Person identification is a pivotal challenge in the security domain, with important and impactful applications such as identifying crime suspects and locating missing persons. One convenient person identification method is gait identification, where individuals are identified by their unique walking style. However, traditional methods of gait identification are often affected by variations in appearance and occlusion. This work introduces a novel and robust spatiotemporal kinematics‐informed non‐invasive gait identification (STONI‐GID) method that uses human pose estimation, occlusion state estimation and deep machine learning. Furthermore, unlike some existing methods, we demonstrate that our method remains unaffected by everyday appearance changes, environment, or viewing angle. Our approach achieved identification accuracy of up to 98.66% when evaluated using our primary dataset of 65 diverse participants in real‐world environments. Moreover, the model outperformed existing methods during cross‐dataset validation on the large Southampton dataset and the Gait Recognition Image and Depth Dataset (GRIDDS), achieving identification accuracies of 97.68% and 99.12%, respectively. Our findings will particularly advance the research frontiers of real‐world gait identification and impact interdisciplinary areas of security and healthcare applications.

Students' performance assessment is crucial in the context of education especially prior to levelling students or recommending personalised learning. In a multicultural environment, multiple factors play a role in students' performance that go beyond the students'-teacher interaction. These factors are related to students' characteristics and experience, learning environment and material as well as the material delivered. Considering the role of these factors in students' performance, this work proposed the use of two multivariate regression algorithms for predicting year 6 school students' performance in math over three semesters being autumn, spring and summer. Principal Component Regression (PCR) and Partial least Square Regression (PLSR) models were constructed and validated for predicting students' performance in end of block assessment over 15 blocks per year: six per autumn semester, six per spring semester and three in summer semester. The results showed that both PCR and PLSR models demonstrated accurate predictions for end of block assessments with correlation coefficient values up to 0.97 and low root mean square error of predictions that was below 5% in most cases. Best performing models were those that assessed fractions, perimeter and geometry and that indicated the strong relationship between the students' factors and end of block assessment. Out of 30 regression models, six models performed poorly and were related to four operations, decimals and ratios. Yet, the performance of students could be predicted accurately and precisely using multivariate regression algorithms. Future work involves evaluating these models to different cohorts of students to determine feasibility of the explored models.

Drug detection in oral fluid has become popular over the last few years with oral fluid being a non-invasive matrix. Handheld surface enhanced Raman spectroscopy (SERS) is a rapid technique that detects drugs at low concentration and in any field. This work proposes using handheld SERS with machine learning algorithms for detecting drugs in oral fluid. Three drugs were evaluated being cocaine, its metabolite (benzoylecgonine) and paracetamol. Raman spectra of drug solutions mixed with gold or silver nanoparticles were collected through glass vials. These spectra showed high signal to noise ratios and each spectrum of a drug solution showed characteristic drugs bands for each drug. Then three machine learning algorithms were applied and were correlation in wavenumber space, principal component analysis and partial least square regression. The correlation in wavenumber space and principal component analysis classified the different drugs in oral fluid with accuracy up to 99% depending on the model. The partial least square regression informed about the levels of drugs in the oral fluid solution with high accuracy and precision. In conclusion, handheld SERS could instantly detect and predict concentrations of drugs in oral fluid.

Drugs of abuse are often cut by pharmacological and non-pharmacological impurities that impact their adverse events. Attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR) offers a rapid technique that requires minimal sample preparation and can be carried to the field in portable form. This study utilized ATR-FTIR spectroscopy for detecting street drugs of abuse (n = 291). Few milligrams of powder or powdered tablets were measured directly on the instrument. Reference analysis was made using immunoassays and gas chromatography-mass spectrometry. The results showed that ATR-FTIR spectroscopy could identify more than 50% of the drugs measured. The main drugs found contained cocaine, ketamine, benzodiazepines, piperazines, and amfetamine derivatives. Accurate drug identification depended on the number of impurities, types of impurities and concentration of the drug in the product. Hence, drugs could be identified via their IR signatures that were able to differentiate a base from a salt. When correlation method (CM) was applied to the spectra, drugs were correctly identified if they did not have multiple impurities. On the other hand, the presence of impurities affected the accuracy of identification and showed mismatches. Mismatches were addressed by applying principal component analysis (PCA) to the IR spectra of the products. PCA in this case four key clusters with few overlaps. corresponding to cocaine, piperazines, amfetamines and ketamine. There were yet some overlap in the PCA scores due to presence of common impurities between products example benzocaine, cocaine and lactose. In summary, ATR-FTIR combined with chemometrics was accurate in identifying street drugs on the spot.

Cocaine is often cut by multiple diluents and adulterants that increase the volume or alter the pharmacological activity. Handheld near-infrared (NIR) and Raman spectroscopy are rapid and can be carried on the site for detection of drugs of abuse. Both techniques are complementary and give a chemical and physical fingerprint of the drugs measured. This research combined NIR and Raman spectroscopy for quantifying cocaine in mixtures non-destructively. Mixtures of cocaine with adulterants and/or diluents were prepared and stored in glass vials. Then each mixture was measured three times through the glass vials. Likewise, pure substances were measured through glass vials. NIR and Raman spectra were exported in Matlab 2024b where partial least square regression (PLSR) was applied. PLSR models were evaluated for accuracy and precision considering the correlation coefficient (r2) and root mean square errors of calibration and prediction (RMSEC and RMSEP) values. In this respect, models based on NIR spectral data showed higher accuracy and precision than those based on Raman spectral data. Thus, the r2values of calibration and prediction sets for NIR spectral models were in the range of 0.9815-0.9925 and 0.9604-0.9907 respectively. Yet, the r2values of calibration and prediction sets for Raman spectral models were in the range of 0.8891-0.9905 and 0.6882-0.9394 respectively. Moreover, the RMSEC and RMSEP values for models based on NIR spectral data were in the range of 2.77-6.04 and 3.13-8.34% m/m respectively. In addition, the RMSEC and RMSEP values for models based on Raman spectral data were in the range of 3.01-8.61 and 6.13-12.7% m/m respectively. The difference in accuracy could be related to NIR spectral data showing more information regarding the measured powders being collected in diffuse reflectance mode. On the other hand, the Raman measurement mode comprised surface reflection. However, the difference in accuracy and precision was not major and both techniques proved accurate and precise in predicting cocaine in mixtures of drug and food products.

This study investigated using near-infrared (NIR) and Raman spectroscopy with chemometrics for detecting counterfeit antibiotics. Antibiotics were measured nondestructively using portable spectrometers in diffuse reflectance (NIR), conventional reflectance and spatially offset modes (Raman). Spectra were exported to Matlab 2025a where two chemometric algorithms were applied being correlation (CM) and principal component analysis (PCA) methods. The results showed that powders had stronger spectroscopic activity than tablets. CM and PCA were accurate in differentiating genuine from counterfeit antibiotics with exception observed in Fabamox Duo and Lamivir products. Spatially offset Raman spectroscopy, validated most sample identities and detected discrepancies not visible to NIR spectroscopy. The findings highlighted the synergistic strengths of both techniques being: sensitivity of near-infrared spectroscopy to physical properties and Raman's specificity to chemical properties. Moreover, chemometrics showed powerful in classifying antibiotics of different manufacturers.

In recent years, saliva has emerged as an alternative biological matrix, offering several advantages such as its accumulative nature and non-invasive, non-intrusive sampling. Moreover, paired with novel vibrational spectroscopic techniques such as attenuated total reflectanceFourier transform infrared (ATR-FTIR) and Raman spectroscopy, saliva can be utilized for the detection and monitoring of drug use. Previous detection methods required extensive sample preparation and do not allow for rapid and portable analysis. Therefore, this work employed two vibrational spectroscopic instruments, those being: the Agilent 4500a ATR-FTIR spectrometer and the Agilent Resolve Raman spectrometer for the detection of drugs and their metabolites in artificial saliva. Both instruments were successful in the detection of illicit and over-the-counter drugs including benzoylecgonine, cocaine hydrochloride (HCl), diazepam, delta-9-tetrahydrocannabinol (THC) and paracetamol. A surface enhanced Raman spectroscopy (SERS) method was also developed for enhanced Raman signals. The chosen vibrational spectroscopic techniques utilized demonstrated the ability to detect key drug-related bands at concentrations as low as 0.05 mg/mL and over a four-week period. However, particularly in the case of SERS, the activity of drug-related bands decreased over this time.

As an alternative biological matrix, fingernails act as a non-invasive window into systemic diseases such as cardiovascular diseases (CVDs) or diabetes mellitus (DM). The presence of such diseases manifests physically, altering the fingernail plate's topography, as well as its elemental composition. Scanning electron microscopy (SEM) equipped with energy dispersive X-ray spectrometry (EDX) and scanning transmission electron microscopy detector (STEM), allows for detailed composition analysis, elemental mapping and spectroscopy. As complementary detectors, the presence of key elements such as calcium, oxygen, potassium and silicon can be quantified and investigated in relation to the presence of disease. Furthermore, topographical STEM images provide insight into the prevalence of tissue damage to the fingernail, which is often attributed to hyperglycemia or poor circulation. The EDX weight% values of identified elements within the fingernails were exported into Matlab R2024a, where a machine learning algorithm, principal component analysis (PCA), was applied to identify patterns between the elemental composition of healthy and diseased fingernails. Analysis of variance (ANOVA) results demonstrated relationships between confounding variables such as biological sex and diet and elemental composition. Female participants demonstrated a significantly higher weight% value of titanium than males due to the exposure of titanium in personal-care products and sun creams. The weight% value of calcium was also significantly different in fingernails of individuals who practiced extremely healthy, healthy and unhealthy diets. In the presence of disease, calcium and sodium showed significantly different weight% values in healthy versus diseased fingernails. STEM images further confirmed the presence of disease, with CVD and/or diabetic fingernail clippings showing rough, topographical textures. In contrast, fingernails taken from healthy participants displayed smooth areas, with small amounts of rough texture. Therefore, demonstrating the ability of SEM to detect the presence and severity of disease.

In recent years, augmented reality has received a considerable lot of interest. Augmented reality application cases are expanding all the time. People may now readily experience augmented reality because to the widespread availability of smartphones. This enables scholars from all around the world to use it. The use of augmented reality-based interactive technologies in education is on the rise. In this study, we proposed a method that allows students to learn the human skeletal system and anatomy using their smartphones. The proposed method offers visualizing the human skeletal system, including bones, in 3D using augmented reality and also interacting with the 3D bones. The substantial finding of the study reflects on how students can benefit from this Augmented Reality-based interactive method. Qualitative assessment was accumulated from 159 medical students who have experience with the traditional human skeleton learning experience and also participated in the augmented reality-based human skeleton system.

Speech enhancement algorithms and machine learning can play a fundamental role in signal processing to improve speech quality. These techniques can be used to reduce noise and distortions in speech signals, hence ensuring clearer and more intelligible speech. By leveraging advanced machine learning, speech enhancement algorithms not only improve the listener’s auditory system, but also increase the efficacy of speech recognition systems. In particular, deep learning is a class of machine learning techniques, which have recently been used in speech enhancement. This paper proposes the use of Discrete Hahn polynomials (DHPs) o extract spectral features from noisy signals using fully connected neural networks and convolutional neural network. Deep learning can efficiently capture the contextual information of speech signals, resulting in superior improvements in speech quality and intelligibility properties. The results are evaluated based on the well-known TIMIT database. The results show that the presented model is able to enhance the speech signal for different conditions.

Water issues related to Iraqi rivers and reservoirs have devastating consequences on the citizens’ health and country’s economy. This has been seen in the increased number of non-communicable diseases and jobs’ shortage in the country as-a-whole. This paper discusses the factors contributing to water scarcity in Iraq and proposes intelligent solutions. Factors contributing to water issues are not limited to extreme weather conditions, and include water scarcity, evaporation, water contamination and water salinity. What makes the situation more complicated is the outdated water systems that have been used for monitoring, analysis, irrigation, and control of water. In addition, human factors play important role in decision-making in terms of use of these systems. Uses of these systems is not an easy task as it requires well-established standard operating procedures and comprehensive/integrated databases; where, both are lacking in Iraq. The paper is envisaged to implement an Intelligent Water System that utilises the latter technologies for trying to solve all the challenges within the existing water management system. Implementing such intelligent water system and intelligent barriers will benefit Iraq on the short and long-term with specific aids to the environment, economy, citizens and the country as-a-whole. Thus, the proposed intelligent water system will result in cleaner air and water, better quality crop and land, and less pollution. Citizens will have better health and quality of life and more job opportunities. In addition, the country will have new jobs and industries, smarter and more sustainable agricultures, self-sustainable smart cities, self-sufficient economy, and healthier.

Identifying cosmetics on substrates is essential in any crime scene processing. It is important in such cases to warrant the sample integrity and continuity. Spectroscopic techniques offer the advantage of analyzing samples non-destructively thus addressing the aforementioned requirements. When used in handheld modality, spectroscopic techniques offer rapid and on-site analysis with the ability to collect numerous datasets in minimal time. |Each spectrum is a unique fingerprint of the sample measured and that urges the need to collect large datasets and apply machine learning algorithms to make meaningful conclusions from analysis. Therefore, this work involved applying machine learning algorithms to infrared, near-infrared, and Raman spectroscopic data of cosmetics applied to different substrates. The cosmetics included powder, creams, lipsticks and nail polish; and the substrates included paper, fabric and glass. Machine learning algorithms were correlation method and principal component analysis. Both algorithms showed to be complementary in identifying cosmetics on different substrates, Thus, the approach proved accurate and precise for identifying substrates encountered at crime scenes.

Cloud storage capacity for surveillance videos is restricted by the massive amounts of bandwidth needed to upload them and the substantial storage space they consume. As a result, researchers are actively exploring methods to reduce file sizes while maintaining critical visual details. The goal is to achieve a balance between minimizing the storage size required and preserving video quality, all while keeping costs as low as possible and achieving the best possible results. This paper proposes a developed approach to optimize surveillance video compression. Specifically, each frame, after being acquired, is applied to extract regions of interest (ROI) where motion has occurred, ensuring that the entire desired area is captured. Next, the extracted areas with no changes are zeroed out, reducing unnecessary data. The resulting area is then encoded and transmitted. When the encoded video is received, the decoding process is carried out to restore the video to its original content, i.e., video frames. Three datasets are used to evaluate the performance of the developed algorithm. In addition, the obtained results are compared to the basic video, which shows that the developed algorithm produced good results, outperforming the MJPEG algorithm and existing algorithms.

The wealth of information associated with the exponential increase in digital text, particularly within the biomedical field, has the potential to advance medical research, improve patient care, and enhance public health outcomes. However, the sheer volume and complexity of this data necessitate advanced computational tools for effective processing and analysis. We investigated the use of various pretrained transformer-based language models, particularly BERT, PubMedBERT, SciBERT, ClinicalBERT, DistilBERT, and the application of prompt engineering with GPT-4, within the context of biomedical Named Entity Recognition. Our approach incorporates a comprehensive performance evaluation analysis utilizing standard NLP evaluation metrics and computational resource usage metrics such as training time, memory usage, and inference time. Through this multifaceted approach, we sought to find out how the few-shot prompting approach using GPT4 performs in comparison to the BERT-variant language models while at the same time identifying models that not only excel in performance efficiency but also demonstrate computational affordability. Our experimental results show that even the most basic transformer-based language model outperforms the few-shot prompting approach of GPT-4, despite the popularity of the LLM in the more general Natural Language Processing tasks.

Constructing a Question Answering system is a challenging task despite a significant amount of study that has been conducted in recent times on this topic. It is even more difficult to provide satisfactory responses to the inquiries raised by users in an organizational setting as opposed to in an informal setting. We present in this paper, the results of our study into the use of a transformer-based model in the development of a technical document query system with machine reading comprehension. Our method fine-tunes a pre-trained transformer model with hyperparameter optimization using a pre-processed training dataset and tested on a different dataset. We experimented using eight pre-trained models from seven different variations of the BERT transformer architecture including BERT, RoBERTa, XLM-RoBERTa, ELECTRA, ALBERT, MobileBERT, and MPNet using the SQuAD1.1 dataset for fine-tuning and the Oracle Knowledge Documentation for testing. We found that the ALBERT pre-trained model is the best model achieving 0.891, 0.950, and 0.882 performance when measured using the Exact Match, F1 score, and Confidence Score metrics - despite its relatively small model size.

Speech is considered the most important way for communication between humans. However, various types of noise degrade speech signals and reduce speech clarity. Usually, speech should be clear as much as possible to be used in the application at hand such as mobile telephony, Tele-communication and hearing aids systems, smart phone applications. Speech enhancement techniques aim to enhance the clarity and quality of speech, thereby improving its overall intelligibility. This is performed using various speech enhancement algorithms (SEA) like filtering, spectral subtraction, and deep learning techniques. This paper provides a brief review on different SEA, and it contains the study of several enhancement models with a discussion of their properties. An investigation of the enhancement process in time and transform domain is performed. Some basic types of background noise are explained with providing a brief description of the challenges and opportunities of speech enhancement processes. The presented paper relates to several research studies in the field of speech enhancement, observed up to 2024. This paper presented the use of enhancement techniques for suppression process through judging several enhancement algorithms for getting the best performance.

To date, cardiovascular disease (CVD) is responsible for a considerable number of deaths each year. Hence, developing an effective CVD prediction model is essential to reducing mortality rates. To this end, this paper makes use of different machine learning (ML) classifiers such as logistic regression (LG), K-nearest neighbor (KNN), support vector machine (SVM), gradient boosting (GB), and adaptive boosting (AdaB) to improve CVD prediction performance. In addition, this paper investigates the use of ML based on the ANOVA feature selection method and voting ensemble model by aggregating different ML classifiers to improve CVD prediction. The CVD performance is evaluated using key metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The results demonstrate that the proposed approach achieves the highest CVD prediction accuracy compared to state-of-the-art methods recording 93.44%. The findings obtained in this paper suggest that the SVM ANOVA feature selection and ensemble approaches can be considered practical strategies for improving the prediction accuracy of CVD.

Non-destructive identification of cosmetics is essential to confirm their identity and purity. Near-infrared (NIR) spectroscopy provides a fast and non-destructive method for cosmetic identification. For this study, 99 raw materials and 30 products were measured using a palm sized NIR spectrometer. Spectral pre-treatment and analysis involved techniques such as multiplicative scatter correction-first derivative (MSC-D1), correlation in wavelength space (CWS), and Principal Component Analysis (PCA) respectively. Among the raw materials, 66 exhibited strong NIR activity, 25 showed medium NIR activity, and eight had weak NIR activity, while all 30 samples were found to be NIR active. The CWS method revealed a high frequency of Type II errors, with 81 out of 99 raw materials mismatching. All 30 of the products also resulted in mismatches. PCA proved to be the more accurate of the data analysis techniques with creams $\mathbf{9 7 \%}$ of variance was accounted for in PC1, and PC scores demonstrating strong differentiation among seven of the eight cream products. In contrast, the perfume products displayed $\mathbf{8 4 \%}$ variance in PC1 and $13 \%$ in PC2, with two of the seven products showing significant discrimination from the others. This study confirmed that NIR spectroscopy is well-suited for this application as it provides a quick analysis time, no sample preparation and allows for sample preservation.

Covid-19 is a novel coronavirus that emerged in 2019 and spread across the globe, establishing a worldwide pandemic. Vaccination was presented as the most effective solution against the virulence of Covid-19. Accelerated vaccination programmes pushed several nucleic acid-based vaccines into production. Global desperation and limited vaccine supply allowed substandard and falsified (SF) Covid-19 vaccines to enter the supply chain. Conventional analytical methods can be cumbersome, costly and sophisticated to operate. Thus, this study presented a comparison of handheld surface-enhanced Raman spectroscopy (SERS) and Raman microscopy with machine learning algorithms (MLAs) for the rapid authentication of Covid-19 vaccines. Measurements were taken using the Metrohm MIRA XTR DS handheld Raman spectrometer and the Horiba XploRA Plus Raman microscope. Raman spectroscopy showed strong potential as a vaccine authentication method, allowing identification of nucleic acid-specific bands in spectra. SERS showed enhancement of up to $498 \%$ when applied to vaccines of sufficient concentration. Clustering based on principal component analysis (PCA) showed some accuracy but indicated poor repeatability for SERS, although, multiple classification models obtained $100 \%$ accuracy and area under the curve (AUC) for vaccine brand prediction based on spectral characteristics. Raman microscopy produced variable results with improved spectral quality over Raman spectroscopy for a number of samples. However, significant fluorescence was observed in numerous vaccine spectra, limiting the identification potential of the method. Clustering based on PCA showed accuracy in distinguishing between vaccine samples, but showed limited performance in vaccine brand identification. Therefore, this paper presents proof of concept for the use of both handheld Raman spectroscopy and confocal Raman microscopy alongside MLAs for the rapid, on-site authentication of Covid-19 vaccines, with further method optimisation required to combat fluorescence interference in vaccine spectra and expansion of sample size to address the potential of overfitting in the MLAs.

The prevalence of cardiovascular diseases (CVDs) and diabetes mellitus (DM) has become a global concern with figures as high as $\mathbf{1 7. 9}$ and $\mathbf{1. 5}$ million lives lost annually [1, 2]. Global figures also suggested that the majority of CVDs and DM are present within low- and middle-income countries (LMICs), where medical equipment, staff and training is limited. As a result, many patients go underdiagnosed or undertreated and instead are left to manifest into further complications such as heart failure or diabetic ketoacidosis, respectively. Therefore, this study aimed to investigate the use of nearinfrared (NIR) spectroscopy paired with machine learning algorithms (MLAs) for detection of CVDs and DM in fingernails. The findings showed key NIR bands related to the glycation of proteins within the fingernails and indicated the presence of disease. Furthermore, binary and multi-class classification models were explored for the classification of healthy, unhealthy, CVD and diabetic fingernails.

In the Beyond-5G (B5G) and sixth generation (6G), several advanced techniques are based on high-frequency millimeter-wave wireless communications. This paper proposes the design of a novel B5G and 6G wireless radio access network (RAN) architecture. This architecture aims to be a key enabling factor for significantly increasing network capacity, promoting the deployment of new services, and integrating with the evolution of the previous cellular wireless access network architecture. Furthermore, the proposed architecture is adaptable to the various characteristics of high-frequency millimeter-wave communication. It leverages on the allocation of each layer resources of the different networks for more efficient deployment.

Alzheimer's disease (AD) is neurodegenerative brain illness. It is classified as a degenerative illness since it worsens with time. A multitude of risk factors contribute to the development of Alzheimer's disease, such as demographic information, test scores, and genetics. The paper presents the comparison of machine learning algorithms to identify the highest accuracy level in classification of Late Onset Alzheimer's disease. Dataset from the Alzheimer's Disease Neuroimaging Initiative has been requested to train and test the machine learning models. The dataset included 539 normal controls and 411 Alzheimer's Disease individuals. A main dataset includes variables that are often used in clinical practice to develop the machine learning algorithms. Another dataset was created that exclusively included subjects aged 65 and up in order to assess the accuracy of algorithms used to diagnose late-onset Alzheimer's disease. According to the benchmarked findings, Linear Discriminant Analysis performed the most efficiently, achieving accuracy and an F1-score of 1.

The recent era of technology, Industry 4.0 finds its way to the field of manufacturing based on advanced technology such as artificial intelligence, internet of things, augmented reality, robotics, and more. These technologies can truly lead a massive transformation in production and manufacturing processes. This study aims to understand the extent to which undergraduate students in the field computer science and information technology in Iraq are aware of the techniques and applications of Industry 4.0. For this purpose, we have reviewed the literature as well as have collected opinions of students using a paper-based survey at the college of computer science and IT, University of Anbar. This can help in determining the level of students’ awareness of Industry 4.0 and to identify limitations, if any, when it comes to their educational journey. Data has been analyzed and results shown no differences between males and females when it comes to Industry 4.0 applications understanding. Beside this, students from different departments shown somewhat different sense regarding their knowledge of Industry 4.0 techniques and applications, which may be a big indication of the urgent need of curriculum revision and update.

The number of livestock farms and their sizes (particularly the sheep farms) are on the rise, in response to the growing demands of food supply chain for increasing population. The detection and monitoring of sheep activities particularly in huge farms is tedious and challenging task. Therefore, a reliable and cost-effective sheep activity detection system which can be utilized for the virtual fencing, is of high demand. Existing data-driven approaches use accelerometer data for sheep monitoring and activity detection however, there are several limitations with these methods such as generating high volume of data with noise, relatively expensive, and not very reliable. This study presents a non-invasive computer vision-based approach along with deep transfer learning for sheep detection and determining whether the corresponding state is ‘active’ or ‘inactive’. We complied a primary dataset comprising sheep in diverse poses and activities in a realistic outdoor environment. A custom YOLOV5s model is trained over new dataset and validated on purely unseen sheep instances for the model evaluation. The statistical outcomes demonstrate the robustness of proposed approach for various sheep activity detection. Our method has diverse implications and uses in the development of reliable and economical systems for monitoring sheep, particularly in extensive farms and virtual fencing applications.

The act of trading in the financial markets from a discretionary standpoint comes with a vast number of pitfalls that lead to participants achieving poor returns on their investments. With trading being a psychologically intense activity, the paper presents development of trading algorithms that will not only eliminate the psychological barriers to trading but do so in a way that ensures that significant returns on investments are made, with these returns being evaluated by testing the strategies on past historical price data of various assets. Findings noted that the algorithms performances varied depending on the market circumstances with certain strategies only being applicable to either strong or weak market conditions. The implication of these findings opens the door to new discussions since the algorithms developed resided outside of the traditional high frequency trading model which are the most prominent trading applications found on the markets. This unconventional algorithmic approach to the markets verifies a way of obtaining significant returns without the requisite of having low latency, thus enabling one to compete with the more sophisticated algorithms developed and used by the major financial institutions without the need for human intervention or any additional resources.

ChatGPT is an extensive language model under the umbrella of generative artificial intelligence that produces answers from data and images curated from online resources. Despite the capability to produce accurate responses, but requires verification; the responses are based on statistical patterns rather than true comprehension, i.e., it does not have consciousness and does not understand the questions from the perspective of human comprehension. The ability of ChatGPT to understand and react to questions in a humanistic way has garnered a lot of public and scientific interest over the past year. This study analyzes responses of ChatGPT to 100 questions on epilepsy in order to assess the validity of the tool in this field. Besides, this work sheds light on the advantages and disadvantages of the approach in this particular topic by analyzing responses of ChatGPT to queries on epilepsy. The study evaluates the model performance by looking at the completeness, correctness, and relevancy of responses. The findings in this paper indicate that ChatGPT has limits because of its training data and design structure, even though it could give insightful and appropriate answers to inquiries about epilepsy. It is concluded that ChatGPT can be an advantageous tool for medical professionals working on the subject of epilepsy. Nonetheless, it should be noted that ChatGPT should be utilized cautiously and in conjunction with various information sources, like clinical practice guidelines and peer-reviewed studies.

The Internet of Things refers to a vast and interconnected distributed systems in which components have a high degree of heterogeneity in terms of software, hardware, and connectivity, while they deliver different services. The quality of service for users accessing the Internet of Things supported by cloud computing is increasing exponentially. However, the deployment of Internet of Things applications in a cloud environment can be very dynamic, resulting in service demands and high resource requirements. The task of effectively managing and optimising resource allocation while taking into account time-sensitive requests is a significant and complex problem that has implications on service quality. The proposed solution aims to improve task scheduling in a hybrid cloud environment for Internet of Things applications. This improvement involves implementing load-balancing techniques to achieve cost reduction, energy consumption, and enhanced overall execution time. The designed solution encompasses two main phases. In the first phase, clustering is performed on computing hosts. In the subsequent phase, user requests are assigned to a suitable cluster, utilising the enhanced Firefly algorithm. The simulation results demonstrated the efficiency of the proposed solution in terms of energy consumption and execution time compared to a benchmark algorithm.

This paper introduces a proof-of-concept study focused on AI-powered pre-surgery planning for cheiloplasty, a vital aspect of plastic surgery dedicated to enhancing and reshaping the lips. The research tackles the intricate task of selecting the most suitable surgical approach by harnessing the capabilities of artificial intelligence (AI) and machine learning. The methodology entails a comprehensive analysis and the extraction of features from various facial components, including the lips, nose, eyes, and eyebrows alongside an assessment of overall facial aesthetics. Utilizing advanced computer vision algorithms, these facial components are extracted from preoperative images. Central to the system is a Multi-Modal Convolutional Neural Network (CNN) architecture, which leverages the extracted facial features to predict outcomes for specific cheiloplasty techniques. Rigorous training and validation of the CNN involve meticulous comparisons with ground truth data and expert assessments to ensure precision and dependability. Furthermore, the study underscores the system’s user-friendliness and practicality by gathering feedback from seasoned plastic surgeons. Adherence to strict ethical guidelines guarantees the protection of patient data and the mitigation of potential biases. The successful development of this proof of concept highlights the vast potential of AI integration in pre-surgery planning for cheiloplasty. By equipping surgeons with technique-specific insights derived from facial components and style analysis, the system enhances decision-making, ultimately benefiting patient care and treatment outcomes. Future endeavours will expand the dataset, consider additional variables, and encompass prospective clinical trials to validate the system’s real-world impact in the field of lip-repair surgery.

Animal-Vehicle Accidents have shown deep increase in the middle east regions over the last decades. These collisions resulting from camels fleeing the wildlife and crossing the roads and hence endangering drivers and camel's lives and leading to habitat degradation. Additionality, the size, strength, and the unpredictable behavior of camels play a key role in high mortality rates in the camel-vehicle collisions. Various solutions and countermeasures such as warning signs and fences have been adopted in the past. However, several drawbacks are associated to them, and their effectiveness are reducing with time. Therefore, this study proposes a framework for the use of machine learning approaches and computer vision for the detection and recognition of camels. This can help to provide warning to drivers about potential animal crossings in an effort to mitigate camel-vehicle accidents.

Water resources such as rivers and reservoirs are affected by multiple factors such as climate change and rainfall patterns. Therefore, forecasting river discharges becomes crucial for effective water resource management. River discharge forecasting techniques, such as artificial neural models, provide a framework for analyzing and predicting river flow patterns over specific periods. These forecasts can be used to better manage water resources through water resource planning, dam operation, and flood prevention. Forecasting river discharges improve water resource management and make sustainable strategic decisions to optimize water use and reduce risks associated with floods and water scarcity. The study aims to use artificial neural network models to predict the daily discharge of the Euphrates River upstream of Haditha reservoir in Anbar province. Two different models were used: The feed-forward back Propagation single layer (FFBP) neural network and the Multilayer Perceptron (MLP) neural network. The models were trained and tested using daily discharge time series data (2018-2023). The results showed that the Multilayer neural network structure with the combination (3-12-6-1) was better than the single layer (FFBP) based on the coefficient of determination (R2) values of 0.90 for the second model MLP and 0.88 for the first model (FFBP) and the values root mean square error (RMSE) of 52.64 and 14.97, respectively. The results revealed the effect of time delay and dependence on previous discharges on the inputs of artificial neural network models (ANNs). A time delay of three days turned out to be the best and provided excellent performance for both models.

This comprehensive review explores the landscape of assistive technology designed to support physically disabled adults. The paper encompasses a thorough examination of technological interventions aimed at enhancing the independence and quality of life for individuals facing physical disabilities. Focusing on a diverse range of assistive devices and systems, including mobility aids, communication tools, and adaptive interfaces, the review assesses their effectiveness, usability, and impact on daily living. It synthesizes current research findings, technological advancements, and user experiences, offering insights into the evolving field of assistive technology. Additionally, the review addresses challenges, potential future developments, and the role of emerging technologies in furthering the integration of assistive solutions. This synthesis contributes to a holistic understanding of the state-of-the-art in assistive technology for physically disabled adults, providing a valuable resource for researchers, practitioners, and policymakers working towards enhancing inclusivity and empowerment.

Predicting the criminals' behaviour is a difficult task to accomplish. It is unexpected in most cases and can possibly transpire at any time, which is challenging for police agencies and victims being affected by the offences. The proposed work presents a crime prediction model using the stop & search dataset and the demographic of those charged with possession of a weapon. The study is first of its kind using multiple publicly available datasets to predict the effectiveness of ‘stop & search’ interventions by the police. We employ multiple machine learning algorithms to predict whether a ‘further action’ is required following the stop & search by the police. We utilise several data science techniques mainly including pre-processing, feature engineering and appropriate use of model selection. The proposed model produced 93.20% accuracy using Random Forest classifier. The outcomes of this research can be useful by relevant authorities to anticipate the crime at a specific time and location through the analysis of patterns that will support decision-making and help on deterrent effective strategies to lower offences being committed.

Amongst different types of cancer, skin cancer has shown an increasing trend over the decade. Skin cancer is mainly caused due to exposure of human skin to ultraviolet rays, due to overexposure to the sun. Early diagnosis of skin cancer can help in preventing the further spread of the deadly disease. But there is a lack of clinical services and expertise, and this situation has worsened due to the ongoing pandemic. An automated system to guide the clinicians is the need of the hour. There are a lot of AI-based systems developed using datasets that are publicly available. Especially, deep learning-based solutions are available which detect the malignancy and classify it into a particular type of malignancy. CNN is a proven technology in the diagnosis of skin cancer. Various models based on transfer learning have been developed. The various systems that have been developed are still in the early stages of clinical deployment. There are still many challenges and open issues. It is proposed to investigate the work done so far and to develop a model with matching or improved performance. HAM 10000 dataset containing dermoscopic images is used for the research work. Dataset preprocessing is done to resize the images and to augment the dataset. The class imbalance has been addressed using data augmentation. Three models have been trained and tested. CNN-based, MobileNet V2 and Resnet50 based models have been built and tested. Achieved a validation accuracy of 86% for CNN, 96% for MobileNet and 89% for ResNet50.

Counterfeit medicinal and lifestyles products are a global issue that impacts public health. Counterfeit products are often made in unsafe and unsanitary conditions before their release to the public without testing by regulatory bodies. One product that is particularly susceptible to online counterfeiting is Viagra, which is one of the highest selling medicines worldwide. A total of 57 Viagra tablets were used for the study; this included 27 authentic and 30 counterfeit tablets which were measured using near-infrared spectroscopy (NIRS). Spectra obtained using the NIR spectrometer non-destructively were exported into a multi-paradigm numerical computing environment where machine learning algorithms (MLAs) were applied using Matlab 2007a. Four algorithms were used related to correlation in wavelength space (CWS), K-nearest neighbour (KNN), principal component analysis (PCA) and PCA combined with fuzzy C-mean clustering (PCA-FCM). The algorithms were applied unsupervised to the authentic and counterfeit tables with no prior labelling to any of the tablets. The results showed two clear groups/clusters between the authentic and counterfeit tablets. In particular, PCA and PCA-FCM showed further subgroups among the counterfeit tablets that corresponded to their varying manufacturing sources. In summary, the use of NIRS and MLAs proved an effective method for identifying counterfeit Viagra medicines rapidly and non-destructively.

Gesture recognition is a topic in computer science and language technology with the goal of interpreting human gestures via mathematical algorithms. It is a subdiscipline of computer vision. In this paper, we describe some of Gesture recognition techniques such as Vision based gesture recognition and Graph based gesture recognition. Also, we explore these techniques with previous studies.

Gesture recognition is a computing process that attempts to recognize and interpret human gestures through the use of mathematical algorithms. In this paper, we describe Point Based Gesture Recognition and Point Clouds nearest neighbors and sampling. Also, we explore these techniques with previous studies.

Oral fast dissolving films (FDFs), have gained attention as an alternative dosage form to solid oral dosage forms such as tablets as their ease of use increases patient acceptability and adherence. This study aimed to investigate spatially offset Raman spectroscopy (SORS) and attenuated total reflectance Fourier Transform Infrared (ATR-FTIR) spectroscopy as quality control methods, to assess the suitability of these techniques in hospital pharmacy settings for individualised dosage forms. The findings showed that both Raman spectroscopy and FTIR were successful in identifying the active pharmaceutical ingredient (API) present in the samples however, further investigation with more sensitive techniques such as Surface Enhanced Raman Spectroscopy (SERS) should be conducted.

COVID-19 is a novel coronavirus first emerging in Wuhan, China in December 2019 and has since spread rapidly across the globe escalating into a worldwide pandemic causing millions of fatalities. Emergency response to the pandemic included social distancing and isolation measures as well as the escalation of vaccination programmes. The most popular COVID-19 vaccines are nucleic acid-based. The vast spread and struggles in containment of the virus has allowed a gap in the market to emerge for counterfeit vaccines. This study investigates the use of handheld Raman spectroscopy as a method for nucleic acid-based vaccine authentication and utilises machine learning analytics to assess the efficacy of the method. Conventional Raman spectroscopy requires a large workspace, is cumbersome and energy consuming, and handheld Raman systems show limitations with regards to sensitivity and sample detection. Surface Enhanced Raman spectroscopy (SERS) however, shows potential as an authentication technique for vaccines, allowing identification of characteristic nucleic acid bands in spectra. SERS showed strong identification potential through Correlation in Wavelength Space (CWS) with all vaccine samples obtaining an r value of approximately 1 when plotted against themselves. Variance was observed between some excipients and a selected number of DNA-based vaccines, possibly attributed to the stability of the SERS colloid where the colloid-vaccine complex had been measured over different time intervals. Further development of the technique would include optimisation of the SERS method, stability studies and more comprehensive analysis and interpretation of a greater sample size.

Near infrared (NIR) spectroscopy offers portable and rapid analysis of endogenous constituents and drugs within fingernails. Fingernails are a useful alternative biological matrix to blood and urine specimen as they provide the advantage of being non-invasive and require minimal sample size (1–3 mm). This work utilised NIR spectroscopy for the detection of (1) drugs in fingernails including benzocaine, calcium carbonate, cocaine hydrochloride (HCl), levamisole HCl, lidocaine HCl and procaine HCl; and (2) endogenous constituents such as carbohydrates, lipids, proteins and water. Fingernails were analysed initially ‘as received’ to identify the aforementioned endogenous constituents. Seven sets of fingernails were then spiked with one the identified drugs and measured over a six-week period. Spectra were exported into Matlab 2019a for spectral interpretation and machine learning analytics (MLAs). MLAs included correlation wavenumber space (CWS), principal component analysis (PCA) and Artificial Neural Networks Self-Organising Maps (SOM). The results showed that NIR spectra of spiked nails showed key characteristic features at specific wavelengths that corresponded to their spiked drug (1). When combined with CWS and PCA, NIR spectroscopy was able to differentiate between spiked and un-spiked nails and distinguish between the drugs that did not share similar chemical structures. CWS values (r values) and PCA loading scores highlighted spectra/spectral features that were significant. In addition, SOM showed further classes beyond PCA that corresponded to changes in physical properties of the fingernails. Thus, finding confirmed that NIR spectroscopy combined with MLAs possessed the ability to characterise fingernails based on their endogenous constituents and to detect the presence of drugs within fingernails.

The use of handheld Raman spectroscopy has increased in popularity based on its ability to provide portable and rapid analysis of endogenous compounds and diagnostic biomarkers in alternative biological matrices, such as fingernails. The application of fingernails as a diagnostic matrix allows for non-invasive, non-intrusive sampling, which can be carried out in the comfort of the patient’s home. This study aimed to identify diagnostic biomarkers in fingernails related to cardiovascular diseases (CVDs) and diabetes mellitus (DM) using Raman spectroscopy and machine learning algorithms (MLAs). The findings showed that Raman spectroscopy successfully identified the presence of disease specific biomarkers in CVD and diabetic fingernails. Furthermore, when used in combination with MLAs, Raman spectroscopy was able to differentiate between healthy, CVD and diabetic fingernails. Further investigation will look at applying additional MLAs for determining the prognosis of disease.

Alzheimer's disease (AD) is a type of brain disorder that is regarded as a degenerative disease because the corresponding symptoms aggravate with the time progression. Single nucleotide polymorphisms (SNPs) have been identified as relevant biomarkers for this condition. This study aims to identify SNPs biomarkers associated with the AD in order to perform a reliable classification of AD. In contrast to existing related works, we utilize deep transfer learning with varying experimental analysis for reliable classification of AD. For this purpose, the convolutional neural networks (CNN) are firstly trained over the genome-wide association studies (GWAS) dataset requested from the AD neuroimaging initiative. We then employ the deep transfer learning for further training of our CNN (as base model) over a different AD GWAS dataset, to extract the final set of features. The extracted features are then fed into Support Vector Machine for classification of AD. Detailed experiments are performed using multiple datasets and varying experimental configurations. The statistical outcomes indicate an accuracy of 89% which is a significant improvement when benchmarked with existing related works.

Summary Discrete Tchebichef polynomials (DTPs) and their moments are effectively utilized in different fields such as video and image coding, pattern recognition, and computer vision due to their remarkable performance. However, when the moments order becomes large (high), DTPs prone to exhibit numerical instabilities. In this article, a computationally efficient and numerically stable recurrence algorithm is proposed for high order of moment. The proposed algorithm is based on combining two recurrence algorithms, which are the recurrence relations in the and ‐directions. In addition, an adaptive threshold is used to stabilize the generation of the DTP coefficients. The designed algorithm can generate the DTP coefficients for high moment's order and large signal size. By large signal size, we mean the samples of the discrete signal are large. To evaluate the performance of the proposed algorithm, a comparison study is performed with state‐of‐the‐art algorithms in terms of computational cost and capability of generating DTPs with large polynomial size and high moment order. The results show that the proposed algorithm has a remarkably low computation cost and is numerically stable, where the proposed algorithm is 27 times faster than the state‐of‐the‐art algorithm.

Alzheimer's disease is one of the brain disorders. It's also characterized as a degenerative disease because it becomes worse over time. Apolipoprotein E (APOE) is a genetic risk factor for Alzheimer's disease that has been linked to the disease in several genome-wide association studies (GWAS). Single nucleotide polymorphisms are the most common type of genetic variation among individuals (SNPs). SNPs have been identified as important biomarkers for this condition. SNPs aid in the study and detection of the disease in its early stages. We focus on employing a stacked Machine Learning (ML) model to categories Alzheimer's patients in this paper. The model was tested on all AD genetic data from phase 1 of the neuroimaging project (ADNI-1). The results showed that the stacked model outperformed other machine learning methods with an overall accuracy of 93.7 percent. The findings suggest that stacking approaches are effective in detecting Alzheimer's disease.

We are delighted to present this novel special issue, which emphasizes semantic eSystems and their engineering methods, techniques, and tools. “eSystems” are those interdisciplinary cost-effective and interconnected solutions that leverage advanced information and communication technologies' techniques and tools to gain competitive advantage. Recent years have witnessed increasing interest in the design and development of various eSystem-based applications, ranging from real-world to machine and robotic applications. An essential feature in eSystems is their intelligent ability to “speak” and interact with one another to support function “extensibility” so that complex interactions could be established with other eSystems. Therefore, connecting disparate eSystems “on the fly” necessitates engineering a dialog channel such that it enables data fusion, exchange, and link in a unified and understandable way. While data emitted from eSystems are of different formats, sizes, and types, adopting semantic data technologies is a natural way to address these differences. Simply put, semantics is about agreeing on a common understanding of data that need to be exchanged between systems and between humans and systems. This special issue received 22 submissions, which were aligned with the theme of semantic eSystems' methods, techniques, and tools. Those submissions came from diverse researchers from academia, industry, and individuals from all over the globe. First, all submissions were screened closely by the editors to check their suitability with the special issue's list of topics. Second, after multiple rounds of peer review, only 11 high-quality submissions were accepted for publication in this special issue. Those accepted papers address the semantic eSystems theme from different perspectives including, for instance, efficient semantic–visual indexing model for large-scale image retrieval in cloud environment, trilateration-based indoor localization engineering technique for visible light communication system, graph-based system to enable efficient transformation of enterprise infrastructures, recognizing physical activities having complex interclass variations using semantic data of smartphone, spatiotemporal-based sentiment analysis on tweets for risk assessment of an event using the deep-learning approach, sentiment-based eSystem using hybridized fuzzy and deep neural network for measuring customer satisfaction, data fusion analysis for emotion recognition with thermal image and Internet of Thing devices, unified framework to manage cybersecurity and safety in manufacturing industry, graph-based convolutional neural network stock price prediction with leading indicators, author classification using transfer learning and predicting stars in coauthor networks, and DNA signal analysis tool: intelligent noise suppression window filter. The authors express their sincere thanks to the Editor-in-Chief for allowing them to organize this special issue. The editorial office staff members are excellent and are thanked for their support. The authors are also thankful to all the contributors who made this special issue possible and to the reviewers for their thoughtful contributions.

Cloud services are often distributed across several data centers requiring new scalable approaches to efficiently perform searching to reduce the energy and price cost of fulfilling requests. Multiagent-based systems have arisen as a powerful technique for improving distributed processing on a wide scale, which can operate in environments where partial observability is the norm and the cost of prolonged search can be exponential. In this paper, we present a multiagent-based service composition approach, using agent-matchmakers and agent-representatives, for the efficient retrieval of distributed services and propagation of information within the agent network to reduce the amount of brute-force search. Our extensive simulation results indicate that by introducing localized agent-based memory searches, the amount of actions (with their associated energy costs) can be reduced by over 50 percent which results in a lower energy cost per composition request.

Ground-level ozone concentration is one of the main concerns for air pollution, due to the negative impacts on human health, animals, foliage, climate and the whole ecosystem. The aim of this paper is to reduce the influential outliers by including weightages within robust method to avoid the bias of the model. The influential outliers from x-space (predictors) have been identified using leverage values. Furthermore, Cook's distance and standardized residual have been computed to clarify the influential outliers from both of x-space and y-direction. S-estimation and MM-estimation have been introduced as a new approach for reducing the influential outliers from x-space and both of y-direction and x-space respectively. The comparison between the robust method and the ordinary least square method shows that, the accuracy measures of the robust method have been improved by around 0.94% (D+1), 0.56% (D+2) and 1.85% (D+3) respectively.

Epistasis is a progressive approach that complements the 'common disease, common variant' hypothesis that highlights the potential for connected networks of genetic variants collaborating to produce a phenotypic expression. Epistasis is commonly performed as a pairwise or limitless-arity capacity that considers variant networks as either variant vs variant or as high order interactions. This type of analysis extends the number of tests that were previously performed in a standard approach such as Genome-Wide Association Study (GWAS), in which False Discovery Rate (FDR) is already an issue, therefore by multiplying the number of tests up to a factorial rate also increases the issue of FDR. Further to this, epistasis introduces its own limitations of computational complexity and intensity that are generated based on the analysis performed; to consider the most intense approach, a multivariate analysis introduces a time complexity of O(n!). Proposed in this paper is a novel methodology for the detection of epistasis using interpretable methods and best practice to outline interactions through filtering processes. Using a process of Random Sampling Regularisation which randomly splits and produces sample sets to conduct a voting system to regularise the significance and reliability of biological markers, SNPs. Preliminary results are promising, outlining a concise detection of interactions. Results for the detection of epistasis, in the classification of breast cancer patients, indicated eight outlined risk candidate interactions from five variants and a singular candidate variant with high protective association.

Video feedback and machine speech recognition are fast-becoming a popular choice for companies to gain insight into their products. In conjunction with this, text analytics can be used to extract insight from these video translations. Currently, there is little work in the area to analyse and compare techniques for natural language processing, information retrieval and information extraction. A commonly practiced technique in text analytics is the extraction of stop words; words whose presence do not contribute context or information to a document. In this paper, we explore statistical techniques for the automated extraction of stop words, comparing 4 datasets from written and translated reviews. Using statistical variations of the successful technique `term ranking', we evaluate their performance using a common list of stop words. Results suggest that variation, TFnormIDFnorm, was the most successful with a best performing precision rate of 46.7% and a recall rate of 86.6%. The best results were seen in the largest dataset using written reviews, however comparison of the remaining 3 datasets revealed that spoken text performed 0.4% better in precision than the next best dataset and 2.6% better in recall. Initial results show marginally better performance in machine speech recognition transcribed texts from videos in comparison to comparably size datasets of written reviews.

This paper aims to discuss the state-of-the-art medical training simulators developed for the training and enhancement of technical skills related to complex procedures. The article discusses the skills and medical procedures reproduced by these simulators. Furthermore, the paper identifies the limitations of existing state-of-the-art technology and discusses the obstacles presented by these limitations. The paper then looks at novel approaches to these obstacles and systems currently being developed.

In this study, we propose and compare neural network models that use unsupervised layers for the prediction of financial time series. We compare the novel FL-RBM and FL-SMIA-RMB models that integrate a Restricted Boltzmann Machine (RBM) and the self-organizing layer of the Selforganized Multi-Layer Network using the Immune Algorithm (SMIA) with the FL-SMIA network and a standard MLP. We aim to investigate the performance of unsupervised learning in comparison to purely supervised and other mixed models. The FL-RBM model combines the products of raw input features (the Functional Link, FL), with the Restricted Boltzmann Machine RBM as a self-organizing first hidden layer, while the FL-SMIA model uses the Immune Algorithm on the first layer. The FLSMIA- RBM model, combines both self-organizing layers with a back-propagation network. The results show that the FL-SMIA model outperforms the FL-RBM, the FL-SMIA-RBM and the MLP as measured by Annualized Return (AR) in one-day-ahead prediction on exchange rates time series. In terms of volatility, the FL-SMIA and MLP perform similarly.

Several steps need to be considered when conducting a data mining study on a text dataset, this will also involve the use of multiple techniques before achieving any results or extracting any hidden knowledge. Hence, the complexity of working with text data. One of the main steps would be the pre-processing of the text dataset, and this might include multiple techniques such as tokenisation, word stemming, stop words removal, and text vectorisation. To extract knowledge from the text data after preprocessing, depending on the use case or end goal, the application steps might include clustering of text documents, classification of the text documents, and the extraction of document topics and entities. For each of these steps there are several methods and techniques being presented in different research studies. In this paper we present a framework that would categorise, cluster and classify a corpus of unclassified documents. The framework extracts named entities and uses a linked data Knowledge Graph to assign several topics and categories to each document. Then automatically cluster the documents into groups using the K-Mean model with the Elbow and Silhouette methods. Each cluster then gets assigned to a readable name from the extracted linked data based on word frequency in each cluster.

The process of cement manufacturing produces a huge amount of carbon dioxide (CO2). The utilization of alternative waste materials from various industrial processes as a partial substitution to cement is encouraged due to environmental and specific technical requirements. This strategy will have the potential to reduce cost of cement, conserve energy, and reduce waste volumes. Therefore, the aim of this research is to investigate effect of the replacement of cement with modified fly ash (MFA) and ground granulated blast furnace slag (GGBS) to reach 80% total replacement on mechanical and durability performance of cement mortar. Normal consistency, the initial and final setting times, compressive strength and electrical resistivity of all the ternary mixtures were determined and compared with the control binder. Compressive strength and electrical resistivity were tested at various curing ages of 3, 7, 14, and 28 days. Test results revealed that the normal consistency of the ternary mixtures increased with increasing the GGBS and MFA content, while the initial and final setting time decreased compared to that of control mixture. The results also showed that the compressive strength of all the ternary blends mortars were lower at early and later ages in comparison with control mortar. The reductions in the compressive strengths of the ternary mixtures T40, T60 and T80 compared to the control mixture were approximately 16%, 29% and 37%, respectively at 28 days. The surface electrical resistivity of ternary blends mixtures was higher than the control mixture at all curing ages. The use of GGBS and MFA in the production of cement mortar and concrete can significantly help in reducing the CO2 emissions of the cement industry and reduce the overall cost of cement.

Type 2 Diabetes condition is a multifactorial disorder involves the convergence of genetics, environment, diet and lifestyle risk factors. This paper investigates genetic and conventional (clinical, sociodemographic) risk factors and their predictive power in classifying Type 2 Diabetes. Six statistically significant Single Nucleotide Polymorphisms (SNPs) associated with Type 2 Diabetes are derived by conducting logistic association analysis. The derived SNPs in addition to conventional risk factors are used to model supervised machine learning algorithms to classify cases and controls in genome wide association studies (GWAS). Models are trained using genetic variable analysis, genetic and conventional variable analysis, and conventional variable analysis. The results demonstrate of the three models, higher predictive capacity is evident when genetic and conventional predictors are combined. Using a Random Forest classifier, the Area Under the Curve=73.96%, Sensitivity=68.42 %, and Specificity=78.67%.

Chronic Kidney Disease is a serious lifelong condition that induced by either kidney pathology or reduced kidney functions. Early prediction and proper treatments can possibly stop, or slow the progression of this chronic disease to end-stage, where dialysis or kidney transplantation is the only way to save patient's life. In this study, we examine the ability of several machine-learning methods for early prediction of Chronic Kidney Disease. This matter has been studied widely; however, we are supporting our methodology by the use of predictive analytics, in which we examine the relationship in between data parameters as well as with the target class attribute. Predictive analytics enables us to introduce the optimal subset of parameters to feed machine learning to build a set of predictive models. This study starts with 24 parameters in addition to the class attribute, and ends up by 30 % of them as ideal sub set to predict Chronic Kidney Disease. A total of 4 machine learning based classifiers have been evaluated within a supervised learning setting, achieving highest performance outcomes of AUC 0.995, sensitivity 0.9897, and specificity 1. The experimental procedure concludes that advances in machine learning, with assist of predictive analytics, represent a promising setting by which to recognize intelligent solutions, which in turn prove the ability of predication in the kidney disease domain and beyond.

This paper addresses the central problem of automatic segmentation of lumbar spine Magnetic Resonance Imaging (MRI) images to delineate boundaries between the anterior arch and posterior arch of the lumbar spine. This is necessary to efficiently detect the occurrence of lumbar spinal stenosis as a leading cause of Chronic Lower Back Pain. A patch-based classification neural network consisting of convolutional and fully connected layers is used to classify and label pixels in MRI images. The classifier is trained using overlapping patches of size 25×25 pixels taken from a set of cropped axial-view T2-weighted MRI images of the bottom three intervertebral discs. A set of experiment is conducted to measure the performance of the classification network in segmenting the images when either all or each of the discs separately is used. Using pixel accuracy, mean accuracy, mean Intersection over Union (IoU), and frequency weighted IoU as the performance metrics we have shown that our approach produces better segmentation results than eleven other pixel classifiers. Furthermore, our experiment result also indicates that our approach produces more accurate delineation of all important boundaries and making it best suited for the subsequent stage of lumbar spinal stenosis detection.

In this paper, a novel application of machine learning algorithms including Neural Network architecture is presented for the prediction of flood severity. Floods are considered natural disasters that cause wide-scale devastation to areas affected. The phenomenon of flooding is commonly caused by runoff from rivers and precipitation, specifically during periods of extremely high rainfall. Due to the concerns surrounding global warming and extreme ecological effects, flooding is considered a serious problem that has a negative impact on infrastructure and humankind. This paper attempts to address the issue of flood mitigation through the presentation of a new flood dataset, comprising 2000 annotated flood events, where the severity of the outcome is categorised according to 3 target classes, demonstrating the respective severities of floods. The paper also presents various types of machine learning algorithms for predicting flood severity and classifying outcomes into three classes, normal, abnormal, and high-risk floods. Extensive research indicates that artificial intelligence algorithms could produce enhancement when utilised for the pre-processing of flood data. These approaches helped in acquiring better accuracy in the classification techniques. Neural network architectures generally produce good outcomes in many applications, however, our experiments results illustrated that random forest classifier yields the optimal results in comparison with the benchmarked models.

The ability to forecast natural phenomena relies on understanding causality. By definition this understanding must include a temporal component. In this paper, we consider the ability of an emerging class of neural network, which encode temporal information into the network, to perform the difficult task of Natural Event Forecasting. The Axonal Delay Network (ADN) models axonal delay in order to make predictions about sunspot activity, the Auroral Electrojet (AE) index and daily temperatures during a heatwave. The performance of this network is benchmarked against older types of neural networks; including the Multi-Layer Perceptron (MLP) network and Functional Link Neural Network (FLNN). The results indicate that the inherent temporal characteristics of the Axonal Delay Network make it well suited to the processing and prediction of natural phenomena.

This paper presents an investigation into the reed houses that was first built in Iraq 6000 years ago with different methods and techniques used for construction these types of houses. Additionally, it presents a detailed comparison between the reed and modern houses in terms of sustainability and environmental impact.

The initial monitoring of patients with headache is an essential part of ongoing patient safety. Usually, patients are asked to fill in traditional paper-based diaries or outcome measures (e.g., HIT-6 and MIDAS) on a regular basis to measure the impact of headache on a patient's life. However, within publicly funded health care systems such as the UK's National Health Service (NHS), long term monitoring in neurology clinics appears not to be possible for all patients with chronic headache due to the continued decline in funding over the past decade. Nowadays, there is scope to improve patient monitoring and safety in the headache clinic by employing mobile health (mhealth) technologies. The M-health application represents an intelligent solution and holds potential to allow specialists to monitor a larger number of patients than would be possible within the current service model. Mobile applications could replace traditional paper-based diaries and outcome measures and provide several advantages including improved monitoring of historical responses to therapies, improved recording of side effects and can be adapted to improve communication between patients and clinicians. We therefore developed a mobile application-based system to allow remote monitoring of patients with chronic headache.

The rate at which people miss hospital appointments has decreased but remains a big concern for health care professionals as well as funding agencies. This research paper used an open data obtained from the NHS database to determine the factors that may lead to missed appointments and create a model that can be used to predict the likelihood of a patient missing an appointment. Logistic regression models and bivariate analysis were used to determine whether there was a meaningful relationship/association between "did not attend" and forgetfulness, gender, apathy, and transportation. An extensive literature review was conducted to narrow down the reasons that might lead to missed appointments. In conclusion, the research showed there was a significant difference between gender, type of clinic and apathy in organizations.

The contextual compendium analysis presented in this paper focuses on the Industry 4.0 and healthcare services innovation that relate to it. The appraisal discerns the specific components of Industry 4.0 and their related innovations or contribution in the healthcare industry. The first component, Cyber-physical systems, has led to Medical Cyber-physical systems applied in different circumstance to improve the efficiency of service provision. The second component, Internet of Things, has brought with it expanded networks, biosensors, smart pharmaceuticals, and other artificial organs. The final component has inspired the integrated of Natural Language Processing model as a calm-system operating in the background to complete a host of the process that improves diagnoses among other service provision and assistance functions. Additionally, the paper discusses Cognitive Computing, mHealth, and eHealth as emerging medical fields that can benefit from Industry 4.0.

Education With the inclusion and integration of internet and digital learning Education 2. 0 brought tools in the different context of education. The use of social networking concepts such as chat rooms and the ever-growing student data have placed education on the brink of becoming one of the craters and users of Big Data. As such, this paper explores educational data mining techniques alongside some of the emerging learning analytics with the objective of gaining insight into some of the common learning behaviors among students. The task at hand embraces predictive analytics and it employs decision trees, neural networks, and Naïve Bayes algorithms to classify and cluster student learning patterns that can explain academic performance. Predictive analytics has emerged as one of the tools furthering adaptive learning among other lifechanging novelties. Nonetheless, integration of big data in academia is in its infancy although the western hemisphere is making progress towards the integration. Such progress will increase the relevance of data mining in education and this paper envisages to be among the first ones to address the applicability of machine learning in improving education. Hence, the objective of this paper is to develop predictive models based on the decision tree, neural network, and Naïve Bayes algorithms.

Within genomic studies, a considerable amount of publications have reported SNP variants associated with COPD with little to no reproducibility. In this paper, we present a robust methodology which analyses a COPD cohort dataset using a genome-wide association study, additionally an investigation of the associated results using a variety of machine learning (ML) methods is performed. We use a logistic regression model to provide preliminary results and for further analysis we use machine learning models, RF, MLP, GLM and SVM. Within this study, indications of well established SNPs in previous publications occur in the preliminary results but fail to provide further indication of associative relationship when using ML methods for classification purposes. Results within this study show little to no predictive power after performing a robust methodology. These results indicate that a standardization of practice should be implemented to ensure the publication of false positive results is reduced and deterred. Further investigation of associative features should be considered a standard practice given the resulting information that can be provided with its' use.

This study designed to explore load displacement of steel open-ended model piles driven in cohesionless soil and subjected to axial uplift loads. The feasibility of a novel computational intelligence (CI) scheme to correlate the full behavior of the pile load-deformation has also been examined. Self-tuning Levenberg-Marquardt (LM) training algorithms, enhanced by the null-hypothesis tests (T-tests and F-tests), have been implemented in this process. The pile aspect ratios were varied from 12, 17, and 25. The piles were tested using an innovative pile-testing chamber in three relative densities of noncohesive soil, ranging from dense, medium and loose sand. The prediction metrics indictors demonstrate an excellent performance of the adopted modelling approach in capturing the full behavior of the pile load-displacement, thus yielding a Root Mean Square Error, Determination Coefficient, and Mean Absolute Error of 0.14, 0.96, and 6.8×10-3, respectively.

This article considers how teachers and university administrators can use a significant amount of data stored in the information systems of institutions. Intelligent analysis of these learning processes is of great use in the higher education system. The use of learning analytics (LA) by a large number of higher educational institutions shows the interest and participation of universities in this matter. Learning analytics can tell a lot about the progress of students and the environment in which learning takes place. Intellectualization of educational analytics will help provide predictive models that can serve as a basis for quality assurance and quality improvement. This article gives an idea of the current level of LA development at the international level. The article also draws conclusions about the problems and limitations associated with learning analytics (LA). The existing experience has been studied, and the conclusion have been made about the existing limitations that prevent the wider use of LA.

Data and databases play an important role in managing heritage resources. Arches software is being used to design and build a prototype radiocarbon date database or model in order to improve the way in which disparate radiocarbon datasets are stored and shared. The database is one of many resource models designed within an Arches framework. The model complies with the Council of Museums Conceptual Reference Model, which is an international standard for the recording of heritage data. Arches is web-based, meaning that the radiocarbon database will be fully accessible online for data entry, querying and report production. The resource model will provide the next generation standard for managing radiocarbon datasets and linking them with other forms of heritage data in a highly structured and coherent manner.

In this paper, association results from genome-wide association studies (GWAS) are combined with a deep learning framework to test the predictive capacity of statistically significant single nucleotide polymorphism (SNPs) associated with obesity phenotype. Our approach demonstrates the potential of deep learning as a powerful framework for GWAS analysis that can capture information about SNPs and the important interactions between them. Basic statistical methods and techniques for the analysis of genetic SNP data from population-based genome-wide studies have been considered. Statistical association testing between individual SNPs and obesity was conducted under an additive model using Iogistic regression. Four subsets of loci after quality-control (QC) and association analysis were selected: P- values lower than l×10-5(5 SNPs), l×10-4(32 SNPs), l×10-3(248 SNPs) and l×10-2(2465 SNPs). A deep learning classifier is initialised using these sets of SNPs and fine-tuned to classify obese and non-obese observations. Using a deep learning classifier model and genetic variants with P-value-2(2465 SNPs) it was possible to obtain results (SE=0.9604, SP=0.9712, Gini=0.9817, LogLoss=0.1150, AUC=0.9908 and MSE=0.0300). As the P-value increased, an evident deterioration in performance was observed. Results demonstrate that single SNP analysis fails to capture the cumulative effect of less significant variants and their overall contribution to the outcome in disease prediction, which is captured using a deep learning framework.

Biometric fingerprints are one of the most broadly used form of biometric identification. Everyone is known to have unique, immutable fingerprints. In this area, the most challenging task is fingerprint recognition and identification system. This filed of the biometric data is significantly depends on the major quality data (input and tested images). A latent intelligent model is proposed in this paper. Our approach relies on develop an alternative approach to solve the localization problem based on Swarm Intelligence (SI) methodology for a robustness rotational and spatially invariant fingerprint recognition and verification model. In our latent model, a group of partial local features is extracted from fingerprint based on swarm-intelligence methodology such as Particle Swarm Optimization Algorithm (PSO) as a first one, and Firefly Optimized Algorithm (FOA) Algorithms as a second algorithm. The search strategy in swarm-intelligence methodology is an iteratively process which is guided by a fitness function that is been defined to maximize the class distribution separation. This methodology allows the latent model to detect and extract new features instead of using the typical model (Minutiae based feature extraction). Two main contributions have assumed in this paper to achieve the efficacity and solve the spatially invariant of the fingerprint recognition problems. The first contribution of this paper is proposing a new formulation method for finding a new feature selection approach fashion, which is based on Discrete Wavelet Transform. This formulation feature selection solves the locality problem of the fingerprint feature selection by applying swarms separately to four sub-bands fingerprint image, that to diversify the feature selection, and to improve the recognition/identification rate in additional to speed up the feat an invariant moment matching algorithm to address the potentially misclassified features to improve the matching accuracy, and to solve the miss-sequentially features tracking for the swarm-intelligent approach. The proposed approach (PSO) and (FOA) are found to generate significant improvement for recognition results by admitted about 99.1-100% accuracy. The proposed system has been applied on large scale dataset. However, it admits accuracy that ranged (96.35-99.00%), when it has been applied for fingerprints with a significant rotation issues of 0°-360°.

Nowadays, the internet is considered as one of the key building blocks of modern communities and a primary function to every aspect of our daily life activities. The internet is widespread and progress in the realm of the information and communication technologies demonstrated great improvements that can be utilized by government entities that strive towards achieving sustainable excellence and utmost performance. In the meantime, government organizations should maintain the delivery of high quality of services and continuously monitor and measure their performance based on appropriate approaches namely, organizing the map of corporate strategy, set of organizational strategic objectives and formulating key performance indicators. The quality levels of organizations operations can be witnessed and improved by identifying an effective planning procedure which indicate areas of enhancements and effective process for decision making to respond to dynamical changes. This paper aims to develop an interactive system to enhance strategic planning processes and quality of aviation operations using balanced scorecard. The proposed system will be integrated with the balanced scorecard approach and shall be evaluated for its effectiveness and usefulness in the aviation operations.

Current efforts move to improve healthcare services in Saudi Arabia (SA). Given the essential roles of these services within the country, ongoing effort to improve health informatics services in SA is required in order to ensure the sector is up-to-date. One area for improvement focuses on the referral system in place in Madinah city. This paper presents a solution to the above problem by proposing a Web-based healthcare information system link that can connect four healthcare centres in Madinah city. This will serve as a pilot project. This link could help healthcare providers to access patient information within their own system. Many healthcare applications have problems with interoperability. Hence, one of the aims of this research is to look at system integration of some of the existing healthcare information systems.

Disc herniation is considered as the main cause for lower back pain (LBP), a health issue that affects a very high proportion of the UK population and is costing the UK government over £1.3 million per day in health care cost. Currently, the process to diagnose the cause of LBP involves a visual examination of a large number of Magnetic Resonance Images (MRI) but this process is both expensive in terms time and effort. Automatic detection of the lumbar disc herniation will reduce the time to diagnose and detect the cause of LBP by the orthopedist. There has been very limited progress towards automatic detection of disc herniation and all of the proposed techniques still require substantial manual intervention in many of the stages. Our analysis of the problem suggests that using the axial view of the MRI could potentially improve the outcome as opposed to the sagittal view used by these techniques. In this paper, we propose using the Centroid Distance Function as a shape feature of a segmented disc MRI taken from the axial view. Visual observation of the feature indicates that the feature could be used as a suitable indicator of the presence of herniation in the lumbar disc

This paper presents the utilisation of dynamical recurrent neural network architectures in the purpose of classifying the Sickle Cell disorder data. It is indicted that recurrent neural networks such as the Jordan network produce a great improvement with clinical data sets and have helped in acquiring high accuracy. The main aim of this study is to provide a sophisticated model to differentiate applications of dynamical neural networks for medically related problems. We attempt to classify the amount of medications for each patient with Sickle Cell disorder. We use different recurrent neural network architectures in terms of examining performance for each model within this study. The motivation for the classification approach used in this study is to support medical sectors to offer proper therapy advice depending on the former data set. The outcomes yield from different classifiers during our experiments indicated that Elman and hybrid recurrent neural networks produced inferior results when compared to Jordan neural networks. Results have indicated that for the recurrent network models tested, the Jordan architecture was found to yield considerably better results over the range of performance measures that been selected for this research.

In this paper we propose the FL-SMIA model, a novel neural network model that combines the principles of the Functional Link Neural Network (FLNN) with the Self-organizing Multilayer Neural Network using the Immune Algorithm (SMIA). We describe the FL-SMIA architecture and operation and evaluate its predictive performance on different financial time series in comparison to other neural network models. The FL-SMIA model combines the higher-order inputs of the tensor-product FLNN, i.e. the products of raw input features, with the self-organizing hidden layer of SMIA that dynamically grows and adapts to the input vectors. The FL-SMIA has two advantages over other models. First, it can dynamically adapt to growing amounts of data with a model that grows increasingly complex. Second, it keeps an explicit representation of the patterns it recognises in the data. Experimental results show that the FL-SMIA improves performance, as measured by annualised return in five-days-ahead and one-day-ahead prediction tasks for share prices and exchange rates, over the SMIA networks alone and over standard multilayer perceptrons. It performs on the same level as the FLNN, sometimes better but not significantly so. The result that FLNN and FL-SMIA outperform other multilayer models indicates that particularly the higher-order features contribute to the improved performance and motivate further research into mixed neural network architectures for financial time series prediction.

Nowadays, Massively Multiplayer Online Games (MMOGs) become one of the significant kind of online games. It can support over millions of concurrent players deployed over the world and participating with each other within a single online game. The rapid increase in the number of players for MMOGs has led to some issues with the demand of adding new servers. Resulting in a considerable increase in costs for the game industry and effect to the quality of service offered to users. In order to provide a scalable MMOGs, area of interest management (AoIM) is considered a fundamental ingredient to decrease unnecessary network traffic. In this paper, we have proposed a novel dynamic area of interest management to minimize the end-to-end delay as well as network traffic of MMOGs Hybrid P2P system. We have used OPNET Modeler 18.0, in particular the custom application to simulate the new technique, which required the execution of new nodes models and behaviors in the simulator to emulate correctly the new architecture. The scenarios comprise both MMOGs hybrid P2P and client-server system in order to evaluate the game communication with (125, 500, and 1000) peers. The simulation results show that AoIM of MMOGs based on hybrid P2P architectures produce low delay and low network traffic received compared to MMOGs based on client-server system without AoIM.

This paper presents a robust methodology to find biomarkers that are predictive of any given clinical outcome, by combining three critical steps: Adjustment for correlated biomarkers, through Linkage Disequilibrium pre-processing; False Detection Rate (FD) control with q-values; multivariate predictive modelling with neural networks. The results show that neural network modelling with pre-processing using p-values can be misleading. In particular, the interpretation of the neural network through calculation of the conditional probabilities P(x|c) where x represents covariates and c the classes, haw an important role in elucidating the predictive power (or lack of it) of the biomarkers. The methodology is generally applicable to p>n modelling where the initial pool of potential predictive parameters p, e.g. biomarkers, is greater than the sample size n.

We consider the use of intelligent systems to address the long-standing medical problem of diagnostic differentiation between harmful (secondary) and benign (primary) headache conditions. In secondary headaches, conditions are caused by an underlying pathology, in contrast to primary headaches where the production of pain represents the sole constituent of the disorder. Conventional diagnostic paradigms carry an unacceptable risk of misdiagnosis, leaving patients open to potentially catastrophic consequences. Intelligent systems approaches, grounded in artificial intelligence, are adopted in this study as a potential means to unite contributions from multiple settings, including medicine, the life sciences, pervasive computation, sensor technologies, and autonomous intelligent agency, in the fight against headache uncertainty. In this paper, we therefore present the first steps in our research towards a data intensive, unified approach to headache dichotomisation. We begin by presenting a background to headache and its classification, followed by analysis of the space of confounding symptoms, in addition to the problem of primary and secondary condition discrimination. Finally, we proceed to report results of a preliminary case study, in which the epileptic seizure is considered as a manifestation of a headache confounding neuropathology. It was found that our classification approach, based on supervised machine learning, represents a promising direction, with a best area under curve test outcome of 0.915. We conclude that intelligent systems, in conjunction with biosignals, could be suitable for classification of a more general set of pathologies, while facilitating the medicalisation of arbitrary settings.

We present Random Forest, Support Vector Machine and Feedforward Neural Network models to classify 2519 variable star light curves. These light curves are generated from a reduction of non-survey optimized observational images gathered by wide-field cameras mounted on the Liverpool Telescope. We extract 16 features found to be highly informative in previous studies and achieve an area under the curve of 0.8495 using a feedforward neural network with 50 hidden neurons trained with stratified 10-fold cross-validation with 3 repeats. We propose using an automated visual feature extraction technique by transforming bin-averaged phase-folded light curves into image based representations. This eliminates much of the noise and the missing phase data, due to sampling defects, should have a less destructive effect on these shape features as they still remain at least partially present. There is also no need for feature engineering as the learning algorithms can learn shape features directly from the light curves. We produced a set of scaled images based on a threshold of data points in each pixel. Training on the same feedforward network, we achieve an area under the curve of 0.6348. By introducing the Period and Amplitude as features into this dataset therefore giving meaning to the dimensions of the image we show this improves to 0.7952. Our current models lack translational-invariance and the method may be better suited to specific sub-classification problems common in the variable object hierarchical multi-class problem.

This paper presents a novel approach based on the analysis of genetic variants from publicly available genetic profiles and the manually curated database, the National Human Genome Research Institute Catalog. Using data science techniques, genetic variants are identified in the collected participant profiles and then indexed as risk variants in the National Human Genome Research Institute Catalog. Indexed genetic variants or Single Nucleotide Polymorphisms are used as inputs in various machine learning algorithms for the prediction of obesity. Body mass index status of participants is divided into two classes, Normal Class and Risk Class. Dimensionality reduction tasks are performed to generate a set of principal variables - 13 SNPs - for the application of various machine learning methods. The models are evaluated using receiver operator characteristic curves and the area under the curve. Machine learning techniques including gradient boosting, generalized linear model, classification and regression trees, k-nearest neighbours, support vector machines, random forest and multilayer perceptron neural network are comparatively assessed in terms of their ability to identify the most important factors among the initial 6622 variables describing genetic variants, age and gender, to classify a subject into one of the body mass index related classes defined in this study. Our simulation results indicated that support vector machine generated the highest area under the curve value of 90.5%.

Massively Multiplayer Online Games (MMOGs) can involve millions of synchronous players scattered across the world and participating with each other within a single shared game. One of the most significant issues in MMOGs is scalability and it is impact on the responsiveness and the quality of the game. In this paper, we propose a new architecture to increase the scalability without affecting the responsiveness of the game, using a hybrid Peer-to-Peer system. This mechanism consists of central servers to control and manage the game state, as well as super-peer and clone-super-peer to control and manage sub-networks of nodes sharing common regions of the game world. We use the OPNET Modeler to simulate the system and compare the results with client/server system to show the difference in delay and traffic received for various applications such as remote login, database, HTTP, and FTP sessions which are all part of an MMOG system. We use four scenarios for each system to evaluate the scalability of the system with different number of peers (i.e.125, 250, 500, and 1000 peers). The results show that the hybrid P2P system is more scalable for MMOGs when compared with client/server system.

In recent years, there has been an important growth of online gaming. Today's Massively Multiplayer Online Games (MMOGs) can contain millions of synchronous players scattered across the world and participating with each other within a single shared game. The increase in the number of players in MMOGs has led to some issues with the demand of server which generates a significant increase in costs for the game industry and impacts to the quality of service offered to players. With the number of players gradually increasing, servers still need to work efficiently under heavy load and, new researches are required to improve the established MMOG system architectures. In dealing with a considerable scale of massively multiplayer online games, several client-server and peer-to-peer solutions have been proposed. Although they have improved the scalability of MMOGs in different degrees, they faced new serious challenges in interest management. In this paper, we propose a novel static area of interest management in order to reduce the delay and traffic of Hybrid P2P MMOGs. We propose to use OPNET Modeler 18.0, and in particular the custom application to simulate the new architecture, which required the implementation of new nodes models and behaviors in the simulator to emulate correctly the new architecture. The scenarios include both client-server and hybrid P2P system to evaluate the communication of games with (125, 500, and 1000) peers. The simulation results show that area of interest management for MMOGs based on the hybrid P2P architectures have low delay and traffic received compared with MMOGs based on client-server system.

The risk assessment of any Network or Security systems has a high level of uncertainties because usually probability and statistics were used to evaluate the security of different cyber security systems. In this paper we will use Shannon entropy to represent the uncertainty of information used to calculate systems risk and entropy weight method since the weight of the object index is normally used and point to the significant components of the index. We evaluate the risk of security systems in terms of different security layers and protections. The information system is analysed by perimeter, network, host, application and data layers' protections. The capability of protections is measured by introducing the concept of protection effectiveness. We write the security evaluations algorithm to normalized the protection matrix and calculate the entropy and the entropy weight, then we will use the weight and paths to evaluate and calculate the total risk in the system and give the systems administrator a clear guidance on the vulnerable security entities. We try to develop a novel approach to evaluate the cyber security suitable for the majority of cyber systems by introducing the term of security entities.

There has been an increase of survival rates among children born premature. The rate of survival differs globally from developed countries to developing countries. Some follow-up studies of children born prematurely are concerned of the neurodevelopmental impact on children as they progress from infant through adulthood and they indicated the range of deficits that comes with premature children. This research addresses the gap of how the education of children born premature is affected. A survey methodology was utilized and questionnaires were distributed to teachers in five special needs schools and one normal school in the North West of the United Kingdom. The results of the special needs schools were compared to normal school with respect to awareness of children born premature in classes, the technologies used by the impaired children, and the educational improvement of impaired children using the technology. The results showed that 100% of teachers in both schools were unaware of children born premature in their classes, 100% of teachers in special needs schools are aware of the assistive technologies compared to only 25% of teachers in normal school and 100% teachers in special needs schools support the use of assistive technologies for educational improvement compared to 1% teachers in normal school.

In recent years, there has been an important growth in online gaming. Nowadays, Massively Multiplayer Online Games (MMOGs) may involve millions of synchronous players scattered around the world and engaging with each other within a single shared game. In this paper, we propose a new technique to communicate between players and game server, and between them based on hybrid Peer-to-Peer architecture. We propose to use OPNET Modeler 18.0, and in particular the custom application to simulate the new architecture, which required the implementation of new nodes models and behaviors in the simulator to emulate correctly the new architecture. We use OPNET Modeler 18.0 to simulate the network, applying two transport protocols TCP and UDP, and with different scenarios. The scenarios include both client-server and hybrid P2P system to evaluate the communication of games with (125, 500, and 1000) peers.

The optimization and evaluation of a pattern recognition system requires different problems like multi-class and imbalanced datasets be addressed. This paper presents the classification of multi-class datasets which present more challenges when compare to binary class datasets in machine learning. Furthermore, it argues that the performance evaluation of a classification model for multi-class imbalanced datasets in terms of simple "accuracy rate" can possibly provide misleading results. Other parameters such as failure avoidance, true identification of positive and negative instances of a class and class discrimination are also very important. We, in this paper, hypothesize that "misclassification of true positive patterns should not necessarily be categorized as false negative while evaluating a classifier for multi-class datasets", a common practice that has been observed in the existing literature. In order to address these hidden challenges for the generalization of a particular classifier, several evaluation metrics are compared for a multi-class dataset with four classes, three of them belong to different neurodegenerative diseases and one to control subjects. Three classifiers, linear discriminant, quadratic discriminant and Parzen are selected to demonstrate the results with examples.

Artificial intelligence is the capability of computing machines to perform at par with humans in some cognitive tasks. Since its conception in the 1940s, AI has ambitiously evolved to naturally and comfortably immerse in extraordinary and multidisciplinary fields including computer science, education, engineering and medicine. This survey aims to provide and highlight the importance of AI work in the field of medical informatics and biomedicine. We have reviewed latest AI research in this immense field of medical science with special attention given to medical diagnosis. Various intelligent computing tools from rule-based expert systems and fuzzy logic to neural networks and genetic algorithms used in medical diagnosis were considered. We have explored hydrocephalus, a medical condition causing headaches. We also analysed a prototype of what is known as NeuroDiary Web application that is currently being tested as a software mobile application for collecting data of patients with hydrocephalus. We finally propose the development of an expert mobile application system to assist clinicians in the diagnosis, analysis and treatment of hydrocephalus.

This study builds on previous research, where a technology acceptance model for electronic health (e-HTAM) was investigated, developed and evaluated. The e-HTAM questionnaire originally used showed some weakness in terms of its overall reliability, which highlighted the need for a second phase of study to address the shortfalls reported by the first model. The second phase of the study was conducted after the questionnaire used in the initial phase was modified. The results suggested that when creating e-Health websites or services, the principle of how e-Health websites and services should be designed and delivered, and under which cultural setting they will be used, should be taken into consideration from the initial design stage.

This paper presents a novel Dynamic Self-Organised Multilayer Neural Network that can be used for prediction of noisy time series data. The proposed technique is based on the Immune Algorithm for financial time series prediction; combining the properties of both recurrent and self-organised neural networks. The network is derived to ensure that a unique equilibrium state can be achieved to overcome the known stability and convergence problems. Extensive simulations for multi-step prediction in stationary and non-stationary time series were performed. The resulting projection made by the proposed network shows substantial profits on financial historical signals when compared to other neural network approaches. These simulations have suggested that dynamic immunology-based self-organised neural networks have a better ability to capture the chaotic movement in financial signals.

This paper presents a novel Dynamic Self-Organised Multilayer Neural Network that can be used for prediction of noisy time series data. The proposed technique is based on the Immune Algorithm for financial time series prediction; combining the properties of both recurrent and self-organised neural networks. The network is derived to ensure that a unique equilibrium state can be achieved to overcome the known stability and convergence problems. Extensive simulations for multi-step prediction in stationary and non-stationary time series were performed. The resulting projection made by the proposed network shows substantial profits on financial historical signals when compared to other neural network approaches. These simulations have suggested that dynamic immunology-based self-organised neural networks have a better ability to capture the chaotic movement in financial signals.

As wireless and 3G networks become more crowded, users with mobile devices experience difficulties in accessing the network. Opportunistic networks, created between mobile phones using local peer-to-peer connections, have the potential to solve such problems by dispersing some of the traffic to neighbouring smart phones. Recently various opportunistic routing and dissemination algorithms were proposed and evaluated in various scenarios emulating real-world phenomena as close as possible. Such algorithms generally rely on mobility patterns of users and the context of communication. In this we investigate the addition of social data to improve the performance of communication algorithms and data transmission schema. When the routing decision is influenced by the chance of a particular user being able to successfully carry the data to the next hop, we believe that opportunistic communication algorithms could greatly benefit not only from learning the behaviour of users, but also their history of contacts coupled with the online social familiarity patterns between them. We believe users tend to be in contact more with familiar sets of users, with whom they share common interests. We investigate our approach using two real-world traces collected in two different environments. We first investigate our hypothesis using mobility data collected in an indoor academic environment. We then evaluate our assumptions in an outdoor urban scenario. We present an analysis of our findings, highlighting key social and mobility behaviour factors that can influence such opportunistic solutions. Most importantly, we show that by adding knowledge such as social links between participants in an opportunistic network routing and dissemination algorithms can be greatly improved.

Technology integration is currently considered to be one of the most prominent challenges in the field of education, with a global trend towards integrating technology into various aspects of education. eLearning is considered to be the output of the technological revolution that emerged from the sectors of science, research and development. This paper focuses on firstly developing an effective learning environment to support the teaching and learning of geography within Oman secondary system, and secondly proposing the application of the Technology Acceptance Model (TAM) to assess this environment, in the light of teachers attitudes and intentions to adopt a new technology. Therefore, the TAM will be applied to compare different cultures; the UK and Middle East (Sultanate of Oman) focusing on the Social and Cultural factors in conjunction with the Davis model factors of Perceived Usefulness (PU) and Perceived Ease of Use (PEU)factors; in terms of technological acceptance in the context of eLearning. A Quantitative research method and analysis was prepared to capture data.

This research work aims to investigate and evaluate ways of enhancing the learning process by the use of technology. The technology offers a pedagogical strategy to assess the students (online) by describing an evaluating strategy of student's assessment. The proposed system is being developed to provide an interactive web based learning environment. Three different types of assessment techniques have been introduced in this paper; Diagnostic Assessment, Self-Assessment and Summative Assessment which help the students and the teachers to improve teaching and learning capabilities. UML has been used to describe the proposed system specification while the whole system is implemented using .NET Framework. e-Learning and e-Assessment System with its web based features presents an equal opportunity of education for both the students in the classroom and the distant students. This is a student-centric system and the student's progress depends upon his/her own learning efforts. The proposed assessment system presented in this paper is aimed at supporting students in their learning by providing them with instant feedback.