• Cognitively inspired feature extraction and speech recognition for automated hearing loss testing

      Nisar, S; Tariq, M; Adeel, A; Gogate, M; Hussain, A (Springer Science and Business Media LLC, 2019-02-13)
      © 2019, Springer Science+Business Media, LLC, part of Springer Nature. Hearing loss, a partial or total inability to hear, is one of the most commonly reported disabilities. A hearing test can be carried out by an audiologist to assess a patient’s auditory system. However, the procedure requires an appointment, which can result in delays and practitioner fees. In addition, there are often challenges associated with the unavailability of equipment and qualified practitioners, particularly in remote areas. This paper presents a novel idea that automatically identifies any hearing impairment based on a cognitively inspired feature extraction and speech recognition approach. The proposed system uses an adaptive filter bank with weighted Mel-frequency cepstral coefficients for feature extraction. The adaptive filter bank implementation is inspired by the principle of spectrum sensing in cognitive radio that is aware of its environment and adapts to statistical variations in the input stimuli by learning from the environment. Comparative performance evaluation demonstrates the potential of our automated hearing test method to achieve comparable results to the clinical ground truth, established by the expert audiologist’s tests. The overall absolute error of the proposed model when compared with the expert audiologist test is less than 4.9 dB and 4.4 dB for the pure tone and speech audiometry tests, respectively. The overall accuracy achieved is 96.67% with a hidden Markov model (HMM). The proposed method potentially offers a second opinion to audiologists, and serves as a cost-effective pre-screening test to predict hearing loss at an early stage. In future work, authors intend to explore the application of advanced deep learning and optimization approaches to further enhance the performance of the automated testing prototype considering imperfect datasets with real-world background noise.
    • Comprehensive review of cybercrime detection techniques

      Al-Khater, Wadha Abdullah; Al-Ma’adeed, Somaya; Ahmed, Abdulghani Ali; Al-Shakarchi, Ali; Khan, Muhammad Khurram (IEEE, 2020-07-22)
      Cybercrimes describe cases of indictable offences and misdemeanours in which computer or any communication tools are involved as targets, commission instruments, incidental to, or that cases are associated with the prevalence of computer technology. Common forms of cybercrimes could be child pornography, cyberstalking, identity theft, cyber laundering, credit card theft, cyber terrorism, drug sale, data leakage, sexually explicit content, phishing and other cyber hacking. These kinds of cybercrimes are mostly leading to breaching users’ privacy, security violation, business loss, financial fraud, or damage in public as well as government properties. Hence, this paper intensively reviews cybercrime detection and prevention methods. It first explores the different types of cybercrimes then discusses their threats against privacy and security in computer systems. It also describes the strategies that cybercriminals might utilize in committing these crimes against individuals, organizations, and societies. The paper then reviews the existing techniques of cybercrime detection and prevention. It objectively discusses the strengths and critically analyses the vulnerabilities of each technique. As a future study, the paper provides recommendations for the development of cybercrime detection model in which it is capable to effectively detect cybercrime in comparison to the existing techniques.
    • On textual analysis and machine learning for cyberstalking detection

      Frommholz, Ingo; al-Khateeb, Haider M.; Potthast, Martin; Ghasem, Zinnar; Shukla, Mitul; Short, Emma (Springer, 2016-06-01)
      Cyber security has become a major concern for users and businesses alike. Cyberstalking and harassment have been identified as a growing anti-social problem. Besides detecting cyberstalking and harassment, there is the need to gather digital evidence, often by the victim. To this end, we provide an overview of and discuss relevant technological means, in particular coming from text analytics as well as machine learning, that are capable to address the above challenges. We present a framework for the detection of text-based cyberstalking and the role and challenges of some core techniques such as author identification, text classification and personalisation. We then discuss PAN, a network and evaluation initiative that focusses on digital text forensics, in particular author identification.
    • Optimising driver profiling through behaviour modelling of in-car sensor and global positioning system data

      Ahmadi-Assalemi, Gabriela; Al-Khateeb, Haider; Maple, Carsten; Epiphaniou, Gregory; Hammoudeh, Mohammad; Jahankhani, Hamid; Pillai, Prashant (Elsevier, 2021-03-03)
      Connected cars have a massive impact on the automotive sector, and whilst this catalyst and disruptor technology introduce threats, it brings opportunities to address existing vehicle-related crimes such as carjacking. Connected cars are fitted with sensors, and capable of sophisticated computational processing which can be used to model and differentiate drivers as means of layered security. We generate a dataset collecting 14 hours of driving in the city of London. The route was 8.1 miles long and included various road conditions such as roundabouts, traffic lights, and several speed zones. We identify and rank the features from the driving segments, classify our sample using Random Forest, and optimise the learning-based model with 98.84% accuracy (95% confidence) given a small 10 seconds driving window size. Differences in driving patterns were uncovered to distinguish between female and male drivers especially through variations in longitudinal acceleration, driving speed, torque and revolutions per minute.
    • SPY-BOT: machine learning-enabled post filtering for social network-integrated industrial internet of things

      Rahman, Md Arafatur; Zaman, Nafees; Asyhari, A Taufiq; Sadat, SM Nazmus; Pillai, Prashant; Arshah, Ruzaini Abdullah (Elsevier, 2021-07-09)
      A far-reaching expansion of advanced information technology enables ease and seamless communications over online social networks, which have been a de facto premium correspondents in the current cyber world. The ever-growing social network data has gained attention in recent years and can be handy for industrial revolution 4.0. With the integration of social networks with the Internet of Things being noticed in different industries to enhance human involvement and increase their productivity, security in such networks is increasingly alarming. Vulnerabilities can be characterized in the form of privacy invasion, leading to hazardous contents, which can be detrimental to social media actors and in turn impact the processes of the overall Social Network-Integrated Industrial Internet of Things (SN-IIoT) ecosystem. Despite this prevalence, the current platforms do not have any significant level of functionality to capture, process, and reveal unhealthy content among the social media actors. To address those challenges by detecting hazardous contents and create a stable social internet environment within IIoT, a statistical learning-enabled trustworthy analytic tool for human behaviors has been developed in this paper. More specifically, this paper proposes a machine learning (ML)-enabled scheme SPY-BOT, which incorporates a hybrid data extraction algorithm to perform post-filtering that arbitrates the users’ behavior polarity. The scheme creates class labels based on the featured keywords from the decision user and classifies suspicious contacts through the aid of ML. The results suggest the potential of the proposed approach to classify the users’ behavior in SN-IIoT.