arXiv research

LEMPS predicts malaria prevalence with high accuracy in Ibadan, West Africa.

The paper improves marine buoy placement to detect ships robustly against disruptions.

Proposes a stochastic model for South African actuarial use.

WEST compresses word embeddings and softmax layers for memory efficiency.

West Frisian lemmatizer, POS tagger, and parser created.

WEST uses EHRs and expert cases to improve rare disease phenotyping.

EcoCast predicts biodiversity risks using satellite data and citizen science records.

A statistical analysis of financial, economic, and demographic indicators performed by the authors demonstrates (1) that the main countries of East Africa (Uganda, Kenya, and Tanzania) have not escaped the Malthusian Trap yet; (2) that this countries are not likely to follow the "North African path" and to achieve this…

Paper classifies symmetries of cross caps using invariants.

One of the fundamental postulates of the Unified Growth Theory is the claimed existence of three distinctly different regimes of economic growth governed by three distinctly different mechanisms of growth. However, Galor also proposed that the timing of these regimes is different for developed countries and for less-de…

Machine learning speeds up LSM parameter optimization and uncertainty quantification.

We analyze the quarterly average sale prices of new houses sold in the USA as a whole, in the northeast, midwest, south, and west of the USA, in each of the 50 states and the District of Columbia of the USA, to determine whether they have grown faster-than-exponential which we take as the diagnostic of a bubble. We fin…

Machine learning predicts seasonal precipitation for East Africa.

Twitter has provided a great opportunity for public libraries to disseminate information for a variety of purposes. Twitter data have been applied in different domains such as health, politics, and history. There are thousands of public libraries in the US, but no study has yet investigated the content of their social …

New method for selecting clusters in residential electricity data.

Model predicts unseen climate extremes to inform risk planning.

Optimizes QoS in FSO links over South Africa using ensemble learning.

A new model predicts wind speed using multiple meteorological variables.

TinyBayes detects crop diseases from images on edge devices with high accuracy and minimal resources.

SAGDA generates synthetic agricultural datasets to improve ML in African farming.

I present a construction of real or complex selfdual conformal 4-manifolds (of signature (2,2) in the real case) from a natural gauge field equation on a real or complex projective surface, the gauge group being the group of diffeomorphisms of a real or complex 2-manifold. The 4-manifolds obtained are characterized by …

East African tech experts identify machine learning challenges.

The UN Sustainable Development Goals allude to the importance of infrastructure quality in three of its seventeen goals. However, monitoring infrastructure quality in developing regions remains prohibitively expensive and impedes efforts to measure progress toward these goals. To this end, we investigate the use of wid…

There certainly is little or no doubt that politicians, sometimes consciously and sometimes not, exert a significant impact on stock markets. The evolving volatility over the Republican Donald Trump's surprise victory in the US presidential election is a perfect example when politicians, through announced policies, sen…

Machine learning predicts mask mandates reduce COVID-19 deaths.

Satellite imagery helps adjust for unobserved confounders in observational studies.

What are East Africa's industrial opportunities? In this article we explore this question by using the Product Space to study the productive structure of five south-east African countries: Kenya, Mozambique, Rwanda, Tanzania and Zambia. The Product Space is a network connecting products that tend to be exported by the …

Neural network model improves longevity risk assessment.

THEOREM. For every prime $p$ and each $n=2, 3, ... \infty$, there is an action of $G=\prod_{i=1}^{\infty}(Z/ pZ)$ on a two-dimensional compact metric space $X$ with $n$-dimensional orbit space. This theorem was proved in [DW: A.N. Dranishnikov and J.E. West, Compact group actions that raise dimension to infinity, Topol…

In this paper, we discuss the impact of some mortality data anomalies on an internal model capturing longevity risk in the Solvency 2 framework. In particular, we are concerned with abnormal cohort effects such as those for generations 1919 and 1920, for which the period tables provided by the Human Mortality Database …

Derives a size premium from automated market makers in decentralized AI subnets.

This paper analyzes the informational efficiency of oil market during the last three decades, and examines changes in informational efficiency with major geopolitical events, such as terrorist attacks, financial crisis and other important events. The series under study is the daily prices of West Texas Intermediate (WT…

Over the past few years, the futures market has been successfully developing in the North-West region. Futures markets are one of the most effective and liquid-visible trading mechanisms. A large number of buyers are forced to compete with each other and raise their prices. A large number of sellers make them reduce pr…

Paper aims to improve education online in South Africa using NMT for Setswana.

Mobile apps and machine learning improve malaria prevention and treatment.

A singular Riemannian foliation $F$ on a complete Riemannian manifold $M$ is called a polar foliation if, for each regular point $p$, there is an immersed submanifold $Σ$, called section, that passes through $p$ and that meets all the leaves and always perpendicularly. A typical example of a polar foliation is the part…

We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief…

Cost overruns in transport infrastructure projects know no geographical limits, overruns are a global phenomenon. Nevertheless, the size of cost overruns varies with location. In the Netherlands, cost overruns appear to be smaller compared to the rest of the world. This paper tests whether Dutch projects perform signif…

The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges. While model-driven representations remain the classic approaches, data-driven representations become more and more appealing to benefit from available large-scale observation and simulation dat…

Effective utilization of photovoltaic (PV) plants requires weather variability robust global solar radiation (GSR) forecasting models. Random weather turbulence phenomena coupled with assumptions of clear sky model as suggested by Hottel pose significant challenges to parametric & non-parametric models in GSR conversio…

Neural machine translation models trained for 5 South African languages.

In 1969 M. Gromov in his PhD thesis greatly generalized Smale-Hirsch-Phillips immersion-submersion theory by proving what is now called the h-principle for invariant open differential relations over open manifolds. Gromov extracted the original geometric idea of Smale and put it to work in the maximal possible generali…

Framework simulates systemic risk in South African banking sector.

Examines how central bank policies affect stock markets and asset prices.

Paper presents a new algorithm for predicting crop yield across fields.

The study uses equity order flow to forecast stock returns and resolves the liquidity premium puzzle.

A singular riemannian foliation F on a complete riemannian manifold M is said to admit sections if each regular point of M is contained in a complete totally geodesic immersed submanifold (a section) that meets every leaf of F orthogonally and whose dimension is the codimension of the regular leaves of F. We prove that…

We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes)…