Browsing by Author "Mariam, Asma"

Now showing 1 - 3 of 3

Blind Guard
(2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), IEEE, 2021-07-30) Hoque, Mozibul; Hossain, Monir; Ali, Md. Yeasin; Moon, Nazmun Nessa; Mariam, Asma; Islam, Mohammad Raiful
This research project is an Android app for blind people's guidance that will provide the visually impaired person guidelines, protection, and security. It would be easier for blind people to walk and speak with others if they use this app. Any blind person can be able to walk and communicate with their guardians by using this app. This program uses an intelligent stick that informs a blind person about barriers along the way in advance. Their guardian will be able to trace their whereabouts through the location tracker. They will quickly find anything they need like maintaining contacts, also will be able to establish communication, and will be able to read every text. Any questions asked via the blind person in this application will be answered. It will indicate the best route of the blind person's destination. For front-end design, Java, and SDK are used and for Back-end design, firebase is used. This application proved to operate after the completion of all the tasks and the evaluation procedure.
Mobile Device and Social Media Forensic Analysis
(2021 1st International Conference on Emerging Smart Technologies and Applications (eSmarTA), IEEE, 2021-08-23) Saha, Debanjana; Karmakar, Sajal; Nur, Fernaz Narin; Mariam, Asma; Moon, Nazmun Nessa; Ahmed, Akash
This research work has focused on a digital forensic analysis of social media through mobile devices to determine the primary criminal. This proposed system considered the mobile device used by the prime suspect as the main evidence of cybercrime and tried to find out the degree of criminal involvement in terms of probability likelihood. At first, the most critical data elements were obtained, e.g., deleted files and keywords, through the forensic analysis of the mobile device. This will also help in the identification of the main culprits in the investigation of cybercrime. Next, the system classified the criminals in one of three zones based on the analysis of the keywords to determine the level of crime. The system also takes into account the most probable timeframe for the crime. Thus, the proposed system helps to identify the main culprits in investigating cybercrime more efficiently than the traditional approaches. The system is also looking into the most probable timeframe for the crime, for example, it has been observed that most cybercrime happens on the weekends. The proposed system investigates using cookies and the logical image of the device that cyber criminals left behind.
Sentiment Analysis on Bangla Conversation Using Machine Learning Approach
(Daffodil International University, 22-06-20) Hassan, Mahmudul; Shakil, Shahriar; Moon, Nazmun Nessa; Islam, Mohammad Monirul; Hossain, Refath Ara; Mariam, Asma; Nur, Fernaz Narin
Nowadays, online communication is more convenient and popular than face-to-face conversation. Therefore, people prefer online communication over face-to-face meetings. Enormous people use online chatting systems to speak with their loved ones at any given time throughout the world. People create massive quantities of conversation every second because of their online engagement. People's feelings during the conversation period can be gleaned as useful information from these conversations. Text analysis and conclusion of any material as summarization can be done using sentiment analysis by natural language processing. The use of communication for customer service portals in various e-commerce platforms and crime investigations based on digital evidence is increasing the need for sentiment analysis of a conversation. Other languages, such as English, have well-developed libraries and resources for natural language processing, yet there are few studies conducted on Bangla. It is more challenging to extract sentiments from Bangla conversational data due to the language's grammatical complexity. As a result, it opens vast study opportunities. So, support vector machine, multinomial naïve Bayes, k-nearest neighbors, logistic regression, decision tree, and random forest was used. From the dataset, extracted information was labeled as positive and negative.