Sukkur IBA Journal of Computing and Mathematical Sciences

Review of Applications of Artificial Intelligence in Health Care

Bushra Memon — Thu, 18 Jan 2024 00:00:00 +0100

Twenty-first century is famously termed the age of the fourth industrial revolution, which is because of the massive amount of data being generated and stored which could be interpreted and analyzed by intelligible programs. Just as the discovery of the microscope in the sixteenth century led humans to discover things about human biology that the naked eye could not see, likewise artificial intelligence could be used to look for patterns in the data which humans otherwise would have less likely perceived. This paper will capitalize on this. How much potential could aid in the health care field A review and guide are compiled for any researcher or student who might want to practically implement the ideas discussed. The implementation of artificial intelligence for the analysis of medical images and beyond is to be discussed in this paper. Tools and software developed from these ideas could help medical practitioners make more accurate decisions.Machine Learning

Towards a Trustworthy and Efficient ETL Pipeline for ATM Transaction Data

Thu, 18 Jan 2024 00:00:00 +0100

ATMs generate vast amounts of data daily, which needs to be analyzed and stored. Dealing with this data, also termed big data, is a complex task, and here comes the role of ETL pipelines. ETL pipelines need extensive resources for operations, and their performance optimization is necessary as data must be dealt with in near or even real-time. If the pipeline deals with financial data such as ATM transactions, steps should be taken to ensure the data's security, privacy, confidentiality, and integrity. This can be achieved using Blockchain technology. It is a distributed ledger technology having an immutable nature. It has significant advantages in terms of providing security, but it has disadvantages as well, such as low throughput and transactional latency. If blockchain is used in an ETL pipeline, it will affect the overall performance. So, to prevent the decline in performance, steps should be taken to optimize it. In this paper, we are using parallelization and partitioning as techniques to optimize performance. The primary goal here is to achieve maximum security while maintaining performance.

Dynamic Time Quantum Computation for Improved Round Robin Scheduling Algorithm Using Quartiles and Randomization (IRRQR)

Bushra Jamil, Asif Yar, Humaira Ijaz — Thu, 18 Jan 2024 00:00:00 +0100

Scheduling is a decision-making process through which large numbers of tasks compete for various system resources. The availability of limited resources makes scheduling a challenge. Among resources, the processor is the most important resource for in-time completion of tasks therefore; developing an efficient processor scheduler is still a topic of interest. In this paper, we have proposed a modified Round Robin scheduling algorithm, in which the dynamic time quantum is computed based on Quartiles and randomness. We have considered average waiting time, average turnaround time, and the number of context switches as performance metrics and compared the proposed scheduling algorithm with existing approaches. The results show that the average waiting time, average turnaround time, and the number of context switches using the proposed algorithm are significantly reduced as compared other algorithms.

PREDICTIVE ANALYSIS OF CLIMATE DISASTER DATA

Anum Aziz — Thu, 18 Jan 2024 00:00:00 +0100

In this paper, the Total deaths and Cost per Index (CPI) of worldwide climate disaster dataset has been modelled. The time period of the dataset is from 1900 to 2021. The Autoregressive Integrated Moving Average (ARIMA) has been applied to forecast the Total Deaths and CPI of the study area. The total of 75% of the train data is used for construction of the model and the remaining 25% dataset is used for testing the model. The ARIMA model is general provides more accurate projection especially interval forecast and is more reliable than other common statistical techniques. The best-fitted model is identified as ARIMA(2,0,1) and (2,1,2) for Cost per Index CPI and Total Deaths respectively, generated on the basis of minimum values of Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) procedures. The accuracy parameter considered as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) both parameters shows the model is accurate respectively. There is a 7% difference between the auto and manual models for the CPI feature, similarly, there is a 4% difference for Total Deaths, indicating that CPI plays a significant impact in climatic disasters. In order to identify best fitted model, we applied the model manually and automatic processing. By means of Auto Correlation Function (ACF) and Partial Auto Correlation Function (PACF) plots, the most appropriate order of the ARIMA model are determine and evaluated. Accordingly the created model can help in determining future strategies related to climate disaster dataset of the world. From the forecast result it is found that the results seems to show an increasing trend in CPI values and the minimal decreasing in total death condition and economic activities of the world.