Detecting Left Heart Failure in Echocardiography through Machine Learning: A Systematic Review

Background: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other hand, studies have shown that artificial intelligence (AI) is highly potential in complementing the work of clinicians to diagnose heart failure accurately and rapidly. Methods: We systematically searched Europe PMC, ProQuest, Science Direct, PubMed, and IEEE following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and our inclusion and exclusion criteria. The 14 selected works of literature were then assessed for their quality and risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). Results: A total of 2105 studies were retrieved, and 14 were included in the analysis. Five studies posed risks of bias. Nearly all studies included datasets in the form of 3D (three dimensional) or 2D (two dimensional) images, along with apical four-chamber (A4C) and apical two-chamber (A2C) being the most common echocardiography views used. The machine learning algorithm for each study differs, with the convolutional neural network as the most common method used. The accuracy varies from 57% to 99.3%. Conclusions: To conclude, current evidence suggests that the application of AI leads to a better and faster diagnosis of left heart failure through echocardiography. However, the presence of clinicians is still irreplaceable during diagnostic processes and overall clinical care;thus, AI only serves as complementary assistance for clinicians.

Can trade credit rejuvenate Islamic banking?

This study proposes a renewal of the contemporary Islamic banking Murabaha financing model as it aggravates financial fragility with waning economic efficiency. We adapt the working capital framework of successful US companies like Amazon and Walmart and model an innovative Murabaha facility as trade credit within the real sector of the economy. We then test its robustness in a range of simulation tests. Our approach is novel and stands in contrast to the familiar financial sector fixed-income facilities, characteristic of Western economies, stealthily mimicked as mark-up (interest rate based) Murabaha by Islamic banks. We argue that this is neither appropriate nor effective for Islamic economies, making them fragile under monetary pressures in crises like the current coronavirus and energy ones. Our simulation results indicate that the trade credit Murabaha not only transforms debt into a risk-sharing one but also offers more competitive financing rates, reduces systemic risk, and improves financial stability. Furthermore, our results imply that the trade credit Murabaha can increase the efficiency of Islamic financial systems and make them more resilient to shocks. Consequently, this paper discusses the integration of our novel Murabaha within a recreated architecture of Universal Banking. As an implication, this should promote business activity and contribute to global growth. Finally, we recommend how to deploy our novel Murabaha based on trade credit (as opposed to the currently deployed fixed-income-mimicked Murabaha) to alleviate twin agency debt costs (risk shifting, underinvestment) and solve the ownership transfer problem of modern Islamic banking. © 2022, The Author(s).

FaceNet with RetinaFace to Identify Masked Face

The use of masks due to the Covid-19 pandemic reduces the accuracy of facial recognition systems applied to camera-based security systems. The use of the mask by the people covers most of the facial featureswhich is located from middle to bottom area. In addition, the area which are still visible are the upper face which are eyes and forehead. This paper proposes a masked face recognition using a combination of RetinaFace as a face detector and FaceNet as a face recognizer. The MFR2 dataset with 53 identities was used to train and test this method. The test data in this study are only images of masked faces. Cosine Distance was implemented to measure the face similarity. Based on the experiment results, the proposed method obtained 98.2% of detection accuracy. The proposed method provided 78% accurate performance with 3.63 s for processing a single frame in terms of face recognition. The performance indicates that our system can potentially be applied in security systems with many different identities. © 2021 IEEE.

Low-Cost Camera-Based Smart Surveillance System for Detecting, Recognizing, and Tracking Masked Human Face

A surveillance system is still the most exciting and practical security system to prevent crime effectively. Surveillance systems run on edge devices such as the low-cost Raspberry mobile camera with the Internet of Things (IoT). The primary purpose of this system is to recognize the identity of the face caught by the camera. However, it raises the challenge of unstructured image/video where the video contains low quality, blur, and variations of human poses. Moreover, the challenge is increasing because people used to wear a mask during the Covid -19 pandemic. Therefore, we proposed developing an all-in-one surveillance system with face detection, recognition, and face tracking capabilities. The surveillance system integrated three modules: Multi-Task Cascaded Convolutional Network (MTCNN) face detector, VGGFace2 face recognition, and Discriminative Single-Shot Segmentation (D3S) tracker. We train new face mask data for face recognition and tracking. This system utilizes the Raspberry Pi camera and processes the frame on the cloud as a mobile sensor approach. The proposed method was successfully implemented and got competitive detection, recognition, and tracking results under an unconstrained surveillance camera. © 2021. All Rights Reserved.

Developing Smart COVID-19 Social Distancing Surveillance Drone using YOLO Implemented in Robot Operating System simulation environment

The Novel Coronavirus, termed as COVID-19 outbreak, is faced by almost all countries in the world. It spread through communal interaction between people, especially in densely populated areas. An effort to prevent Covid-19 transmission is social distancing regulation. However, this policy is not obeyed by the public, so the government needs to supervise the movement and people's interaction. The government needs a crowd surveillance system that can detect people's presence, identify the crowd, and give social distancing warnings. Therefore, we propose a drone that has the ability of localization, navigation, people detection, crowd identifier, and social distancing warning. We utilize YOLO-v3 to detect people and define adaptive social distancing detector. In this paper, we implemented a road segmentation on the IRIS PX4 drone in the Robot Operating System and Gazebo simulation. The proposed system also successfully demonstrated people and crowd detection with varying degrees of the crowd. The system obtained crowd detection accuracy is around 90% and expected to be readily implemented on real hardware drones and tested in real environments. © 2020 IEEE.