Browsing by Author "Mahmood, Tropa"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Automated Electricity Billing System for Bangladesh
    (Department of Computer Science and Engineering, Military Institute of Science and Technology, 2013-12) Hasan Ibne Obayed, Chowdhury; Mahmood, Tropa; Rahman, Mahmudur
    TherearemainlythreeutilityservicesavailableinBangladesh. TheyareElectricity,Natural Gas and Water. The procedures of these services are mainly manual. We tried to give an automated solution for these utility services, starting from applying for the service to the billing system along with all other facilities required. We mainly focused on electricity utility service for the proposed solution. But this solution can be equally applicable to any other utility services with certain modification. Since the bill payment can be done through online banking and application for new connection can be done online, we emphasized on meter reading and its processing to generate bill. We proposed a GSM based meter reading service and tried to make a prototype with present electric meter available in Bangladesh. We believe this solution can upgrade the utility service of Bangladesh. It will be helpful to monitor the usage of the services, to control the services remotely, to stop corruption in this sector and also to make efficient consumption of valuable energy of Bangladesh.
  • Thumbnail Image
    Item
    Detecting fake co-visitation attack in recommendation systems
    (Department of computer Science and Engineering, 2021-12-22) Mahmood, Tropa; Adnan, Dr. Muhammad Abdullah
    Recommendation systems are vulnerable to injection attacks by malicious users due to their fundamental openness. One of the vulnerabilities is the fake co-visitation injection attack, which significantly impacts recommendation systems since it modifies the system according to the attacker’s wishes. To date, the detection of co-visitation injection attacks are challenging as: (1) the choice of attribute representation of nodes is hard, (2) practical evidence for analyzing and detecting anomalies on real-world data is insufficient, (3) it is challenging to filter between the original and injected co-visitation data in terms of node behaviors. This paper investigates a detection framework that combines attribute and network structure information more synergistically to detect outlier nodes based on CUR decomposition and residual analysis. At first, co-visitation graphs are constructed using association rules, and their nodes attribute representations are developed. Then, both attributes and network structure information are blended in order to identify suspicious nodes. Extensive experiments on both synthetic and real-world data exhibit the efficacy of the proposed detection approach compared with other state-of-the-art approaches. The detection performance can improve by up to 50% for co-visitation injection attacks over the baselines in terms of false alarm rate (FAR) while keeping the highest detection rate (DR).