Research Articles (Electrical, Electronic and Computer Engineering)

Permanent URI for this collectionhttp://hdl.handle.net/2263/1693

Browse

Now showing 1 - 20 of 1071

A two-stage optimization framework for greenhouse climate control and MPC-based multi-source irrigation scheduling under demand uncertainty
Dong, Yun; Lin, Dong; Ren, Zhiling; Ye, Xianming; Fan, Yuling; Zhang, Lijun (Elsevier, 2026-09)
Greenhouse cultivation supports stable food production but faces rising electricity costs, water scarcity, and carbon-emission pressures. This study develops a two-stage optimization framework for sustainable greenhouse operation. The framework couples minute-level climate control with hourly multi-source irrigation scheduling through an evapotranspiration-based water-demand mapping. In the first stage, the climate control regulates temperature, relative humidity, CO concentration, and light intensity using a total cost minimization (TCM) strategy that considers time-of-use tariffs and CO supply cost, compared with an energy consumption minimization (ECM) strategy. In the second stage, the irrigation scheduling allocates harvested rainwater, groundwater, and municipal water via an irrigation cost minimization (ICM) strategy compared with a rule-based approach. To address water demand uncertainty, a model predictive control (MPC) strategy is proposed to enable real-time dynamic adjustment of irrigation decisions. Results show that, compared with the ECM strategy, the proposed TCM strategy reduces the total operating cost by 36.40%. Compared with the rule-based method, ICM reduces the irrigation cost by 16.19%. MPC maintains supply–demand balance across different demand-uncertainty levels and during sudden demand surges, while achieving lower irrigation costs than the rule-based strategy. This study provides a practical pathway to cost-effective and reliable greenhouse operation under coupled electricity and water constraints. HIGHLIGHTS • Two-stage framework couples climate control and irrigation scheduling. • Total cost control reduces greenhouse operating cost by 36.40%. • Multi-source irrigation scheduling cuts water-supply cost by 16.19%. • MPC maintains supply–demand balance under uncertain irrigation demand. • Sensitivity analyses reveal impacts of electricity, CO2, and water prices.
From local legacy to global impact : the SAIEE Africa research journal’s journey through international indices
Sinha, Saurabh; Lacquet, Beatrys; Maharaj, Bodhaswar T. Sunil; Maddali, Naveen (SAIEE Publications, 2025-09)
The SAIEE Africa Research Journal, incorporating the Transactions of the South African Institute of Electrical Engineers (SAIEE), has evolved from a local cornerstone of South African engineering research into a globally recognized publication platform. Since its establishment in 1909, the journal has consistently fostered innovation and academic excellence in electrical engineering and related disciplines. This article summarizes the journal’s transformative journey, highlighting its integration into prominent global databases/indices such as IEEE Xplore, Scopus, SciELO SA, DOAJ and WoS. These achievements have amplified its international visibility and impact, as reflected in steadily increasing SCImago Journal Rank (SJR) metrics and the attainment of its first Impact Factor in 2024. The journal’s commitment to ethical publishing practices and alignment with global best practices in peer-review have further bolstered its credibility. Key milestones, such as the integration of over a century of archives into IEEE Xplore and the adoption of Open Access Creative Commons licensing, highlight the journal’s mission to make African engineering research globally accessible. Additionally, its diverse editorial board and international collaboration highlight its role as a bridge between researchers worldwide.
Analysis of transient power angle stability with dual-sequence Andronov-Hopf oscillator adaptive virtual inertia enhancement during low-voltage ride-through
Li, Guangdi; Wang, Hongchi; Kumar, Abhishek; Sah, Bikash; Li, Si; Yang, Dongsheng; Bansal, Ramesh C. (Institute of Electrical and Electronics Engineers, 2026-07)
Andronov–Hopf oscillator (AHO) control is a grid forming inverter strategy in which time-domain synchronization is combined with steady-state droop to enable integration into broader system frameworks. This paper enhances the low-voltage ride-through (LVRT) performance of an AHO-based grid forming inverter. The proposed dual-sequence AHO generates the positive-sequence voltage reference while attenuating negative-sequence components during unbalanced faults. The voltage-reference-forming behavior of the inverter is retained in the tested LVRT cases, while reactive power is injected to support the grid, and the fault current is kept below the prescribed limits. Furthermore, adaptive virtual inertia and damping are introduced into the positive-sequence AHO voltage loop, and a transient power-angle stability condition for voltage sag and recovery is derived for the current-limited but unsaturated operating region. This approach restores frequency and reduces the rate of change of frequency without requiring switching between current-control modes. Finally, hardware-in the-loop test results demonstrate that reactive power is injected into the grid within 50 ms after a voltage sag, while the fault current remains limited. The frequency is restored to 50 Hz within 50 ms, with deviations below 0.2 Hz, and the cosine of the power angle generated by the dual-sequence AHO remains close to 0.99 under various faults.
Integrated attack-defense framework for minecart suspension systems: polynomial-driven flexibility enhancement and HIL experimental validation
Wang, Jiayi; Xie, Xiangpeng; Hancke, Gerhard P. (Institute of Electrical and Electronics Engineers, 2026-05-12)
This article centers on constructing an integrated attack-defense framework for maliciously compromised minecart active suspension systems (MASSs) amid the advancement of network and communication technologies. First, in view of the attackers’ limited energy budget, a membership drift-dependent dynamic-intensity (MDD) attack model is developed. With the exfiltration of key system information, the attacker can assess the system state via the degree of membership drift and dynamically tune the attack intensity to achieve maximum damage. Second, by virtue of homogeneous polynomial techniques, an attack-pattern-detection-guided redundancy compensation (ARC) defense mechanism is devised correspondingly. Through the deployment of redundant transmission paths, this scheme enables the reachability of critical information via auxiliary paths, even if the primary channel is sabotaged by adversarial attacks. Moreover, to mitigate the asynchrony in attack mode observation under practical conditions, a probabilistic detection framework is introduced to characterize imperfect mode matching. On this basis, dynamic compensation is implemented by leveraging the exceptional flexibility of gain scheduling within the polynomial framework. Finally, software simulations and hardware-in-the-loop (HIL) experiments are provided to illustrate the effectiveness of the obtained results.
A unified loss analysis framework for grid-based generalized switched-capacitor topologies
Li, Zikang; Yao, Ranyu; Wu, Ning; Deng, Yan; Kumar, Abhishek; Sah, Bikash; Bansal, Ramesh C. (Institute of Electrical and Electronics Engineers, 2026-08-04)
Switched-capacitor converters (SCCs) are widely adopted in integrated circuits and increasingly used in data centers for their high power density and efficiency.Acomprehensive analysis and selection of SCC topologies for a given conversion ratio is essential for high-efficiency design. Although grid-based synthesis methods enable the generation of numerous novel topologies, evaluating their losses still relies heavily on time-consuming simulations. This is because traditional theoretical analysis methods cannot be applied to “underdetermined topologies”, as their charge multiplier vectors cannot be uniquely determined by conventional methods. In this paper, we propose the dual-limit asymptotic current model and apply it to analyze underdetermined topologies, which constitute 96.61% of 4:1 SCC topologies. By constructing an analysis framework based on this model, we successfully achieved rapid analysis across the full topology space, with an analysis speed 235 times faster than the traditional parallel simulation. Theoretical analysis results were validated through simulations and prototype experiments, identifying several novel topologies that differ from conventional designs while demonstrating favorable efficiency under the evaluated parameter set.
Namibian astronomy : exploiting favorable conditions for multi-wavelength observatories
Katjaita, H.; Backes, M.; Frans, L.; Stander, T.; Neate, Reuben (SISSA Medialab srl, 2025-12-05)
Namibia stands out as an exceptional location for astronomical research, offering pristine night skies and ideal observation conditions. Home to Africa's first International Dark Sky Reserve, the country boasts an arid climate with minimal rainfall, resulting in abundant cloudless nights perfect for extended viewing hours. This environment is ideal for facilities like the High Energy Stereoscopic System (H.E.S.S.). As the third least densely populated country globally, Namibia benefits from minimal light pollution, enhancing its appeal for astronomical endeavors. Recent studies have shown low radio frequency interference at proposed Africa Millimeter Telescope (AMT) sites, in-part highlighting Namibia's radio quietness. The country's low population density and minimal industrial activity contribute to reduced interference across various astronomical radio bands, creating versatile observing conditions. These unique advantages position Namibia to pioneer the world's first comprehensive multi-wavelength observatory. This ambitious project aims to integrate cm-wave and mm-wave radio instruments, optical instruments, and gamma-ray detectors. By combining existing facilities like H.E.S.S. with planned projects such as the AMT, Namibia is set to become a global leader in astronomical exploration across the electromagnetic spectrum.
Variational Bayesian algorithms for independent vector analysis with flexible source models
Hanekom, Natalie; Hanekom, Johannes Jurgens (Elsevier, 2026-11-15)
Fully Bayesian independent vector analysis algorithms derived using variational Bayes are proposed for guided source separation, providing control over the type, amount and influence of prior information. Speaker-dependent modelling is enabled by expressive Gaussian mixture models and hidden Markov models, with explicit noise modelling and an arbitrary number of sensors enabling joint separation and noise reduction in environments with dominant sources of interest contaminated by background interference. Maximum likelihood counterparts for the algorithms are also provided. Compared to state-of-the-art baselines, the proposed algorithms achieve stronger suppression of noise and interference, including background interference and other sources of interest. These gains may partially be attributed to enhanced source and noise modelling, and more principled integration of prior information. The framework additionally demonstrated speaker-dependent voice activity detection and closed-set multi-speaker recognition via Bayesian model comparison.
Energy-efficient resource management in CIoT for B5G networks
Osman, Nagy; Alnajjar, Khawla A.; Bansal, Ramesh C. (Wiley, 2025-09-25)
The rapid growth of the internet of things (IoT) in urban settings necessitates innovative approaches to tackle spectrum and energy efficiency issues. This study introduces an innovative resource management approach for Cognitive IoT (CIoT) networks in Beyond 5G (B5G) environments, using hybrid orthogonal frequency multiple access, time division multiple access, and non-orthogonal multiple access (OFDMA-TDMA/NOMA) methodologies with radio frequency energy harvesting (RFEH). The proposed approach enhances resource distribution to promote energy efficiency (EE) while adhering to quality-of-service (QoS) requirements. Fractional programming and the Lagrangian multiplier approach, in conjunction with the subgradient method, are used to address the optimization problem. Simulation results indicate that the proposed system attains enhanced EE, scalability, and convergence speed relative to traditional approaches, including genetic algorithm (GA), particle swarm optimization (PSO), and rate-splitting multiple access (RSMA). The results underscore the efficiency of the hybrid technique in accommodating an increasing number of users without compromising performance, offering a resilient option for energy-efficient B5G CIoT networks.
Numerical study on the inhibition effect of C6F12O on the combustion of transformer oil decomposition gases under electric field
Tian, Shuangshuang; Yang, Runlong; Yang, Dunpeng; Pan, Shaoming; Ye, Xianming; Zhang, Xiaoxing; Li, Zhe (Elsevier, 2026-08)
Please read abstract in the article.
Directional mask-aware diffusion for coherent object-background editing
Chen, Xiangrui; Si, Qi; Wang, Bo; Zhang, Zhao; Ye, Xianming; Yang, Yun; Zhang, Haijun; Wang, Meng (Elsevier, 2026-08)
While diffusion models excel at generating diverse, high-fidelity images via text prompts, current training-free editing methods struggle to simultaneously modify foreground objects and background scenes. This stems from three key limitations: 1) lack of spatially precise structural control for distinct regions; 2) inflexible region specification hindering multi-object editing; 3) inaccurate semantic guidance from suboptimal editing directions. To address these challenges, we propose a training-free editing framework that facilitates collaborative object-background co-editing by harmonizing semantic manipulation with structural preservation. We propose Mask-Restricted Self-Attention Guidance to preserve geometric integrity via object-specific token tracking and mask-constrained attention. For semantic manipulation, we introduce Mask-Restricted Cross-Attention, which injects region-adaptive directional guidance derived from our novel Random Token Direction Calculation. This method eliminates dependency on external language models by extracting semantic shifts directly from latent gradients via random sampling. Combined with mask-constrained attention maps, it ensures precise content modification, enhanced by noise regularization for refined latents. Extensive experiments demonstrate that our framework achieves superior editing fidelity and multi-object editing capability compared to baselines. HIGHLIGHTS • Novel edit direction calculation method simplifies and broadens applications. • Mask-Restricted Self-Attention Guidance enables fine-grained structural control. • Mask-Restricted Cross-Attention enables localized, fine-grained editing.
Explainable data-driven approach for smart crop yield prediction in Sub-Saharan Africa : performance and interpretability analysis
Olatinwo, Damilola D.; Myburgh, Hermanus Carel; De Freitas, Allan; Abu-Mahfouz, Adnan (MDPI, 2026-04-08)
The increasing demand for innovative strategies in sustainable food production—driven by rapid global population growth, particularly in sub-Saharan Africa (SSA)—necessitates urgent attention to agricultural resilience. Recent technological advancements have enhanced crop productivity, post-harvest preservation, and environmentally sustainable farming practices. However, three critical bottlenecks remain: (i) the lack of accurate, maize-specific yield prediction methods tailored to SSA; (ii) limited multimodal modeling approaches capable of capturing complex, nonlinear interactions among heterogeneous data sources; and (iii) a lack of explainability mechanisms, which render high-performing models “black boxes” and hinder stakeholder trust. To address these gaps, this study presents an explainable machine learning framework for smart maize yield prediction. We integrate multimodal SSA-specific soil, crop, and weather data to capture the multidimensional drivers of maize productivity. Six diverse algorithms—including extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), categorical boosting (CatBoost), support vector machine (SVM), random forest (RF), and an artificial neural network (ANN) combined with a k-nearest neighbors (kNN)—were benchmarked to evaluate predictive performance. To ensure robustness against spatial heterogeneity, we employed a Leave-One-Plot-Out (LOPO) cross-validation strategy. Empirical results on unseen test data identify CatBoost as the best-performing model, achieving a coefficient of determination of (R2 = ∼ 76%), demonstrating its ability to capture complex, nonlinear relationships in agricultural data. To enhance transparency and stakeholder trust, we integrated Local Interpretable Model-agnostic Explanations (LIME), providing plot-level insights into the physiological and environmental drivers of maize yield. Together, these contributions establish a scalable and interpretable modeling framework capable of supporting data-driven agricultural decision-making in SSA.
Discharge characteristics of motion and aggregation of fiber impurity particles based on multiphysics coupling
Zhang, Guozhi; Wang, Lingyi; Jin, Shuo; Ma, Shouxiao; Ye, Xianming; Lee, Chengkuo; Zhang, Xiaoxing (Institute of Electrical and Electronics Engineers, 2026-08)
Addressing the issue of impurity particle precipitation and aggregation within existing converter transformers, which can trigger partial discharge or dielectric breakdown. This paper employs finite element simulation methods to establish a multi-physics field model of solid-liquid two-phase flow involving the mixing of impurity particles from dielectric barrier fibers with flowing insulating oil. The simulation investigates the movement and aggregation characteristics of fiber impurity particles under different voltage application times, flow rates, and voltage amplitudes. Additionally, an experimental platform for simulating oil flow circulation discharge is established to experimentally validate and analyze the aggregation of fiber impurities and their associated discharge characteristics. The analysis shows that under dielectric barrier conditions, fiber particles mainly aggregate in the central region of the electrode plate, with minimal aggregation at the plate edges. As the voltage application time increases, the fiber particles gradually form a "particle bridge," and after 600 seconds of continuous voltage application, the amplitude of discharge pulse currents and high-frequency currents increases significantly. At an electric field strength of 20 kV/cm and an oil flow velocity of 0.3 m/s, fiber particles almost do not aggregate between the electrodes, effectively improving the degradation of the electric field. When fiber particles aggregate in a uniform electric field and discharge, the energy spectra of the generated UHF signals, high-frequency CT signals, and pulse current signals are mainly distributed in the ranges of 0.01-0.3 GHz, 10-120 MHz, and 0.1-1.5 MHz with fluctuating amplitudes.
Full-wave synthesis technique for the design of an optimized 0.5-18 GHz 90° hybrid coupler
Du Toit, Johannes Bartholomeus; Joubert, Johan; Odendaal, Johann Wilhelm (Wiley, 2026-04-09)
An optimization technique that can be used to design high performance, wideband 90° hybrid couplers is described. Optimization is performed not by using the traditional theoretical coupling factors, but rather by directly synthesizing the geometric dimensions of the hybrid in full-wave simulations. Simulated results thus include all secondary, nonideal transmission line and implementation effects, and can be optimized for the required equiripple results. The full-wave synthesis technique is explained in detail, and simulated results of a 2–18 GHz design with 0.5 dB magnitude imbalance improvement over any previous results are shown. It is also used to implement a unique 0.5–18 GHz 3 dB, 90° tandem hybrid, of which measurements are presented showing near optimally minimized magnitude imbalance of 1.47 dB, loss of less than 1.8 dB, and phase imbalance below 8°, over the complete ultrawideband bandwidth.
Optimization of renewable energy based hybrid energy system using evolutionary computational techniques
Adefarati, T.; Potgieter, S.; Sharma, G.; Bansal, Ramesh C.; Onaolapo, A.K.; Borisade, S.G.; Oloye, A.O. (Springer, 2025-02-11)
The sudden increase in global energy demandefor renewable energy resources. The global transition to renewable energy has emphasized the need for efficient, sustainable and cost-effective hybrid renewable energy system in the conventional power system. This study focuses on the optimization of HRES witeeh the aim objective of improving energy efficiency, sustainability and affordability. The proposed HRES which consists of standby diesel generator, wind turbines, battery storage system and photovoltaic system is designed to satisfy energy demands while reducing dependency on fossil fuels. The optimization of the power system is implemented with the eevolutionary computation techniques governed by particle swarm optimization and genetic algorithm in the MATLAB environment to coordinate the optimal power flow among several components of HRES. The techniques present in this research are based on the optimization of the total cost of the system and cost of energy of DG/PV/WT/BSS hybrid energy system. The hybridization of WT, PV and BSS in a single power system provides uninterrupted power supply to consumers at minimum CT of $11399 and $10906 as well as minimum COE of $0.1369/kWh and $0.1316/kWh by using GA and PSO. The findings show that the computational time to solve the problem by PSO is significantly less than that provided by GA. The optimal configuration has 72 PV panels (8.64 kW), 1 unit of WT (3 kW) and 76 battery systems (159.6 kWh) with computational time of 0.146831 s. The outcomes of the study demonstrate that HRES is a cost-effective solution to satisfy the power demand of the selected location and other regions based on similar meteorological data. The results obtained from the study align with Sustainable Development Goals by promoting clean energy access and fostering sustainable infrastructure development.
Stochastic energy management operation strategy for high penetrated grid connected solar with incorporation of battery storage system
Semwal, Gourav; Sharma, Sachin; Rawat, Tanuj; Sharma, Gulshan; Bansal, Ramesh C. (Springer, 2025-02-27)
The present distribution systems are heading towards smart distribution systems to attain large socio economic benefits. For achieving these benefits, the distribution system will include the practical aspect of the flexible modern technologies like renewable energy based distributed generators, demand response and battery energy storage system to manage load governance. There is source of uncertainty present in the non-dispatch able based distributed generations (DGs) that affects the operation schedule of distribution system. Therefore, this paper proposes a novel operation strategy for battery energy storage in coordination with uncertain large scale Photo-voltaic system based DG for distribution system. The optimal discharging and charging plans of battery energy storage for accommodation of uncertain photovoltaic are condition to the constraint like nodal power balance, feeder current limit and node voltage limit etc. Grey wolf optimization algorithm (GWO) is developed for analyzing the impact of multiple battery energy storage strategies, for controlling the demand deviation and node voltage of the distribution system. GWO algorithm is investigated on IEEE-33 bus radial distribution systems. The efficacy of the result shows the successful achieving the promised voltage profile and grid demand deviation profile.
MHealth technologies in voice disorders : a scoping review
Du Toit, Linette; Du Toit, Maria; Vermeulen, Rouxjeanne; Swanepoel, De Wet; Myburgh, Hermanus Carel; Patel, Rita; Van der Linde, Jeannie (Elsevier, 2026)
BACKGROUND : Technological advancements in healthcare offer the potential to improve patient outcomes, clinician productivity, and access to care. Evidence on their availability, clinical application, and long-term effectiveness in voice disorders remains unclear, highlighting the need for a comprehensive scoping review. AIM : To map and describe existing evidence on the use of mobile health (mHealth) technologies for the early detection, assessment, and treatment of voice disorders. METHODS : A scoping review was conducted according to the Joanna Briggs Institute (JBI) framework and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews Checklist (PRISMA-ScR) to ensure a comprehensive and systematic approach. RESULTS : Eighty-four studies were included, predominantly published between 2016 and 2025 and conducted in mostly high-income countries. Most focused on adult populations (67%) and the use of smartphones (51%) or telehealth platforms (19%). The mHealth solutions primarily targeted neurological (27%) and functional voice disorders (20%) and have demonstrated feasibility, accessibility, and potential for early detection, monitoring, and treatment. Most studies (31%) relied on acoustic assessments, while only 4% used gold-standard laryngeal imaging techniques, such as stroboscopy or endoscopy. CONCLUSION : mHealth technologies have the potential to enhance accessibility, equity, and cost-effectiveness in voice disorder care, particularly in underserved regions. Further research is needed to expand applications in early detection, diagnosis, and treatment, especially incorporating laryngeal imaging, as these solutions could potentially transform care into a preventative and globally sustainable model.
Towards a wearable skin tone responsive optical sensor
Ndiweni, Nomakhosi N.; Joubert, Trudi-Heleen (MDPI, 2025-09-22)
Melanin is one of the key light absorbers in skin and is responsible for the colour of the skin. This study evaluates the responsivity of different skin tones to white light within the visible spectral range of 300–700 nm on 12 participants. The results show that the peak amplitude of the reflected light signal decreased by 90% for darker skin tones, compared to 70% for lighter skin tones. There were also visible differences at the 460 nm and 570 nm wavelengths between the skin tones, suggesting that the standard one-glove-fits-all pulse oximeter might not be ideal.
Veterinary blood oxygen detection
Mpala, Kimberly; Joubert, Trudi-Heleen (MDPI, 2025-11-28)
A multimodal sensor was developed to record dissolved oxygen, L*a*b* colour, temperature, and pH. This work builds on an existing model that correlates blood oxygen saturation with L*a*b* colour values. An L*a*b* colour sensor was constructed from an RGB sensor and validated against a commercial colourimeter. Sensor performance was confirmed using reference colours. Dissolved oxygen was measured with a screen-printed electrode and an analogue-to-digital converter. The results highlight potential for future optical determination of oxygen saturation, combined with electrochemical measurement of oxygen partial pressure, and compensation for pH and temperature.
Paired emitter–detector diode array for colorimetric detection of water treatment chemicals
Olivier, Duane; Joubert, Trudi-Heleen (MDPI, 2025-09-13)
Optical spectroscopy is a versatile analytical technique with a diverse range of applications. Point-of-need systems are required to be affordable, miniaturized instruments that are easy to use. This paper proposes using an array of LEDs to create paired emitter detector diodes where commercial LEDs function as both a light source and detector. This system can measure the concentration of different chemicals via a set of discrete wavelengths. Calibration curves are presented for series of known concentrations of three water treatment chemicals using the K-matrix method. The spectral fingerprint identifies the chemical correctly with 99% accuracy using the Pearson correlation.
Use of machine learning to detect dangerous level of coal mine methane (CMM) concentrations during underground mining operations
Mooroogen, Rubeshen; Ayomoh, Michael Kweneojo (MDPI, 2025-11-07)
Underground coal mining is considered to be a highly dangerous activity and has been responsible for large amounts of accidents, causing the death of many mine workers. One of the factors responsible for the fatal aspect of underground coal mining is the presence and accumulation of toxic gases during underground mining operations. This paper focused its investigation specifically on coal mine methane (CMM), which is released as a result of the extraction of coal and the disturbance inflicted to surrounding rock formations during deep mining operations. Methane is considered a highly dangerous gas as it holds the capacity to cause explosions due to its highly inflammable nature. It can also displace oxygen, which eventually leads to asphyxiation. This research was based on the use of machine learning models to successfully predict dangerous concentrations of methane over the authorized threshold. Those predictions were made from a dataset containing information on the temperature, airflow, humidity, pressure and methane concentration in an underground coal mine. The temperature, airflow, humidity and pressure measurements were recorded by a series of sensors, namely anemometers and component sensors THP2/93. Three machine learning classification models were implemented and compared, with the objective to find the best model to predict and detect dangerous levels of coal mine methane. The models that were investigated included naïve Bayes, logistic regression and artificial neural networks (ANNs). This paper concludes with an engineering decision matrix that illustrates the precision of these models in predicting and detecting dangerous levels of methane concentrations in underground mines. Furthermore, recommendations for capacity improvement towards successfully predicting and detecting dangerous levels of coal mine methane from an artificial intelligence’s perspective are provided.

Browse

Recent Submissions