Dedan Kimathi University of Technology (or DeKUT) is a public, coeducational technological university in Nyeri, Kenya. It is one of 22 public universities in Kenya, having been a constituent college of Jomo Kenyatta University of Agriculture and Technology since the year 2007 until it was chartered to become a fully fledged public university on 14 December 2012.It was the first university in Kenya to be chartered under the new universities act of 2012 and the eighth public university to be established in the country.It started as a middle-level national technical and business-oriented learning institution in 1972 and was elevated in 2007 to a constituent university college of Jomo Kenyatta University of Agriculture and Technology through a Kenya Gazette notice to become a full-fledged university in three years. However, this came later on 14 December 2012 when President Mwai Kibaki officiated and awarded the institution a charter in a ceremony attended by government officials and higher education stakeholders.It is located 6 km from Nyeri along the Nyeri – Mweiga highway. The college land spans about 1,000 acres (4.0 km2) consisting of 350 acres (1.4 km2) of natural forest, 350 acres (1.4 km2) of mature coffee and 300 acres (1.2 km2) of open space for expansionOn 26 November 2008 construction of a multi-purpose resource centre began. The second phase, out of four, of this project reached completion in late 2010. It serves as the main hub for activities and events in the college..
Solar-powered irrigation Systems (SPIS) are critical for agricultural production enhancement, food security and climate change adaptation, especially in Arid and Semi-Arid Lands (ASAL). There is increased attention towards shifting to more abundant and cleaner energy potential sources for revitalising irrigation strategies in ASAL areas. This study employed a geospatial approach to identify suitable locations for solar-powered irrigation systems (SPIS) in Baringo County, Kenya. Based on an integrated use of GIS spatial analysis and analytical hierarchy procedure (AHP), suitable locations for solar-powered irrigation were mapped. Precipitation, irrigated areas, proximity to rivers, slope, and solar radiation were analysed and processed to derive spatially explicit SPIS suitability classes ranging from very low to very high suitability. The thematic layers were assigned weights based on Saaty’s AHP method, where weights for each factor were determined from a pairwise comparison matrix, and a Weighted Linear Combination (WLC) approach was used to derive the final suitability classes for the county. The findings reveal that approximately 58
AfriVoices-KE is a large-scale multilingual speech dataset comprising approximately 3,000 hours of audio across five Kenyan languages: Dholuo, Kikuyu, Kalenjin, Maasai, and Somali. The dataset includes 750 hours of scripted speech and 2,250 hours of spontaneous speech, collected from 4,777 native speakers across diverse regions and demographics. This work addresses the critical underrepresentation of African languages in speech technology by providing a high-quality, linguistically diverse resource. Data collection followed a dual methodology: scripted recordings drew from compiled text corpora, translations, and domain-specific generated sentences spanning eleven domains relevant to the Kenyan context, while unscripted speech was elicited through textual and image prompts to capture natural linguistic variation and dialectal nuances. A customized mobile application enabled contributors to record using smartphones. Quality assurance operated at multiple layers, encompassing automated signal-to-noise ratio validation prior to recording and human review for content accuracy. Though the project encountered challenges common to low-resource settings, including unreliable infrastructure, device compatibility issues, and community trust barriers, these were mitigated through local mobilizers, stakeholder partnerships, and adaptive training protocols. AfriVoices-KE provides a foundational resource for developing inclusive automatic speech recognition and text-to-speech systems, while advancing the digital preservation of Kenya's linguistic heritage.
Accurate and explainable household load forecasting is critical for demand-side management, tariff-aware scheduling, and reliable smart grid operation. This study introduces a leakage-controlled multi-horizon forecasting pipeline that integrates predictive accuracy with statistical validation, interpretability, robustness, and operational relevance. We model multivariate household demand using an hourly smart-meter dataset spanning 14 months (Nov 2022-Jan 2024; N=10,234 time steps), incorporating aligned local weather covariates. A hybrid Transformer-BiLSTM is trained using a multi-output configuration to predict 24-hour and 168-hour trajectories. Hyperparameters are optimized via Bayesian optimization (Optuna) employing chronological train/validation/test splits and a rolling-origin evaluation protocol. Performance is assessed using MAE, RMSE, and MAPE, while pairwise forecast differences are validated using the Diebold–Mariano procedure. Model explanations are generated through SHAP and attention analyses, further complemented by robustness testing (noise and feature dropout) and inference-efficiency measurements. At the 24-hour horizon, the hybrid model achieves MAE and RMSE values of 0.0539/0.0701 (MAPE 29.7
This research presents a behaviorally informed framework for synthesizing financial time-series data, specifically designed to emulate the complex dynamics of foreign exchange markets. Deviating from conventional generative adversarial networks (GANs) or purely statistical distribution-matching, the proposed methodology adopts a game-theoretic architecture. This framework integrates trader-interaction dynamics, stochastic strategies, and information asymmetry, treating the market as a strategic participant to reproduce authentic volatility patterns and structural dependencies. To ensure numerical stability across extensive simulations, the study introduces a uniform upward scaling procedure and controlled initialization, preventing pathological price behaviors without compromising the underlying statistical properties. The framework's analytical fidelity was rigorously evaluated against a suite of econometric and machine learning models, including ARIMA, XGBoost, LSTM, N-BEATS, and DLinear. Experimental results involving 12,960 hourly observations demonstrate that the synthetic data maintains strong alignment with empirical benchmarks. DLinear emerged as the superior model, exhibiting exceptional stability with an R2 frequently exceeding 0.98 and a Mean Absolute Scaled Error (MASE) near unity. While XGBoost and N-BEATS yielded competitive results, ARIMA and LSTM showed anticipated performance degradation due to temporal noise. Comprehensive residual diagnostics, including Ljung-Box tests and stationarity assessments, confirm that the generated series are behaviorally consistent and analytically reliable. This framework thus provides a robust foundation for comparative modeling and experimental financial research.
The arid and semiarid pastoral and agropastoral systems across sub-Saharan Africa face increasing pressure from climate change, land degradation, and changing land use, endangering food security, livestock productivity, and ecosystem health. However, specific evidence on how these combined pressures interact locally is still limited. This study addresses this gap with a long-term case study of Tiaty, Baringo County, Kenya, where pastoral and agro-pastoral livelihoods are increasingly influenced by climate variability and land-use changes.Landscape dynamics from 1994 to 2024 were examined using Landsat imagery, CHIRPS and CRU TS climate records, agroecological data, and socioeconomic surveys. Land-use/land-cover changes were mapped using random forest classification and change detection in Google Earth Engine. Results revealed a marked shift from dense shrublands to sparse shrublands, grasslands, and croplands. Rainfall during the March–May season declined while heatwave frequency increased, altering farming and grazing practices. Goats and camels showed greater resilience than cattle, while settlements shifted farther from croplands, reflecting expanding rangeland.This studydepended on gridded climate datasets that may obscure microclimatic differences. The study also employed limited temporal observations that could hinder causal inference, and used spectral similarity among transitional land-use classes in medium-resolution imagery which may have introduced uncertainty in area estimates. The observed relationships therefore, should be seen as indicators of system responses rather than definitive causal effects.These findings underscore the need for targeted adaptation strategies, including drought-tolerant crops, climate-resilient livestock breeds, and sustainable rangeland management, supported by policies strengthening market access, irrigation infrastructure, and community capacity.
