Browsing by Author "Maksuda"

Now showing 1 - 2 of 2

Broca’s Area of Brain to Analyze the Language Impairment Problem and Behavior Analysis of Autism
(Springer, 2022-01-01) Islam, Md Ashiqul; Karim, Rafat; Ahmed, Faruq; Maksuda; Hossen, Md Sagar; Akter, Shamima
The brain is a tremendous three-pound organ that controls all functions of the body, interprets data from the surface world. The human brain may be a hub for specific primary tasks. When our brain does not work properly or fails to complete his tasks our science contemplates it as an unfit brain. In our trendy science day by day we wish to understand a couple of human brain and behavior. During this continuation, we tend to see that the ordinary brain and unfit brain have some variations. The spectrum disorder syndrome people face some difficulties [1]. They cannot socially interact with people very well, the communication gap, and abnormal behaviors are facing in their faces. In the frontal lobe, Broca’s area is one of the reasons that play an important role in language production. Though its precise linguistic functions are still a bit unclear. It is named by physician Paul Broca. In this problem with aphasia reading and writing are also impaired but language comprehension is typically relatively preserved. Some symptoms are involved with producing movements like the tongue and mouth that help speech to be produced [2]. And also some other symptoms are that is involved producing grammar, verbal memory, syntax. Broca’s area also has some linguistic and non-linguistic functions. It plays a role in language comprehension,
Imbalance Data Classification to Identify Fraudulent Transactions
(Daffodil International University, 2019-12-10) Karim, Rafat; Mahmud, Md. Rifat; Maksuda; Jannatus Saiyem, MD.
Because of the expansion of social media and globalization now a days, peta byte scale of data is being generated in every second. Data mining is the process of extracting knowledge from this huge amount of data. Data mining applications are becoming more useful and key pre-requisite for any kind of business scenarios. However, for certain applications is supervised learning, lack of sufficient data for certain classes creates data imbalance problem. For example, in a credit card fraud detection application, most of the transactions are not fraud and few of them are fraud. In our research, we have applied some classification techniques on an imbalanced data set. We have tested synthetic data from a financial payment system because it is a great challenge to obtain real dataset. Synthetic data is artificially constructed which mimics real world events. We have tested Decision tree, Support Vector Machine, Artificial Neural Network and Adaboost algorithms to treat with class imbalance problem. Among these algorithms, we find promising accuracy from Adaboost compared of others. So in this paper, our main target is that for an imbalance dataset which classification algorithm performs better.