Browsing by Author "Hossain, Maisha"

Now showing 1 - 5 of 5

A counseling system to predict the study path for freshmen
(BRAC University, 2019-04) Usha, Rowshni Tasneem; Parvez, Shiny Raisa; Sejuti, Fariha Sazid; Hossain, Maisha; Majumdar, Mahbub
Now a days, dilemma related to one's career has been considered as a serious issue, specially among fresh graduates. Starting at the age of 18, the students usually fail to grasp the idea of which career path to pursue as they lack maturity and experience on the matter. Moreover, students su er greatly in deciding which faculty would result the highest bene t for them due to the insu ciency of counselors in the pre-university education. The students do not have the su cient knowledge to make themselves aware of the real life career related challenges, which is supported by academic majors. It is crucial for a student to make the proper decision on the matter of their career in order to avoid consequences that may be the result of wrong career selection. As a result, selecting an proper career with highest bene t has become one of the most di cult as well as challenging task for the students because wrong career selection may lead to a work eld which was not meant for them. This paper presents a counselling system to predict study path for the freshmen by analyzing necessary attributes such as skills, interests, values and motivation, academic background. Moreover, the proposed freshmen counseling system helps the freshmen in their career choice as well as guides toward their respective appropriate career for future. We have used several di erent approaches for modeling and prediction such as Decision tree classi er, Random Forest, SVM, K-Nearest-Neighbors Classi ers etc. and di erentiated between the resulting precision scores. The results were also cross-checked which determined the best parameters that is responsible for providing highest accuracy scores. Furthermore, some ranking algorithms were used to generate a ranked output for the student counseling system. In this paper, we have separated our work into di erent parts. Chapter 1 contains the overall idea about our work. Chapter 2 contains Related Works, followed by Chapter 3, where we have mentioned about the methodologies which we have used for the system. After that Chapter 4 contains the implementation of the system. Next in Chapter 5 result analysis has been mentioned. Lastly, Chapter 6 ended with conclusion, our limitations and future scopes of improvements related to our work.
Deep learning based predictive analytics for decentralized content caching in hierarchical edge networks
(BRAC University, 2022-01) Chakraborty, Dhruba; Rabbi, Mahima; Hossain, Maisha; Khaled, Saraf Noor; Oishi, Maria Khanom; Alam, Md. Golam Rabiul; Shakil, Arif
Content centric network is a state-of-the-art networking architecture for content distribution and content caching. However, it is inefficient to cache every content in each network device. The modern edge computing technology opens the door for content caching in the edge of the network. However, still we have to decide which contents we should cache and which content we should replace from the cache. Deep learning based predictive analytics can play an important role in selecting contents for caching purposes. In this research, we will use Long shortterm memory(LSTM) based Recurrent Neural Network(RNN) for decentralized content caching at the hierarchical edge of the network.
Islamic learning and research center
(BRAC University, 2014-12) Hossain, Maisha
Safety Perception of Pedestrians at Level Crossings
(Department of Civil and Environmental Engineering(CEE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-04-30) Rahman, Pretom Md Tahmidur; Hossain, Maisha; Yousuf, Tasfia
Rail-pedestrian crashes are a persisting tragedy in Bangladesh, with a growing magnitude of fatalities. Pedestrian crashes on road are prevalent but it’s not highly noticed on railway lines. Hence, a good number of studies have been done on pedestrian accidents involving roads, however, insignificant numbers of studies, if any, addressed the safety perception of pedestrians at road-rail crossing specifically in developing countries’ perspective. Moreover, road-pedestrian might result in severe injuries but rail-pedestrian collisions often end up in fatalities. With a view to finding the influence of the demographic traits of the victims, for instance, age, education, and gender, alongside propensity for suicides, and distractions due to electronic gadgets and other numerous reasons behind pedestrian crashes on railways, this paper will explore the safety perception of pedestrians at a level crossing. A questionnaire was prepared reviewing previous literatures, local context, and pilot survey. Questionnaires were again divided into 8 sub-groups namely socioeconomic characteristics, situational case, accident experience, safety knowledge, safety perception, personal crossing characteristics, surrounding conditions, and awareness. The survey was conducted by collecting data from level crossings of 8 different locations from 250 pedestrians, who use level crossings frequently. Independent variables were formed using the responses from this survey. The dependent variable is formed from the perceived safe distance of the respondents to cross the railway track in front of an oncoming train. The ordered probit model has been used because of ordinal behavior of the dependent variable considered in the study to find the significant factors effecting the safety perception of pedestrians. The model assists to find out the most and least risk-taking cohort. Moreover, independent variables with substantial impacts on the safety perceptions of pedestrians are also perceived. The study will disclose the less safety conscious cohort of pedestrians to the policymakers so that necessary measures can be taken by introducing safety education to them and implementing robust monitoring systems near railroads.
The influence of artificial intelligence on the progress of humanity
(Brac University Research For Development Club (BURED), 2024-07-03) Novo, Muhtasim Sanaan; Mithi, Nujhat Tabassum; Hossain, Maisha; Nasit, Moontaka
The examination of how artificial intelligence affects people's daily lives is the main topic of this essay. The world began to significantly shift after technology was created. This advancement has received a new impetus from artificial intelligence. Artificial intelligence is somewhat entirely necessary for survival. This essay will examine our use of artificial intelligence and the extent to which we rely on it. Additionally, this essay will touch on the ongoing discussion about the employment issue and how it relates to artificial intelligence.