Kumbirayi Nyachionjeka

Dr. Kumbirayi Nyachionjeka

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2020 in Scientific African
Verified
Journal Article
Open access
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
HTHillary Tarus
Hillary Tarus
KLKibet Langat
Kibet Langat

Verified
Journal Article
Open access
PDF file
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
Ehab H. E. BayoumiEhab H. E. Bayoumi
Ehab H. E. Bayoumi
Battery state-of-health (SoH) estimation is central to transportation electrification because it conditions safety limits, warranty accounting, power capability management, and long-horizon fleet optimization. Although deep temporal architectures can achieve high laboratory accuracy, field deployment is frequently limited by laboratory (Lab)-to-field (L2F) domain shift that alters input statistics, feature definitions, and noise regimes. Under such a shift, predictors may remain strongly monotonic, preserving degradation ordering and become operationally unreliable due to systematic output distortion (e.g., compression/warping of the SoH scale). A deployment-complete L2F transfer learning pipeline is presented, built around a gated Temporal Convolutional Network (TCN)–Transformer fusion backbone, domain-specific adapters and heads, alignment-regularized fine-tuning, and row-level inference via sliding-window overlap averaging. To address the dominant deployment failure mode, a Safe Calibration stage robustly filters calibration pairs and selects among candidate calibrators under a strict do-no-harm criterion. On an unseen deployment stream (2154 labeled rows), overlap-averaged raw inference achieves MAE = 0.0439, RMSE = 0.0501, and R2 = 0.7451, consistent with mid-to-high SoH range compression, while Safe Calibration (Isotonic-Balanced selected) corrects nonlinear scaling without violating monotonic structure, improving to MAE = 0.0188, RMSE = 0.0252, and R2 = 0.9357 to obtain a complete understanding of the challenges due to domain shifts, evaluation is extended to include other architecture baselines such as TCN-only, Transformer-only, Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM), and a Ridge regression baseline. Also added is explicit alignment and calibration ablations that include CORAL off/on, that is, none vs. Safe-Global vs. Context-Aware under identical leakage-safe splits and the same overlap-averaged deployment inference operator. This work goes beyond peak-score reporting and looks at the robustness of a pipeline under domain shift, which is quantified across four random seeds and multiple deployment streams, with uncertainty summarized via mean ± std and bootstrap confidence intervals for Mean of Absolute value of Errors (MAE)/Root of the Mean of the Square of Errors (RMSE) computed from per-example absolute errors.

20 October 2023 in Journal of Electrical and Computer Engineering
Verified
Journal Article
Open access
PDF file
SNSamuel Ndegwa
Samuel Ndegwa
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
EMEdwell Tafara Mharakurwa
Edwell Tafara Mharakurwa
Vertical handover management plays an essential role in wireless network technologies, mainly due to the rapid development of various radio access technologies (RATs) that require users to connect seamlessly from one RAT to another. However, in multiple RAT environments, vertical handover management encounters different challenges, including unnecessary handovers, handover failures, ping-pong handovers, and unsuitable access network selection. Essential in vertical handover management is maintaining the desired quality of service (QoS) by the mobile device user. The seamless movement of mobile device users as they run various applications depends on a well-performing vertical handover decision-making algorithm. This bears special significance in a heterogeneous network environment. This paper proposes a vertical handover algorithm that considers user preferences (i.e., a vertical handover algorithm that evaluates the application currently running on a user device). The main objective of the algorithm is to determine when it is necessary to perform the handover, depending on the applications running on the mobile device. The proposed algorithm utilizes a fuzzy logic system to assess whether the handover is necessary and a multiattribute decision-making (MADM) method to select the best available radio access network. A simulation scenario involving different applications at various mobile device velocities was developed. The results proved the algorithm’s effectiveness compared to some of the earlier proposed vertical handover algorithms. At velocities below 10 m/s and 30 m/s, the proposed algorithm had 0% and 15.02% unnecessary handovers, respectively, while the technique for order preference by similarity to ideal solution (TOPSIS) utility’s function-based algorithm obtained 12.38% and 23.24% at the same velocities, respectively. In addition, compared to TOPSIS, the obtained results of the proposed algorithm demonstrated a lower handover failure rate and ping-pong rate for a velocity span of 1–30 m/s for the considered user applications.

30 October 2014 in International Scholarly Research Notices
Verified
Journal Article
Open access
PDF file
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
WMWellington Makondo
Wellington Makondo
In this paper, the performance and feasibility of a hybrid wavelength division multiplexing/time division multiplexing passive optical network (WDM/TDM PON) system with 128 optical network units (ONUs) is analysed. In this system, triple play services (video, voice and data) are successfully communicated through a distance of up to 28 km. Moreover, we analysed and compared the performance of various modulation formats for different distances in the proposed hybrid WDM/TDM PON. NRZ rectangular emerged as the most appropriate modulation format for triple play transmission in the proposed hybrid PON.

27 July 2026 in Batteries
Verified
Journal Article
Open access
PDF file
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
EAEmad Abd-Elrady
Emad Abd-Elrady
Ehab H. E. BayoumiEhab H. E. Bayoumi
Ehab H. E. Bayoumi
Reliable remaining useful life (RUL) estimation is important for the safe and efficient use of lithium-ion (Li-ion) batteries in electric vehicles (EVs) and energy-storage systems. Most data-driven RUL models are trained under controlled laboratory conditions, but their performance can weaken during field operation, where usage, sensing quality, and degradation paths are less predictable. This study proposes a physics-informed laboratory-to-field (L2F) deep learning framework for battery RUL prediction under limited or unavailable target labels. The framework combines three components: a six-channel laboratory cycle representation comprising voltage, current, temperature, cumulative charge throughput, cumulative energy throughput, and voltage derivative; a gated Transformer–Temporal Convolutional Network (TCN) Fusion backbone for modeling long-range and local degradation patterns; and a staged adaptation policy based on paired-view consistency and covariance alignment. The Fusion backbone achieved the lowest held-out XJTU laboratory root mean square error (RMSE) of 46.67, compared with 48.27 for TCN and 48.85 for the Transformer. In the Tsinghua University (Tsinghua) deployment experiment, measured target RUL labels were unavailable after preprocessing and window construction. Therefore, the direct field-side mean absolute error (MAE), RMSE, and coefficient of determination R2 were not computed. The Tsinghua results are interpreted as an unlabeled deployment-credibility and trajectory-regularity assessment, showing operational continuity, finite vehicle-specific predicted trajectories, and reduced local trajectory volatility after staged adaptation. The S2a + S2b policy reduced Fusion RUL volatility from 8.376 to 0.632. In the XJTU laboratory source representation, Integrated Gradients showed that physics-aware channels contributed 30.98% of the attribution mass, increasing from 19.50% in early-life windows to 31.86% in late-life windows. These attributions explain the laboratory six-channel waveform model and are not used as direct evidence of Tsinghua field-feature importance.

7 October 2019 in Advances in OptoElectronics
Verified
Journal Article
Open access
PDF file
KNKumbirayi Nyachionjeka
Kumbirayi Nyachionjeka
HTHillary Tarus
Hillary Tarus
KKibet Langat
Kibet Langat
In this paper, we seek to compare the two design theories for fiber optical parametric amplifier through simulation. The two-sideband method (standard method) has been the most widely used method in fiber optical parametric amplifier design, but it does not predict the gain shrinkage around the pumps. This technique does not consider the gain shrinking dynamics around the pump(s). The four-sideband analytical technique is an alternative technique for fiber optical parametric amplifier design, and it allows for a simplified investigation of the gain shrinking dynamics around the pump(s) due to the interaction of the various arising high-order idlers within the vicinity of the pump waves. The undertaking in this paper is to present a dual-pump fiber amplifier based on the highly nonlinear fiber and another one based on the photonic crystal fiber and ascertain if gain shrinking affects both FOPAs.