Decoding degeneration:the implementation of machine learning for clinical detection of neurodegenerative disorders

Machine learning represents a growing subfield of artificial intelligence with much promise in the diagnosis,treatment,and tracking of complex conditions,including neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases.While no definitive methods of diagnosis or treatment exist for either disease,researchers have implemented machine learning algorithms with neuroimaging and motion-tracking technology to analyze pathologically relevant symptoms and biomarkers.Deep learning algorithms such as neural networks and complex combined architectures have proven capable of tracking disease-linked changes in brain structure and physiology as well as patient motor and cognitive symptoms and responses to treatment.However,such techniques require further development aimed at improving transparency,adaptability,and reproducibility.In this review,we provide an overview of existing neuroimaging technologies and supervised and unsupervised machine learning techniques with their current applications in the context of Alzheimer’s and Parkinson’s diseases.

Volatility and Dynamic Herding in Energy Sector of Developed Markets During COVID-19:A Markov Regime-Switching Approach

This study examines a novel relationship between volatility and dynamic herding behavior during COVID-19 by examining the relationship of oil market volatility,Global volatility and Infectious disease equity market volatility with time-varying herding behavior in energy stock of Developed markets.Using country level data,this study observes that market switch between anti-herding to herding state during pandemic and all three volatility measures have significant impact on dynamic herding state under high dispersion regime.However,in low dispersion regime only global volatility has significant impact on time-varying herding behavior.This study suggests that the level of speculation in energy sector affect investor behavior;therefore,policy makers should monitor and model possible signals related to health crisis that can be transformed in to financial market crisis.

Integral Transform Method for a Porous Slider with Magnetic Field and Velocity Slip

Current research is about the injection of a viscous fluid in the presence of a transverse uniform magnetic field to reduce the sliding drag.There is a slip-on both the slider and the ground in the two cases,for example,a long porous slider and a circular porous slider.By utilizing similarity transformation Navier-Stokes equations are converted into coupled equations which are tackled by Integral Transform Method.Solutions are obtained for different values of Reynolds numbers,velocity slip,and magnetic field.We found that surface slip and Reynolds number has a substantial influence on the lift and drag of long and circular sliders,whereas the magnetic effect is also noticeable.

A Cascaded Design of Best Features Selection for Fruit Diseases Recognition

Fruit diseases seriously affect the production of the agricultural sector,which builds financial pressure on the country’s economy.The manual inspection of fruit diseases is a chaotic process that is both time and cost-consuming since it involves an accurate manual inspection by an expert.Hence,it is essential that an automated computerised approach is developed to recognise fruit diseases based on leaf images.According to the literature,many automated methods have been developed for the recognition of fruit diseases at the early stage.However,these techniques still face some challenges,such as the similar symptoms of different fruit diseases and the selection of irrelevant features.Image processing and deep learning techniques have been extremely successful in the last decade,but there is still room for improvement due to these challenges.Therefore,we propose a novel computerised approach in this work using deep learning and featuring an ant colony optimisation(ACO)based selection.The proposed method consists of four fundamental steps:data augmentation to solve the imbalanced dataset,fine-tuned pretrained deep learning models(NasNetMobile andMobileNet-V2),the fusion of extracted deep features using matrix length,and finally,a selection of the best features using a hybrid ACO and a Neighbourhood Component Analysis(NCA).The best-selected features were eventually passed to many classifiers for final recognition.The experimental process involved an augmented dataset and achieved an average accuracy of 99.7%.Comparison with existing techniques showed that the proposed method was effective.

Handling Class Imbalance in Online Transaction Fraud Detection

With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every transaction.However,the fraud cases have also increased causing the loss of money to the consumers.Hence,an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in real-time.Generally,the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance problem.In this research work,an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e.,fraud transactions.A novel loss function named Weighted Hard-Reduced Focal Loss(WH-RFL)has been proposed which has achieved maximum fraud detection rate i.e.,True PositiveRate(TPR)at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate(TNR)in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional datasets.Also,Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results.

Automotive Aerodynamics Analysis Using Two Commonly Used Commercial Software

Aerodynamics analysis has become a mindset for high performance vehicles. This is because it provides valuable insight on a vehicle motion during different phases. There are vast varieties of software available like ANSYS Workbench, Star CCM+, Autodesk Simulation, SimFlow, FeatFlow, Autodesk Inventor etc. Amongst these softwares, Star CCM+ and ANSYS Workbench are the most widely used. Normally, it is observed that considerable users are confused in choosing the right software for CFD simulation because of a large variety of commercially available softwares. The present study provides comparative results to users of Computational Fluid Dynamics (CFD) with the driven case study. In the present case, authors chose the most commonly used CFD softwares, the ANSYS Workbench Fluent and the Star CCM+. Polyhedral meshing was applied on computer aided model of a car in both of these softwares. It has been found that coefficients of drag and lift achieved by aerodynamic analysis of a car are in a small marginal approximation between both ANSYS Workbench Fluent and Star CCM+ softwares. In the case of Star CCM+, CD was around 0.261 and CL was 0.07;however, in the case of ANSYS Workbench Fluent approximations were found to be 0.271 for CD and 0.05 for CL.

Neural Machine Translation Models with Attention-Based Dropout Layer

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of alignment.NMT model has obtained state-of-the-art performance for several language pairs.However,there has been little work exploring useful architectures for Urdu-to-English machine translation.We conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and Transformer.Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen data.The trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,respectively.From a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more frequently.The attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear structure.Therefore,we considered refining the attention-based models by defining an additional attention-based dropout layer.Attention dropout fixes alignment errors and minimizes translation errors at the word level.After empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation score.The ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as well.We empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

Diagnostically untypable hepatitis C virus variants:It is time to resolve the problem

Pakistan is a low income country with more than 10million hepatitis C virus(HCV)infections and the burden is on continuous raise.Accurate viral genotyping is very critical for proper treatment of the infected individuals as the sustained virological response of the standard antiviral interferon therapy is genotype dependent.We observed at our diagnostic center that15.6%of HCV patient’s samples were not genotypeable by using Ohno et al method.The genotyped samples showed that 3a(68.3%)is the major prevalent genotype in Pakistan followed by 2a(10.3%),3b(2.6%),1b(1.5%),2b(1.2%)and 1a(0.5%).Presence of large number of untypable HCV variants in the current study highlights an important issue of health care setup in Pakistan.Untypable HCV cases create difficulties in treatment of these patients.The problem of routine diagnostics setup of Pakistan should be addressed on priority basis to facilitate the medical professionals in patient’s treatment and to help in achieving the maximum sustained virological response.

An efficient hash-based authenticated key agreement scheme for multi-server architecture resilient to key compromise impersonation

During the past decade,rapid advances in wireless communication technologies have made it possible for users to access desired services using hand-held devices.Service providers have hosted multiple servers to ensure seamless online services to end-users.To ensure the security of this online communication,researchers have proposed several multi-server authentication schemes incorporating various cryptographic primitives.Due to the low power and computational capacities of mobile devices,the hash-based multi-server authenticated key agreement schemes with offline Registration Server(RS)are the most efficient choice.Recently,Kumar-Om presented such a scheme and proved its security against all renowned attacks.However,we find that their scheme bears an incorrect login phase,and is unsafe to the trace attack,the Session-Specific Temporary Information Attack(SSTIA),and the Key Compromise Impersonation Attack(KCIA).In fact,all of the existing multi-server authentication schemes(hash-based with offline RS)do not withstand KCLA.To deal with this situation,we propose an improved hash-based multi-server authentication scheme(with offline RS).We analyze the security of the proposed scheme under the random oracle model and use the t4Automated Validation of Internet Security Protocols and Applications''(AVISPA)tool.The comparative analysis of communication overhead and computational complexity metrics shows the efficiency of the proposed scheme.

ExpressionHash: Securing Telecare Medical Information Systems Using BioHashing

The COVID-19 outbreak and its medical distancing phenomenon have effectively turned the global healthcare challenge into an opportunity for Telecare Medical Information Systems.Such systems employ the latest mobile and digital technologies and provide several advantages like minimal physical contact between patient and healthcare provider,easy mobility,easy access,consistent patient engagement,and cost-effectiveness.Any leakage or unauthorized access to users’medical data can have serious consequences for any medical information system.The majority of such systems thus rely on biometrics for authenticated access but biometric systems are also prone to a variety of attacks like spoong,replay,Masquerade,and stealing of stored templates.In this article,we propose a new cancelable biometric approach which has tentatively been named as“Expression Hash”for Telecare Medical Information Systems.The idea is to hash the expression templates with a set of pseudo-random keys which would provide a unique code(expression hash).This code can then be serving as a template for verication.Different expressions would result in different sets of expression hash codes,which could be used in different applications and for different roles of each individual.The templates are stored on the server-side and the processing is also performed on the server-side.The proposed technique is a multi-factor authentication system and provides advantages like enhanced privacy and security without the need for multiple biometric devices.In the case of compromise,the existing code can be revoked and can be directly replaced by a new set of expression hash code.The well-known JAFFE(The Japanese Female Facial Expression)dataset has been for empirical testing and the results advocate for the efcacy of the proposed approach.

First COVID-19 related death in Pakistan in a patient with a travel history in Saudi Arabia

Rationale: Severe acute respiratory syndrome coronavirus-2(SARS-CoV-2) has been recognized as highly pathogenic. The current pandemic of SARS-CoV-2 has been spread globally and infected more than 200 countries. Patient concerns: We report the first confirmed fatal case of COVID-19 in Pakistan. A 50-year-old man returned from Saudi Arabia on March 09, 2020 and presented with cough, fever, malaise, poor appetite and difficulty in breathing to the Pulmonologist at District Headquarter Hospital Mardan. Diagnosis: The patient was initially diagnosed as COVID-19 suspected case. A oropharyngeal swab sample was positive by realtime RT-PCR tests. Lessons: This report highlights the importance of close coordination between clinicians and public health authorities as well as the importance of early laboratory-based confirmation of COVID-19 cases.

Determination of water content in corn stover silage using near-infrared spectroscopy

The aim of this study was to evaluate the feasibility of utilizing near-infrared spectroscopy to determine the water content of corn stover silage across a wide range.The water contents of 208 samples were measured,and their corresponding near-infrared spectra were simultaneously collected.The effects of different preprocessing methods,such as derivation,standard normal variety(SNV),multiplicative scatter correction(MSC),and non-preprocessing methods for the obtained near-infrared spectra on the performance of calibration models were compared.The calibration models were established by modified partial least squares(MPLS)regression.The results showed that the calibration model developed from the successive preprocessing of MSC and first-order derivation(1-D)achieved the optimal performance.The correlation coefficients of the calibration and validation subset were 0.974 and 0.949,respectively,and the standard errors of the calibration and cross validation were 4.249% and 4.256%,respectively.External validation was performed on 60 samples.The correlation coefficient between the measured and predicted values of the calibration model was 0.973 and the prediction model’s relative percent deviation was 4.317.This indicated that the mathematical model of near-infrared spectroscopy predicted the water content in corn stover silage with high accuracy.The study showed that the near-infrared spectroscopy technology can be used for rapid and non-destructive testing across a wide range of water contents in the corn stover silage.