Papers by Muhammad Nomani Kabir
International Journal of Automotive and Mechanical Engineering, Mar 30, 2017
The concept of Internet of Things (IoT) can be utilised in vehicles, since the number of sensor n... more The concept of Internet of Things (IoT) can be utilised in vehicles, since the number of sensor nodes in vehicles is rising tremendously because of the uplifting demand of applications for security, safety and convenience. In order to establish the communication among these nodes inside a vehicle, a controller area network with wired architecture provides a prominent solution. However, this solution is not flexible because of the architectural complexity and the demand for a large number of sensors inside the vehicle; hence wired architectures are replaced by wireless ones. Moreover, scalability will be an important issue while introducing the IoT concept in Intra-Vehicular Wireless Sensor Networks (IVWSNs). In this paper, a comprehensive performance investigation on the IoT enabled IVWSNs (IoT-IVWSNs) to be carried out in order to address this issue. The overview of the IoT-IVWSNs with a comparative study of the existing technologies and the design challenges for such network are provided. The link design between an enddevice and the control unit is analysed, and the performance of the network has been investigated and some open research issues are addressed. It reveals that the delay in packet transmission increases due to higher traffic loads and the number of end-devices. This result demonstrates that the existing MAC protocol works well for a small network (i.e., a network with a maximum number of 50 nodes) but is not suitable for a large network (i.e., a network with more than 50 nodes). The outcome of this research helps to design a smart car system.
Studies in computational intelligence, 2022
Artificial Intelligence (AI) is one of the disruptive technologies that is shaping the future. It... more Artificial Intelligence (AI) is one of the disruptive technologies that is shaping the future. It has growing applications for data-driven decisions in major smart city solutions, including transportation, education, healthcare, public governance, and power systems. At the same time, it is gaining popularity in protecting critical cyber infrastructure from cyber threats, attacks, damages, or unauthorized access. However, one of the significant issues of those traditional AI technologies (e.g., deep learning) is that the rapid progress in complexity and sophistication propelled and turned out to be uninterpretable black boxes. On many occasions, it is very challenging to understand the decision and bias to control and trust systems' unexpected or seemingly unpredictable outputs. It is acknowledged that the loss of control over interpretability of decision-making becomes a critical issue for many data-driven automated applications. But how may it affect the system's security and trustworthiness? This chapter conducts a comprehensive study of machine learning applications in cybersecurity to indicate the need for explainability to address this question. While doing that, this chapter first discusses the black-box problems of AI technologies for Cybersecurity applications in smart city-based solutions. Later, considering the new technological paradigm, Explainable Artificial Intelligence (XAI), this chapter discusses the transition from black-box to white-box. This chapter also discusses the transition requirements concerning the interpretability, transparency, understandability, and Explainability of AI-based technologies in applying different autonomous systems in smart cities. Finally, it has presented some commercial XAI platforms that offer explainability over traditional AI technologies before presenting future challenges and opportunities.
2017 3rd International Conference on Electrical Information and Communication Technology (EICT)
Optimization is the selection of a best set of parameters from available alternative sets. Global... more Optimization is the selection of a best set of parameters from available alternative sets. Global optimization is the task of finding the absolutely best set of parameters. In this paper, we present an adaptive flower pollination algorithm for solving an optimization problem, i.e., minimization of software testing redundancy. In software testing, test engineers often generate a set of test cases to validate against the user requirements to avoid deficiency of the software. A large number of lines of codes cause potential redundancies in software testing. In order to tackle the issue of redundancy, global optimization algorithms are used to systematically minimize the test suite for software testing. We tested the adaptive flower pollination algorithm on a number of experiments in software tests. The results were compared with existing results of some existing algorithms to demonstrate the strength of our algorithm. Comparison shows that our algorithm performs slightly better than the existing algorithms and thus, the proposed algorithm can potentially be used by researchers and test engineers to obtain optimal test suite requiring the minimum time for software testing.
2020 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)
Computational method can be used for investigation of the protein sequences for developing a vacc... more Computational method can be used for investigation of the protein sequences for developing a vaccine against infections. In this present study, a protein derived from non-O157 Verotoxin-producing E. coli (VTEC) was identified as a potential vaccine candidate that can be used to evaluate their immunogenicity and protective capability against VTEC infections. Identification of potential B-cell epitopes for promising vaccine was carried out by evaluating the protein derived from non-O157 VTEC with the methods of beta turns, hydropathicity, surface accessibility and antigenicity. The methods were implemented in MATLAB. Our test results demonstrated that the VTEC-derived protein has plausible characteristics which provide significant insights for further investigations and will assist in finding potential drug targets/vaccine candidates.
2020 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), 2020
Mechanical Ventilation is used to support the respiratory system malfunction by assisting recover... more Mechanical Ventilation is used to support the respiratory system malfunction by assisting recovery breathing process which could result from diseases and viruses such as pneumonia and COVID-19. Mathematical models are used to study and simulate the respiratory system supported by mechanical ventilation using different modes such as volumecontrolled ventilation (VCV). In this research, a single compartment lung model ventilated by VCV is developed during real time mechanical ventilation using pressure signal. This mathematical model describes the lung volume and compliance correctly considering positive end expiration pressure (PEEP) value. The model is implemented using LabVIEW tools and can be used to monitor the volume, flow and compliance as outputs of the model. Two experiments are carried out on the proposed lung model at three input scenarios of volume (400, 500 and 600 ml) for each experiment considering a PEEP value. To validate the model, an artificial lung connected to a VCV with the same scenarios is used. Validation check is conducted by comparing the outputs of the lung model to that of the artificial lung. The experimental results showed that the measured lung model outputs with negative feedback are the same for pressure and flow as the outputs without negative feedback, whereas the measured volume is comparatively lower for negative feedback. Average percent error in the experiment with negative feedback (5.14%) is smaller compared to the experiment without negative feedback (9.28%). Furthermore, the average error of the calculated compliance decreases from 16% (without negative feedback) to 2% (with negative feedback). The obtained results of the proposed method showed good performance and acceptable accuracy. Thus, the model facilitates the clinicians and practitioners as a training tool to learn real-time mechanical ventilation functionalities.
IEEE Systems Journal, 2021
A combination of mobile and cloud computing delivers many advantages such as mobility, resources,... more A combination of mobile and cloud computing delivers many advantages such as mobility, resources, and accessibility through seamless data transmission via the Internet anywhere at any time. However, data transmission through vulnerable channels poses security threats such as man-in-the-middle, playback, impersonation, and asynchronization attacks. To address these threats, we define an explicit security model that can precisely measure the practical capabilities of an adversary. A systematic methodology consisting of 16 evaluation criteria is used for comparative evaluation, thereby leading other approaches to be evaluated through a common scale. Finally, we propose a dynamic reciprocal authentication protocol to secure data transmission in mobile cloud computing. In particular, our proposed protocol develops a secure reciprocal authentication method, which is free of Diffie-Hellman limitations, and has immunity against basic or sophisticated known attacks. The protocol utilizes multifactor authentication of usernames, passwords, and a onetime password. The one-time password is automatically generated and regularly updated for every connection. The proposed protocol is implemented and tested using Java to demonstrate its efficiency in authenticating communications and securing data transmitted in the mobile cloud computing environment. Results of the evaluation process indicate that compared with the existing works, the proposed protocol possesses obvious capabilities in security and in communication and computation costs.
2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), 2019
Web extension is a software that can be installed on a web browser. A web-extension link is displ... more Web extension is a software that can be installed on a web browser. A web-extension link is displayed as an icon on the toolbar of the browser. Based on browsing activity, the extension works automatically or by clicking the extension icon depending on the functionalities made in the extension software. In this work, we developed a web extension on Google Chrome browser to verify online texts by simply clicking on an extension button. Upon clicking the button, the underlying algorithm in the extension software retrieves the texts from the current web-page being displayed. Verification and authentication of texts are performed by comparing the retrieved texts with text database. According to the comparison, texts are highlighted in colors. We consider authentication of Arabic Hadith texts for a case study. The authentic Hadith texts are highlighted by green color; authentic texts with partial diacritics, by yellow; and unauthentic texts, by red. This technique can also be used to authenticate laws, constitutions and Government documents in any language.
Intelligent Computing & Optimization, 2018
In the field of medical science, one of the major recent researches is the diagnosis of the abnor... more In the field of medical science, one of the major recent researches is the diagnosis of the abnormalities in brain. Electroencephalogram (EEG) is a record of neuro signals that occur due the different electrical activities in the brain. These signals can be captured and processed to get the useful information that can be used in early detection of some mental and brain diseases. Suitable analysis is essential for EEG to differentiate between normal and abnormal signals in order to detect epilepsy which is one of the most common neurological disorders. Epilepsy is a recurrent seizure disorder caused by abnormal electrical discharges from the brain cells, often in the cerebral cortex. This research focuses on the usefulness of EGG signal in detecting seizure activities in brainwaves. Artificial Neural Network (ANN) is used to train the data set. Then tests are conducted on the test data of EEG signals to identify normal (nonseizure) and abnormal (seizure) states of the brain. Finally, accuracy is computed to evaluate the performance of ANN. The experiments are carried out on CHB-MIT Scalp EEG Database. The experiments show plausible results from the proposed approach in terms of accuracy.
In the field of medical science, one of the major recent researches is the diagnosis of the abnor... more In the field of medical science, one of the major recent researches is the diagnosis of the abnormalities in brain. Electroencephalogram (EEG) signal is a neuro signal which is generated due the different electrical activities in the brain. These signals can be captured and processed to get the useful information that can be used in early detection of some mental and brain diseases. Suitable analysis is essential for EEG to differentiate between normal and abnormal signals in order to detect epilepsy which is one of the most common neurological disorders. Epilepsy is a recurrent seizure disorder caused by abnormal electrical discharges from the brain cells, often in the cerebral cortex. This research focuses on the usefulness of EGG signal in detecting seizure activities in brainwaves. Feature extraction of EEG signals is core issue to carry out brain analysis. In this research, feature extraction has been performed using wavelet transform. These features have been applied to Neural...
Use of Internet of Things (IoT) with modern wireless network is a trend of the emerging technolog... more Use of Internet of Things (IoT) with modern wireless network is a trend of the emerging technologies for different systems which can be deployed in various kinds of environment to monitor, communicate with or control the associated elements in the system. The activities e.g., monitoring and communication by IoT can play an important role to design an Intelligent Transportation System (ITS). In this paper, we assess the suitability of IoT enabled wireless technology to be used for ITS. We performed some comparative study to find the best wireless technology that provides reliability, low cost, less power consumption and less data latency for next generation ITS.This technology will reduce energy consumption of the deployed IoT devices as well as ensure safety, efficiency and convenient for transportation systems.
Data protection laws
Authentication Technologies for Cloud Computing, IoT and Big Data, 2019
Data protection, data privacy, and information privacy are all terms defined as the process of pr... more Data protection, data privacy, and information privacy are all terms defined as the process of protecting important data/information from corruption, scam, fraud, loss, or compromise. This includes the relationship between the data collection and technology, the public perception and expectation of privacy, and the political as well as legal roots surrounding that data. Therefore, data protection laws aim to provide a balance between the individual’s privacy rights and the proper use of data.
2019 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), 2019
Information security for connected devices with network system is under threat due to fraudulent ... more Information security for connected devices with network system is under threat due to fraudulent activities, denial-of-service (DoS), and malware. Phishing attacks are a major fraud activity which can be controlled by human factors. This research is aimed to increase the information security awareness of the vocational students in Malaysia. An enhanced knowledge-attitude-behavior model has been developed to increase the awareness level on phishing attacks. In this model, the existing knowledge of the sample students is measured and repeated after educational treatment. The model hypothesis is validated by the collected data on the students and the model output is thoroughly analyzed. Thus, it demonstrates that the proposed model is an enhanced model in strengthening the information security knowledge and awareness of the students.
2020 16th IEEE International Colloquium on Signal Processing & Its Applications (CSPA), 2020
Intrusion detection system (IDS) is one of the important parts in security domains of the present... more Intrusion detection system (IDS) is one of the important parts in security domains of the present time. Distributed Denial of Service (DDoS) detection involves complex process which reduces the overall performance of the system, and consequently, it may incur inefficiency or failure to the network. In this paper, the attacks database is split into a set of groups by classifying the attack types in terms of the most dominant features that define the profile of each attack along with the sensitive network traffic features. Decision Tree, AdaBoost, Random Forest, K-Nearest Neighbors and Naive Bayes are then used to classify each attack according to their profile features. DDoS attack was considered for all chosen classifiers. It is found that the average classification accuracy for the above-mentioned algorithms is 95.31%, 95.68%, 95.69%, 92.61% and 83.11%, respectively, providing plausible results when comparing to other existing models.
IEEE Access, 2020
Accidental falls are a major source of loss of autonomy, deaths, and injuries among the elderly. ... more Accidental falls are a major source of loss of autonomy, deaths, and injuries among the elderly. Accidental falls also have a remarkable impact on the costs of national health systems. Thus, extensive research and development of fall detection and rescue systems are a necessity. Technologies related to fall detection should be reliable and effective to ensure a proper response. This article provides a comprehensive review on state-of-the-art fall detection technologies considering the most powerful deep learning methodologies. We reviewed the most recent and effective deep learning methods for fall detection and categorized them into three categories: Convolutional Neural Network (CNN) based systems, Long Short-Term Memory (LSTM) based systems, and Auto-encoder based systems. Among the reviewed systems, three dimensional (3D) CNN, CNN with 10-fold cross-validation, LSTM with CNN based systems performed the best in terms of accuracy, sensitivity, specificity, etc. The reviewed systems were compared based on their working principles, used deep learning methods, used datasets, performance metrics, etc. This review is aimed at presenting a summary and comparison of existing state-of-the-art deep learning based fall detection systems to facilitate future development in this field.
Recent Trends in Information and Communication Technology, 2017
Blockchain technology is widely known because it is the underlying technology used by the bitcoin... more Blockchain technology is widely known because it is the underlying technology used by the bitcoin. It became more popular because it also can be used as backbone for various applications in finance, media, security and others. One of the main concerns for this technology is how secure the information that the users distributed over the network. This paper studies and highlights the important security issues concerned and discusses the solutions that proposed by the researchers and theoretical solution proposed to address some of the issues. However, this approach needs to be investigated further if it is to be implemented later in the near future. This paper can give direction for future researchers who are interested of this area.
SN Computer Science, 2020
Early detection of disease has become a crucial problem due to rapid population growth in medical... more Early detection of disease has become a crucial problem due to rapid population growth in medical research in recent times. With the rapid population growth, the risk of death incurred by breast cancer is rising exponentially. Breast cancer is the second most severe cancer among all of the cancers already unveiled. An automatic disease detection system aids medical staffs in disease diagnosis and offers reliable, effective, and rapid response as well as decreases the risk of death. In this paper, we compare five supervised machine learning techniques named support vector machine (SVM), K-nearest neighbors, random forests, artificial neural networks (ANNs) and logistic regression. The Wisconsin Breast Cancer dataset is obtained from a prominent machine learning database named UCI machine learning database. The performance of the study is measured with respect to accuracy, sensitivity, specificity, precision, negative predictive value, false-negative rate, false-positive rate, F1 score, and Matthews Correlation Coefficient. Additionally, these techniques were appraised on precision-recall area under curve and receiver operating characteristic curve. The results reveal that the ANNs obtained the highest accuracy, precision, and F1 score of 98.57%, 97.82%, and 0.9890, respectively, whereas 97.14%, 95.65%, and 0.9777 accuracy, precision, and F1 score are obtained by SVM, respectively.
Revue d'Intelligence Artificielle, 2019
Eyes and other visionary organs are essential to human physiology, due to their ability to receiv... more Eyes and other visionary organs are essential to human physiology, due to their ability to receive and process subtle details to the brain. However, some individuals are unable to visually perceive things in the surroundings. These visually impaired people face various hinderances in the daily life, and cannot navigate themselves without guidance. To help them navigate around the surroundings, this paper develops a hybrid system for the detection of staircase and the ground, using a pre-trained model and an ultrasonic sensor. The proposed system consists of an ultrasonic sensor, an R-GBD camera, a raspberry pi and a buzzer fixed on a walking stick. During the detection process, staircase images are captured by an RGB-D camera and then compared with pre-trained template images. Finally, our system was applied to detect different staircase images under various conditions (e.g. dark and noise), and found to achieve an average accuracy of 98.73%. This research provides an effective aid to the visually impaired.
International Journal of Engineering & Technology, 2018
Background and objective: With the widespread internet availability, now-a-days Hadith texts whic... more Background and objective: With the widespread internet availability, now-a-days Hadith texts which are essential sources of Islamic knowledge appear on many websites. In this paper, a client-based web-extension program that can authenticate online Hadith texts from Sahih Bukhari and Sahih Muslim is presented.Materials and Methods: First, the program reads the content of the specific browsed website and identifies Arabic language only. Then this Arabic text is screened to verify whether this contains any Hadith text by comparing with the authentic source. If complete match occurs in comparison, then the text is marked with green color proving the text as authentic. If some words/letters are missing, then the text will be marked with red color indicating that the Hadith is unauthentic and requires to be verified.Results: Using this web-extension, the authenticity of Hadith from Sahih Bukhari and Sahih Muslim can be verified simply by clicking a button of the web-extension. If the Hadi...
IEEE Access, 2019
Watermarking technique is a method to protect ownership of digital multimedia. Most existing wate... more Watermarking technique is a method to protect ownership of digital multimedia. Most existing watermarking techniques achieve a good level of imperceptibility and robustness. The challenges to achieve higher invisibility and resistance with lower computational time motivate researchers to work on new watermarking schemes. Robustness against noise attacks and JPEG2000 compression needs to be improved to acquire a better resistance capability of the watermark. In this paper, we present a block-based Tchebichef watermarking technique for protecting copyrights. In this technique, the host image is first divided into non-overlapping blocks and Tchebichef moments are calculated for each block. The watermarks are embedded into the blocks with lower visual entropies. The watermark image is scrambled by Arnold transform before embedding into the Tchebichef moments of the selected image blocks. The proposed watermarking scheme was tested under noise additions, filtering, cropping and compressing attacks. Our scheme was verified and compared to the existing watermarking techniques under image geometric and processing attacks. Furthermore, the proposed scheme demonstrated a superior performance in robustness under noise attacks and JPEG2000. INDEX TERMS Watermarking, copyright protection, embedding algorithm, tchebichef moments, visual entropies.
Advanced Science Letters, 2018
This paper presents an analysis of awareness level on phishing attack among Malaysians. Phishing ... more This paper presents an analysis of awareness level on phishing attack among Malaysians. Phishing and fraudster activities have been important issues in Malaysia. The methodology involves the questionnaires which are distributed and answers were collected and recorded as random samples. Next, statistical data were analyzed and categorized into different parts for enhanced knowledge and experience in data exploration. The test results related to hypothesis tests are provided. Using this analysis, influence of source problem and weakness of victims are revealed in order to mitigate the issue. Based on this, recommendations have been provided to encounter the issues.
Uploads
Papers by Muhammad Nomani Kabir