the most challenging datasets–Maximum Unbiased Validation Dataset–which contains 17 activity classes carefully selected from PubChem. The proposed algorithms were then compared with other machine learning techniques such as support vector machine, random forest, and similarity searching. The results show that CWS-ELM in conjunction with support vector clustering yields the best performance when utilised together with Sokal/Sneath(1) coefficient. Furthermore, ECFP_6 fingerprint presents the best results in our framework compared to the other types of fingerprints, namely ECFP_4, FCFP_4, and FCFP_6.

No abstract

No abstract

Extreme Learning Machine is a powerful classification method very competitive existing classification methods. It is extremely fast at training. Nevertheless, it cannot perform face verification tasks properly because face verification tasks require comparison of facial images of two individuals at the same time and decide whether the two faces identify the same person. The structure of Extreme Leaning Machine was not designed to feed two input data streams simultaneously, thus, in 2-input scenarios Extreme Learning Machine methods are normally applied using concatenated inputs. However, this setup consumes two times more computational resources and it is not optimized for recognition tasks where learning a separable distance metric is critical. For these reasons, we propose and develop a Siamese Extreme Learning Machine (SELM). SELM was designed to be fed with two data Funding from King Mongkut's Institute of Technology Ladkrabang and project BIBECA (RTI2018-101248-B-I00 MINECO/FEDER)