Now showing items 1-20 of 93

    • Deep Learning based Human Detection in Privacy-Preserved Surveillance Videos

      Yousuf, Muhammad Jehanzaib; Kanwal, Nadia; Ansari, Mohammad Samar; Asghar, Mamoona; Lee, Brian; Technological University of the Shannon; Keele University; University of Chester; University of Galway
      Visual surveillance systems have been improving rapidly over the recent past, becoming more capable and pervasive with incorporation of artificial intelligence. At the same time such surveillance systems are exposing the public to new privacy and security threats. There have been an increasing number of reports of blatant abuse of surveillance technologies. To counteract this, data privacy regulations (e.g. GDPR in Europe) have provided guidelines for data collection and data processing. However, there is still a need for a private and secure method of model training for advanced machine learning and deep learning algorithms. To this end, in this paper we propose a privacy-preserved method for visual surveillance. We first develop a dataset of privacy preserved videos. The data in these videos is masked using Gaussian Mixture Model (GMM) and selective encryption. We then train high-performance object detection models on the generated dataset. The proposed method utilizes state-of-art object detection deep learning models (viz. YOLOv4 and YOLOv5) to perform human/object detection in masked videos. The results are encouraging, and are pointers to the viability of the use of modern day deep learning models for object detection in privacy-preserved videos.
    • Local-Partial Signal Combining Schemes for Cell-Free Large-Scale MU-MIMO Systems with Limited Fronthaul Capacity and Spatial Correlation Channels

      Alammari, Amr A.; Sharique, Mohd; Moinuddin, Athar Ali; Ansari, Mohammad Samar; Aligarh Muslim University; University of Chester (MDPI, 2022-09-01)
      Cell-free large-scale multi-user MIMO is a promising technology for the 5G-and-beyond mobile communication networks. Scalable signal processing is the key challenge in achieving the benefits of cell-free systems. This study examines a distributed approach for cell-free deployment with user-centric configuration and finite fronthaul capacity. Moreover, the impact of scaling the pilot length, the number of access points (APs), and the number of antennas per AP on the achievable average spectral efficiency are investigated. Using the dynamic cooperative clustering (DCC) technique and large-scale fading decoding process, we derive an approximation of the signal-tointerference-plus-noise ratio in the criteria of two local combining schemes: Local-Partial Regularized Zero Forcing (RZF) and Local Maximum Ratio (MR). The results indicate that distributed approaches in the cell-free system have the advantage of decreasing the fronthaul signaling and the computing complexity. The results also show that the Local-Partial RZF provides the highest average spectral efficiency among all the distributed combining schemes because the computational complexity of the Local-Partial RZF is independent of the UTs. Therefore, it does not grow as the number of user terminals (UTs) increases.
    • AFOM: Advanced Flow of Motion Detection Algorithm for Dynamic Camera Videos

      Aribilola, Ifeoluwapo; Asghar, Mamoona; Kanwal, Nadia; Ansari, Mohammad Samar; Lee, Brian; Technological University of the Shannon; National University of Ireland; University of Keele; University of Chester (IEEE, 2022-07-19)
      The surveillance videos taken from dynamic cam-eras are susceptible to multiple security threats like replay attacks, man-in-the-middle attacks, pixel correlation attacks etc. Using unsupervised learning, it is a challenge to detect objects in such surveillance videos, as fixed objects may appear to be in motion alongside the actual moving objects. But despite this challenge, the unsupervised learning techniques are efficient as they save object labelling and model training time, which is usually a case with supervised learning models. This paper proposes an effective computer vision-based object identification algorithm that can detect and separate stationary objects from moving objects in such videos. The proposed Advanced Flow Of Motion (AFOM) algorithm takes advantage of motion estimation between two consecutive frames and induces the estimated motion back to the frame to provide an improved detection on the dynamic camera videos. The comparative analysis demonstrates that the proposed AFOM outperforms a traditional dense optical flow (DOF) algorithm with an average increased difference of 56 % in accuracy, 61 % in precision, and 73 % in pixel space ratio (PSR), and with minimal higher object detection timing.
    • A single-layer asymmetric RNN with low hardware complexity for solving linear equations

      Ansari, Mohammad Samar; University of Chester (Elsevier, 2022-01-25)
      A single layer neural network for the solution of linear equations is presented. The proposed circuit is based on the standard Hopfield model albeit with the added flexibility that the interconnection weight matrix need not be symmetric. This results in an asymmetric Hopfield neural network capable of solving linear equations. PSPICE simulation results are given which verify the theoretical predictions. A simple technique to incorporate re-configurability into the circuit for setting the different weights of the interconnection is also included. Experimental results for circuits set up to solve small problems further confirm the operation of the proposed circuit.
    • FireNet-v2: Improved Lightweight Fire Detection Model for Real-Time IoT Applications

      Shees, Anwer; Ansari, Mohammad Samar; Varshney, Akshay; Asghar, Mamoona; Kanwal, Nadia; Aligarh Muslim University; University of Chester; Adobe India; University of Galway; Keele University
      Fire hazards cause huge ecological, social and economical losses in day to day life. Due to the rapid increase in the prevalence of fire accidents, it has become vital to equip the assets with fire prevention systems. There have been numerous researches to build a fire detection model in order to avert such accidents, with recent approaches leveraging the enormous improvements in computer vision deep learning models. However, most deep learning models have to compromise with their performance and accurate detection to maintain a reasonable inference time and parameter count. In this paper, we present a customized lightweight convolution neural network for early detection of fire. By virtue of low parameter count, the proposed model is amenable to embedded applications in real-time fire monitoring equipment, and even upcoming fire monitoring approaches such as unmanned aerial vehicles (drones). The fire detection results show marked improvement over the predecessor low-parameter-count models, while further reducing the number of trainable parameters. The overall accuracy of FireNet-v2, which has only 318,460 parameters, was found to be 98.43% when tested over Foggia's dataset.
    • Deep Learning based Wireless Channel Prediction: 5G Scenario

      Varshney, Rajat; Gangal, Chirag; Sharique, Mohd; Ansari, Mohammad Samar; Aligarh Muslim University; Aligarh Muslim University; Aligarh Muslim University; University of Chester
      In the area of wireless communication, channel estimation is a challenging problem due to the need for real-time implementation as well as system dependence on the estimation accuracy. This work presents a Long-Short Term Memory (LSTM) based deep learning (DL) approach for the prediction of channel response in real-time and real-world non-stationary channels. The model uses the pre-defined history of channel impulse response (CIR) data along with two other features viz. transmitter-receiver update distance and root-mean-square delay spread values which are also changing in time with the channel impulse response. The objective is to obtain an approximate estimate of CIRs using prediction through the DL model as compared to conventional methods. For training the model, a sample dataset is generated through the open-source channel simulation software NYUSIM which realizes samples of CIRs for measurement-based channel models based on various multipath channel parameters. From the model test results, it is found that the proposed DL approach provides a viable lightweight solution for channel prediction in wireless communication.
    • Watchdog Monitoring for Detecting and Handling of Control Flow Hijack on RISC-V-based Binaries

      Oyinloye, Toyosi; Speakman, Lee; Eze, Thaddeus; O'Mahony, Lucas; University of Chester; University of Salford (SAI Organization, 2022-08-31)
      Abstract—Control flow hijacking has been a major challenge in software security. Several means of protections have been developed but insecurities persist. This is because existing protections have sometimes been circumvented while some resilient protections do not cover all applications. Studies have revealed that a holistic way of tackling software insecurity could involve watchdog monitoring and detection via Control Flow Integrity (CFI). The CFI concept has shown a good measure of reliability to mitigate control flow hijacking. However, sophisticated attack techniques in the form of Return Oriented Programming (ROP) have persisted. A flexible protection is desirable, which not only covers as many architecture structures as possible but also mitigates known resilient attacks like ROP. The solution proffered here is a hybrid of CFI and watchdog timing via inter-process signaling (IP-CFI). It is a software-based protection that involves recompilation of the target program. The implementation here is on vulnerable RISC-V-based process but is flexible and could be adapted on other architectures. We present a proof of concept in IP-CFI which when applied to a vulnerable program, ROP is mitigated. The target program incurs a run-time overhead of 1.5%. The code is available.
    • An Immersive Haptic-enabled Training Simulation for Paramedics

      Gutiérrez-Fernández, Alexis; Hogan, Chloe; Rees, Nigel; Fernández-Llamas, Camino; John, Nigel W.; University of León; Welsh Ambulance Service NHS Trust; University of Chester
      This paper describes the integration of haptics support into a virtual reality training simulation aimed at skills retention for paramedics. We focus on a chest decompression, a life-saving invasive procedure used for trauma-associated cardiopulmonary resuscitation (and other causes) that every emergency physician needs to master. It is not regularly performed by a paramedic, however, and therefore skills maintenance is a challenge. In our simulation, a virtual Russell PneumoFix-8 device is used to carry out the procedure and it is controlled with the 3D Systems Touch grounded force feedback device. We describe how this device has been integrated into an immersive virtual environment so that it or any other tool can be used at any location in the scene. Quantitative data has been obtained from an evaluation exercise carried out with 21 paramedics. The majority of these participants reported a good feeling of presence, according to the Spatial Presence Experience Scale. They indicated strongly that the use of haptic-enabled simulators that include the kind of interaction techniques implemented in our simulator would be beneficial for training and skills retention. The realism of using the simulator at a 1 to 1 scale was also highly scored. A System Usability Scale was also calculated and the results show that the simulator is close to an acceptable standard for usability but more work is needed. We will address this in future work.
    • CAP: Patching the Human Vulnerability

      Eze, Thaddeus; Hawker, Neil; University of Chester (2022-07-22)
      Cyber threats to organisations across all industries are increasing in both volume and complexity, leading to significant, and sometimes severe, conse-quences. The common weakest link in organisations security is the human vulnerability. The sudden popularity of remote-working due to the Covid-19 pandemic opened organisations and their employees up to more risks, partic-ularly as many workers believe that they are more distracted when at home. Existing cyber training using a ‘one-size-fits-all’ approach has been proven inefficient/ineffective and the need for a more fit-for-purpose training is re-quired. When it comes to cyber training, we know that there is no single-training-fits-all solution – people have different technical skills, different prior knowledge and experience, are in different roles, exposed to different security risks, and require knowledge that is relevant to what they do. This study makes a case for tailored role-based cybersecurity training suitable for awareness within organisations across multiple industries. The study ex-plores the strengths and weaknesses of existing cyber training and literature to make recommendations on efficient awareness and training programme strategies. The study carries out knowledge and task analysis of job roles to create profiles of skills and knowledge they require. These are grouped by topic and level to form scenario-based multiple-choice questions which are mapped to create a Cyber Awareness Platform (CAP). A CAP prototype is in-troduced as a flexible web-based system allowing users to assess their prior knowledge and skills personalised to their role. Knowledge gaps and training needs are identified, and recommendations are tailored to the individual. Ini-tial analysis of CAP shows promising results, indicating that such role-sensitive solution would be highly beneficial to users. This offers further de-velopment opportunities in producing an all-in-one cyber assessment and training platform.
    • Forensic Trails Obfuscation and Preservation via Hard Drive Firmware

      Underhill, Paul; Oyinloye, Toyosi; Eze, Thaddeus; Speakman, Lee; University of Chester; University of Salford (Academic Conferences International, 2022-06-08)
      The hard disk drive stores data the user is creating, modifying, and deleting while a firmware facilitates communication between the drive and the operating system. The firmware tells the device and machine how to communicate with each other and will share useful information such as, disk size and information on any bad sectors. Current research shows that exploits exist that can manipulate these outputs. As an attacker, you can change the size of the disk displayed to the operating system to hide data in, likewise by marking an area of the disk as bad. Users may not be aware of these changes as the operating system will accept the readings from the firmware. However, although the data is not reachable via the operating system this paper looks at the traceability of manipulated data using data recovery software FTK Imager, Recuva, EaseUS and FEX Imager. This report examines the use of malicious techniques to thwart digital forensic procedures by manipulating the firmware. It is shown how this is possible and current forensic techniques or software does not easily detect a change within the firmware. However, with the use of various forensic tools, obfuscated trails are detectable. This report follows a black box testing methodology to show the validation of forensic tools or software against anti-forensic techniques. The analysis of the results showed that most tools can find the firmware changes, however, it requires an analyst to spot the subtle differences between standard and manipulated devices. The use of multiple software tools can help an analyst spot the inconsistencies.
    • Visualization for Epidemiological Modelling: Challenges, Solutions, Reflections & Recommendations

      Dykes, Jason; Abdul-Rahman, Alfie; Archambault, Daniel; Bach, Benjamin; Borgo, Rita; Chen, Min; Enright, Jessica; Fang, Hui; Firat, Elif E.; Freeman, Euan; et al. (The Royal Society, 2022-08-15)
      We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs – a series of ideas, approaches and methods taken from existing visualization research and practice – deployed and developed to support modelling of the COVID-19 pandemic. Structured independent commentary on these efforts is synthesized through iterative reflection to develop: evidence of the effectiveness and value of visualization in this context; open problems upon which the research communities may focus; guidance for future activity of this type; and recommendations to safeguard the achievements and promote, advance, secure and prepare for future collaborations of this kind. In describing and comparing a series of related projects that were undertaken in unprecedented conditions, our hope is that this unique report, and its rich interactive supplementary materials, will guide the scientific community in embracing visualization in its observation, analysis and modelling of data as well as in disseminating findings. Equally we hope to encourage the visualization community to engage with impactful science in addressing its emerging data challenges. If we are successful, this showcase of activity may stimulate mutually beneficial engagement between communities with complementary expertise to address problems of significance in epidemiology and beyond. https://ramp-vis.github.io/RAMPVIS-PhilTransA-Supplement/
    • A survey of modern deep learning based object detection models

      Zaidi, Syed Sahil Abbas; Ansari, Mohammad Samar; Aslam, Asra; Kanwal, Nadia; Asghar, Mamoona; Lee, Brian; Technological University of the Shannon; University of Chester; National University of Ireland; Keele University; Lahore College for Women University (Elsevier, 2022-03-08)
      Object Detection is the task of classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. This article surveys recent developments in deep learning based object detectors. Concise overview of benchmark datasets and evaluation metrics used in detection is also provided along with some of the prominent backbone architectures used in recognition tasks. It also covers contemporary lightweight classification models used on edge devices. Lastly, we compare the performances of these architectures on multiple metrics.
    • Immersive Virtual Reality for the Cognitive Rehabilitation of Stroke Survivors

      Chatterjee, Kausik; Buchanan, Alastair; Cottrell, Katy; Hughes, Sara; Day, Thomas W.; John, Nigel W.; Countess of Chester Hospital NHS Foundation Trust; Cadscan Limited; University of Chester (IEEE, 2022-03-10)
      We present the results of a double-blind phase 2b randomized control trial that used a custom built virtual reality environment for the cognitive rehabilitation of stroke survivors. A stroke causes damage to the brain and problem solving, memory and task sequencing are commonly affected. The brain can recover to some extent, however, and stroke patients have to relearn how to carry out activities of daily living. We have created an application called VIRTUE to enable such activities to be practiced using immersive virtual reality. Gamification techniques enhance the motivation of patients such as by making the level of difficulty of a task increase over time. The design and implementation of VIRTUE is described together with the results of the trial conducted within the Stroke Unit of a large hospital. We report on the safety and acceptability of VIRTUE. We have also observed particular benefits of VR treatment for stroke survivors that experienced more severe cognitive impairment, and an encouraging reduction in time spent in the hospital for all patients that received the VR treatment.
    • LevelEd SR: A Substitutional Reality Level Design Workflow

      Beever, Lee; John, Nigel W.; University of Chester (IEEE, 2022-04-20)
      Virtual reality (VR) and augmented reality (AR) have continued to increase in popularity over the past decade. However, there are still issues with how much space is required for room-scale VR and experiences are still lacking from haptic feedback. We present LevelEd SR, a substitutional reality level design workflow that combines AR and VR systems and is built for consumer devices. The system enables passive haptics through the inclusion of physical objects from within a space into a virtual world. A validation study (17 participants) has produced quantitative data that suggests players benefit from passive haptics in entertainment VR games with an improved game experience and increased levels of presence. Including objects, such as real-world furniture that is paired with a digital proxy in the virtual world, also opens up more spaces to be used for room-scale VR. We evaluated the workflow and found that participants were accepting of the system, rating it positively using the System Usability Scale questionnaire and would want to use it again to experience substitutional reality.
    • Application of Virtual Reality and Electrodermal Activity for the Detection of Cognitive Impairments

      Patient, Rebecca; Ghali, Fawaz; Kolivand, Hoshang; Hurst, William; John, Nigel W.; Liverpool John Moores; Wageningen University; University of Chester (IEEE, 2022-03-01)
      Mild Cognitive Impairment (MCI) is a definition of the diagnosis of early memory loss and disorientation. This study aims to identify people’s symptoms through technology. However, machine learning (ML) can classify Cognitive Normal (CN) and Mild Cognitive Impairment (MCI) and Early Mild Cognitive Impairment (EMCI) using standard assessments from the Alzheimer’s Disease Neuroimaging Initiative (ADNI); Montreal Cognitive (MoCA), Mini-Mental State Examination (MMSE), Functional Activities Questionnaire (FAQ). Consequently, a Multilayer Perceptron (MLP) model was assembled into tables; MCI vs CN, MCI vs EMCI, and CN vs MCI. Additionally, an MLP model was developed for CN vs MCI vs EMCI. As a result, of advanced model performance, a cascade 3-path categorisation approach was created. Similarly, the exploitation of meta-analysis indicated a combination of MLP models (MCI vs CN, MCI vs EMCI, and CN vs MCI) with an overall accuracy within an acceptable limit. In addition, better results were found when assessments were combined rather than individually. Furthermore, applying class weights and probability thresholds could improve the MLP framework by performance achieving a balanced specificity and sensitivity ratio. Altering class weights and probability thresholds when training the MLP neuro network model, the sensitivity and Accuracy could be progressed further. In conclusion, ML, VR and electrodermal activity are constrained. Introducing the possibility of activity-based applications to enhance innovative solutions for cognitive impairment diagnosis and treatment.
    • Virtual reality training in cardiopulmonary resuscitation in schools

      Rees, Nigel; John, Nigel W.; Beever, Lee; Vaughan, Neil; Powell, C; Fletcher, A; Welsh Ambulance Services NHS Trust; Swansea University; University of Chester; University of Exeter; British Heart Foundation; London School of Hygiene & Tropical Medicine (Mark Allen Healthcare, 2021-09-11)
      UK average survival from Out of Hospital Cardiac Arrest (OHCA) survival is around 8.6%, which is significantly lower than other high performing countries with survival rates of over 20%. A cardiac arrest victim is 2–4 times more likely to survive OHCA with bystander CPR provision. Mandatory Teaching CPR to children in school is acknowledged to be the most effective way to reach the entire population and improving the bystander CPR rate and is endorsed by the World Health Organization (WHO) “Kids Save Lives” statement. Despite this, Wales is yet to follow other home nations by including CPR training as a mandatory within the school’s curriculum. In this paper, we explore the role of teaching CPR to schoolchildren and report on the development by Computer scientists at the University of Chester and the Welsh Ambulance Services NHS Trust (WAST) of VCPR, a virtual environment to help teach the procedure. VCPR was developed in three stages: identifying requirements and specifications; development of a prototype; and management—development of software, further funding and exploring opportunities for commercialisation. We describe the opportunities in Wales to skill up the whole population over time in CPR and present our Virtual reality (VR) technology is emerging as a powerful for teaching CPR in schools.
    • Talos: a prototype Intrusion Detection and Prevention system for profiling ransomware behaviour

      Wood, Ashley; Eze, Thaddeus; Speakman, Lee; University of Chester (Academic Conferences International, 2021-06-24)
      Abstract: In this paper, we profile the behaviour and functionality of multiple recent variants of WannaCry and CrySiS/Dharma, through static and dynamic malware analysis. We then analyse and detail the commonly occurring behavioural features of ransomware. These features are utilised to develop a prototype Intrusion Detection and Prevention System (IDPS) named Talos, which comprises of several detection mechanisms/components. Benchmarking is later performed to test and validate the performance of the proposed Talos IDPS system and the results discussed in detail. It is established that the Talos system can successfully detect all ransomware variants tested, in an average of 1.7 seconds and instigate remedial action in a timely manner following first detection. The paper concludes with a summarisation of our main findings and discussion of potential future works which may be carried out to allow the effective detection and prevention of ransomware on systems and networks.
    • An Endoscope Interface for Immersive Virtual Reality

      John, Nigel W.; Day, Thomas W.; Wardle, Terrence; University of Chester
      This is a work in progress paper that describes a novel endoscope interface designed for use in an immersive virtual reality surgical simulator. We use an affordable off the shelf head mounted display to recreate the operating theatre environment. A hand held controller has been adapted so that it feels like the trainee is holding an endoscope controller with the same functionality. The simulator allows the endoscope shaft to be inserted into a virtual patient and pushed forward to a target position. The paper describes how we have built this surgical simulator with the intention of carrying out a full clinical study in the near future.
    • ParaVR: A Virtual Reality Training Simulator for Paramedic Skills maintenance

      Rees, Nigel; Dorrington, Keith; Rees, Lloyd; Day, Thomas W; Vaughan, Neil; John, Nigel W; Welsh Ambulance Services NHS Trust, University of Chester
      Background, Virtual Reality (VR) technology is emerging as a powerful educational tool which is used in medical training and has potential benefits for paramedic practice education. Aim The aim of this paper is to report development of ParaVR, which utilises VR to address skills maintenance for paramedics. Methods Computer scientists at the University of Chester and the Welsh Ambulance Services NHS Trust (WAST) developed ParaVR in four stages: 1. Identifying requirements and specifications 2. Alpha version development, 3. Beta version development 4. Management: Development of software, further funding and commercialisation. Results Needle Cricothyrotomy and Needle Thoracostomy emerged as candidates for the prototype ParaVR. The Oculus Rift head mounted display (HMD) combined with Novint Falcon haptic device was used, and a virtual environment crafted using 3D modelling software, ported (a computing term meaning transfer (software) from one system or machine to another) onto Oculus Go and Google cardboard VR platform. Conclusion VR is an emerging educational tool with the potential to enhance paramedic skills development and maintenance. The ParaVR program is the first step in our development, testing, and scaling up of this technology.
    • LevelEd VR: A virtual reality level editor and workflow for virtual reality level design

      Beever, Lee; Pop, Serban W.; John, Nigel W.; University of Chester
      Virtual reality entertainment and serious games popularity has continued to rise but the processes for level design for VR games has not been adequately researched. Our paper contributes LevelEd VR; a generic runtime virtual reality level editor that supports the level design workflow used by developers and can potentially support user generated content. We evaluated our LevelEd VR application and compared it to an existing workflow of Unity on a desktop. Our current research indicates that users are accepting of such a system, and it has the potential to be preferred over existing workflows for VR level design. We found that the primary benefit of our system is an improved sense of scale and perspective when creating the geometry and implementing gameplay. The paper also contributes some best practices and lessons learned from creating a complex virtual reality tool, such as LevelEd VR.