Search

This study uses a two-stage learning computer-aided diagnosis (CAD) scheme that has a convolutional neural network(CNN) with self-supervised learning(SSL) to classify polyps as either a hyperplastic polyp (HP) or a Tubular Adenoma (TA). The proposed model uses look-into-object (LIO) and contrastive learning in SimCLR to focus on the holistic polyp region and allows greater model performance. However, the LIO scheme relies on pretraining a model to provide basic representations so this model is modified using a warm-up scheme to improve the loss function. There are insufficient medical images to train efficient representation for polyp classification so another approach uses natural images, instead of polyp images, for the pretext task. The experimental results show that the proposed scheme which uses polyp object structure information and self-supervised learning produces a robust model that allows better classification as either HP or TA in the prediction head by transferring a backbone. The backbone model uses ResNet-18 effectively to concentrate on the holistic polyp using limited labeled polyp images. The proposed scheme outperforms an existing method with a 4% increase in accuracy and a 3% improvement in F1-score.

The need for cloud servers for training deep neural network (DNN) models is increasing as more complex architecture designs of DNN models are developed. Nevertheless, cloud servers are considered semi-honest. With great attention to the privacy issues of medical diagnoses using a DNN, previous studies have proposed the idea of learnable image encryption. Though some methods have been presented to partially attack previous encryption schemes, there is still some space for improvement. We proposed a learnable image encryption scheme that is an enhanced version of previous methods and can be used to train a great DNN model and simultaneously keep the privacy of training images. We conducted an experiment on medical datasets from open sources and the result demonstrates the effectiveness of our proposed method in performance and privacy-preserving.

This study presents a compact $L$ -points discrete cosine transform (DCT) hardware accelerator for $M$ -points Mel-scale Frequency Cepstral Coefficients (MFCC). The main contributions of this work can be summarized as 1) proposing an algorithm with lower complexity; 2) achieving higher accuracy performance; 3) implementing a low-cost accelerator with a unique group of cosine coefficients. For algorithm derivation, the proposed method converts the original formula into the type IV of discrete cosine transform (DCT-IV) with a preprocessing procedure. The kernel computation of DCT-IV can be further derived into the same cosine multiplication with the proposed preprocessing. Therefore, a total of ( $M$ -1) ( $L$ -1) additions, ( $M$ -1) $L$ multiplications, and $L$ coefficients are required for the computation. Compared with Jo et al.’s algorithm, the proposed method respectively reduces the number of additions and multiplications by 42.32 % and 41.67 %. Instead, the number of coefficients is increased by 33.33 %. Moreover, the proposed algorithm exhibits a higher peak signal-to-noise ratio (PSNR) value which is achieved at 90.1dB with a 16-bit coefficient word length. For hardware realization, the FPGA implementation results show that it can operate at a clock rate of 135.85 MHz and requires only 113 combinational elements, 87 registers, 3 DSP multipliers, $64\times 16$ bits RAM and $32\times 16$ bits ROM. Overall, it would be a good choice for integrating MFCC applications in the future.

Utilizing supervised machine learning algorithms to develop a surveillance and response system based on symptoms of diarrhoea, contingent on the Support Vector Machine (SVM) to predict the probable disease using labelled data. Diarrhoea is amongst the top ten diseases which kill. A prototype system is developed based on the SVM algorithm. The prototype system takes six patient symptoms that which is input, from the user and the output result becomes the prognosis which may likely occur based solely on the given symptoms. Two other supervised learning models have been utilized in the prediction process, Random Forest Model (RFC) and Naïve Bayes Model (NB). Furthermore, a visualization on google maps (my maps) on the area in which a diarrhoea outbreak would likely occur. The constituency and the region of the patient will be used to place a pin on my maps, giving a visualization on the map, with a mapping structure this allows for a vivid demonstration of how diarrhoea is spreading in Eswatini. SVM received an average of 100% accuracy. The other two supervised learning models, random forest model and naïve Bayes model received 97.62% average accuracy on the same dataset. It shows that the SVM does well in data classification and with a small dataset.