Browsing by Author "Whaiduzzaman, Md."

Now showing 1 - 9 of 9

A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization
(IEEE, 2023-02-23) Paula, Luiz Paulo Oliveira; Faruqui, Nuruzzaman; Mahmud, Imran; Whaiduzzaman, Md.; Hawkinson, Eric Charles; Trivedi, Sandeep
Security has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovative automatic Front Door Security (FDS) algorithm that uses Human Activity Recognition (HAR) to detect four different security threats at the front door from a real-time video feed with 73.18% accuracy. The activities are recognized using an innovative combination of GoogleNet-BiLSTM hybrid network. This network receives the video feed from the CCTV camera and classifies the activities. The proposed algorithm uses this classification to alert any attempts to break the door by kicking, punching, or hitting. Furthermore, the proposed FDS algorithm is effective in detecting gun violence at the front door, which further strengthens security. This Human Activity Recognition (HAR)-based novel FDS algorithm demonstrates the potential of ensuring better safety with 71.49% precision, 68.2% recall, and an F1-score of 0.65.
A Review on VANET Security: Future Challenges and Open Issues
(Institute of Electrical and Electronics Engineers Inc., 2023-05-02) Mahi, Md. Julkar Nayeen; Chaki, Sudipto; Humayun, Esraq; Imran, Hafizul; Barros, Alistair; Whaiduzzaman, Md.
Vehicular Adhoc Network (VANET) is an established technology that is well-suited for emerging technologies such as the Internet of Vehicles (IoV) and Unmanned Aerial Vehicles (UAVs). However, while VANET offers improved methods for addressing contemporary technology, it also presents significant challenges in providing adequate security measures for intended access. VANET operates on multiple execution platforms, such as roadside units, vehicle-tovehicle, vehicle-to-device, and vehicle-to-everything (V2X) communication. As a result, VANET must establish robust security measures for future purposes and strengthen protocol authentications to ensure secure data delivery and network-wide execution. In this work, we provide an overview of some of the recent security problems faced by VANET to raise awareness among developers and engineers about the specific security needs of VANET and how to avoid errors or intrusions when deploying VANETs in cities and urban areas. We cover topics such as the classification of security attacks, standard or security protocol problems and solutions, and the best feasible security criteria for extended VANETs. Finally, we discuss open issues and future VANET security developments or concerns.
Cyber-Physical System Security Based on Human Activity Recognition through IoT Cloud Computing
(MDPI Publications, 2023-04-17) Achar, Sandesh; Faruqui, Nuruzzaman; Whaiduzzaman, Md.; Awajan, Albara; Alazab, Moutaz
Cyber-physical security is vital for protecting key computing infrastructure against cyber attacks. Individuals, corporations, and society can all suffer considerable digital asset losses due to cyber attacks, including data loss, theft, financial loss, reputation harm, company interruption, infrastructure damage, ransomware attacks, and espionage. A cyber-physical attack harms both digital and physical assets. Cyber-physical system security is more challenging than software-level cyber security because it requires physical inspection and monitoring. This paper proposes an innovative and effective algorithm to strengthen cyber-physical security (CPS) with minimal human intervention. It is an approach based on human activity recognition (HAR), where GoogleNet–BiLSTM network hybridization has been used to recognize suspicious activities in the cyber-physical infrastructure perimeter. The proposed HAR-CPS algorithm classifies suspicious activities from real-time video surveillance with an average accuracy of 73.15%. It incorporates machine vision at the IoT edge (Mez) technology to make the system latency tolerant. Dual-layer security has been ensured by operating the proposed algorithm and the GoogleNet–BiLSTM hybrid network from a cloud server, which ensures the security of the proposed security system. The innovative optimization scheme makes it possible to strengthen cyber-physical security at only USD 4.29±0.29 per month.
Impact Prediction of Online Education During COVID-19 Using Machine Learning: A Case Study
(Springer Nature, 2023-01-25) Hossain, Sheikh Mufrad; Rahman, Md. Mahfujur; Barros, Alistair; Whaiduzzaman, Md.
The transition from traditional to online education is challenging and has many obstacles in various situations. Due to the Covid-19 situation, we use digital blended education from the traditional system. However, in some cases, it can harm our student’s academic performance. In this research, we aim to identify the factors that impact the student’s academic performance in online education. On the other hand, this study also finds the student Cumulative Grade Point Average (CGPA) fluctuation using machine learning classifiers. To achieve this, we survey to gather data perspective of Bangladesh private university, and this data allows us to analyze and classify using machine learning techniques such as Logistic Regression (LR), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Tree (DT), and Random Forest (RF). This study finds Random Forest (RF) outperforms the other state-of-art classifiers.
IoT Based Low-Cost Posture and Bluetooth Controlled Robot for Disabled and Virus Affected People
(Daffodil International University, 2022-06-15) Akhund, Tajim Md. Niamat Ullah; Hossain, Mosharof; Kubra, Khadizatul; Nurjahan; Barros, Alistair; Whaiduzzaman, Md.
IoT-based robots can help people to a great extent. This work results in a low-cost posture recognizer robot that can detect posture signs from a disabled or virus-affected person and move accordingly. The robot can take images with the Raspberry Pi camera and process the image to identify the posture with our designed algorithm. In addition, it can also take instructions via Bluetooth from smartphone apps. The robot can move 360 degrees depending on the input posture or Bluetooth. This system can assist disabled people who can move a few organs only. Moreover, this system can assist virus-affected persons as they can instruct the robot without touching it. Finally, the robot can collect data from a distant place and send it to a cloud server without spreading the virus.
IoT-Based Low-Cost Automated Irrigation System for Smart Farming
(Springer, 2022-05-13) Akhund, Tajim Md. Niamat Ullah; Newaz, Nishat Tasnim; Zaman, Zahura; Sultana, Atia; Barro, Alistair; Whaiduzzaman, Md.
In this research, we present a low-cost intelligent irrigation system for farming. Nowadays, farming is shifted to automated and remote monitoring and management systems integrated with Cloud, Fog, and IoT networks. Our developed prototype can measure water level, temperature, and humidity with a hardware sensor and micro-controller unit. We use different sensors to take different readings and values to decide to turn on or off the motor. We provide essential algorithm and flowchart to explain the system. Our IoT-application-based automated developed system makes an automated system for irrigation and provides notification via mobile SMS to inform us of the irrigation field’s details remotely.
MRIAD: A Pre-clinical Prevalence Study on Alzheimer’s Disease Prediction Through Machine Learning Classifiers
(Springer Nature, 2023-08-31) Loba, Jannatul; Mia, Md. Rajib; Mahmud, Imran; Mahi, Md. Julkar Nayeen; Whaiduzzaman, Md.; Ahmed, Kawsar
Alzheimer’s disease (AD) is a neurological illness that worsens with time. The aged population has expanded in recent years, as has the prevalence of geriatric illnesses. There is no cure, but early detection and proper treatment allow sufferers to live normal lives. Furthermore, people with this disease’s immune systems steadily degenerate, resulting in a wide range of severe disorders. Neuroimaging Data from magnetic resonance imaging (MRI) is utilized to identify and detect the disease as early as possible. The data is derived from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) collection of 266 people with 177 structural brain MRI imaging, DTI, and PET data for intermediate disease diagnosis. When neuropsychological and cognitive data are integrated, the study found that ML can aid in the identification of preclinical Alzheimer’s disease. Our primary objective is to develop a model that is reliable, simple, and rapid for diagnosing preclinical Alzheimer’s disease. According to our findings (MRIAD), the Logistic Regression (LR) model has the best accuracy and classification prediction of about 98%. The ML model is also developed in the paper. This article profoundly, describes the possibility to getting into Alzheimer’s disease (AD) information from the pre-clinical or non-preclinical trial datasets using Machine Learning Classifier (ML) approaches.
SafetyMed: A Novel IoMT Intrusion Detection System Using CNN-LSTM Hybridization
(MDPI Publications, 2023-08-22) Faruqui, Nuruzzaman; Yousuf, Mohammad Abu; Whaiduzzaman, Md.; Azad, AKM; Alyami, Salem A.; Liò, Pietro; Kabir, Muhammad Ashad; Moni, Mohammad Ali
The Internet of Medical Things (IoMT) has become an attractive playground to cybercriminals because of its market worth and rapid growth. These devices have limited computational capabilities, which ensure minimum power absorption. Moreover, the manufacturers use simplified architecture to offer a competitive price in the market. As a result, IoMTs cannot employ advanced security algorithms to defend against cyber-attacks. IoMT has become easy prey for cybercriminals due to its access to valuable data and the rapidly expanding market, as well as being comparatively easier to exploit.As a result, the intrusion rate in IoMT is experiencing a surge. This paper proposes a novel Intrusion Detection System (IDS), namely SafetyMed, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to defend against intrusion from sequential and grid data. SafetyMed is the first IDS that protects IoMT devices from malicious image data and sequential network traffic. This innovative IDS ensures an optimized detection rate by trade-off between False Positive Rate (FPR) and Detection Rate (DR). It detects intrusions with an average accuracy of 97.63% with average precision and recall, and has an F1-score of 98.47%, 97%, and 97.73%, respectively. In summary, SafetyMed has the potential to revolutionize many vulnerable sectors (e.g., medical) by ensuring maximum protection against IoMT intrusion.
Unmasking Banking Fraud: Unleashing the Power of Machine Learning and Explainable AI (XAI) on Imbalanced Data
(MDPI Publications, 2024-06-23) Nobel, S. M. Nuruzzaman; Sultana, Shirin; Singha, Sondip Poul; Chaki, Sudipto; Mahi, Md. Julkar Nayeen; Jan, Tony; Barros, Alistair; Whaiduzzaman, Md.
Recognizing fraudulent activity in the banking system is essential due to the significant risks involved. When fraudulent transactions are vastly outnumbered by non-fraudulent ones, dealing with imbalanced datasets can be difficult. This study aims to determine the best model for detecting fraud by comparing four commonly used machine learning algorithms: Support Vector Machine (SVM), XGBoost, Decision Tree, and Logistic Regression. Additionally, we utilized the Synthetic Minority Over-sampling Technique (SMOTE) to address the issue of class imbalance. The XGBoost Classifier proved to be the most successful model for fraud detection, with an accuracy of 99.88%. We utilized SHAP and LIME analyses to provide greater clarity into the decision-making process of the XGBoost model and improve overall comprehension. This research shows that the XGBoost Classifier is highly effective in detecting banking fraud on imbalanced datasets, with an impressive accuracy score. The interpretability of the XGBoost Classifier model was further enhanced by applying SHAP and LIME analysis, which shed light on the significant features that contribute to fraud detection. The insights and findings presented here are valuable contributions to the ongoing efforts aimed at developing effective fraud detection systems for the banking industry.