scholarly journals A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility

2021 ◽  
Vol 3 (2) ◽  
pp. 481-506
Author(s):  
Albert Whata ◽  
Charles Chimedza
Keyword(s):  
Short Term Memory ◽  
Causal Effect ◽  
World Health Organisation ◽  
World Health ◽  
P Value ◽  
Population Mobility ◽  
Times Series ◽  
Kernel Quantile Estimator ◽  
Long Short Term Memory ◽  
National Disaster

Following the declaration by the World Health Organisation (WHO) on 11 March 2020, that the global COVID-19 outbreak had become a pandemic, South Africa implemented a full lockdown from 27 March 2020 for 21 days. The full lockdown was implemented after the publication of the National Disaster Regulations (NDR) gazette on 18 March 2020. The regulations included lockdowns, public health measures, movement restrictions, social distancing measures, and social and economic measures. We developed a hybrid model that consists of a long-short term memory auto-encoder (LSTMAE) and the kernel quantile estimator (KQE) algorithm to detect change-points. Thereafter, we utilised the Bayesian structural times series models (BSTSMs) to estimate the causal effect of the lockdown measures. The LSTMAE and KQE, successfully detected the changepoint that resulted from the full lockdown that was imposed on 27 March 2020. Additionally, we quantified the causal effect of the full lockdown measure on population mobility in residential places, workplaces, transit stations, parks, grocery and pharmacy, and retail and recreation. In relative terms, population mobility at grocery and pharmacy places decreased significantly by −17,137.04% (p-value = 0.001 < 0.05). In relative terms, population mobility at transit stations, retail and recreation, workplaces, parks, and residential places decreased significantly by −998.59% (p-value = 0.001 < 0.05), −1277.36% (p-value = 0.001 < 0.05), −2175.86% (p-value = 0.001 < 0.05), −370.00% (p-value = 0.001< 0.05), and −22.73% (p-value = 0.001 < 0.05), respectively. Therefore, the full lockdown Level 5 imposed on March 27, 2020 had a causal effect on population mobility in these categories of places.

scholarly journals Association of p53, VEGF and Microvascular Density in Colorectal Carcinoma

2020 ◽  
Author(s):  
Rituparna Ghosh ◽  
Sarojini Raman ◽  
Jayasree Rath
Keyword(s):  
World Health Organisation ◽  
Microvascular Density ◽  
Nodal Status ◽  
World Health ◽  
Clinicopathological Parameters ◽  
P Value ◽  
Significant Prognostic Factor ◽  
Statistical Association ◽  
Cd34 Expression ◽  
Significant Statistical Association

Introduction: Colorectal Cancer (CRC) is third most common malignancy worldwide. Various genomic alterations play fundamental role in initiation and progression of CRC. Among these, p53 mutation has a crucial role in survival and metastasis and its point mutation induces Vascular Endothelial Growth Factor (VEGF) promoting vascular permeability, migration and differentiation. The degree of angiogenesis can be measured by Microvascular Density (MVD) using CD34, which is helpful in identifying high risk patients for recurrence and metastasis. Aim: The aim of the study was to analyse the expression of p53, VEGF and MVD in CRC and their association with clinicopathological parameters. Materials and Methods: The ambispective study of 2 year duration was conducted from September 2015 to July 2017 in the Department of Pathology, Kalinga Institute of Medical Sciences and PBMH, Bhubaneswar. It included CRC resection specimens and archival tissue blocks. Tissue microarray blocks were prepared manually for IHC application in total 70 cases (58 (82.9%) adenocarcinomas and 12 (17.1%) adenomas) which were histologically staged and graded as per American Joint Committee on Cancer (AJCC) and World Health Organisation (WHO) guidelines. Pearson chi-square test and fisher’s-exact method were used to find significance of p53, VEGF and CD34 expression in adenomas and adenocarcinomas with respect to clinicopathological parameters. Results: No significant statistical association was found between p53, VEGF and MVD with tumour grade and nodal status. Majority, 41 (70.69%) cases were hypervascular (MVD-High). Adenomas 9 (75%) cases, were mostly hypovascular (MVD-Low) with p-value of 0.003. There was significant statistical association between VEGF and MVD with a p-value of 0.01. VEGF and MVD were more expressed on left-sided colon cancers. There was significant statistical association (p=0.01) between p53 graded expression and diagnosis in the present study. MVD and tumour nodal status had an inversely significant relationship (p=0.03). Conclusion: p53 and VEGF expressed more on carcinomas than adenomas. Both p53 and VEGF induce angiogenesis which can be effectively measured by CD34 expression (MVD). There is a directly proportional relationship of angiogenesis and malignant transformation. So these three IHC markers together can be considered a significant prognostic factor involved in CRC.

Hubungan Komunikasi Terapeutik Perawat dan Fasilitas dengan Kepuasan Pasien Rawat Inap di Rumah Sakit Umum Cut Meutia Kota Langsa Tahun 2019

2020 ◽  
pp. 21-29
Author(s):  
Bambang Irawan ◽  
Erizal
Keyword(s):  
World Health Organisation ◽  
Cross Sectional Study ◽  
World Health ◽  
P Value ◽  
Sectional Study ◽  
Chi Square ◽  
Cross Sectional

Badan kesehatan dunia yaitu World Health Organisation (WHO) berupaya agar pelayanan kesehatan di dunia ini dapat memberikan suatu sistem pelayanan yang baik untuk meningkatkan derajat kesehatan masyarakat diberbagai belahan dunia. Penelitian ini bertujuan untuk mengetahui hubungan komunikasi terapeutik perawat dan fasilitas dengan kepuasan pasien rawat inap di Rumah Sakit Umum Cut Meutia Kota Langsa tahun 2019. Penelitian ini bersifat analitik dengan desain penelitian cross sectional study. Sampel dalam penelitian ini sebanyak 84 responden yang merupakan pasien rawat inap. Data dianalisa secara univarat dan bivariat menggunakan uji Chi square. Hasil penelitian diperoleh ada hubungan komunikasi terapeutik perawat dengan kepuasan pasien rawat inap di Rumah Sakit Umum Cut Meutia Kota Langsa tahun 2019 dengan nilai p-value (0,007) dan ada hubungan fasilitas dengan kepuasan pasien rawat inap di Rumah Sakit Umum Cut Meutia Kota Langsa tahun 2019 dengan nilai p-value (0,030).

scholarly journals A Data Organization Method for LSTM and Transformer When Predicting Chinese Banking Stock Prices

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Zong-Yu Peng ◽  
Pei-Chang Guo
Keyword(s):  
Stock Prices ◽  
Input Data ◽  
Short Term Memory ◽  
Basic Knowledge ◽  
Data Organization ◽  
Short Term ◽  
Times Series ◽  
Comparison Results ◽  
Long Short Term Memory ◽  
Transformer Model

The accurate prediction of stock prices is not an easy task. The long short-term memory (LSTM) neural network and the transformer are good machine learning models for times series forecasting. In this paper, we use LSTM and transformer to predict prices of banking stocks in China’s A-share market. It is shown that organizing the input data can help get accurate outcomes of the models. In this paper, we first introduce some basic knowledge about LSTM and present prediction results using a standard LSTM model. Then, we show how to organize the input data during the training period and give the comparison results for not only LSTM but also the transformer model. The numerical results show that the prediction results of LSTM and transformer can be improved after the input data are organized when training.

scholarly journals EFEKTIVITAS RANGE OF MOTION (ROM ) JARI-JARI TANGAN DAN SPHERICAL GRIP TERHADAP KEKUATAN EKSTREMITAS PADA PASIEN STROKE NON HEMORAGIK DI RSUD K.R.M.T WONGSONEGORO SEMARANG

2021 ◽  
Vol 5 (1) ◽  
pp. 1-5
Author(s):  
Sonhaji Sonhaji
Keyword(s):  
Range Of Motion ◽  
World Health Organisation ◽  
T Test ◽  
World Health ◽  
P Value ◽  
Purposive Sampling ◽  
Post Test ◽  
Paired T Test

Latar belakang: Stroke menurut WHO  (World  Health Organisation) adalah gangguan otak fokal ataupun global secara mendadak yang disebabkan oleh gangguan vaskuler. Tujuan mengetahui  efektivitas Range Of Motion (ROM) jari-jari tangan dan spherical  grip terhadap kekuatan ekstremitas pada pasien stroke  non hemoragik di RSUD K.R.M.T Wongsonegoro Semarang. Metode penelitian yang digunakan adalah deskriptif kuantitatif dengan teknik sampling yaitu purposive sampling, populasi penelitian ini sebanyak 32 orang dengan rancangan pre-post  Test dengan menggunakan kelompok kontrol, untuk kelompok intervensi  16 responden dengan memberikan latihan terapi ROM jari-jari tangan dan spherical grip, kelompok kontrol responden sebanyak 16 responden dengan memberikan latihan terapi ROM jari-jari tangan, uji statistik menggunakan shapirowilk, dependent paired t test, dan independent t-test. Hasil  analisis statistik diperoleh kelompok intervensi (latihan terapi Range Of Motion (ROM) jari-jari tangan dan spherical grip memberikan pengaruh yang lebih efektif dibandingkan dengan pemberian terapi pada kelompok kontrol (Range Of Motion (ROM) jari-jari tangan) dapatkan rata-rata perbedaan kekuatan otot ekstremitas dengan p-value 0.000. Simpulan pemberian terapi spherical grip maupun Range Of Motion (ROM) jari-jari tangan efektif terhadap peningkatan kekuatan ekstremitas pada penderita pasien stroke non hemoragik. Saranpenelitain selanjutnya dapat melakukan penelitian dengan menggunakan atau menambah variabel lain dengan desain penelitian yang lebih baik dengan mempertahankan karakteristik responden.  

scholarly journals Knowledge, Attitude and Awareness on Effect of Air Pollution on Children among Parents

2021 ◽  
pp. 347-354
Author(s):  
B. Ashwin Krishna ◽  
R. Gayatri Devi ◽  
A. Jothi Priya
Keyword(s):  
Air Pollution ◽  
World Health Organisation ◽  
World Health ◽  
Survey Study ◽  
P Value ◽  
Cross Sectional Survey ◽  
Chi Square ◽  
Cross Sectional ◽  
The People ◽  
Chi Square Test

Introduction: The World Health Organisation [WHO] recommended that breathing clean air reduces the risk of diseases such as Asthma and Lung cancer. Inhaling low quality of air causes several health problems such as headaches, nausea and tiredness. The main aim of this study is to create awareness among parents about the effect of air pollution on children. Materials and Methods: This is a cross sectional survey study. The standard questionnaire was prepared and distributed as Google forms to nearly 100-120 parents. The population was randomly selected. A self-administered structured questionnaire was prepared based on Knowledge attitude and awareness on effects of air pollution on children among parents. It was circulated to participants through an online platform (google forms). The statistics were done using SPSS software, chi square test was used to check the association and P value of 0.05% was said to be statistically significant. Results: 78.53% of the populations were aware that air pollution affects cognitive ability. 50.98% of the population responded that exposure of polluted air to pregnant female’s cause’s premature birth. 45.28% of females were aware that air pollution affects neutron development in the brain. As a result of this study most of the parents were aware about air pollution and its effects on their children. Conclusion: In this study females were slightly more aware about air pollution than males. If this awareness persists among all the people in the society many harmful effects such as air pollution and other related problems can be solved.

PREDIKSI RATA-RATA ZAT BERBAHAYA DI DKI JAKARTA BERDASARKAN INDEKS STANDAR PENCEMAR UDARA MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

2021 ◽  
Vol 26 (1) ◽  
pp. 41-55
Author(s):  
Anisa Oktaviani ◽  
Hustinawati
Keyword(s):  
Artificial Intelligence ◽  
Air Quality ◽  
World Health Organization ◽  
Quality Index ◽  
Short Term Memory ◽  
World Health ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Health Organization

Indonesia menempati peringkat ke-6 dari 98 negara paling berpolusi di dunia pada tahun 2019. Di tahun tersebut, rata-rata AQI (Air Quality Index) sebesar 141 dan rata-rata konsentrasi PM2.5 sebesar 51.71 μg/m3 yang lima kali lipat diatas rekomendasi World Health Organization (WHO). Salah satu kota penyumbang polusi udara yaitu Jakarta. Berdasarkan data ISPU (Indeks Standar Pencemar Udara) yang diambil dari SPKU (Stasiun Pemantau Kualitas Udara) Dinas Lingkungan Hidup DKI Jakarta melampirkan pada tahun 2019, Jakarta memiliki kualitas udara sangat tidak sehat. Oleh karena itu perlu adanya model Artificial Intelligence dalam memperdiksi rata-rata tingkat zat berbahaya pada udara di DKI Jakarta. Salah satu algoritma yang dapat diterapkan dalam membuat model prediksi dengan menggunakan data timeseries adalah Long Short-Term Memory (LSTM). Tujuan dari penelitian ini membangun model prediksi rata-rata ISPU di DKI Jakarta menggunakan metode LSTM yang berguna bagi para pemangku kepentingan dibidang lingkungan hidup khususnya mengenai polusi udara. Penelitian mengenai prediksi rata-rata ISPU di DKI Jakarta menggunakan metode LSTM, menghasilkan nilai evaluasi MAPE 12.28%. Berdasarkan hasil evaluasi MAPE yang diperoleh, model LSTM yang digunakan untuk prediksi rata-rata ISPU di DKI Jakarta masuk kedalam kategori akurat.

scholarly journals Hubungan Kebiasaan Meminum Teh dan Kopi dengan Kejadian Anemia pada Ibu Hamil di BPM Bidan “E” Desa Ciwangi Kecamatan Balubur Limbangan Kabupaten Garut

2019 ◽  
Vol 13 (2) ◽  
pp. 68-71
Author(s):  
Oktarina Sri Iriani ◽  
Ulfah Ulfah
Keyword(s):  
Vitamin C ◽  
World Health Organisation ◽  
World Health ◽  
P Value ◽  
Chi Square ◽  
Cross Sectional

Anemia adalah penurunan kapasitas darah dalam membawa oksigen karena jumlah sel darah merah yang kurang dari normal. Menurut World Health Organisation (WHO), 40% kematian ibu di negara berkembang berkaitan dengan anemia pada kehamilan dan kebanyakan anemia ini disebabkan oleh defisiensi besi. Anemia defisiensi besi adalah anemia yang terjadi akibat kekurangan zat besi dalam darah. Zat besi yang berasal dari makanan seperti daging, hati, telur, sayuran hijau dan buah- buahan diabsorpsi di usus halus. Penyerapan zat besi ini dipengaruhi oleh faktor adanya protein hewani dan vitamin C, sedangkan yang menghambat serapan adalah kopi, teh, garam kalsium dan magnesium karena bersifat mengikat zat besi, Di samping itu, dalam the dan kopi ada senyawa yang bernama tanin. Tanin ini dapat mengikat beberapa logam seperti zat besi, kalsium, dan aluminium, lalu membentuk ikatan kompleks secara kimiawi. Karena dalam posisi terikat terus, maka senyawa besi dan kalsium yang terdapat pada makanan sulit diserap tubuh sehingga menyebabkan penurunan zat besi (Fe). Tujuan penelitian ini untuk mengetahui Hubungan Kebiasaan Meminum Teh dan Kopi Dengan kejadian Anemia pada Ibu Hamil di BPM Ny. E Periode April-Juni 2018 Kabupaten Garut. Jenis penelitian kuantitatif dengan pendekatan Cross sectional. Jumlah sampel sebanyak 50 orang yang di ambil secara insidental sampling. Data yang digunakan yaitu data primer yang diambil secara langsung menggunakan lembar ceklis dan alat cek Hb Easy Touch. Analisa data berupa univariat dan bivariat dengan menggunakan uji chi- square. Hasil data 28 orang (56,0%) mengalami anemia dan 22 orang (44,0%) tidak anemia. Terdapat korelasi antara kebiasaan meminum teh dan kopi dan kasus anemia pada ibu hamil di BPM Ny. E chi square (24.219) > chi tabel (7,38) dan p value (0,000) < a (0,05). Penelitian ini menyarankan bagi ibu hamil agar menghindari meminum teh atau kopi secara langsung sebelum dan sesudah makan karena dapat menghambat penyerapan zat besi dalam darah.

A machine learning pipeline for fuel-economical driving model

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Neetika Jain ◽  
Sangeeta Mittal
Keyword(s):  
Anomaly Detection ◽  
Fuel Economy ◽  
Short Term Memory ◽  
Support Vector ◽  
Short Term ◽  
Term Memory ◽  
Content Type ◽  
Driving Behaviour ◽  
Kernel Quantile Estimator ◽  
Long Short Term Memory

PurposeA cost-effective way to achieve fuel economy is to reinforce positive driving behaviour. Driving behaviour can be controlled if drivers can be alerted for behaviour that results in poor fuel economy. Fuel consumption must be tracked and monitored instantaneously rather than tracking average fuel economy for the entire trip duration. A single-step application of machine learning (ML) is not sufficient to model prediction of instantaneous fuel consumption and detection of anomalous fuel economy. The study designs an ML pipeline to track and monitor instantaneous fuel economy and detect anomalies.Design/methodology/approachThis research iteratively applies different variations of a two-step ML pipeline to the driving dataset for hatchback cars. The first step addresses the problem of accurate measurement and prediction of fuel economy using time series driving data, and the second step detects abnormal fuel economy in relation to contextual information. Long short-term memory autoencoder method learns and uses the most salient features of time series data to build a regression model. The contextual anomaly is detected by following two approaches, kernel quantile estimator and one-class support vector machine. The kernel quantile estimator sets dynamic threshold for detecting anomalous behaviour. Any error beyond a threshold is classified as an anomaly. The one-class support vector machine learns training error pattern and applies the model to test data for anomaly detection. The two-step ML pipeline is further modified by replacing long short term memory autoencoder with gated recurrent network autoencoder, and the performance of both models is compared. The speed recommendations and feedback are issued to the driver based on detected anomalies for controlling aggressive behaviour.FindingsA composite long short-term memory autoencoder was compared with gated recurrent unit autoencoder. Both models achieve prediction accuracy within a range of 98%–100% for prediction as a first step. Recall and accuracy metrics for anomaly detection using kernel quantile estimator remains within 98%–100%, whereas the one-class support vector machine approach performs within the range of 99.3%–100%.Research limitations/implicationsThe proposed approach does not consider socio-demographics or physiological information of drivers due to privacy concerns. However, it can be extended to correlate driver's physiological state such as fatigue, sleep and stress to correlate with driving behaviour and fuel economy. The anomaly detection approach here is limited to providing feedback to driver, it can be extended to give contextual feedback to the steering controller or throttle controller. In the future, a controller-based system can be associated with an anomaly detection approach to control the acceleration and braking action of the driver.Practical implicationsThe suggested approach is helpful in monitoring and reinforcing fuel-economical driving behaviour among fleet drivers as per different environmental contexts. It can also be used as a training tool for improving driving efficiency for new drivers. It keeps drivers engaged positively by issuing a relevant warning for significant contextual anomalies and avoids issuing a warning for minor operational errors.Originality/valueThis paper contributes to the existing literature by providing an ML pipeline approach to track and monitor instantaneous fuel economy rather than relying on average fuel economy values. The approach is further extended to detect contextual driving behaviour anomalies and optimises fuel economy. The main contributions for this approach are as follows: (1) a prediction model is applied to fine-grained time series driving data to predict instantaneous fuel consumption. (2) Anomalous fuel economy is detected by comparing prediction error against a threshold and analysing error patterns based on contextual information.

Covid-19-related criminalisation in South Africa

2020 ◽  
Vol 33 (3) ◽  
pp. 685-707
Author(s):  
Emma Charlene Lubaale
Keyword(s):  
South Africa ◽  
Criminal Law ◽  
World Health Organisation ◽  
World Health ◽  
Health Issues ◽  
Fair Share ◽  
Global Pandemic ◽  
Multiple Issues ◽  
National Disaster ◽  
Principle Of Legality

Covid-19, a virus first identified in China, has since December 2019 wreaked its fair share of havoc across the globe. It has claimed hundreds of thousands of lives, with no continent spared. In March 2020, the World Health Organisation declared the virus a global pandemic and proceeded to call on states to take urgent measures to contain its spread. Governments across continents heeded the call by rolling out measures ranging from lockdowns to regulations giving effect to the measures adopted. On 15 March 2020, South Africa declared a state of national disaster and days later, a national lockdown in response to the Covid-19 pandemic. This lockdown was followed by regulations, all geared towards containing the further spread of this virus. Criminal law came into play in dealing with the violators of the Covid-19 Regulations and while these measures were well-intentioned, multiple issues have hardly been examined from a criminal law perspective. The purpose of this article is to demonstrate the limitation of criminalisation as a response to health issues. The article does this by engaging with previous failed attempts to rely on criminalisation to address public health issues; underscoring the effect that some of the regulations have on the criminal law principle of legality and bringing to the fore the unintended consequence of criminalising poverty in a society that is already unequal. In engaging with these three themes, the analysis provides a context through which Covid-19-related criminalisation should be viewed and affords reasons why the criminalisation approach is counterproductive and should not be considered in dealing with future pandemics. The conclusions drawn are instructive to other countries in light of the fact that criminalisation in the wake of the Covid-19 pandemic was not unique to South Africa.

scholarly journals 301 Theatre Timing Audit (TTA): HPB and Transplant theatre timing during COVID

2021 ◽  
Vol 108 (Supplement_6) ◽  
Author(s):  
Marios Ghobrial ◽  
Jos Crush ◽  
Igor Chipurovski ◽  
Fanourios Georgiades
Keyword(s):  
World Health Organisation ◽  
World Health ◽  
P Value ◽  
Anaesthetic Induction ◽  
Mortality And Morbidity ◽  
Morbidity Burden ◽  
Period 2 ◽  
The World ◽  
The Uk ◽  
The Impact

Abstract Introduction Severe-Acute-Respiratory-Syndrome-Coronavirus-2 is a novel, highly infectious virus that has spread throughout the world causing respiratory disease (COVID-19). COVID-19 was declared a global pandemic by the World Health Organisation in March 2020. The UK has been severely affected with around 70000 deaths recorded by December 2020. Surgical practice during this pandemic has changed, as peri-operative infections carry significant mortality and morbidity burden. Method Theatre timing from a large volume hospital specifically for HPB-Transplant dedicated theatres were assessed to evaluate the impact of the national/local COVID-19 protocols on service delivery. “Pre-COVID period” was defined by auditing times from ward-to-theatre, anaesthetic induction-to-start of procedure and end of procedure-to-transfer out of theatre for 2 consecutive weeks in October/November 2019. “COVID period-1” and “COVID period-2” were defined as two consecutive weeks during the UK government-imposed lockdown in April and November 2020, respectively. Results Under the care of the HPB-Transplant team pre-COVID 56 individuals were treated in 30 sessions. Only 16 patients (28.6% of capacity) in 12 sessions were treated in COVID period-1 and 48 patients were treated (85.7% of capacity) in 30 sessions in COVID period-2. Similar times were observed in transferring patients to theatre (p-value=0.265) and induction of anaesthesia (p-value=0.698) across the 3 periods. Significant delays were observed in transferring patients out of theatre during COVID period-1, that returned to near normal timing during COVID period-2 (16.6±12.8 Vs 39.4±10.9 Vs 17.6±10.5 min; p-value = &lt;0.00001). Conclusions Despite returning to near normal theatre timings in COVID period-2, we treat fewer patients, adversely affecting waiting lists.

Sign in / Sign up

Export Citation Format

Share Document