Research Work

ARVA: An Augmented Reality-based Visual Aid for Mobility Enhancement Through Real-time Video Stream Transformation

Arezoo Sadeghzadeh, Md Baharul Islam, Md Nur Uddin, Tarkan Aydin

Abstract

Visual field loss (VFL) is a persistent visual impairment characterized by blind spots (scotoma) within the normal visual field, significantly impacting daily activities for affected individuals. CurrentVirtual Reality (VR) and Augmented Reality (AR)-based visual aids suffer from low video quality, content loss, high levels of contradiction, and limited mobility assessment. To address these issues, we propose an innovative vision aid utilizing AR headset and integrating advanced video processing techniques to elevate the visual perception of individuals with moderate to severe VFL to levels comparable to those with unimpaired vision. Our approach introduces a pioneering optimal video remapping function tailored to the characteristics of AR glasses. This function strategically maps the content of live video captures to the largest intact region of the visual field map, preserving quality while minimizing blurriness and content distortion. To evaluate the performance of our proposed method, a comprehensive empirical user study is conducted including object counting and multi-tasking walking track tests and involving 15 subjects with artificially induced scotomas in their normal visual fields. The proposed vision aid achieves 41.56% enhancement (from 57.31% to 98.87%) in the mean value of the average object recognition rates for all subjects in object counting test. In walking track test, the average mean scores for obstacle avoidance, detected signs, recognized signs, and grasped objects are significantly enhanced after applying the remapping function, with improvements of 7.56% (91.10% to 98.66%), 51.81% (44.85% to 96.66%), 49.31% (43.18% to 92.49%), and 77.77% (13.33% to 91.10%), respectively. Statistical analysis of data before and after applying the remapping function demonstrates the promising performance of our method in enhancing visual awareness and mobility for individuals with VFL.

Original language: English

Journal: IEEE Access

Publication status: Accepted/In press - 2024

Externally published: Yes

Keywords

Access to Document

10.1109/ACCESS.2024.3462628

Title: Financial Distress Prediction in Bank Sector Using Data Mining and Machine Learning Techniques

Status: Ready for Submission

Abstract: Nowadays, bank failures are a common and sensitive issue in a developing country like Bangladesh. So, it's important to examine and predict the financial health of a bank so that it can help minimize and rectify the upcoming or present losses of banks and customers. As we know, data mining has various uses in the prediction field, but in Bangladesh, the use of data mining techniques in the banking and financial distress sectors has rarely been seen, where previous studies worked with only the Altman z-score method. So our study focuses on using different performance matrices and also compering their performance accuracy with the model. Basically, it will help to widen the use of data mining in predicting distress in the banking sector. However,  we have collected data of 8 banks of Bangladesh and found out the important features or financial ratios and on those datasets, each of these ML techniques were tested and their performance accuracy were measured. According to the result the decision tree, random forest classifier, and gradient boosting performed better compared to SVM, logistic regression, and K-nearest neighbors in predicting distress.

Skills

Coding: Python, C, C++, Java, Kotlin, C#, JavaScript

ML: Pytorch, Transformers, Matplotlib, Tensorflow, Keras, Sklearn, NLTK, Pandas, Numpy, Scipy, OpenCV

IDE: Jupyter Notebook, PyCharm, Visual Studio, Android Studio, Unity3D

SWE: Git, Data Structure and Algorithm, HTML, CSS, Linux

Databases: SQL, SQLite, Firebase, Mongo DB

SDK: DreamWorld AR SDK, Magic Leap 1 SDK, Android SDK, Zoom SDK

Others: Academic Research, Teaching, Training, Competitive Programming