Search

Health-related data has a decisive role in disease diagnosis. Collecting relevant information from health-related data in medical records has been facilitated by evaluating the features of the data. Relevant research has shown that outcomes are significantly impacted by the use of feature selection (FS) in different medical domain data. FS provides an analysis of the most significant features to improve classification accuracy. The FS technique aims at minimizing the number of input variables and computational overload to maximize classification performance results. However, identifying the optimal features poses issues due to the high dimensionality of large features and the small sample size of health-related data. The metaheuristics optimization algorithm (MOA) plays an important role in generating the best subset features with exploration and exploitation phases. This study experiments with well-known MOAs and supervised learning from the UC Irvine Machine Learning Repository, PhysioNet, Kent Ridge Bio-Medical Dataset, and MIMIC-III v1.4 Repository with varying feature dimensions. To increase the quality of health-related data, this study proposes missing data imputation based on a deep learning approach, an autoencoder (AE). With AE imputation, the performance results obtain 0.0167 mean squared error (MSE) and 0.129 root mean squared error (RMSE). As a result, MOA shows its excellence in achieving minimal features, but still outstanding performance in low- and high-dimensional data. MOA is successfully applied to varying diverse health-related datasets with low- and high-dimensional data.

The advent of the fifth-generation mobile communication technology (5G) era has catalyzed significant advancements in medical diagnosis delivery, primarily driven by the surge in medical data from wearable Internet of Medical Things (IoMT) devices. Nonetheless, the IoMT paradigm grapples with challenges related to data security, privacy, constrained computational capabilities at the edge, and an inadequate architecture for handling traditionally error-prone data. In this context, our research offers: (1) an exhaustive review of large-scale medical data propelled by IoMT, (2) an exploration of the prevailing cloud-edge Artificial Intelligence (AI) framework tailored for IoMT, and (3) an insight into the application of Edge Federated Learning (EFL) in bolstering medical big data analytics to yield secure and superior diagnostic outcomes. We place a particular emphasis on the proliferation of IoMT wearable devices that incessantly stream medical data, either from patients or healthcare institutions, to centralized repositories. Furthermore, we introduce a federated cloud-edge AI blueprint designed to position computational resources proximate to the edge network, facilitating real-time diagnostic feedback to patients. We conclude by delineating prospective research trajectories in enhancing IoMT through AI integration.

Presents corrections to the paper, (Corrections to “A Review on the Application of Internet of Medical Things in Wearable Personal Health Monitoring: A Cloud-Edge Artificial Intelligence Approach”).

Amyotrophic lateral sclerosis, also known as ALS, is a progressive nervous system disorder that affects nerve cells in the brain and spinal cord, resulting in the loss of muscle control. For individuals with ALS, where mobility is limited to the movement of the eyes, the use of eye-tracking-based applications can be applied to achieve some basic tasks with certain digital interfaces. This paper presents a review of existing eye-tracking software and hardware through which eye-tracking their application is sketched as an assistive technology to cope with ALS. Eye-tracking also provides a suitable alternative as control of game elements. Furthermore, artificial intelligence has been utilized to improve eye-tracking technology with significant improvement in calibration and accuracy. Gaps in literature are highlighted in the study to offer a direction for future research.

Ocean waves that impact along the coast are among the most promising renewable energy sources that can be extracted from the environment. The ocean’s energy can be extracted by a few methods and converted from kinetic energy into electrical energy using turbine blades and power generators installed in areas with strong waves. The best and most widely established wave energy converters use an Oscillating Water Column (OWC) conversion concept. During the past few years, numerous research projects have been conducted to ensure a continuous development of OWC technologies that could provide more systematic, consistent, and environmentally friendly electrical supply sources to the nearby communities and electric-powered facilities. OWC has distinctive techniques for every section of the energy converting process, differing from other methods. Several things need to be considered to ensure that a maximum amount of energy can be generated from the established system. This paper discusses the OWC system design characteristics and functions. This paper also summarizes the current technology developments for the OWC and their achievements.

Delineating the electrocardiogram (ECG) waveform is an important step with high significance in cardiology diagnosis. It refers to extract the ECG morphology in start, peak, end points of waveform. Due to various shapes and abnormalities presented in ECG signals, several conventional computer algorithms always fail to extract the essential feature of heart information. Thus, it is critical to investigate an automated ECG signal delineation with its result accuracy. In this study, we propose the delineation process by using bidirectional long short-term memory (BiLSTM) classifier. Such process was conducted as one beat to the next (beat-to-beat), that means the ECG waveform classification is start of P-wave1 to start of P-wave2. However, such classifier lack of feature extraction process, reducing the classification accuracy result. To improve the classifier performance, convolutional layers as facture extraction are stacked with BiLSTM named ConvBiLSTM. We conducted the experimental based on seven-class ECG waveform using a publicly available QT Database with annotation of the main waveforms to produce high accurate classifier, i.e., Pstart–Pend, Pend – QRSstart, QRSstart – Rpeak, Rpeak – QRSend, QRSend – Tstart, Tstart–Tend, and Tend–Pstart. It was found that the proposed model showed remarkable results with overall average performances of 99.83% accuracy, 98.82% sensitivity, 99.90% specificity, 98.86% precision, and 98.84% F1 score. Based on these promising results, the efficacy of the proposed stacked ConvBiLSTM model in classifying ECG waveform provides a great opportunity to help cardiologists in diagnosis decision-making for faster assessment.

Accurate screening for septal defects is important for supporting radiologists' interpretative work. Some previous studies have proposed semantic segmentation and object detection approaches to carry out fetal heart detection; unfortunately, the models could not segment different objects of the same class. The semantic segmentation method segregates regions that only contain objects from the same class. In contrast, the fetal heart may contain multiple objects, such as the atria, ventricles, valves, and aorta. Besides, blurry boundaries (shadows) or a lack of consistency in the acquisition ultrasonography can cause wide variations. This study utilizes Mask-RCNN (MRCNN) to handle fetal ultrasonography images and employ it to detect and segment defects in heart walls with multiple objects. To our knowledge, this is the first study involving a medical application for septal defect detection using instance segmentation. The use of MRCNN architecture with ResNet50 as a backbone and a 0.0001 learning rate allows for two times faster training of the model on fetal heart images compared to other object detection methods, such as Faster-RCNN (FRCNN). We demonstrate a strong correlation between the predicted septal defects and ground truth as a mean average precision (mAP). As shown in the results, the proposed MRCNN model achieves good performance in multiclass detection of the heart chamber, with 97.59% for the right atrium, 99.67% for the left atrium, 86.17% for the left ventricle, 98.83% for the right ventricle, and 99.97% for the aorta. We also report competitive results for the defect detection of holes in the atria and ventricles via semantic and instance segmentation. The results show that the mAP for MRCNN is about 99.48% and 82% for FRCNN. We suggest that evaluation and prediction with our proposed model provide reliable detection of septal defects, including defects in the atria, ventricles, or both. These results suggest that the model used has a high potential to help cardiologists complete the initial screening for fetal congenital heart disease.

Malaysia has a great potential to harness energy in water due to its long coastline within the South China Sea and the Straits of Malacca. Malaysia’s energy mix could be improved using marine current energy devices (MCEDs) to replace fossil fuel and it is predictable energy compare to hydropower, solar photovoltaic (PV), and biomass. However, MCEDs is not been fully developed in Malaysia. The objectives of this paper are to provide a useful background for policymakers or researchers in the types of MCEDs and potential sites location of MCEDs that are applicable in Malaysia. This review also discusses the issues and challenges of MCEDs in Malaysia. Five types of MCEDs were discussed including tidal range device, tidal stream turbine, wave energy converter, ocean thermal energy conversion, and salinity gradient energy. These MCEDs are compared for their suitability of application in Malaysia. Among all MCEDs, tidal stream turbine is identified as high potential and commercially viable in Malaysia. However, ocean characteristics in Malaysia are low kinetic energy-flux density, low current speed, low tide, and shallow water; only fulfill the minimum requirement of tidal stream turbine making the tidal stream energy resources not significant enough to contribute to the nation’s energy mix. Therefore, using diffuser augmented tidal stream turbines to increase the flow velocity should be studied thoroughly.

Malaysia's Eleventh Plan started to encourage green building developments and green industries to stimulate green growth. Eventually, the Malaysian government had launched a new commitment to accelerate the green and efficient energy sector and revised the quota of Renewable Energy (RE) towards higher capacity for electricity generation. These scenarios had highlighted the latest commitment of the Malaysian government to implement both green building development and concurrently, streamline the additional quota for RE generation. Due to this, the evolution of the requirement of RE-based Distributed Generation (DG) in the green building development for higher installed-capacity was expected to occur in ensuring the government key achievement becomes more visible. This study focuses on measuring the expanded-capacity performance of the Solar Photovoltaic (PV)-type DG unit (PV-DG) through the Green Building Rating System (GBRS), particularly on the useful energy consumption yield for load and total line loss minimization. Previous work has conducted a MATLAB simulation on a PV-DG capacity expansion guided by the Net Energy Metering (NEM) specification considering the total line loss minimization as the main objective function. These results are being adopted to obtain the ratio of useful energy consumption from the generated PV-DG through the selected distribution network. Consequently, the Performance Ratio (PR) - as the internationally recognized formulation for a complete PV-DG system - is proposed to be revolutionized towards extended version, considering the specific total line losses minimization, via the formed of the proposed ratio.

The measurement of partial discharges (PD) in electrical equipment or machines subjected to high voltage can be considered as one of the most important indicators when assessing the state of an insulation system. One of the main challenges in monitoring these degradation phenomena is to adequately measure a statistically significant number of signals from each of the sources acting on the asset under test. However, in industrial environments the presence of large amplitude noise sources or the simultaneous presence of multiple PD sources may limit the acquisition of the signals and therefore the final diagnosis of the equipment status may not be the most accurate. Although different procedures and separation and identification techniques have been implemented with very good results, not having a significant number of PD pulses associated with each source can limit the effectiveness of these procedures. Based on the above, this research proposes a new algorithm of artificial generation of PD based on a Deep Convolutional Generative Adversarial Networks (DCGAN) architecture which allows artificially generating different sources of PD from a small group of real PD, in order to complement those sources that during the measurement were poorly represented in terms of signals. According to the results obtained in different experiments, the temporal and spectral behavior of artificially generated PD sources proved to be similar to that of real experimentally obtained sources.

Partial discharge (PD) monitoring is one of the most used tools for diagnosing the condition of electrical equipment and machines that operate normally at high voltage levels. Ideally, PD identification can be easily done if there is a single source acting over the electrical asset during the measurement. However, in industrial environments, it is common to find the presence of multiple sources acting simultaneously, which hinders the identification process, due to sources of greater amplitude hiding the presence of other types of sources of lesser amplitude that could eventually be much more harmful to the insulation system. In this sense, the separation of PD through the use of clustering techniques allows individual source recognition once they have been clearly separated. This article describes the main clustering techniques that have been used over time to separate PD sources and electrical noise. The results obtained by the different authors in the utilization of each technique demonstrates good performance in terms of separation.

Water pipeline leakage detection is still an important issue, particularly for the development of smart cities. Thus, this paper reviews water pipeline leakage detection techniques, which can be classified into three different categories, namely, software-based, hardware-based, and conventional methods. We compare the advantages and disadvantages for all the methods in the groups and thoroughly discuss the hardware-based method, which is our focus. Specifications on water pipeline testbeds used in the previous works are also highlighted. Since many recent techniques are based on accelerometer or vibration sensors, a comparative study that includes the cost and accuracy in identifying the pipeline leaks is presented. The theoretical computation of the vibration induced from our water pipeline testbed is also demonstrated and compared with the actual vibration data collected from the experimental works using three different sensors, namely, MPU6050, MMA7361, and ADXL335.