Search

In today’s world, higher security deployments are needed, as the expansion of the transportation system has accelerated with time. Road traffic disasters have become a widespread problem in recent years. With the tremendous increase in traffic accidents, the fatality rate among people is quickly expanding. Whenever a mishap occurs on the roadways, it becomes a devastating situation for the victims. As an output result of the proposed model in this article, critical notification regarding the scene of an accident and car number was successfully sent to the pre-programmed number after determining the accident scene. The relevant contacts that were configured and added to the system successfully received an emergency message, providing the exact geographic coordinates of the accident scene. Following the receipt of the message, an audio call with a recorded voice was made to the pre-defined number. Moreover, Global Positioning System (GPS) was used to get the coordinates from the satellite. For this purpose, Global System for Mobile Communications (GSM) was utilized to attain the (GPS) coordinates in the event of an accident. Following on, the current location of an automobile through (GPS) was transmitted to certain contact details that were pre-programmed within the application. The system also reported the severity of the accident, as well as whether a vehicle collided with another vehicle or a disaster occurred to the vehicle itself.

Information and Communication Technology (ICT) has changed the computing paradigm. Various new channels for communication are created through these developments, and the Internet of Things (IoT) is one of them. Internet of Medical Things (IoMT) is a part of IoT in which medical devices are connected through a network. IoMT has resolved many traditional health-related problems and has some security concerns. This article uses three Machine Learning algorithms, Random Forest, Gradient Boosting, and Support Vector Machine (SVM), to detect cyberattacks. Machine Learning models are best for performing cyberattack detection. Proposed Machine Learning models are evaluated on the WUSTL EHMS 2020 dataset, which consists of main in-themiddle, data injection, and spoofing attacks. The evaluation of the result analysis shows that the proposed Machine Learning models outperformed existing techniques.

Agriculture activities are completely dependent upon energy production worldwide. This research presents sensorless speed control of a three-phase induction motor aided with an extended Kalman filter (EKF). Although a proportional integral (PI) controller can ensure tracking of the rotor speed, a considerable magnitude of ripples is present in the torque generated by a motor. Adding a simple derivative to have a proportional integral derivative (PID) action can cause a further increase in ripple magnitude, as it allows the addition of high-frequency noise in the system. Therefore, a fractional-order-based PID control is presented. The proposed control scheme is applied in a closed loop with the system, and simulation results are compared with the PID controller. It is evident from the results that the fractional order control not only ensures 20 times faster tracking, but ripple magnitude in torque was also reduced by a factor of 50% compared to that while using PID and ensures the effectiveness of the proposed strategy.

Detecting cardiovascular disease (CVD) in the early stage is a difficult and crucial process. The objective of this study is to test the capability of machine learning (ML) methods for accurately diagnosing the CVD outcomes. For this study, the efficiency and effectiveness of four well renowned ML classifiers, i.e., support vector machine (SVM), logistics regression (LR), naive Bayes (NB), and decision tree (J48), are measured in terms of precision, sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC), correctly and incorrectly classified instances, and model building time. These ML classifiers are applied on publically available CVD dataset. In accordance with the measured result, J48 performs better than its competitor classifiers, providing significant assistance to the cardiologists.

This article examines the effect of outbound FDI on labour market volatility and, thereby, on economic insecurity in home countries of FDI distinguishing between greenfield FDI (GFDI) and cross-bor...

The results of gender equality indicators across the world in the form of prevalence of intimate partner violence (IPV) against women are striking and has thus drawn the attention of policy makers as well as necessitates the adoption of a comprehensive system to deal with. The situation of IPV in Pakistan is alarming. This study examines the acceptability attitude of women and men toward intimate partner violence against women through data science. It discovers and contrasts the frequently co-occurring reasons due to which husbands’ behaviour of beating their wives is believed to be legitimate by both partners in the province of Punjab, Pakistan. Though the discovered frequently co-occurring reasons, such as “arguing with the husband and neglecting the children” altogether, are similar in both genders but the fraction of wives believing in such reasons are significantly greater than that of husbands. This psychological disparity across genders could help in identifying the social and cultural factors to whom this disparity is attributed. It is expected that the identified co-occurring groups of reasons would help to understand the problem to the next level and devise better strategies to mitigate them.

The substantial rise in the demand for electric vehicles (EVs) has emphasized an environment-friendly and intelligent design for speed control strategies. In this paper, a Mamdani fuzzy logic controller (MFLC) was proposed to vigorously control the speed of EVs at discrete levels. MFLC member functions (MFs) are tuned for EVs operating at three different speed modes (40, 60, and 80 km/h). The proposed speed controller operation for the speed tracking of EVs was designed and tested in MATLAB (Simulink) environment. The proposed speed controller validated a remarkable improvement in dynamic speed control compared with existing P-I, FLC, Fuzzy FOPID (ACO), Fuzzy FOPID (GA), and Fuzzy FOPID (PSO) controllers. Its stability under a user-defined drive pattern is also observed. In this proposed work, the speed controller highlights the better tracking of user-defined speed response compared to the conventional aforementioned controllers. Moreover, the speed tracking of the designed model was tested for robustness against speed transients at predefined time instants, respectively. The comparison suggests that the MFLC model removes overshoot and significantly reduces the steady-state time.

The methods used in chemical engineering are strongly reliant on having a solid grasp of the thermodynamic features of complex systems. It is difficult to define the behavior of ions and molecules in complex systems and to make reliable predictions about the thermodynamic features of complex systems across a wide range. Deep learning (DL), which can provide explanations for intricate interactions that are beyond the scope of traditional mathematical functions, would appear to be an effective solution to this problem. In this brief Perspective, we provide an overview of DL and review several of its possible applications within the realm of chemical engineering. DL approaches to anticipate the molecular thermodynamic characteristics of a broad range of systems based on the data that are already available are also described, with numerous cases serving as illustrations. Web of Science 15 24 art. no. 9344

Featured Application: The proposed automatic emotion recognition system has been deployed in the classroom environment (education) but it can be used anywhere to monitor the emotions of humans, i.e., health, banking, industries, social welfare etc. Abstract: Emotions play a vital role in education. Technological advancement in computer vision using deep learning models has improved automatic emotion recognition. In this study, a real-time automatic emotion recognition system is developed incorporating novel salient facial features for classroom assessment using a deep learning model. The proposed novel facial features for each emotion are initially detected using HOG for face recognition, and automatic emotion recognition is then performed by training a convolutional neural network (CNN) that takes real-time input from a camera deployed in the classroom. The proposed emotion recognition system will analyze the facial expressions of each student during learning. The selected emotional states are happiness, sadness, and fear along with the cognitive–emotional states of satisfaction, dissatisfaction, and concentration. The selected emotional states are tested against selected variables gender, department, lecture time, seating positions, and the difficulty of a subject. The proposed system contributes to improve classroom learning. Web of Science 12 23 art. no. 12134

Background Adequate sleep duration in childhood has important implications for social, mental, and physical well-being. Recent evidence has demonstrated declining sleep durations in children; therefore effective interventions to improve sleep measures are needed. Despite some trials suggesting that multi-behavioural interventions promoting bed-time routines may be beneficial, the effectiveness of such interventions has not been adequately quantified. Moreover, specific themes and strategies which increase sleep duration, and by how much, have not been formally quantified. Methods We carried out a systematic review and meta-analysis to quantify the effectiveness of sleep interventions to improve sleep duration in children within community settings (PROSPERO ID CRD42019160089). Studies involving infants under 1 year, those using medications, and targeting children with behavioural problems were excluded. We screened 11621 randomised control trials (RCT), after carrying out a search using combined text words and MeSH criteria in CENTRAL, MEDLINE, EMBASE, PSYCHINFO, Web of science, clinicaltrials.gov, and WHO trials databases. Full text screening of 341 studies identified 39 studies for data extraction. All screening was carried out independently by two reviewers using a web-based platform for systematic reviews. Results Studies were categorised by age as follows: 20% in >1–5 years of age, 25% >5–10 years, 33% >10–15 years, 22% >15 years. The mode of delivery of most interventions was face to face (74%). The intervention setting was most commonly school based (54%), with 21% based at home. Intervention duration was less than one month in 49% of studies. Qualitative data to describe each intervention was collected using a framework based on the TIDieR checklist. We are mapping this onto behavioural frameworks (COM-B, theoretical domains framework), to categorise interventions. Our initial analysis, from 9911 participants (4719, intervention, 5192 control) from 33 studies, suggests that mean differences in interventions increase sleep duration by 11 minutes (95% CI 6, 17 mins). However, caution is needed in interpreting this overall effect size (pooled using random effects) given the considerable heterogeneity across studies (I2 = 91%). The influence of study design characteristics in explaining heterogeneity (including age of participants, duration and type of intervention) will be outlined. Conclusion This review furthers our understanding of the most effective interventions to improve sleep duration in children and provides a platform to develop population level health interventions to improve sleep. Given challenges assimilating data, an overarching aim is to develop approaches that could be used to homogenise reporting in future RCTs in order that evidence can be summarised more easily.

Background The first wave of the COVID-19 pandemic in England resulted in an approximate 50% increase in all-cause mortality during mid-March to mid-May 2020. Previous analyses have studied COVID-related deaths, but these were under-recorded early in the pandemic due to paucity of virological testing. We propose a novel method to identify excess mortality during the pandemic by accounting for usual all-cause mortality in pre-pandemic years using a large electronic primary care database. We estimated the impact of risk factors (RFs) on excess mortality during the first wave and compared these with the impact of the same RFs on total mortality in non-pandemic times. Methods An average of 4.8 million patients aged 30–104 years active in 770 CPRD Aurum practices between 18th March and 19th May over a 6-year period (2015–2020) were included. Concurrent medical history, ethnicity, area-based deprivation and fatalities were extracted for each year. Poisson regression models fitted total mortality adjusting for age and sex, with interactions between each RF and the pandemic and reference periods. Total mortality during the pandemic was partitioned into ‘usual’ and ‘excess’ components, assuming 2015–19 rates represented ‘usual’ mortality. The association of each RF with the 2020 ‘excess’ component was derived as the excess mortality ratio (EMR), to compare with the usual mortality ratio (UMR). Results RFs where excess mortality was greatest and notably higher than usual were age >80, black ethnicity, BMI>40, dementia, learning disability, London practices and people in care-homes. For example, people of black ethnicity vs. white had an EMR=2.50 (95%CI 1.97–3.18) compared to a UMR=0.92 (95%CI 0.85–1.00). Excess mortality was more comparable to usual mortality for sex and area deprivation. The EMR for men (1.46, 95%CI 1.32–1.60) was not significantly different than the UMR=1.34 (95%CI 1.32–1.37). The EMR=2.05 (95%CI 1.76–2.38) in the most deprived quintile (vs. least) was only slightly higher than the UMR=1.70 (95%CI 1.65–1.75). Although some RFs produced EMRs significantly lower than their UMRs (Cancer, COPD), the EMRs were still >1. However, current smoking was inversely associated with excess mortality: while current smokers were 64% more likely to die than non-smokers in 2020, when the UMR=2.12 (95%CI 2.07–2.18) was accounted for, the EMR=0.80 (95%CI 0.65–0.98). Conclusion Utilising large electronic patient databases to study trends in excess mortality during the pandemic confirmed some reported findings (e.g. ethnicity, obesity and care-homes), but also highlighted important differences not apparent from studying cause specific mortality during the pandemic (e.g. smoking, sex and area deprivation).

Background Large-scale electronic primary care datasets can provide up-to-date, accurate epidemiological information on rarer diseases. In the UK, approximately 70,000 people are estimated to be living with neuromuscular disease (NMD), but this approximation is over 10 years old and used historical estimates from different sources. While GPs are unlikely to make NMD diagnoses themselves, specialist diagnoses from hospital discharges and clinic letters are well recorded and electronically searchable within primary care records. The recent expansion of the Clinical Practice Research Datalink (CPRD) allows timely reporting on the recorded incidence and prevalence of NMD in the UK over the last 20 years. Methods A harmonised dataset of CPRD GOLD and Aurum was developed to provide annual denominators of actively registered patients between 2000 and 2019. A Read code hierarchy was developed for a wide range of NMDs; the database was then searched electronically to estimate incidence and (lifetime) prevalence rates in each year. To compare trends over time, rates were age standardised to the most recent CPRD population (2019). Results The combined CPRD database contained approximately 13 million patients actively registered in each year. By 2019, 28,230 active patients had ever received a Read code for one of the NMDs (223.6 per 100,000), which would scale up to approximately 149,000 people in the UK. Lifetime prevalence rates per 100,000 were higher among males (239.0) than females (208.3). The most common classifications were Guillain-Barre syndrome (40.1), myasthenia gravis (33.7), muscular dystrophy (29.5), Charcot-Marie-Tooth (29.5) and inflammatory myopathies (25.0). Since 2000, overall prevalence grew by 63% but incidence remained steady over time. All age groups showed an increase in prevalence, with the largest increases seen at older ages (≥65-years). Among individual conditions since about 2008, incidence of myasthenia gravis has been steadily rising while new cases of muscular dystrophy fell over the same period. Conclusions Lifetime recording of many NMDs on primary care records exceeds current estimates of people living with these conditions; these are important data for health service and care planning. Temporal trends suggest this number is steadily increasing and there may be twice as many people living with these conditions than currently thought. While this may be partially due to increases in recording, it cannot be simply explained by new cases as incidence is largely unchanged over time. The increase in prevalence among older ages suggest increases in life expectancy among those living with NMDs may have taken place.

A considerable fraction of the female workforce worldwide is making ends meet by doing various jobs informally at home or in nearby places, rather than at employers’ premises. The contribution of these female home-based workers (FHBWs) is significant to the country’s economic growth. FHBWs are often confronted with numerous occupational diseases due to a lack of awareness of occupational safety and health measures, and unhealthy living and working conditions. The informality of FHBWs prevents them from getting proper healthcare, safety, and other dispensations enjoyed by formal employees. Despite their undeniable importance, health issues of FHBWs are still overlooked. This study is an attempt to discover the frequent co-occurring occupational diseases encountered by FHBWs in Punjab, a province of Pakistan. Frequent itemset mining (FIM) or co-occurrence grouping is a technique of data science that identifies the associations among different entities in the data. Based on FIM, the D-GENE algorithm is applied in this study to efficiently discover frequent co-occurring diseases in the data obtained from the Punjab Home-based Workers Survey (2016). The far-reaching goal of the study is to bring awareness of the occupational health issues and safety risks to the health authorities as well as to the FHBWs.

A 32-year-old male with morbid obesity presented to the emergency department with a one-week history of shortness of breath and productive cough. This patient had previously been evaluated at an urgent care facility, diagnosed with pneumonia, and prescribed oral antibiotics. This patient's worsening shortness of breath and productive cough led this patient to seek further care at the emergency department. Chest radiography revealed acute respiratory distress syndrome (ARDS) with an empyema in the right pleural space. He was admitted to the intensive care unit and subsequently intubated due to severely compromised cardiopulmonary function. The patient then underwent irrigation of the chest cavity and chest tube placement for drainage of the right-sided empyema. Surgical cultures revealed growth of Streptococcus anginosus and appropriate antibiotics were started. The patient's pulmonary function continued to deteriorate and this patient was placed on venous to venous extracorporeal membrane oxygenation (VV ECMO). Due to continued respiratory failure and a persistent air leak, a double-lumen endotracheal tube (DLT) was exchanged to initiate one-lung ventilation (OLV) to optimize ventilation and protect the lung containing the empyema. Over the following days, worsening leukocytosis and atelectasis were noted upon imaging prompting cardiothoracic surgery to return to the operating room to perform a right posterolateral thoracotomy and full right lung decortication. The procedure was successful and a bronchopleural fistula (BPF) was observed, secondary to the necrotizing pneumonia. The observation of the fistula explained the persistent air leak and issues maintaining adequate oxygenation. OLV through a DLT was continued over the following days, and the patient's pulmonary status and leukocytosis ultimately began to improve over the next two weeks. This patient was then able to be weaned off the EMCO device and was extubated. The patient was stabilized and discharged to a rehabilitation facility for further recovery. This case highlights how the use of lung isolation techniques were essential in the recovery of this patient with an estimated 50% mortality rate due to significant pulmonary injury from necrotizing pneumonia and complicated by a BPF.

The speed control of induction machines for multiple-speed handling is critical. When the vector control method is applied to induction machines, it has a significant impact on speed utilization. This strategy of operating the machine at a fixed predefined speed mode presents better results for electric vehicles. An effective model for a speed control loop is proposed in this paper, using a fixed-mode proportional integral (FM-PI) controller based on an upper and lower limit torque limiter. The power supply is fed using a lithium-ion battery with an inverter-fed mechanism. Moreover, the proposed model is validated using simulations with user-defined speed modes (40, 60, and 80 km/h). These speed modes, with different torque commands, have been considered for advanced modeling. In this model, torque is developed via a closed-loop control operation to attain the required speed assigned by the user. The sensors are used to collect data, and a multiple regression algorithm analyzes the dataset to predict input parameters (voltage (Vab), phase current (I), and torque (T)) required to achieve the desired speed mode. The efficiency of the proposed model is compared with induction motors bearing the same rating for the loaded and unloaded speed test. Effective machine parameter control is achieved by reaching the desired performance levels of 94.37% and 78.30% in a shorter time for the loaded and unloaded modes. A speed response comparison of the FOPID, KW-WOA-PID, SVR-PI, and FM-PI controller model simulation results indicates that the FM-PI speed controller guarantees better performance and displays an improvement in rising time and settling time, compared to other controllers. The implementation of different driving scenarios proves the model’s effectiveness for robust speed applications.

Syphilitic myelitis, also known as tabes dorsalis, is a disease affecting the posterior columns of the spinal cord and dorsal roots and presents as sensory ataxia and neuropathic pain and less commonly as paresthesia and gastrointestinal disturbance. Tabes dorsalis is the clinical manifestation of a previous infection with syphilis, and the average latency period from initial infection to presentation of symptoms is approximately 25 years. This is a rarely encountered manifestation of syphilis since the widespread usage of antibiotics. Penicillin G is the mainstay therapy of neurosyphilis and has been shown to improve and resolve spinal cord lesions associated with tertiary syphilis. We present a case of tabes dorsalis in a 56-year-old female with a history of extensive autoimmune disease who initially presented with neck pain and numbness of the right lower extremity. The unique nature of this case lies in the patient's clinical course, as her symptoms were initially attributed to her history of autoimmune disease. A reactive CSF-VDRL (cerebrospinal fluid Venereal Disease Research Laboratory) test and MRI findings led clinicians to suspect neurosyphilis and begin penicillin G. The patient began to show significant clinical improvement after penicillin G therapy was begun and was discharged to a rehabilitation facility to continue antibiotics and begin aggressive physical therapy.

Among the numerous anthropogenic pollutants, nitrogen dioxide (NO2) is one of the leading contaminants mainly released by burning fossil fuels in industrial and transport sectors. This study evaluates the impact of COVID-19 lockdown on the growing trend of NO2 emissions in South Asia. Satellite imagery data of Sentinel-5 Precursor with Tropomi instrument was employed in this study. The analysis was performed using time series data from February–May 2019 and February–May 2020. The time frame from February–May 2020 was further divided into two sub-time-frames, i.e., from 1 February–20 March (pre-lockdown) and from 21 March–May 2020 (lockdown). Results show the concentration of NO2 pollutants over the region declined by 6.41% from February–May 2019 to February–May 2020. Interestingly, an increasing trend of NO2 concentration by 6.58% occurred during the pre-lockdown phase in 2020 (1 February–20 March) compared to 2019 (February–May). However, the concentration of NO2 pollutants reduced considerably by 21.10% during the lockdown phase (21 March–10 May) compared to the pre-lockdown phase in 2020. Furthermore, the country-specific detailed analysis demonstrates the significant impact of COVID-19-attributed lockdown on NO2 concentration in South Asia.

BackgroundStep-count monitors (pedometers, body-worn trackers and smartphone applications) can increase walking, helping to tackle physical inactivity. We aimed to assess the effect of step-count monitors on physical activity (PA) in randomised controlled trials (RCTs) amongst community-dwelling adults; including longer-term effects, differences between step-count monitors, and between intervention components.MethodsSystematic literature searches in seven databases identified RCTs in healthy adults, or those at risk of disease, published between January 2000–April 2020. Two reviewers independently selected studies, extracted data and assessed risk of bias. Outcome was mean differences (MD) with 95% confidence intervals (CI) in steps at follow-up between treatment and control groups. Our preferred outcome measure was from studies with follow-up steps adjusted for baseline steps (change studies); but we also included studies reporting follow-up differences only (end-point studies). Multivariate-meta-analysis used random-effect estimates at different time-points for change studies only. Meta-regression compared effects of different step-count monitors and intervention components amongst all studies at ≤4 months.ResultsOf 12,491 records identified, 70 RCTs (at generally low risk of bias) were included, with 57 trials (16,355 participants) included in meta-analyses: 32 provided change from baseline data; 25 provided end-point only. Multivariate meta-analysis of the 32 change studies demonstrated step-counts favoured intervention groups: MD of 1126 steps/day 95%CI [787, 1466] at ≤4 months, 1050 steps/day [602, 1498] at 6 months, 464 steps/day [301, 626] at 1 year, 121 steps/day [− 64, 306] at 2 years and 434 steps/day [191, 676] at 3–4 years. Meta-regression of the 57 trials at ≤4 months demonstrated in mutually-adjusted analyses that: end-point were similar to change studies (+ 257 steps/day [− 417, 931]); body-worn trackers/smartphone applications were less effective than pedometers (− 834 steps/day [− 1542, − 126]); and interventions providing additional counselling/incentives were not better than those without (− 812 steps/day [− 1503, − 122]).ConclusionsStep-count monitoring leads to short and long-term step-count increases, with no evidence that either body-worn trackers/smartphone applications, or additional counselling/incentives offer further benefit over simpler pedometer-based interventions. Simple step-count monitoring interventions should be prioritised to address the public health physical inactivity challenge.Systematic review registrationPROSPERO numberCRD42017075810.

ObjectiveTo identify randomised controlled trials (RCTs) of physical activity (PA) interventions with objective PA outcomes in adults and to evaluate whether intervention effects were sustained beyond 12 months.DesignSystematic review and meta-analysis.Data sourcesSeven databases (Medline, Embase, PsycINFO, Web of Science, Cochrane library, CINAHL (Cumulative Index of Nursing and Allied Health Literature) and ASSIA (Applied Social Sciences Index and Abstracts)) were searched from January 2000 until December 2019.Eligibility criteriaRCTs reporting objective PA outcomes beyond 12 months with community-based participants aged ≥18 years were included; those where controls received active interventions, including advice to increase PA levels, were excluded.Data extraction and synthesisTwo independent reviewers completed extraction of aggregate data and assessed risk of bias. Meta-analyses used random-effects models at different follow-up points. Primary outcomes were daily steps and weekly minutes of moderate-to-vigorous PA (MVPA).ResultsOf 33 282 records identified, nine studies (at generally low risk of bias) were included, five in meta-analyses with 12 months to 4 year follow-up. We observed 12 month increases for intervention vs control participants in steps/day (mean difference (MD)=554 (95% CIs: 384 to 724) p2=0%; 2446 participants; four studies) and weekly MVPA minutes (MD=35 (95% CI: 27 to 43) p2=0%; 2647 participants; four studies). Effects were sustained up to 4 years for steps/day (MD=494 (95% CI: 251 to 738) p2=0%; 1944 participants; four studies) and weekly MVPA minutes (MD=25 (95% CI: 13 to 37) p2=0%; 1458 participants; three studies).ConclusionsThere are few PA interventions with objective follow-up beyond 12 months, more studies are needed. However, this review provided evidence of PA intervention effects beyond 12 months and sustained up to 4 years for both steps/day and MVPA. These findings have important implications for potential long-term health benefits.PROSPERO registration numberCRD42017075753.

Sparseness is often witnessed in big data emanating from a variety of sources, including IoT, pervasive computing, and behavioral data. Frequent itemset mining is the first and foremost step of association rule mining, which is a distinguished unsupervised machine learning problem. However, techniques for frequent itemset mining are least explored for sparse real-world data, showing somewhat comparable performance. On the contrary, the methods are adequately validated for dense data and stand apart from each other in terms of performance. Hence, there arises an immense need for evaluating these techniques as well as proposing new ones for large sparse real-world datasets. In this study, a novel method: Mining Frequent Itemsets by Iterative TRimmed Transaction lattICE (TRICE) is proposed. TRICE iteratively generates combinations of varying-sized trimmed subsets of $I$ , where $I$ denote the set of distinct items in a database. Extensive experiments are conducted to assess TRICE against HARPP, FP-Growth, optimized SaM, and optimized RElim algorithms. The experimental results show that TRICE outperforms all these algorithms both in terms of running time and memory consumption. TRICE maintains a substantial performance gap for all sparse real-world datasets on all minimum support thresholds. Moreover, assessment of memory use of optimized SaM and RElim algorithms has been performed for the first time.

Background Physical inactivity is a global public health concern. Systematic review evidence indicates interventions can increase short-term physical activity (PA) levels. However, long-term health benefits require sustained increases in PA levels, and evidence from interventions with objective PA measures beyond 12-months is lacking. This review aims to: Identify and describe randomised controlled trials (RCTs) in adults with objective PA measures and long–term follow–up (beyond 12–months) Evaluate the extent to which intervention effects are sustained beyond 12–months Methods We systematically searched seven databases using MeSH headings and keywords to identify RCTs published after 01/01/2000. We included trials reporting long-term effects (≥ 12-months) on objective PA levels with community-based participants, aged ≥18 years, with no specific medical conditions. We conducted quality assessments and meta-analyses at different follow-up points. Results Of 17233 unique records identified, 9 studies were included in the review, 5 in the meta-analyses. Long-term follow-up ranged from 12-months to 4-years. We observed increases in PA at 12-months for steps/day (mean difference (md)=554, 95% CI=383 to 724) and weekly minutes of moderate-to-vigorous PA (MVPA) (md=34.9, 95% CI=26.9 to 42.8). This increase was sustained up to 4 years for both steps/day (md=494, 95% CI 251 to 738) and weekly minutes of MVPA (md=25.2, 95% CI=13.3 to 37.1). Conclusion There are few PA interventions with objective follow up beyond 12-months. This review provided evidence of sustained PA intervention effects beyond 12-months and up to 4-years for both steps/day and MVPA.

One of the important resources required for various Natural Language Processing (NLP) applications like machine translation, information retrieval and text mining, is annotated text corpora. Text corpora annotation process requires parts of speech (POS) tags to mark different parts of text with grammatical annotations in order to identify linguistic properties of a word, sentence or discourse. The process of marking text items is based on two main features 1) grammatical category and 2) context of text (word, sentence or discourse) i.e. relationship with adjacent and related text. Saraiki being one of oldest languages is still resource scarce language in recorded literature as well as in computational context. According to our study, at present, there is no tagset defined for Saraiki language. This work presents first hierarchical POS (MPOST) tag set for the Saraiki language which is designed to be used in morphological, syntactic and lexical annotations of Saraiki language corpora.

Given the increasing size and complexity of datasets needed to train machine learning algorithms, it is necessary to reduce the number of features required to achieve high classification accuracy. This paper presents a novel and efficient approach based on the Monte Carlo Tree Search (MCTS) to find the optimal feature subset through the feature space. The algorithm searches for the best feature subset by combining the benefits of tree search with random sampling. Starting from an empty node, the tree is incrementally built by adding nodes representing the inclusion or exclusion of the features in the feature space. Every iteration leads to a feature subset following the tree and default policies. The accuracy of the classifier on the feature subset is used as the reward and propagated backwards to update the tree. Finally, the subset with the highest reward is chosen as the best feature subset. The efficiency and effectiveness of the proposed method is validated by experimenting on many benchmark datasets. The results are also compared with significant methods in the literature, which demonstrates the superiority of the proposed method.

Machine Learning is a scientific discipline that addresses learning in context is not learning by heart but recognizing complex patterns and makes intelligent decisions based on data. Currently, students have to face the problem of selecting the best suitable university for admission in engineering. There is no predictor system that recommends the students to select the specific category which is best to its academic career. Students have to first appear in the entry test and can’t predict whether he/she can pass the entry test to get admitted in University. To tackle this problem the field of Machine Learning develops algorithms that discover knowledge from specific data and experience, based on sound statistical and computational principles. After going through the entry test students have to face problems for selecting the preferences among different categories due to the lack of knowledge of intake merits of preceding years. Another problem arises when students are waiting for admission in specific university, meanwhile, other universities finish their admission processes and select the students, but some students can’t take admission in any university due to no prediction system for admission in universities. In this work, we would like to develop an E-Assessment and Computer-Aided Prediction online system that enables the student to predict the entry test numbers by giving the Metric and Intermediate marks and other academic numbers. The suggested scheme has been demonstrated to perform at the maximum speed under MATLAB setup.

BackgroundTelehealth care and telephone consultations are increasingly used in primary care for daily triage, patient reviews, and providing clinical information; however little is known about the perceptions of GP trainees.AimTo investigate the knowledge and skills of GP trainees in conducting telephone consultations; evaluate their current experiences and learning needs; and identify future training considerations based on feedback received.MethodUsing a mixed-methods approach, a cross-sectional quantitative survey of North Central and East London (NCEL) GP trainees was initially performed. This was followed-up by qualitative semi-structured interviews, which allowed deeper exploration of themes.ResultsIn total 100 trainees responded to the survey, and eight proceeded with interviews. Trainees were least confident in independently undertaking more complex aspects of telephone consulting, and there was a positive correlation between training received and confidence to work independently. Despite positive and negative experiences, trainees felt that there were gaps in their training and significant differences in overall confidence, supervision and feedback among different training grades and between in-hours and out-of-hours practice. Future considerations included curricular promotion, increased trainer-trainee observations using audio-clinical observation tools or simulated practice, and consideration of formal training.ConclusionThis project has shed light on the current learning, feedback, and assessment practices of GP trainees in conducting telephone consultations. Further evaluation will provide a helpful guide to various stakeholders, foresee any challenges and inform a wider debate among postgraduate learners regarding their training for the use of technology in healthcare.

Epidemiological disaster management, using geo-informatics (GIS), is an innovative field of rapid information gathering. Dengue fever, a vector-borne disease, also known as break bone fever, is a lethal re-emerging arboviral disease. Its endemic flow is causing serious effects to the economy and health at the global level. Even now, many under-developed and developing countries like Pakistan lack the necessary GIS technologies to monitor such health issues. The aim of this study is to enhance the effectiveness of developing countries through disaster management capabilities by using state-of-the-art technologies, which provide the measures to relief the disaster burden on public sector agencies. In this paper, temporal changes and regional burden for distribution of this disease are mapped using GIS tools. For the prevention of disaster burden, these types of studies are widely used to provide an effective help and relief. This study concludes that a public sector institute can use such tools for surveillance purpose and to identify the risk areas for possible precautionary measures.