Search
Search results for
We found
40 results for you
-
Quantitative description of woody plant communities: Part I. An approach
Item type: Journal Article • Journal: Journal of the Grassland Society of Southern Africa • Authors: G.N. Smit --- Department of Agriculture and Water Supply (Transvaal Region), Republic of South AfricaVarious descriptive units for woody plant communities are proposed. These are the Evapotranspiration Tree Equivalent (ETTE), Browse Tree Equivalent (BTE) and Canopied Subhabitat Index (CSI), which describe the status of a woody community in terms of potential moisture use, value... -
'n Nuwe benadering tot die bepaling van hitte-eenhede vir sonneblom
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: H.L. Loubser --- ,Die konvensionele metode vir die bepaling van hitte-eenhede is vergelyk met 'n nuwe benadering. Data uit sewe kultivarproewe insluitende daaglikse maksimum en minimum temperature is gebruik om die hitte-eenhedevereistes van drie kultivars te bepaal. Twee vergelykings is gebruik, een verteenwoordig... -
Typifying late-season weather for maize yield prediction
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: B. St. E. Clemence --- , Republic of South Africa J.B. Mallett --- , Republic of South AfricaLong-term weather data were used to generate typical weather records. By substituting typical weather data for actual late-season weather data it was possible to compute yield predictions using the model CERES-Maize, and compare these with predictions based on full season... -
Development of a simple empirical model for predicting maize yields in a semi-arid area
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: T.B. Zere --- Department of Soil, Republic of South Africa C.W. van Huyssteen --- Department of Soil, Republic of South Africa M. Hensley --- Department of Soil, Republic of South AfricaA yield prediction model is necessary, together with long-term climate data, to calculate the long-term yields needed for making a quantitative productivity evaluation of a crop ecotope in the form of a cumulative probability function (CPF). In this study the... -
Soil indicators of hillslope hydrology in the Bedford catchments, South Africa
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: J.J. van Tol --- Department of Soil, Crop and Climate Sciences, South Africa P.A.L. Le Roux --- Department of Soil, Crop and Climate Sciences, South Africa M. Hensley --- Department of Soil, Crop and Climate Sciences, South AfricaWater plays a primary role in soil genesis and soil strongly influences hydrological processes (flowpaths, residence times and storage). Morphological soil properties serve as indicators of hillslope hydrological behaviour and can facilitate hydrological predictions. Three catchments in the Bedford district... -
Evaluating the Streif index against commercial subjective predictions to determine the harvest date of apples in South Africa
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: Elmi Lötze --- Department of Horticultural Science, South Africa Oloff Bergh --- , South AfricaFor the local deciduous fruit industry, which mainly exports fruit, determination of the optimum physiological harvest maturity for apples to ensure high fruit quality after long-term storage is still an important goal. This is performed by a subjective determination based... -
Alternative Taper Curve Estimation Methods for Eucalyptus cloeziana (F. Muell.)
Item type: Journal Article • Journal: The Southern African Forestry Journal • Authors: K. P.A. Eerikäinen --- Faculty of Forestry, Finland D. Mabvurira --- , Zimbabwe J. Saramäki --- ,Three types of taper estimation methods for Eucalyptus cloeziana were applied and compared by using Zambian and Zimbabwean plantation data. The methods are: (1) Schumacher's taper equation, (2) diameter prediction method and (3) polynomial taper curve. The Schumacher's taper equation... -
Program for the deterministic modelling of genetic gains of tree breeding and seed and clone production strategies
Item type: Journal Article • Journal: The Southern African Forestry Journal • Authors: S.D. Vernyn --- , South Africa C.L. Snedden --- , South Africa R.C. Parfitt --- , South AfricaA deterministic modelling algorithm was developed for the prediction of genetic gains of six breeding and 11 (seed and clone) production strategies. This algorithm can run iteratively over ranges of parameters which affect the genetic gains. These parameters are the... -
Actuarial Criminology: Meeting Current Challenges in Southern Africa
Item type: Journal Article • Journal: Journal of Psychology in Africa • Authors: Johan Prinsloo --- University of South Africa, Anastasios Ladikos --- University of South Africa,South African prisons were overcrowded by more than sixty-three percent in 2005. Overcrowding and poor prison conditions have enormous implications for rehabilitation efforts made by the South African Department of Correctional Services. The South African White Paper on Corrections (2005)... -
A Prospective Model for HIV and AIDS Prevention in an African Setting
Item type: Journal Article • Journal: Journal of Psychology in Africa • Authors: Clvin Gwandure --- Nelson Mandela Metropolitan University, South Africa Thokozile Mayekiso --- Nelson Mandela Metropolitan University, South Africa Diane Elkonin --- Nelson Mandela Metropolitan University, South AfricaThe study conceptualizes locus of control as a behavioural mechanism for HIV and AIDS prevention. The locus of control variables that could build the model are: social systems control, self-control, fatalism, achievement-oriented behaviour, willingness to delay gratification, personal values and... -
Limits to the use of environmental indices to reduce risk and/or increase yield in the South African anchovy fishery
Item type: Journal Article • Journal: African Journal of Marine Science • Authors: JAA De Oliveira DS ButterworthEnvironmental indices that provide short-term predictions of recruitment have the potential to improve the average yield from highly productive resources that sustain recruit fisheries without an associated increase in risk (of resource 'collapse'). This is particularly true for cases where... -
Towards the development of an environmental rule-based model for predicting recruitment in Brazilian sardine Sardinella brasiliensis
Item type: Journal Article • Journal: African Journal of Marine Science • Authors: S Jablonski LFL LegeyA rule-based model was built in order to analyse the effects of environmental variables (wind stress, Ekman transport, turbulence, and sea surface temperature [SST]) on the recruitment of the Brazilian sardine Sardinella brasiliensis. The purpose of modelling was (1) to... -
Site and stand analysis for growth prediction of Eucalyptus grandis on the Zululand coastal plain
Item type: Journal Article • Journal: The Southern African Forestry Journal • Authors: M. du Plessis --- , J Zwolinski --- ,The integration of site information with that of tree growth is of special importance in Zululand, where sustainable supply of timber is essential for local processing and export commitments. Site prediction growth models need to be based on easily attainable... -
Equations for predicting the biomass of Acacia cyclops and Acacia saligna in the western and eastern Cape regions of South Africa Part 1 : Tree-level models
Item type: Journal Article • Journal: The Southern African Forestry Journal • Authors: A. van Laar --- Faculty of Agricultural and Forestry Sciences, J.M. Theron --- Faculty of Agricultural and Forestry Sciences,A forest inventory was carried out in coastal areas infested by the alien tree species Acacia cyclops and A. saligna on the West Coast, Agulhas and Eastern Cape Plains. Sample trees were felled to construct prediction equations, which were subsequently... -
Modelling maximum canopy conductance and transpiration in Eucalyptus grandis stands not subjected to soil water deficits
Item type: Journal Article • Journal: The Southern African Forestry Journal • Authors: J. M. Campion --- , Republic of South Africa P.J. Dye --- Environmentek, CSIR, c/o Agrometeorology, Republic of South Africa M.C. Scholes --- School of Animal, Plant and Environmental Sciences, Republic of South AfricaThere is much current interest in predicting the maximum amount of water that can be transpired by Eucalyptus trees. It is possible that industrial waste water may be applied as irrigation water to eucalypts and it is important to predict... -
Stand basal area model for Cunninghamia lanceolata (Lamb.) Hook. plantations based on a multilevel nonlinear mixed-effect model across south-eastern China
Item type: Journal Article • Journal: Southern Forests: a Journal of Forest Science • Authors: LiFang Zhao --- Center for Earth Observation and Digital Earth, China ChunMing Li --- Institute of Forest Resource Information Techniques, ChinaBased on a multilevel nonlinear mixed-effect model approach, a stand basal area model was developed for Cunninghamia lanceolata (Lamb.) Hook. plantations belonging to the National Forest Inventory in China. The database consists of 583 plots embracing 18 different blocks within... -
Modelling habitat suitability in the Aquatic Warbler wintering ground Djoudj National Park area in Senegal
Item type: Journal Article • Journal: Ostrich: Journal of African Ornithology • Authors: Cosima Tegetmeyer --- Institute of Botany and Landscape Ecology, Germany Annett Frick --- LUP GmbH, Germany Nina Seifert --- Zoological Institute and Museum, GermanyThe only well-studied wintering ground of the globally threatened Aquatic Warbler Acrocephalus paludicola is the ‘Djoudj area’ in Senegal. This study identifies potential Aquatic Warbler habitats within that area and gives an estimate of the size of the local wintering... -
The role of biomarkers and B-type natriuretic peptide in diagnosis and perioperative risk prediction
Item type: Journal Article • Journal: Southern African Journal of Anaesthesia and Analgesia • Authors: N Afshani --- Department of Anaesthesia, BM Biccard --- Department of Anaesthetics, RA Dyer --- Department of Anaesthesia,Biomarkers are important in diagnosis, assessment of disease severity, risk stratification and therapeutic decision-making. Recent studies strongly suggest that there is a role for B-type natriuretic peptide (BtNP) as a powerful prognostic predictor in both the preoperative and postoperative setting... -
Predicting spinal hypotension during Caesarean section
Item type: Journal Article • Journal: Southern African Journal of Anaesthesia and Analgesia • Authors: David G Bishop --- Pietermaritzburg Metropolitan Department of Anaesthesia, Critical Care and Pain Management, South AfricaHypotension under spinal anaesthesia for Caesarean section remains a common problem, with attendant maternal and foetal morbidity. This review examines some of the issues surrounding the prediction of spinal hypotension, including concerns about current evidence, the debate on the mechanism... -
An investigation into the significance of certain firm-specific non-financial variables in a failure prediction model
Item type: Journal Article • Journal: De Ratione • Authors: P W Court --- Rhodes University,Most failure prediction models contain only financial ratios. There are nevertheless a number of firm-specific, non-financial ratios which could point to failure. This article attempts to Investigate the impact of some of these variables in a failure prediction model, it... -
A note on failure prediction models as aids to the credit evaluation procedure in a South African Commercial Bank
Item type: Journal Article • Journal: De Ratione • Authors: G.A. Garbers --- Senior lending officer, Standard Bank Cape Town, E.O. Uliana --- Professor of Accounting,Errors by bank lending officers in assessing a loan application are costly to the bank. The literature suggests that the credit evaluation process can be enhanced by the use of failure prediction models. -
Family versus individual plant selection for stem borer (Eldana saccharina) resistance in early stages of sugarcane breeding in South Africa
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: Marvellous Zhou --- South African Sugarcane Research Institute, South Africa Alfred Mokwele --- South African Sugarcane Research Institute, South AfricaEldana saccharina is an indigenous lepidopteran insect pest and the most damaging stem borer of sugarcane in southern Africa. Breeding for E. saccharina resistance in South Africa started in 1980 by crossing resistant parents (expected to possess resistance genes) and... -
Early enteral nutrition compared to outcome in critically ill trauma patients at a level one trauma centre
Item type: Journal Article • Journal: South African Journal of Clinical Nutrition • Authors: E. Löfgren --- Clintec, Sweden T. Mabesa --- Inkosi Albert Luthuli Central Hospital, South Africa F. Hammarqvist --- Clintec, Sweden Tc. Hardcastle --- Trauma and Trauma Intensive Care Unit, South AfricaObjectives: The benefit of an early enteral nutrition start in critical ill patients is widely accepted. However, limited published data focus on trauma patients. This study aimed to investigate the effect of early enteral nutrition initiation on length of stay... -
Bark thickness and bark volume of Pinus patula in South Africa
Item type: Journal Article • Journal: Southern Hemisphere Forestry Journal • Authors: A. van LaarIn South Africa, tree volume tables and volume functions are usually based on the under bark stem volume. Many forest management studies, however, give the estimated over bark volume, in which case equations are required that estimate bark volume and... -
Determining the optimal phenological stage for predicting common dry bean (Phaseolus vulgaris) yield using field spectroscopy
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: Perushan Rajah --- Discipline of Geography, School of Agricultural, Earth and Environmental Sciences, South Africa John Odindi --- Discipline of Geography, School of Agricultural, Earth and Environmental Sciences, South Africa Elfatih Abdel-Rahman --- Discipline of Geography, School of Agricultural, Earth and Environmental Sciences, South Africa Onisimo Mutanga --- Discipline of Geography, School of Agricultural, Earth and Environmental Sciences, South AfricaOn-farm crop productivity and yield prediction are valuable for, among others, designing food policies, on-farm and after-farm planning and pricing, and marketing. Whereas existing prediction approaches are generally reliable, these require extensive and tedious field surveys and adequate ancillary agrometeorological... -
The winner takes it all: Outperformance drives subsequent flows in South African Unit Trust Funds
Item type: Journal Article • Journal: Investment Analysts Journal • Authors: Jennifer Arendse --- Gordon Institute of Business Science, South Africa Chris Muller --- Gordon Institute of Business Science, South Africa Michael Ward --- Gordon Institute of Business Science, South AfricaThe relationship between unit trust (mutual fund) performance and subsequent investment flows into and out of funds has been the focus of many international studies. Emerging markets, which are characterised by higher risk, weaker institutions, volatile economies and fewer participants,... -
Prediction of overt aggression experienced by college students
Item type: Journal Article • Journal: Journal of Psychology in Africa • Authors: Chris Myburgh --- Department of Educational Psychology and Nursing Science, South Africa Marie Poggenpoel --- Department of Educational Psychology and Nursing Science, South Africa Cornelius Fourie --- Department of Educational Psychology and Nursing Science, South AfricaWe sought to predict overt aggression among college students from their intra- and interpersonal relationships self-perceptions. Respondents were 311 students (females = 69.8%; black = 65.9%, white = 16.7%; mean age = 26.38 years, SD = 9.57 years) from a... -
Stock price prediction using multiple valuation methods based on artificial neural networks for KOSDAQ IPO companies
Item type: Journal Article • Journal: Investment Analysts Journal • Authors: Jae Jung Han --- , Korea Hyun-jung Kim --- , KoreaIt is difficult to predict future payoffs for initial public offerings (IPOs), since the multiple valuation method used to determine IPOs’ prices provides estimates by reflecting current sentiments in specific market environments. As our model reflects accounting information and stock... -
Criminal psychology trend prediction based on deep learning algorithm and three-dimensional convolutional neural network
Item type: Journal Article • Journal: Journal of Psychology in Africa • Authors: Yan Fan --- , ChinaIn the modern era, the empirical analysis of countermeasures against crime has developed rapidly from the perspective of crime causes. The concept of punishment based on preventionism has been vigorously developed. We aimed to apply the principle of convolutional neural... -
Predicting corporate defaults using machine learning with geometric-lag variables
Item type: Journal Article • Journal: Investment Analysts Journal • Authors: Hyeongjun Kim --- , Korea Hoon Cho --- , Korea Doojin Ryu --- , KoreaThis study examines whether corporate default prediction techniques based on machine learning can achieve better performance by using geometrically declining weighted average values of the time series variables, that is, geometric-lag variables. We test four machine learning algorithms: logistic regression,... -
Agreement between measured height, and height predicted from published equations, in adult South African patients
Item type: Journal Article • Journal: South African Journal of Clinical Nutrition • Authors: Hanna Williamson --- , Corinna Walsh --- , Mariette Nel --- , Louise van den Berg --- , -
Farm-scale digital soil mapping of soil classes in South Africa
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: Trevan Flynn --- , Czech Republic Andrei Rozanov --- , South Africa Freddie Ellis --- , South Africa Willem de Clercq --- , South Africa Cathy Clarke --- , South AfricaThis study involved the evaluation of farm-scale digital soil classification in the Sandspruit catchment of the Western Cape Province, South Africa. The study aimed to evaluate a digital soil mapping (DSM) method, from feature selection, spatial predictions and sample design... -
A trait database for southern African freshwater invertebrates
Item type: Journal Article • Journal: African Journal of Aquatic Science • Authors: Oghenekaro N Odume --- Institute for Water Research, Rhodes University, South Africa Frank C Akamagwuna --- Institute for Water Research, Rhodes University, South Africa Pindiwe Ntloko --- Institute for Water Research, Rhodes University, South Africa Helen F Dallas --- , South Africa Chika F Nnadozie --- Institute for Water Research, Rhodes University, South Africa Helen M Barber-James --- , South AfricaInvertebrates are often used as indicators of ecosystem health. In community ecology, the use of organism traits (e.g. behavioural, biological or ecological) can be of value in relation to impact diagnosis and assemblage prediction. It has also been recognised that... -
Measuring corporate failure risk: Does long short-term memory perform better in all markets?
Item type: Journal Article • Journal: Investment Analysts Journal • Authors: Hyeongjun Kim --- Yeungnam University, Korea Hoon Cho --- Korea Advanced Institute of Science and Technology, Korea Doojin Ryu --- Sungkyunkwan University, KoreaRecently, various corporate failure prediction models that use machine learning techniques have received considerable attention. In particular, using a sequence of a company's historical information, rather than just the most recent information, yields better predictive performance by adopting recurrent neural... -
Calculating soil titratable acidity from routine soil analyses of cultivated South African soils using various model structures
Item type: Journal Article • Journal: South African Journal of Plant and Soil • Authors: VG White --- Citrus Research International, South Africa PJ Raath --- Citrus Research International, South Africa AG Hardie --- Stellenbosch University, South Africa V van der Berg --- Stellenbosch University, South Africa GF Sutton --- Rhodes University, South AfricaSoil titratable acidity (TA) is determined through extraction with an acetate-buffered salt solution (potassium sulphate, K2SO4) and is routinely used to predict the soil lime requirement using the Eksteen method. Soil TA is not always reported by commercial soil testing... -
Argument mining from Amharic argumentative texts using machine learning approach
Item type: Journal Article • Journal: African Journal of Science, Technology, Innovation and Development • Authors: Mikru Lake Melie --- Jimma University, Jimma Institute of Technology, Ethiopia Debela Tesfaye --- Jimma University, Jimma Institute of Technology, Ethiopia Alemu Kumilachew Tegegnie --- Bahir Dar University, Bahir Dar Institute of Technology, Ethiopia Derejaw Lake Melie --- Bahir Dar University, Bahir Dar Institute of Technology, EthiopiaArgument mining is an emerging science that deals with the automatic identification and extraction of arguments along with their relation from large, unstructured data that are useful for reasoning engines and computational models. Identification and extraction of argument relation from... -
Forecasting oil futures markets using machine learning and seasonal trend decomposition
Item type: Journal Article • Journal: Investment Analysts Journal • Authors: Ahhyun Kim --- Sungkyunkwan University, Korea Doojin Ryu --- Sungkyunkwan University, Korea Alexander Webb --- University of Wollongong, AustraliaCan machine learning improve prediction for seasonal commodity prices? We explore the effectiveness of a combined method that integrates seasonal trend decomposition using LOESS (STL) with machine learning (ML), referred to as STL-ML. We apply Extreme Gradient Boosting and Random... -
Prediction of ambient air pollution with regression approach using machine learning
Item type: Journal Article • Journal: African Journal of Science, Technology, Innovation and Development • Authors: Bachandeep Singh Bhathal --- University Institute of Computing, Chandigarh University, India Gaurav Gupta --- Punjabi University, India Brahmaleen Kaur Sidhu --- Punjabi University, IndiaAccurate air quality prediction is vital for managing pollution and protecting public health. This study evaluates the performance of three machine learning models – Decision Tree Regression (DTR), Linear Regression (LR), and Random Forest Regression (RFR) – to forecast the... -
Exploiting ChatGPT generated dataset for weather prediction using Seagull Optimization with Deep Learning Model
Item type: Journal Article • Journal: African Journal of Science, Technology, Innovation and Development • Authors: S. Usha --- Assistant Professor (Sr.Gr ), Department of Computer Science and Engineering, University College of Engineering BIT Campus, Anna University, Tiruchirappalli, Tamil Nadu, India K. Rama Devi --- Professor, Department of Information Technology, Panimalar Engineering College, Chennai, India V. Saraswathi --- Professor, Department of Computer Science and Engineering, Chennai Institute of Technology, Chennai, India R. Kavitha --- Assistant Professor, Department of Computer Science and Engineering, University College of Engineering BIT Campus, Anna University, Tiruchirappalli, Tamilnadu, IndiaChatGPT, a powerful language model, can generate diverse fictional weather datasets including temperature, humidity, wind speed, and more. This research proposes the SGOADL-WDC technique, which employs ChatGPT-generated data for weather classification. It integrates data preprocessing with an attention-based bidirectional LSTM... -
Enhancing medical diagnosis with a machine learning-based symptom checker for health assessment
Item type: Journal Article • Journal: African Journal of Science, Technology, Innovation and Development • Authors: Sita Yadav --- Army Institute of Technology, India Manisha Dudhedia --- Marathwada Mitra Mandal’s College of Engineering Pune, India P. G. Chilveri --- CILPL, India Reena Mahapatra Lenka --- Symbiosis International (Deemed) University, India Radhika Vikas Kulkarni --- Vishwakarma Institute of Technology, India K. Nagaiah --- ICFAI University Raipur Chhattisgarh, IndiaThe growing incidences of chronic illnesses and increased complexity of medical diagnoses point to the desire to have effective, precise, and timely diagnostic instruments to assist medical personnel. The goal of the current study is to develop an ML-based system...