Recent Submissions

  • Economic development and construction safety research: a bibliometrics approach

    Luo, Fansong; Li, Rita Yi Man; Crabbe, M. James C.; Pu, Ruihui; Hong Kong Shue Yan University; Oxford University; University of Bedfordshire; Shanxi University; Srinakharinwirot University (Elsevier, 2021-10-14)
    The construction industry contributes significantly to economic development worldwide, yet it is one of the most hazardous industries where numerous accidents and fatalities happen every year. Little research to date has shed light on the impact of economic development on construction safety research. In this paper, we conduct an analysis of construction safety articles published in the 21st century via a bibliometrics approach. We have analysed: (1) construction safety in developed and developing countries; (2) the major organisations that have conducted construction safety research; (3) authors and territories of the research and (4) topics in construction safety and future research directions. The largest number of published construction safety documents were published by scholars from the US and China; the total number of published articles by these two countries was 1,125, at 56% of the 2000 articles that were published. Both countries showed high levels of research collaboration. While our results suggest that economic development may drive academic construction safety research, there has been an increase in construction safety research conducted by developing countries in recent years, probably due to an improvement in their economic development. While authors’ keywords evidenced the popularity of research on safety management and climate, the network analysis on all keywords, i.e. keywords given by Web of Science and authors, suggest that construction safety research focused on three areas: construction safety management, the relationship between people and construction safety, and the protection and health of workers’ impact on construction safety. We found that there is a new interdisciplinary research trend where construction safety combines with digital technologies, with the largest number involving deep learning. Other trends focus on machine learning, Building Information Modelling, machine learning and visualisation.
  • Tracking human motion direction with commodity wireless networks

    Rahaman, Habibur; Dyo, Vladimir; University of Bedfordshire (IEEE, 2021-09-07)
    Detecting when a person leaves a room, or a house is essential to create a safe living environment for people suffering from dementia or other mental disorders. The approaches based on wearable devices, e.g. GPS bracelets may detect such events require periodic maintenance to recharge or replace batteries, and therefore may not be suitable for certain types of users. On the other hand, camera-based systems require illumination and raise potential privacy concerns. In this paper, we propose a device-free walking direction detection approach based on RF-sensing, which does not require a person to wear any equipment. The proposed approach monitors the signal strength fluctuations caused by the human body on ambient wireless links and analyses its spatial patterns using a convolutional neural network to identify the walking direction. The approach has been evaluated experimentally to achieve up to 98% classification accuracy depending on the environment.
  • Time series chlorophyll-A concentration data analysis: a novel forecasting model for aquaculture industry

    Eze, Elias Chinedum; Kirby, Sam; Attridge, John; Ajmal, Tahmina; University of Bedfordshire; Chelsea Technology Group (2021-06-29)
    Eutrophication in fresh water has become a critical challenge worldwide and chlorophyll-a content is a key water quality parameter that indicates the extent of eutrophication and algae concentration in a body of water. In this paper, a forecasting model for the high accuracy prediction of chlorophyll-a content is proposed to enable aquafarm managers to take remediation actions against the occurrence of toxic algal blooms in the aquaculture industry. The proposed model combines the ensemble empirical mode decomposition (EEMD) technique and a deep learning (DL) long short-term memory (LSTM) neural network (NN). With this hybrid approach, the time-series data are firstly decomposed with the aid of the EEMD algorithm into manifold intrinsic mode functions (IMFs). Secondly, a multi-attribute selection process is employed to select the group of IMFs with strong correlations with the measured real chlorophyll-a dataset and integrate them as inputs for the DL LSTM NN. The model is built on water quality sensor data collected from the Loch Duart salmon aquafarm in Scotland. The performance of the proposed novel hybrid predictive model is validated by comparing the results against the dataset. To measure the overall accuracy of the proposed novel hybrid predictive model, the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) were used.
  • Developing a novel water quality prediction model for a South African aquaculture farm

    Eze, Elias Chinedum; Halse, Sarah; Ajmal, Tahmina; University of Bedfordshire; Abagold Limited (MDPI, 2021-06-28)
    Providing an accurate prediction of water quality parameters for improved water quality management is a topical issue in the aquaculture industry. Conventional prediction methods have shown different challenges like a poor generalization, poor prediction accuracy, and high time complexity. Aiming at these challenges, a novel hybrid prediction model with ensemble empirical mode decomposition (EEMD) and deep learning (DL) long-short term memory (LSTM) neural network is proposed in this paper. In this innovative hybrid EEMD-DL-LSTM model, firstly, the integrity of the datasets is enhanced by applying moving average filtering and linear interpolation techniques of water quality parameter datasets pre-treatment. Secondly, the measured real sensor water quality parameters dataset is decomposed with the aid of the EEMD algorithm into disparate IMFs and a corresponding residual item. Thirdly, a multi-feature selection process is applied to make a careful selection of a strongly correlated group of IMFs with the measured real water quality parameter datasets and integrate them as inputs to the DL-LSTM neural network. The presented model is built on water quality sensor data collected from an Abalone farm in South Africa. The performance of the novel hybrid prediction model is validated by comparing the results against the real datasets. To measure the overall accuracy of the novel hybrid prediction model, different statistical indices, namely the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), are used.
  • A non-enzymatic glucose sensor via uniform copper nanosphere fabricated by two-step method

    Yu, Miaomiao; Weng, Zhankun; Hu, Jing; Zhu, Xiaona; Song, Hangze; Wang, Shenzhi; Cao, Siyuan; Song, Zhengxun; Xu, Hongmei; Li, Jinhua; et al. (Elsevier Ltd, 2021-08-10)
    Herein, we explored an effective way to obtain uniform copper nanoparticles by irradiating Cu2O microparticles in ethanol with a 1064 nm laser. The morphology, structure and chemical composition of as-prepared copper nanoparticles were characterized by scanning electron microscopy, transmission electron microscopy, energy-dispersive X-ray spectroscopy, X-ray diffraction and X-ray photoelectron spectroscopy. It is interesting that the diameter of obtained spherical copper nanoparticles can be finely tuned by changing the irradiation time. Moreover, we also found that the particle size of copper nanoparticles can be reduced to ~63 nm when the irradiation time is 30 min. Inspired by the fast-developing non-enzymatic glucose sensors, the electrochemical activity of the copper nanoparticles toward glucose in alkaline media was further investigated. Notably, the electrochemical results reveal that the prepared copper nanoparticles possess a good prospect in non-enzymatic glucose sensor.
  • Privacy-preserving identity broadcast for contact tracing applications

    Dyo, Vladimir; Ali, Jahangir; University of Bedfordshire (2021-08-10)
    Wireless Contact tracing has emerged as an important tool for managing the COVID19 pandemic and relies on continuous broadcasting of a person’s presence using Bluetooth Low Energy beacons. The limitation of current contact tracing systems in that a reception of a single beacon is sufficient to reveal the user identity, potentially exposing users to malicious trackers installed along the roads, passageways, and other infrastructure. In this paper, we propose a method based on Shamir secret sharing algorithm, which lets mobile nodes reveal their identity only after a certain predefined contact duration, remaining invisible to trackers with short or fleeting encounters. Through data-driven evaluation, using a dataset containing 18 million BLE sightings, we show that the method drastically reduces the privacy exposure of users. Finally, we implemented the approach on Android phones to demonstrate its feasibility and measure performance for various network densities.
  • Enable a facile size re-distribution of MBE-grown Ga-droplets via in situ pulsed laser shooting

    Geng, Biao; Shi, Zhenwu; Chen, Chen; Zhang, Wei; Yang, Linyun; Deng, Changwei; Yang, Xinning; Miao, Lili; Peng, Changsi; Soochow University; et al. (Springer, 2021-08-04)
    A MBE-prepared Gallium (Ga)-droplet surface on GaAs (001) substrate is in situ irradiated by a single shot of UV pulsed laser. It demonstrates that laser shooting can facilely re-adjust the size of Ga-droplet and a special Ga-droplet of extremely broad size-distribution with width from 16 to 230 nm and height from 1 to 42 nm are successfully obtained. Due to the energetic inhomogeneity across the laser spot, the modification of droplet as a function of irradiation intensity (IRIT) can be straightly investigated on one sample and the correlated mechanisms are clarified. Systematically, the laser resizing can be perceived as: for low irradiation level, laser heating only expands droplets to make mergences among them, so in this stage, the droplet size distribution is solely shifted to the large side; for high irradiation level, laser irradiation not only causes thermal expansion but also thermal evaporation of Ga atom which makes the size-shift move to both sides. All of these size-shifts on Ga-droplets can be strongly controlled by applying different laser IRIT that enables a more designable droplet epitaxy in the future.
  • Effect of trypsin concentration on living SMCC-7721 cells studied by atomic force microscopy

    Yan, Jin; Xie, Chenchen; Zhu, Jiajing; Song, Zhengxun; Wang, Zuobin; Li, Li (Wiley, 2021-08-05)
    Trypsin is playing an important role in the processes of cancer proliferation, invasion, and metastasis which require the precise information of morphology and mechanical properties on the nanoscale for the related research. In this work, living human hepatoma (SMCC-7721) cells were treated with different concentrations of trypsin solution. The morphology and mechanical properties of the cells were measured via atomic force microscope (AFM). Statistical analyses of measurement data indicated that with the increase of trypsin concentration, the average cell height and the surface roughness were both increased, but the cell viability, the cell surface adhesion and the elasticity modulus were decreased significantly. The force required to puncture the cells was also gradually reduced. It indicates that trypsin not only hydrolyzes the proteins between the cell and the substrate but also the membrane proteins. The results offer valuable clues for the cancerous process study, pathological analysis, and trypsin inhibitor drug development. And this work provides an effective way for overcoming the cell membrane in drug injection for cell-targeted therapy. This article is protected by copyright. All rights reserved.
  • A novel classified ledger framework for data flow protection in AIoT networks

    Han, Daoqi; Wu, Songqi; Hu, Zhuoer; Gao, Hui; Liu, Enjie; Lu, Yueming; Beijing University of Posts and Telecommunications; University of Bedfordshire (Hindawi, 2021-02-19)
    The edge computing node plays an important role in the evolution of the artificial intelligence-empowered Internet of things (AIoTs) that converge sensing, communication, and computing to enhance wireless ubiquitous connectivity, data acquisition, and analysis capabilities. With full connectivity, the issue of data security in the new cloud-edge-terminal network hierarchy of AIoTs comes to the fore, for which blockchain technology is considered as a potential solution. Nevertheless, existing schemes cannot be applied to the resource-constrained and heterogeneous IoTs. In this paper, we consider the blockchain design for the AIoTs and propose a novel classified ledger framework based on lightweight blockchain (CLF-LB) that separates and stores data rights at the source and enables a thorough data flow protection in the open and heterogeneous network environment of AIoT. In particular, CLF-LB divides the network into five functional layers for optimal adaptation to AIoTs applications, wherein an intelligent collaboration mechanism is also proposed to enhance the across-layer operation. Unlike traditional full-function blockchain models, our framework includes novel technical modules, such as block regenesis, iterative reinforcement of proof-of-work, and efficient chain uploading via the system-on-chip system, which are carefully designed to fit the cloud-edge-terminal hierarchy in AIoTs networks. Comprehensive experimental results are provided to validate the advantages of the proposed CLF-LB, showing its potentials to address the secrecy issues of data storage and sharing in AIoTs networks.
  • Unlink the link between COVID-19 and 5G Networks: an NLP and SNA based approach

    Bahja, Mohammed; Safdar, Ghazanfar Ali; University of Birmingham; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2020-11-18)
    Social media facilitates rapid dissemination of information for both factual and fictional information. The spread of non-scientific information through social media platforms such as Twitter has potential to cause damaging consequences. Situations such as the COVID-19 pandemic provides a favourable environment for misinformation to thrive. The upcoming 5G technology is one of the recent victims of misinformation and fake news and has been plagued with misinformation about the effects of its radiation. During the COVID-19 pandemic, conspiracy theories linking the cause of the pandemic to 5G technology have resonated with a section of people leading to outcomes such as destructive attacks on 5G towers. The analysis of the social network data can help to understand the nature of the information being spread and identify the commonly occurring themes in the information. The natural language processing (NLP) and the statistical analysis of the social network data can empower policymakers to understand the misinformation being spread and develop targeted strategies to counter the misinformation. In this paper, NLP based analysis of tweets linking COVID-19 to 5G is presented. NLP models including Latent Dirichlet allocation (LDA), sentiment analysis (SA) and social network analysis (SNA) were applied for the analysis of the tweets and identification of topics. An understanding of the topic frequencies, the inter-relationships between topics and geographical occurrence of the tweets allows identifying agencies and patterns in the spread of misinformation and equips policymakers with knowledge to devise counter-strategies.
  • Detecting advance fee fraud using NLP bag of word model

    Hamisu, Muhammad; Mansour, Ali; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2021-05-25)
    Advance Fee Fraud (AFF) is a form of Internet fraud prevalent within the Cybercrimes domain in literature. Evidence shows that huge financial assets are stolen from the global economy as a result of AFF. Consequently, this paper presents a fraudulent email classifier (FEC) that detects and classifies an email as fraudulent or non-fraudulent using Natural Language Process (NLP) model referred to as Bag-of-Words (BoW). The classifier is designed and trained to detect and classify AFF that originate from known sources using Nigeria as a Case study. Dataset is obtained and used for the training while testing the classifier logs. Experimentally, the classifier was trained using various machine learning algorithms with BoW generated as predictors. By selecting the best algorithms, the classifier was tested and found to perform satisfactorily.
  • Analysis of cybercrime in Nigeria

    Hamisu, Muhammad; Idris, Abubakar Muhammad; Mansour, Ali; Olalere, Morufu; University of Bedfordshire; Federal University of Technology, Minna, Nigeria (Institute of Electrical and Electronics Engineers Inc., 2021-05-25)
    Nigeria has both the largest economy and population in Africa, and this contribute to the growth and fast expansion of ICT and the use of Internet in Nigeria. Like other technologies, Internet has been used by both good and bad actors. The use of internet and computer to commit crime is costing global economy the loss of billions of dollars. In Nigeria, the majority of the population use the Internet for good but some few are using it to commit criminal activities such as Fraud. Cybercriminals in Nigeria, widely called Yahoo Boys in the country specialize in Internet fraud that target mostly International victims. The Nigeria government is stepping efforts to bring an end the activities of these criminals as their actions tarnishes the image of the country. While the efforts of the government had yielded some positive results, the threat of Cybercrime in Nigeria is still high, as criminals continue to take advantage of flaws in the law enforcement tactical approach in addressing the crime. This paper discusses an overview of Cybercrime in Nigeria, the common types of Cybercrime that is perpetuated from the country and the reason of doing so. It also discusses the government's success and areas of strength in its fight against Cybercrime and highlight the areas of weaknesses. Recommendations and suggestions are made on how law enforcement and the government at large can improve to tackle Cybercrime better in Nigeria.
  • Interference system for high pressure environment

    Kumpulainen, Tero; Singh, Amandeep; März, Thomas; Dong, Litong; Li, Dayou; Reuna, Jarno; Vihinen, Jorma; Levänen, Erkki; Tampere University; InnoLas Laser GmbH; et al. (Elsevier Ltd, 2021-05-29)
    Laser interference patterning or lithography has been used in variety of the applications using, patterning, masking and processing structures at top of material. It offers fast processing over as large areas can be processed simultaneously. Additionally, fine patterns are possible to achieve both in micro and sub-micro scale. In this manuscript is presented novel concept to combine interference patterning and high-pressure processing environment. With aid of high-pressure system, it is possible to control processing environment and add co-solvents in desired state (liquid, gas, supercritical) and use developed system as controlled reactive environment in the future studies. Two systems were developed and assembled for testing and proofing the concept. The results of the two 4-beam interference systems (lens- and mirror-based) are presented and compared.
  • Comparative analysis of scheduling algorithms for radio resource allocation in future communication networks

    Ashfaq, Khuram; Safdar, Ghazanfar Ali; Ur-Rehman, Masood; ; University of Bedfordshire; University of Glasgow (PeerJ, 2021-05-18)
    Wireless links are fast becoming the key communication mode. However, as compared to the wired link, their characteristics make the traffic prone to time- and location-dependent signal attenuation, noise, fading, and interference that result in time varying channel capacities and link error rate. Scheduling algorithms play an important role in wireless links to guarantee quality of service (QoS) parameters such as throughput, delay, jitter, fairness and packet loss rate. The scheduler has vital importance in current as well as future cellular communications since it assigns resource block (RB) to different users for transmission. Scheduling algorithm makes a decision based on the information of link state, number of sessions, reserved rates and status of the session queues. The information required by a scheduler implemented in the base station can easily be collected from the downlink transmission. This paper reflects on the importance of schedulers for future wireless communications taking LTE-A networks as a case study. It compares the performance of four well-known scheduling algorithms including round robin (RR), best channel quality indicator (BCQI), proportional fair (PF), and fractional frequency reuse (FFR). The performance of these four algorithms is evaluated in terms of throughput, fairness index, spectral efficiency and overall effectiveness. System level simulations have been performed using a MATLAB based LTE-A Vienna downlink simulator. The results show that the FFR scheduler is the best performer among the four tested algorithms. It also exhibits flexibility and adaptability for radio resource assignment.
  • The influence of different liquid environments on the atomic force microscopy detection of living bEnd.3 cells

    Jin, Yan; Sun, Baishun; Xie, Chenchen; Liu, Yan; Song, Zhengxun; Xu, Hongmei; Wang, Zuobin; Changchun University of Science and Technology; University of Bedfordshire (Royal Society of Chemistry, 2021-05-10)
    Atomic force microscopy (AFM) is one of the most important tools in the field of biomedical science, and it can be used to perform the high-resolution three-dimensional imaging of samples in liquid environments to obtain their physical properties (such as surface potentials and mechanical properties). The influence of the liquid environment on the image quality of the sample and the detection results cannot be ignored. In this work, quantitative imaging (QI) mode AFM imaging and mechanical detection were performed on mouse brain microvascular endothelial (bEnd.3) cells in different liquid environments. The gray-level variance product (SMD2) function was used to evaluate the imaging quality of the cells in liquids with different physical properties, and the variations in cell mechanical properties were quantitatively analyzed. An AFM detection liquid containing less ions and organics compared with the traditional culture medium, which is beneficial for improving the imaging quality, is introduced, and it shows similar mechanical detection results within 3 h. This can greatly reduce the detection costs and could have positive significance in the field of AFM living-cell detection.
  • Study of NSCLC cell migration promoted by NSCLC-derived extracellular vesicle using atomic force microscopy

    Wang, Shuwei; Wang, Jiajia; Ju, Tuoyu; Yang, Fan; Qu, Kaige; Liu, Wei; Wang, Zuobin; Jilin University; Changchun University of Science and Technology; University of Bedfordshire (Royal Society of Chemistry, 2021-02-16)
    Extracellular vesicles (EVs) secreted by cancer cells play a key role in the cancer microenvironment and progression. Previous studies have mainly focused on molecular functions, cellular components and biological processes using chemical and biological methods. However, whether the mechanical properties of cancer cells change due to EVs remains poorly understood. This work studies the effects of mechanical changes in non-small cell lung cancer (NSCLC) cells after treatment with EVs on migration by atomic force microscopy (AFM). Different concentrations of EVs were added into the experimental groups based on co-culture experiments, while the control group was cultured without EVs for 48 h. Cellular migration was evaluated by wound healing experiments. The cellular morphology, cell stiffness and surface adhesion were investigated by AFM. Cytoskeleton changes were detected by fluorescence staining assay. By comparison to the control group, the cell migration was enhanced. After treatment with EVs, the cell length and height show an upward trend, and the adhesion force and Young's modulus show a downward trend, and filopodia were also detected in the cells. Overall, the EVs promoted the migration of NSCLC cells by regulating cells' physical properties and skeletal rearrangement.
  • A numerical study of the effects of oxy-fuel combustion under homogeneous charge compression ignition regime

    Mobasheri, Raouf; Aitouche, Abdel; Peng, Zhijun; Li, Xiang; Centre de Recherche en Informatique Signal et Automatique de Lille; Junia; University of Bedfordshire (SAGE Publications Ltd, 2021-02-16)
    The European Union (EU) has recently adopted new directives to reduce the level of pollutant emissions from non-road mobile machinery engines. The main scope of project RIVER for which this study is relating is to develop possible solutions to achieve nitrogen-free combustion and zero-carbon emissions in diesel engines. RIVER aims to apply oxy-fuel combustion with Carbon Capture and Storage (CCS) technology to eliminate NOx emissions and to capture and store carbon emissions. As part of this project, a computational fluid dynamic (CFD) analysis has been performed to investigate the effects of oxy-fuel combustion on combustion characteristics and engine operating conditions in a diesel engine under Homogenous Charge Compression Ignition (HCCI) mode. A reduced chemical n-heptane-n-butanol-PAH mechanism which consists of 76 species and 349 reactions has been applied for oxy-fuel HCCI combustion modeling. Different diluent strategies based on the volume fraction of oxygen and a diluent gas has been considered over a wide range of air-fuel equivalence ratios. Variation in the diluent ratio has been achieved by adding different percentages of carbon dioxide for a range from 77 to 83 vol.% in the intake charge. Results show that indicated thermal efficiency (ITE) has reduced from 32.7% to 20.9% as the CO2 concentration has increased from 77% to 83% at low engine loads while it doesn’t bring any remarkable change at high engine loads. It has also found that this technology has brought CO and PM emissions to a very ultra-low level (near zero) while NOx emissions have been completely eliminated.
  • Response of bEnd.3 cells to growing behavior on the graphene oxide film with 2-D grating structure by two-beam laser interference

    Yan, Jin; Cao, Liang; Wang, Lu; Xie, Chengcheng; Liu, Yan; Song, Zhengxun; Xu, Hongmei; Weng, Zhankun; Wang, Zuobin; Li, Li (Springer Science and Business Media Deutschland GmbH, 2021-02-22)
    Graphene (G) and its derivatives are important nanomaterials with potential medical applications for biosensors and implanting biomaterials. The hydrophobicity and surface microstructures of substrates have great influences on the biological and physical properties of the surface-bound cells. In this work, we used the two-beam laser interference (TBLI) technique to prepare a two-dimensional (2-D) grating structure on the surface of graphene oxide (GO) film. We investigated the effect of GO and the GO film with the 2-D grating structure substrates on the growth behavior of rat brain microvascular endothelial (bEnd.3) cells. The results demonstrated that the cell spreading area and the number of surface-bound cells were closely related to the hydrophobicity of the substrate and the presence of oxygen-containing functional groups (OCGs). Due to the interaction of laser and GO, the GO in the interference area was transformed into reduced graphene oxide (RGO). The grating-structured GO film significantly affected the direction of cell spreading and morphology. It has a good application prospect as a scaffold in tissue engineering, and promising applications in the fields that require highly directional growth of cells, such as nerve injury repair, tendon repair and regeneration.
  • Sit-to-stand intention recognition

    Wang, Zuobin; Li, Dayou; Lu, Hang; Qiu, Renxi; Maple, Carsten; University of Bedfordshire; Changchun University of Science and Technology; Warwick University (Springer Science and Business Media Deutschland GmbH, 2021-01-23)
    Sit-to-stand (STS) difficulties are common among elderly because of the decline of their cognitive capabilities and motor functions. The way to help is to encourage them to practice their own functions and to assist only at the point where they need during STS processes. The provision of such support requires the elderly’s intention of standing up to be recognised and the amount of support as well as the moment when the support would be needed to be predicted. The research presented in this paper focuses on intention recognition as it is difficult due to uncertainties existing in STS processes and differences in individual’s biomechanical features. This paper presents fuzzy logic based self-adaptive approach to the recognition of standing up intention from sensor signals that contain the uncertainties.
  • Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

    Jakaite, Livija; Schetinin, Vitaly; Hladůvka, Jiří; Minaev, Sergey; Ambia, Aziz; Krzanowski, Wojtek; ; University of Bedfordshire; TU Wien; Stavropol State Medical University; et al. (Nature, 2021-01-27)
    Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients’ cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients’ cases will be available.

View more