Browsing by Author "Yeo, Kheng Cher"

Now showing 1 - 4 of 4

A Novel IoT Based Accident Detection and Rescue System
(IEEE, 2020-08) Karmokar, Pranto; Bairagi, Saikot; Mondal, Anuprova; Nur, Fernaz Narin; Moon, Nazmun Nessa; Karim, Asif; Yeo, Kheng Cher
In South-East Asian cities such as Delhi, Dhaka road accidents are a very common occurrence which brings disaster to human lives as well as infrastructures. Sometimes people cannot reach hospitals prompt after an accident because of the traffic jam, deficit of ambulance, lack of a mechanism to timely propagate information to the appropriate authority. To ensure the safety of lives, this paper proposes an automated IoT based effective accident detection system. Immediately after an incident, the data information is sent to the webserver, instant SMS is forwarded to the victim's acquaintances and also to the relevant authorities such as traffic control room, nearby police station, ambulance service. To evaluate the performance of the system, a simulated road scenario has been designed. The result obtained after a thorough integration and system testing demonstrates that the proposed system not only achieves the stated goal of the research but also can deliver the expected outcome in a rather cost-effective way.
Analysis of Complex Networks for Security Issues Using Attack Graph
(2019 International Conference on Computer Communication and Informatics, IEEE, 2019-09-02) Musa, Tanvirali; Yeo, Kheng Cher; Azam, Sami; Shanmugam, Bharanidharan; Karim, Asif; Boer, Friso De; Nur, Fernaz Narin; Faisal, Fahad
Organizations perform security analysis for assessing network health and safe-guarding their growing networks through Vulnerability Assessments (AKA VA Scans). The output of VA scans is reports on individual hosts and its vulnerabilities, which, are of little use as the origin of the attack can't be located from these. Attack Graphs, generated without an in-depth analysis of the VA reports, are used to fill in these gaps, but only provide cursory information. This study presents an effective model of depicting the devices and the data flow that efficiently identifies the weakest nodes along with the concerned vulnerability's origin.The complexity of the attach graph using MulVal has been greatly reduced using the proposed approach of using the risk and CVSS base score as evaluation criteria. This makes it easier for the user to interpret the attack graphs and thus reduce the time taken needed to identify the attack paths and where the attack originates from.
Empirical Study of Password Strength Meter Design
(Proceedings of the 5th International Conference on Communication and Electronics Systems, ICCES, 2020-07-10) Yang, Yi; Yeo, Kheng Cher; Azam, Sami; Karim, Asif; Ahammad, Ronju; Mahmud, Rakib
Computer password was first used at the Massachusetts Institute of Technology around 1960 when researchers built a large-scale time-sharing computer called CTSS (Compatible Time Sharing System). There are many purposes where regular users require different passwords whenever they send and receive emails, do online shopping and numerous other activities on the internet. Surprisingly since the invention of the password, it has not been capable to protect the user accounts until now. There is no problem in using the similar password, but different passwords are often difficult to remember and mistakes can creep in rather easily. Many users do not know what kind of passwords should be chosen which will be strong enough to thwart all sorts of fraudulent activities. Thus, most passwords are not secure as they should be, and the users could become targets of attacks at any time. This research attempt, after a thorough literature review and in-depth empirical study, developed a software plug-in called `Password Strength Meter', which can be used to visually inform the user about the durability of their chosen password and an estimate on the timeframe it may take to break the password using standard cracking mechanism. The output of this empirical study has been widely appreciated by the users who have tested the developed software, stating that the confidence on their chosen password increases significantly while using this tool to form a password.
MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data
(IEEE, 2023-08-29) Hasib, Khan Md.; Azam, Sami; Karim, Asif; Marouf, Ahmed Al; Shamrat, F M Javed Mehedi; Montaha, Sidratul; Yeo, Kheng Cher; Jonkman, Mirjam
"Searching, retrieving, and arranging text in ever-larger document collections necessitate more efficient information processing algorithms. Document categorization is a crucial component of various information processing systems for supervised learning. As the quantity of documents grows, the performance of classic supervised classifiers has deteriorated because of the number of document categories. Assigning documents to a predetermined set of classes is called text classification. It is utilized extensively in a wide range of data-intensive applications. However, the fact that real-world implementations of these models are plagued with shortcomings begs for more investigation. Imbalanced datasets hinder the most prevalent high-performance algorithms. In this paper, we propose an approach name multi-class Convolutional Neural Network (MCNN)-Long Short-Time Memory (LSTM), which combines two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Time Memory, for text classification in news data. CNN’s are used as feature extractors for the LSTMs on text input data and have the spatial structure of words in a sentence, paragraph, or document. The dataset is also imbalanced, and we use the Tomek-Link algorithm to balance the dataset and then apply our model, which shows better performance in terms of F1- score (98%) and Accuracy (99.71%) than the existing works. The combination of deep learning techniques used in our approach is ideal for the classification of imbalanced datasets with underrepresented categories. Hence, our method outperformed other machine learning algorithms in text classification by a large margin. We also compare our results with traditional machine learning algorithms in terms of imbalanced and balanced datasets."