Skip to content

Volume 11, Issue 09


1) Using Artificial Intelligence in Earthquake Forecasting
Author Details:(1) Pham Van Khanh – Institute of Mathematics and Applied Sciences – Thang Long University, Vietnam (2) Le Huy Chau – Grade 12 Informatics – Ha Noi Amsterdam High School for the Gifted, Vietnam (3) Le Minh Dat – 12A1 – Foreign Language Specialized School, Vietnam
Predicting seismic tremors is a key issue in Earth science because of their overwhelming consequences and vast range. In this article we predict the places where earthquakes are likely to occur in the world and on what dates the earthquake will occur. With geologic location, magnitude and other factors in the dataset from updated every minute, we I predict or forecast time 14 days in the future, places where earthquakes are likely to occur. The application and impact of this prediction improving earthquake risk assessment can save lives and billions of dollars in infrastructure and planning
Keywords:Artificial intelligence, earthquake

[Download Full Paper] [Page 01-12]
2) Use of Cyclophosphamide in Patients with Steroid Resistant Post COVID Interstitial Lung Disease
Author’s Details: Dushantha Madegedara1, Lihini Basnayake2, Damith Nissanka Bandara3
Respiratory Research Unit, National Hospital Kandy, Sri Lanka (1)Consultant Respiratory Physician (2)Senior Registrar in Respiratory Medicine (3) Research Assistant *Corresponding author: Dr. Dushantha Madegedara, Respiratory Research Unit, National Hospital Kandy, Sri Lanka, Tel: +94 812 234220; Fax: +94 812 221270; E-mail:

Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV 2. To date; COVID-19 continues to remain at pandemic proportions. Long COVID-associated complications have been reported worldwide, among which, COVID- 19 associated interstitial lung disease (ILD) is a well-recognized long-term consequence. COVID 19- associated ILD causes significant morbidity in survivors of COVID 19 pneumonia. Although there is no evidence-based definitive treatment, immunosuppression therapy may improve the outcome of post-COVID ILD.
Medical records of 10 patients with confirmed post COVID ILD who received IV cyclophosphamide pulse therapy were prospectively evaluated. Information regarding demographic, clinical, biochemical and radiographic characteristics were extracted.
Intravenous cyclophosphamide therapy was commenced in patients who did not show adequate clinical, radiological, and functional response to corticosteroid therapy. Sequential HRCT scans were performed on all patients for consensus. Spirometry, 6MWT and laboratory investigation trends were evaluated before and after initiating IV cyclophosphamide therapy.
All post COVID ILD patients who underwent IV cyclophosphamide therapy demonstrated significant improvement in clinical, functional, radiological and laboratory parameters.
HRCT findings showed a marked response with resolution of interstitial abnormalities. HRCT with predominant ground-glass pattern showed the greatest response with near total resolution after treatment in three patients. Substantial resolution of linear fibrosis, mosaic appearance, and midzonal crazy paving patterns were also noted. Post cyclophosphamide spirometry revealed improvement in lung volumes in all patients except one. At the time of diagnosis of ILD, eight patients showed 3-6% desaturation and one patient showed 7% desaturation on 6MWT. At the end of six months of follow-up, all patients showed improvement in their functional capacity with only 1-2% of desaturation on 6MWT.
IV cyclophosphamide therapy was well tolerated and associated with significant improvement in post-COVID ILD resistant to steroid therapy. Therefore, it can be used effectively in the treatment of severe progressive COVID-19-related ILD. However, these findings cannot be generalized due to small sample size.
COVID-19, interstitial lung disease, IV cyclophosphamide, Sri Lanka
[Download Full Paper] [Page 13-23]
3) Matthias Alexander, Dr. Alfred B. Olsen, Violet Elliott, and Major Reginald F. E. Austin
Author Details: Jeroen Staring-Retired Dr. mult. Jeroen Staring taught mathematics at secondary schools in The Netherlands. His 2005 Medical Sciences dissertation describes the life, work, and technique of F. Matthias Alexander. In 2013 he successfully defended a second dissertation, on the early history of the NYC Bureau of Educational Experiments.

This case study discusses a meeting between Tasmanian actor and voice and breathing teacher F. Matthias Alexander and Australian contralto singer Violet Elliott in 1904 and indicates that by the end of 1905 Alexander and Royal Army Medical Corps Major Reginald F. E. Austin were jointly writing a book on breathing. The purpose of this case study is to determine whether or not Alexander was a breathing teacher when he arrived in London in 1904.
Key Words: Violet Elliott (1879-1965). Frederick Matthias Alexander (1869-1955); Major Reginald Francis Edmund Austin (1866-1939); Percy Reginald Dix (1866-1917); Arthur Keith (1866-1955); Alfred Berthier Olsen (1869-1960); Robert Henry Scanes Spicer (1857-1925).

[Download Full Paper] [Page 24-53]

4) Using Deep Learning and Reinforcement Learning In Combination with Automatic Vehicles’ Application of the Allee Effect
Author’s Details: (1)Cao Thi Luyen, Faculty of Information Technology-University of Transport and Communications (2)Nguyen Quang Duc – Class 12A1 – Nguyen Sieu High School – Hanoi (3)Nguyen Phuc Thanh K52-A7 Foreign Language Specialized School (4)Nguyen Minh Huy – Graduate student majoring in Industrial Automation – Hanoi University of Science and Technology

Convolutional Neural Network (CNN) can detect images from cameras installed on self-driving cars. First, we drove a car on a simulator and recorded frames from three cameras: left, right, and center. These frames were recorded at the rate of 30 frames per second. Additional data recorded were the distribution of steering angles, average velocity, etc. were passed through a CNN to train a self-driving system. CNN is like the eyes and visual area in the brain, so CNN’s achievements in autonomous vehicle control are somewhat limited. Therefore, this paper proposes the use of algorithms based on Deep Learning (DL) combined with reinforcement learning (RL) in the control of autonomous vehicles. We call this algorithm Deep Reinforcement Learning (DRL) which can send control commands to the vehicle to navigate properly and efficiently along a defined route. CNN tracks multiple objects while RL predicts the environment or assesses the current condition of the vehicle to make the safest decision. DRL-based algorithms have been used to solve Markov Decision Processes (MDPs), where the scope of the algorithm is to compute the optimal policy of an autonomous vehicle for choosing actions in an environment to maximize a reward function.
Key Words: Convolutional Neural Network, self-driving cars, data processing.

[Download Full Paper] [Page 54-67]

5) Using Random Forest Algorithm In Agricultural Production Forecasting
Author’s Details: (1)Trinh Van Chung – IT Faculty – Nguyen Trai University, Hanoi (2)Nguyen Viet Quang – Grade 12 Maths – Tran Phu High School for the Gifted – Hai Phong

Forecasting agricultural output plays an important role in government policies. In recent years, Vietnam has always had an oversupply crisis. Accurate forecasting of agricultural output helps state agencies be proactive in finding output for products and measures to reserve when supply exceeds demand. In case demand exceeds supply, it will push households to increase productivity or add more crops as well as increase acreage to be able to meet the needs of the agricultural market.
There are many methods to forecast a continuous quantity such as linear regression, co-integrated moving average (ARIMA) autoregressive models, and artificial neural networksThis paper uses the random forest regression tool to predict and compare with the multiple linear regression method. Using India’s agricultural data we found that the Random Forest method gave much better results. We will use the Random Forest tool to forecast Vietnam’s agricultural output when sufficient data is collected.
Key Words:
machine learning, Random Forest algorithm, agricultural production, forecasting
[Download Full Paper] [Page 68-75]

6) Goldbach’s Conjecture – A 280-Year-Old Unsolved Problem
Author’s Details:(1)Pham Van Khanh – Institute of Mathematics and Applied Sciences – Thang Long University, Hanoi, Vietnam (2)Van Trong Khoi – 12 Mathematics 1 – Hanoi – Amsterdam High School for the Gifted, Hanoi, Vietnam(3)Nguyen Phuc Thanh – K52-A7 Foreign Language Specialized School, Hanoi, Vietnam

In this paper, we present the content of Goldbach’s conjecture about representing an even number as the sum of 2 primes and Chen’s Theorem. The conjecture has not been proven, but in the middle of the 20th century, Chen Jingrun, a Chinese mathematician, proved half of the conjecture. The proof method is to use linear sieves to give an inequality in the number of ways of representing an even number as the sum of a prime and the other as a prime or as the product of 2 primes. Chen’s entire proof is very long and uses a lot of advanced knowledge, so here we only restate the results’ ideas and content
Key Words:Prime numbers, linear sieve

[Download Full Paper] [Page 76-85]