Automatic speech recognition (ASR) is an area of research which deals with the recognition of speech by machine in several conditions. ASR performs well under restricted conditions (quiet environment), but performance degrades in noisy environments. This paper presents a brief survey on Automatic Speech Recognition on Malays Corpus and multi-modal speech recognition on others Corpus. The audio only speech recognition has been done by many researchers few decades. After years of research and development the performance of automatic speech recognition remains one of the important research challenges (eg., variations of the context, database, and environment). The criteria for designing Speech Recognition system are pre-processing filter, end-point detection, feature extraction techniques, speech classifiers, database, and performance evaluation. The existing problems that are in Automatic Speech Recognition (ASR)-noise environments and the various techniques to solve these problems had constructed. The objective of this review paper is to summarize and compare some of the well know methods used by previous researcher.

Helminthiasis disease is one of the most serious health problems in the world and frequently occurs in children, especially in unhygienic conditions. The manual diagnosis method is time consuming and challenging, especially when there are a large number of samples. An automated system is acknowledged as a quick and easy technique to assess helminth sample images by offering direct visibility on the computer monitor without the requirement for examination under a microscope. Thus, this paper aims to compare the human intestinal parasite ova segmentation performance between machine learning segmentation and deep learning segmentation. Four types of helminth ova are tested, which are Ascaris Lumbricoides Ova (ALO), Enterobious Vermicularis Ova (EVO), Hookworm Ova (HWO), and Trichuris Trichiura Ova (TTO). In this paper, fuzzy c-Mean (FCM) segmentation technique is used in machine learning segmentation, while convolutional neural network (CNN) segmentation technique is used for deep learning. The performance of segmentation algorithms based on FCM and CNN segmentation techniques is investigated and compared to select the best segmentation procedure for helminth ova detection. The results reveal that the accuracy obtained for each helminth species is in the range of 97% to 100% for both techniques. However, IoU analysis showed that CNN based on ResNet technique performed better than FCM for ALO, EVO, and TTO with values of 75.80%, 55.48%, and 77.06%, respectively. Therefore, segmentation through deep learning is more suitable for segmenting the human intestinal parasite ova.

Osteosarcoma is a common type of bone tumor, particularly prevalent in children and adolescents between the ages of 5 and 25 who are experiencing growth spurts during puberty. Manual delineation of tumor regions in MRI images can be laborious and time-consuming, and results may be subjective and difficult to replicate. Therefore, a convolutional neural network (CNN) was developed to automatically segment osteosarcoma cancerous cells in three types of MRI images. The study consisted of five main stages. First, 3692 DICOM format MRI images were acquired from 46 patients, including T1-weighted, T2-weighted, and T1-weighted with injection of Gadolinium (T1W + Gd) images. Contrast stretching and median filter were applied to enhance image intensity and remove noise, and the pre-processed images were reconstructed into NIfTI format files for deep learning. The MRI images were then transformed to fit the CNN’s requirements. A 3D U-Net architecture was proposed with optimized parameters to build an automatic segmentation model capable of segmenting osteosarcoma from the MRI images. The 3D U-Net segmentation model achieved excellent results, with mean dice similarity coefficients (DSC) of 83.75%, 85.45%, and 87.62% for T1W, T2W, and T1W + Gd images, respectively. However, the study found that the proposed method had some limitations, including poorly defined borders, missing lesion portions, and other confounding factors. In summary, an automatic segmentation method based on a CNN has been developed to address the challenge of manually segmenting osteosarcoma cancerous cells in MRI images. While the proposed method showed promise, the study revealed limitations that need to be addressed to improve its efficacy.

Over the year, contact lens detection has attracted attention and interest from many researchers to study further in this field of inspection. This paper provides a comprehensive review of the existing literature surrounding contact lens inspection methods. In this paper, contact lens-related, defects-related, and inspection methods related are described in detail. To detect contact lenses in a single image and also multi-image, numerous techniques have been developed and this paper is aimed at classifying and evaluating these algorithms. Also, contact lens inspection based on conventional and artificial intelligence methods will be discussed in detail. The industrial production process of contact lenses probably needs to be constructed with advanced tools based on recent technologies so that they can help in the inspection system to achieve accurate results of the inspection and reduce processing time.

Face recognition is a technology used to detect human faces and verify their identities. It is widely used across a range of security applications, from securing personal devices to identifying individuals with criminal records through surveillance cameras. This chapter reviews the use of face recognition technology in attendance management while, with particular focus on its application during the COVID-19 pandemic, when the wearing of face masks presented a significant challenge. Human faces comprise of several distinctive cues that make them a valuable subject of study. As such, face images are used within the face recognition system for attendance management. In this framework, seven stages were implemented including, 1) hardware development, 2) graphical user interface (GUI) development, 3) database collection, 4) image pre-processing, 5) face mask detection, 6) face recognition, and 7) attendance marking. A total of 31 classes were used in the face recognition dataset, whilst two classes, “With Mask” and “Without Mask” were designated for face mask detection. For face detection, the Single Shot MultiBox Detector (SSD) Caffe model was employed to detect faces from input images or videos. The extracted face regions were subsequently used to predict both the mask status and the identity of the individual using the convolutional neural network (CNN) models. The face mask detection model employed was MobileNetV2, trained using Adam (Adaptive Moment Estimation) optimiser with a binary cross-entropy loss function, a learning rate of 0.001, and batch size of 32, achieving a classification accuracy of 95%. For face recognition, the CNN architecture, optimiser, and loss function were varied whilst keeping the batch size fixed at 32, and the learning rate at 0.001, over 200 training epochs. The effects on model performance were observed in order to determine the most suitable model for face recognition. It was found that the Visual Geometry Group-16 layers (VGG-16) model, using RMSprop (Root Mean Square Propagation) optimiser with a binary cross-entropy loss function, yielded the best results, achieving 100% accuracy for both training and validation, along with a classification accuracy of 99%.