Most existing driver behavior classification technologies have focused on highways and other primary road infrastructures, despite secondary roads accounting for a disproportionately large number of traffic fatalities worldwide. Compared with highways, secondary roads present greater variability in road geometry, infrastructure quality, and traffic interactions, making driver behavior recognition considerably more challenging. This paper investigates the classification of driver behavior on secondary roads using machine learning techniques. Naturalistic driving data obtained from the publicly available UAH-DriveSet dataset were analyzed using two complementary feature groups describing lane detection and traffic status. Four supervised machine learning algorithms, namely, Logistic Regression (LR), gradient boosting (GB), Random Forest (RF), and Artificial Neural Networks (ANNs), were evaluated to classify driving behavior into three categories: Normal, Aggressive, and Drowsy. The extracted features were first analyzed through statistical profiling and exploratory feature analysis before training and evaluating the classification models. The experimental results show that gradient boosting consistently achieved the highest performance for both feature groups, attaining an overall classification accuracy of approximately 67% while providing balanced precision, recall, and F1-scores across all behavioral classes. Logistic regression and random forest produced competitive but lower performance, whereas the Artificial Neural Network yielded the lowest classification accuracy. The obtained results demonstrate the effectiveness of ensemble learning methods for driver behavior recognition under secondary-road conditions and highlight their potential for integration into intelligent driver monitoring and Advanced Driver Assistance Systems (ADASs). By enabling earlier identification of aggressive and drowsy driving behaviors on secondary roads, the proposed approach could support timely driver warnings and safety interventions, potentially reducing accident risk. Furthermore, the findings provide a benchmark for future machine learning models designed for real-world secondary-road environments, where driving conditions are more variable and challenging than on highways.

Grain boundaries (GBs) are important recombination-active defects in polycrystalline and multicrystalline silicon solar cells, but the effects of their electrical activity, geometry, and spatial arrangement are often difficult to separate. In this work, two-dimensional (2D) drift–diffusion simulations are used to investigate how GB trap density, carrier capture cross-section, orientation, length, number, and network geometry affect silicon solar-cell performance. A controlled comparison between rotating GBs whose length changes with angle and fixed-length GBs shows that the strong apparent orientation dependence is dominated by the accompanying variation in active GB length. When the GB length is fixed at 100 μm, the variations in short-circuit current density (Jsc), open-circuit voltage (Voc), efficiency, and fill factor are comparatively small. As a second contribution, irregular polycrystalline microstructures are generated by Voronoi tessellation, producing distributions of grain sizes, shapes, boundary lengths, and junctions that are more representative than simplified structures based on isolated or regularly spaced boundaries. These networks are used to connect grain size, total electrically active GB length, recombination, local electric fields, carrier-flow redistribution, and device performance. As the characteristic grain size increases from 5 to 100 μm, Jsc rises from 15 to 34mAcm−2, Voc from 0.54 to above 0.61 V, and the power conversion efficiency from 6.5% to 17%. GB-induced photovoltaic loss is therefore governed not by GB number or nominal orientation alone, but by the combined effects of electrical activity, total active boundary length, and network geometry.

This study evaluates an integrated solar energy-energy storage system comprising organic Rankine cycle with open feed heater (ORC-OFH), ejector refrigeration cycle with ORC (ERC-ORC), and reverse osmosis (RO) subsystems aimed at enhancing energy efficiency and freshwater production. Utilizing energy and mass balance equations for system modeling, an exergo-economic assessment was performed to analyze payback period and net present value (NPV). Multi-objective particle swarm optimization (MOPSO) was utilized to optimize exergy efficiency and minimize payback time, focusing on the effects of vapor generator temperatures, mass fractions, and ejector primary pressure ratio on system performance. Key findings indicate that the solar framework experienced the maximum exergy destruction (86 %), with ERC-ORC (8 %), ORC-OFH (4 %), and RO (2 %) contributing less. Increasing vapor generator temperatures improved total power generation and exergy efficiency while reducing cooling loads, resulting in a reduced payback period from 5.97 to 5.68 years. Moreover, variations in working fluid mass fractions revealed complex interdependencies affecting exergetic performance and payback period. The implementation of the MOPSO algorithm optimized system parameters, achieving 6.58 % exergetic efficiency and a 5.11-year payback period. The NPV analysis across three pricing scenarios demonstrated that price fluctuations significantly impacted system viability, with a 50 % price reduction resulting in a 57.41 % decrease in NPV and a 49.27 % increase in payback period, while increased prices declined the payback period to 4.79 years. This research underscores the importance of optimizing integrated solar energy systems for enhanced performance and economic feasibility.

This work aims to explore the magnetohydrodynamic mixed convection boundary layer flow (MHD-MCBLF) on a slanted extending cylinder using Eyring–Powell fluid in combination with Levenberg–Marquardt algorithm–artificial neural networks (LMA-ANNs). The thermal properties include thermal stratification, which has a higher temperature surface on the cylinder than on the surrounding fluid. The mathematical model incorporates essential factors involving mixed conventions, thermal layers, heat absorption/generation, geometry curvature, fluid properties, magnetic field intensity, and Prandtl number. Partial differential equations govern the process and are transformed into coupled nonlinear ordinary differential equations with proper changes of variables. Datasets are generated for two cases: a flat plate (zero curving) and a cylinder (non-zero curving). The applicability of the LMA-ANN solver is presented by solving the MHD-MCBLF problem using regression analysis, mean squared error evaluation, histograms, and gradient analysis. It presents an affordable computational tool for predicting multicomponent reactive and non-reactive thermofluid phase interactions. This study introduces an application of Levenberg–Marquardt algorithm-based artificial neural networks (LMA-ANNs) to solve complex magnetohydrodynamic mixed convection boundary layer flows of Eyring–Powell fluids over inclined stretching cylinders. This approach efficiently approximates solutions to the transformed nonlinear differential equations, demonstrating high accuracy and reduced computational effort. Such advancements are particularly beneficial in industries like polymer processing, biomedical engineering, and thermal management systems, where modeling non-Newtonian fluid behaviors is crucial.

The purpose of this work is to show the potential of estimating a person posture by identifying pelvis deviation through a custom-made belt with retro-reflective markers. Markers are measured and identified utilizing VICON system. two points are identified, rightmost and leftmost. The assessment technique is based on the comparison between displacement centroid of both side of the belt and the geometric center of rightmost and leftmost markers on the belt. The validation of this concept was carried on a test subject with a hip inclination. Two movements are recorded, standing and walking, both identifying the improper posture of the subject by showing a displacement between the displacement of 19.01mm between the displacement centroid and the geometric center of the belt.

Animal sounds exhibit differences often clear to the human hearing, allowing humans to recognize species through sound only. It is possible for machines to perform this task in a computationally efficient way with high performance. In this paper, we propose to recognize the species of an animal using sound characteristics. The emitted sound is submitted to Mel-Frequency Cepstral Coding (MFCC) and then to Gaussian Mixture Model (GMM) classification to identify the species. Evaluations conducted on the system with farm animal sounds study the effects of the presence of noises and signal duration. They demonstrate satisfying performance with promising prospects as recognition rates increase with the studied signal durations and with less noise and can reach 95%.

Latent heat storage (LHS) systems rely on phase change materials (PCMs) to efficiently store and release thermal energy. However, conventional single-body designs often suffer from reliability and scalability issues. A modular multi-section LHS system incorporating three dome-shaped components was developed to address these challenges. Each dome wall serves as a dedicated heat transfer fluid (HTF) channel, eliminating the need for fins. A Multilayer Perceptron (MLP) model was employed to predict energy absorption over 3-hour and 5-hour durations, with key geometric parameters, such as dome height and width. The MLP was coupled with a genetic algorithm to identify optimal configurations, while TOPSIS analysis and Pareto fronts were applied for comprehensive multi-criteria evaluation. The MLP model exhibited excellent performance with an R2 value of 0.99 and very low RMSE and MAE values, confirming its reliability and high predictive accuracy. Identifying optimal configurations becomes paramount, given the crucial role of thermal energy storage in modern energy systems. This study revealed three high-performance designs (Opt1, Opt2, and the TOPSIS-selected case) that markedly outperformed the base configuration regarding energy absorption. The optimization process identified Opt1 as the most effective design for rapid energy uptake, achieving 21,980 kJ of absorbed energy within 5 h, of which 21,912 kJ (99.7 %) was captured within 170 min. This represents a 222 % improvement over the base design and a 17 % enhancement compared to Opt2 in the same timeframe. In contrast, Opt2 delivered the highest cumulative energy storage, highlighting its superiority in long-duration performance. Opt2 achieved 23,495 kJ of energy absorption over 5 h, representing a 115 % increase over the base design and 6.9 % more than Opt1. Ultimately, the configuration selected via TOPSIS analysis provided a balanced trade-off between energy storage capacity and charging speed. It achieved 21,948 kJ and 22,386 kJ of absorbed energy over 3 and 5 h, respectively, marking a 207 % and 105 % improvement relative to the base design.

Solar thermal systems face significant challenges due to daily solar variability, requiring advanced simulation and design methods. This study addresses these issues using a three-state numerical simulation, thermal energy storage, and artificial intelligence-based analysis. The proposed system comprises a solar power tower and an energy storage option designed to support a supercritical CO2 plant. Additionally, this plant is integrated with reverse osmosis desalination and a proton exchange membrane electrolyzer. A three-mode numerical simulation-solar, solar-storage, and storage-is conducted, and an artificial intelligence-driven multi-objective optimization using the NSGA-II algorithm is applied to enhance performance and cost efficiency. Under optimal conditions, the system exhibits a hydrogen production capacity of 54203 m3/day, a net power output of 4415 kW, an exergy round-trip efficiency of 23.01 %, and a unit cost of products (UCOP) of 33.41 $/GJ. The levelized cost of hydrogen is calculated to be 5.06 $/kg, with a net present value of 214.5 M$ and a payback period of 9.4 years. In addition, the entire installation indicates a cost rate of 1436 $/h. Compared to the base case, hydrogen output is improved by 29.7 %, and UCOP is reduced by 12.5 %. These results highlight the system's potential for cost-effective, zero-carbon hydrogen production using solar energy.

This study presents an innovative biomass-based multi-generation system that simultaneously produces power, freshwater, cooling, and hydrogen, leveraging advanced waste heat recovery and multi-effect energy utilization to maximize efficiency and sustainability. Unlike conventional systems, the proposed design synergistically integrates multiple thermodynamic cycles, including a Brayton cycle, supercritical CO2 cycle, humidificationdehumidification unit, absorption chiller, and proton exchange membrane electrolyzer, enabling highly efficient resource utilization and diversified energy production. A comprehensive energy, exergy, economic, and environmental assessment is conducted to quantify system performance across a range of operating conditions. The results reveal that the gasifier integrated with Bryton cycle has the highest cost rate and exergy destruction among other subsystems. Parametric studies demonstrate that increasing the biomass flow rate from 1 to 2 kg/s boosts grid power by 12.5 % and enhances hydrogen production, although exergy efficiency declines by 14.93 % due to rising irreversibilities. To overcome the computational burden of high-fidelity simulations, a novel hybrid optimization framework is introduced, integrating the multi-objective grey wolf optimizer with an artificial neural network. This approach drastically reduces computational time while preserving accuracy, facilitating efficient multi-objective optimization aimed at maximizing exergy efficiency and minimizing cost. Under optimal conditions, the system achieves an exergy efficiency of 38.67 % and a total cost rate of 157.65 $/h, while significantly reducing CO2 emissions to 0.75 ton/MWh. The findings demonstrate that this innovative multigeneration using biomass offers a scalable and sustainable solution for urban energy demands.

This work provides a detailed evaluation of a novel biomass-fueled multigeneration system, conceived to contribute to the growing emphasis on sustainable energy solutions. The architecture comprises a biomass gasifier, an innovative cascaded organic Rankine cycle (CORC) incorporating a high-temperature mixture in the top cycle, a proton exchange membrane electrolyzer (PEME), a Brayton cycle, and waste heat utilization units, all operating together to deliver electricity, hydrogen (H2), and thermal output. A comprehensive thermodynamic modeling framework is established to evaluate the system’s performance across various operational scenarios. The framework emphasizes critical metrics, including exergy efficiency, levelized total emissions (LTE), and payback period (PP). These indicators ensure a holistic assessment of energy, exergy, economic, and environmental considerations. Parametric studies demonstrate that enhancements in biomass mass flow rate and combustion chamber temperature significantly increase power output and H2 production while reducing the payback period, underscoring the system’s flexibility and economic feasibility. Furthermore, the study employs sophisticated machine learning optimization methods, combining artificial neural networks (ANNs) with genetic algorithms (GA), to determine optimal operating conditions with minimal computational effort and maximum efficiency. When evaluated at nominal parameters, the system records an exergy efficiency of 23.72%, achieves a PP of 5.61 years, and yields an LTE value of 0.34 ton/GJ. However, under optimized conditions, these values improve to 35.01%, 3.78 years, and 0.241 ton/GJ, respectively.

Due to the optical properties of the Electron Transport Layer (ETL) and Hole Transport Layer (HTL), inverted perovskite solar cells can perform better than traditional perovskite solar cells. It is essential to compare both types to understand their efficiencies. In this article, we studied inverted perovskite solar cells with NiOx/CH3NH3Pb3/ETL (ETL = MoO3, TiO2, ZnO) structures. Our results showed that the optimal thickness of NiOx is 80 nm for all structures. The optimal perovskite thickness is 600 nm for solar cells with ZnO and MoO3, and 800 nm for those with TiO2. For the ETLs, the best thicknesses are 100 nm for ZnO, 80 nm for MoO3, and 60 nm for TiO2. We found that the efficiencies of inverted perovskite solar cells with ZnO, MoO3, and TiO2 as ETLs, and with optimal layer thicknesses, are 30.16%, 18.69%, and 35.21%, respectively. These efficiencies are 1.5%, 5.7%, and 1.5% higher than those of traditional perovskite solar cells. Our study highlights the potential of optimizing layer thicknesses in inverted perovskite solar cells to achieve higher efficiencies than traditional structures.

This work addresses the significant issue of plasma waves interacting with non-linear dynamical systems in both perturbed and unperturbed states, as modeled by the generalized Whitham–Broer–Kaup–Boussinesq–Kupershmidt (WBK-BK) Equations. We investigate analytical solutions and the subsequent emergence of chaos within these systems. Initially, we apply advanced mathematical techniques, including the transform method and the G′G2 method. These methods allow us to derive new precise solutions and enhance our understanding of the non-linear processes dominating plasma wave dynamics. Through a systematic analysis, we identify the conditions under which the system transitions from orderly patterns to chaotic behavior. This investigation provides valuable insights into the fundamental mechanisms of non-linear wave propagation in plasmas. Our results highlight the dynamic interplay between non-linearity and variation, leading to chaos, which may be useful in predicting and potentially controlling similar phenomena in practical applications.

To comprehend the thermal regulation within the conical gap between a disk and a cone (TRHNF-DC) for hybrid nanofluid flow, this research introduces a novel application of computationally intelligent heuristics utilizing backpropagated Levenberg–Marquardt neural networks (LM-NNs). A unique hybrid nanoliquid comprising aluminum oxide, Al2O3, nanoparticles and copper, Cu, nanoparticles is specifically addressed. Through the application of similarity transformations, the mathematical model formulated in terms of partial differential equations (PDEs) is converted into ordinary differential equations (ODEs). The BVP4C method is employed to generate a dataset encompassing various TRHNF-DC scenarios by varying magnetic parameters and nanoparticles. Subsequently, the intelligent LM-NN solver is trained, tested, and validated to ascertain the TRHNF-DC solution under diverse conditions. The accuracy of the LM-NN approach in solving the TRHNF-DC model is verified through different analyses, demonstrating a high level of accuracy, with discrepancies ranging from 10−10 to 10−8 when compared with standard solutions. The efficacy of the framework is further underscored by the close agreement of recommended outcomes with reference solutions, thereby validating its integrity.

Addressing harmonics, voltage sags, voltage swells, and asymmetrical variations is essential to seamlessly integrate renewable energy sources, electric vehicle charging stations, and power electronics devices into electric power grids. These issues can significantly impact the sinusoidal symmetry of voltage waveforms. Series Active Power Filters (APFs) present a promising solution that can dramatically improve power quality (PQ) by effectively addressing voltage distortions. This paper first identifies several topology-related impracticalities in the existing literature on series APFs, such as using nonlinear loads or linear loads with a current source. Secondly, to understand the motivations behind these impracticalities, commonly used reference extraction methods, namely, Instantaneous Reactive Power Theory (IRPT) and Synchronous Reference Frame (SRF), are tested on a practical topology consisting of a distorted voltage source and a linear RL load. Results conducted in the MATLAB/Simulink environment show that IRPT fails to extract the reference signal under the practical topology, and SRF leads to unacceptable THDs surpassing the 5% threshold mandated by relevant standards set forth for such applications. Thirdly, the matrix pencil method (MPM), a model-based parameter estimation technique that exploits a voltage waveform's underlying exponential signal model to extract the series APF's reference voltage, is proposed. Extensive simulations showcase the superior performance of the MPM-based series APF. It successfully reduces voltage total harmonic distortion (THD) to below 1.13% across various scenarios, including situations involving harmonic-polluted voltage sources, incorporating nonlinear loads, sag and swell phenomenon, and capacitor utilization in DC link implementation.© 2017 Elsevier Inc. All rights reserved.

Marine transportation is a significant contributor to overall energy consumption among transportation sectors and is responsible for producing a considerable amount of greenhouse gases. A potential solution for alternative applications involves implementing combined heat integration, thereby enabling the production of additional utilities and mitigating emissions. The current work introduces an innovative heat integration process for a marine engine, focusing on implementing an optimal thermal matching technique to minimize overall irreversibility in producing liquefied hydrogen and coolant. The process incorporates an organic flash-bi-evaporator cooling cycle, a humidification dehumidification desalination, a polymer electrolyte membrane water electrolysis process, and a Claude cycle. The generated freshwater is delivered to the electrolyzer to produce gaseous hydrogen. This product and the cooling for freezing are utilized in the Claude cycle for hydrogen liquefaction. The study utilizes an advanced thermo-environmental multi-criteria investigation and optimization, considering sensitivity analysis and optimization based on artificial intelligence method. The optimization process incorporates the training and testing of artificial neural networks, NSGA-II method, and TOPSIS decision-making. The primary objective functions include exergetic efficiency and carbon dioxide emission. The findings demonstrate that the specified objectives are computed to be 0.121 and 2.67 kg/MWh, correspondingly. Besides, this condition exhibits a liquefied hydrogen flow rate of 6.44 L/h and a cooling output of 43.61 kW, showing an energy efficiency of 0.1145. Also, the total exergy destruction rate associated with the arranged structure is 124.5 kW. Furthermore, the optimum state reveals an exergoenvironmental index of 0.840 and an exergetic stability factor of 0.869.

Elbow dislocation and instability present significant clinical challenges, necessitating a thorough understanding of the underlyingbio-mechanical mechanisms. In this study, a quasi-static three-dimensional finite element model of the human elbow joint isdeveloped to investigate stress distribution and stages of dislocation in the human elbow under various loading conditions. Themodel simulates the elbow joint in different degrees of flexion (30°, 45°, 60°, and 90°) and forearm positions (pronation andsupination), providing detailed insights into the progression of dislocation. Significant findings include the identification of highstress concentrations on the humerus at 90° flexion and on the radial and coronoid processes at 30°, 45°, and 60° flexion.Three reproducible stages of dislocation were observed, particularly in flexed positions with forearm pronation or supination.These stages align with experimental observations1 and highlight the initial occurrence of bony failures, such as radial headand ulnar coronoid fractures, preceding soft tissue tears. Clinically, the study underscores that early-stage low-impact posteriorelbow dislocations retain enough stability to be managed with closed reduction and early mobilization. However, as dislocationsprogress, significant damage to the medial and lateral collateral ligaments is expected, necessitating more invasive treatments.This research provides valuable bio-mechanical insights into elbow dislocation, aiding in the development of improved treatmentstrategies and enhancing patient outcomes through precise and timely clinical interventions. The validated FEM serves as apowerful tool for pre-surgical planning offering a comprehensive understanding of elbow joint mechanics

A high penetration of renewable energy (RE) in utility grids creates the problems of power system flexibility, high transmission losses, and voltage variations. These problems can be solved using a hybrid combination of transmission network restructuring and optimal placement of distributed energy generator (DEG) units. Hence, this work investigated a technologically and economically feasible solution for improving the flexibility of power networks and reducing losses in a practical transmission utility network by implementing a restructuring of the network and optimal deployment of the distributed energy generators (DEGs). Two solutions for this network restructuring were proposed. Furthermore, a grid-oriented genetic algorithm (GOGA) was designed by combining the conventional genetic algorithm (GA) and mathematical solutions to identify optimal DEG placement. A power system restructuring and GOGA flexibility index (PSRGFI) was formulated for the assessment of network flexibility. A cost–benefit assessment was also performed to estimate the payback period for the investment required for restructuring of the network and DEG placement. The least-square approximation technique was applied for load projection for the year 2031 considering the base year 2021. It was established that minimization of transmission losses, reduction in voltage deviations, and improvement of network flexibility were achieved through hybrid application of network restructuring and DEG placement using GOGA. A network loss saving of 61.19 MW was achieved via optimal restructuring and GOGA. For the projected year 2031, the PSRGFI increased from 30.94 to 132.78 after the placement of DEGs using GOGA and optimal restructuring, indicating that network flexibility increased significantly. The payback period for the investment was very small, equal to 0.985 years. The performance of the designed method was superior to the GA-based method, simulated annealing technique, and bee colony algorithm (BCA) used for placement of DEG units in the test network. The study was completed using MATLAB software, considering data from a practical transmission network owned by Rajasthan Rajya Vidyut Prasaran Nigam Ltd. (RVPN), India.

This paper presents a novel observer-based robust fault predictive control (OBRFPC) approach for a wind turbine time-delay system subject to constraints, actuator/sensor faults, and external disturbances. The proposed approach is based on an augmented state-space representation that contains state-space variables and estimation errors. The proposed augmented representation is then used to synthesize a robust predictive controller. In addition, an observer is developed and used to estimate both state variables and actuator/sensor faults. To ensure that the proposed approach has disturbance rejection capabilities, the disturbance estimates were merged with the prediction model. In addition, the disturbance rejection capabilities and fault tolerance were insured by formulating the control process as an optimization problem subject to constraints in terms of linear matrix inequalities (LMIs). As a result, the controller gains are acquired by solving an LMI problem to guarantee input-to-state stability in the presence of sensor and actuator faults. A simulation example is conducted on a nonlinear wind turbine (1 MW) model with 3 blades, a horizontal axis, and upwind variable speed subject to actuator/sensor faults in the pitch system. The results demonstrate the ability of the proposed method in dealing with nonlinear systems subject to external disturbances and keeping the control performance acceptable in the presence of actuator/sensor faults.

Currently, numerous machine learning (ML) techniques are being applied in the field of renewable energy (RE). These techniques may not perform well if they do not have enough training data. Additionally, the main assumption in most of the ML algorithms is that the training and testing data are from the same feature space and have similar distributions. However, in many practical applications, this assumption is false. Recently, transfer learning (TL) has been introduced as a promising machine-learning framework to mitigate these issues by preparing extra-domain data so that knowledge may be transferred across domains. This learning technique improves performance and avoids the resource expensive collection and labeling of domain-centric datasets; furthermore, it saves computing resources that are needed for re-training new ML models from scratch. Lately, TL has drawn the attention of researchers in the field of RE in terms of forecasting and fault diagnosis tasks. Owing to the rapid progress of this technique, a comprehensive survey of the related advances in RE is needed to show the critical issues that have been solved and the challenges that remain unsolved. To the best of our knowledge, few or no comprehensive surveys have reviewed the applications of TL in the RE field, especially those pertaining to forecasting solar and wind power, load forecasting, and predicting failures in power systems. This survey fills this gap in RE classification and forecasting problems, and helps researchers and practitioners better understand the state of the art technology in the field while identifying areas for more focused study. In addition, this survey identifies the main issues and challenges of using TL for REs, and concludes with a discussion of future perspectives.

Short-reach fiber optical links employing intensity modulation (IM) at the transmitter (Tx) and direct detection (DD) at the receiver (Rx), suffer from linear and nonlinear sources of impairments due to the interaction of chromatic dispersion (CD) with DD. In this article, joint electronic dispersion compensation (EDC) at the Tx, using two distinct Gerchberg-Saxton(GS) based approaches, and at the Rx, using a functional link neural network (FLNN) equalizer is demonstrated for IM/DD transmission. The first Tx approach utilizes the modified iterative GS algorithm, which partially mitigate linear and nonlinear sources of inter-symbol interference (ISI). The second Tx pre-EDC approach only pre-compensates for the linear power fading effect through implementing a GS based finite impulse response (FIR) filter. At the Rx, a T/2-spaced or T-spaced adaptive post-feed forward equalizer (FFE) is employed to fully compensate residual chromatic dispersion prior to attempting nonlinear equalization. Furthermore, a Volterra nonlinear equalizer (VNLE) is introduced to benchmark the performance and complexity of the FLNN, Subsequently, either a FLNN or a VNLE are utilized for nonlinear system identification and subsequent post-equalization mitigating uncompensated nonlinear sources of ISI. The FLNN nonlinear taps resulting from the functional expansion block are optimized using the recursive least square (RLS) algorithm. The Tx-FIR and Rx-FLNN enable 112 Gbit/s non-return to zero (NRZ) on-off keying (OOK) transmission over 20 km of single mode fiber (SMF) and 112 Gbit/s 4-level pulse-amplitude modulation (PAM-4) transmission over 10 km of SMF. It is shown that the use of Tx pre-EDC reduces the complexity of the required equalization at the Rx. In addition, the FLNN was found to offer a 74% reduction in computational complexity relative to the third-order VNLE.