This study focuses on the performance analysis and optimization of renewable energy systems using Artificial Intelligence techniques. Renewable energy sources such as solar and wind are sustainable alternatives to fossil fuels, but their output varies due to weather conditions, temperature, irradiance, wind speed, and load demand. Artificial Intelligence techniques such as Artificial Neural Networks, Fuzzy Logic, Genetic Algorithm, and Particle Swarm Optimization help in forecasting energy generation, reducing losses, improving efficiency, and managing energy storage. The study shows that AI-based optimization enhances system reliability, power output, and sustainable energy management for future clean energy development..

This study focuses on the design optimization of highway geometric parameters for improving road safety and traffic efficiency. Highway elements such as lane width, shoulder width, curve radius, super elevation, gradient, sight distance, median width, and intersection layout directly affect vehicle movement, driver comfort, accident risk, and traffic capacity. The study analyses existing roadway conditions, traffic flow, speed variation, accident patterns, and geometric deficiencies to identify unsafe and inefficient road sections. Optimized design measures were suggested to improve visibility, reduce conflicts, increase capacity, and ensure smoother traffic operation. The study concludes that optimized highway geometry supports safer, efficient, and sustainable transportation infrastructure..

Artificial Intelligence-Based Energy Management Systems provide an intelligent approach for improving power utilization in modern energy networks. The system uses machine learning, predictive analytics, neural networks, and optimization techniques to monitor energy consumption, forecast load demand, reduce peak load, and control electrical devices efficiently. AI helps in identifying wastage, improving renewable energy integration, managing battery storage, and reducing electricity costs. Compared with conventional energy management methods, AI-based systems offer better accuracy, reliability, and sustainability. Therefore, AI plays an important role in smart homes, industries, commercial buildings, and smart grids by ensuring efficient, economical, and eco-friendly power utilization..

This study focuses on Artificial Intelligence-Based Predictive Maintenance Systems for Industrial Machinery to improve machine reliability, reduce downtime, and enhance industrial productivity. Predictive maintenance uses sensor-based data such as vibration, temperature, pressure, current, speed, and load conditions to monitor machine health in real time. Artificial intelligence and machine learning models analyse this data to detect abnormal patterns, predict possible failures, and generate early warning alerts before breakdown occurs. The study highlights that AI-based predictive maintenance reduces maintenance costs, improves fault detection accuracy, increases machine availability, and supports smart manufacturing. Thus, it offers an efficient solution for modern industrial maintenance management..

Digital Manufacturing Systems for Advanced Industrial Automation focus on the integration of intelligent technologies to improve modern production processes. This study highlights the role of CAD/CAM, CNC machines, robotics, Industrial Internet of Things, artificial intelligence, smart sensors, cloud computing, and digital twins in developing smart and automated manufacturing environments. These systems support real-time monitoring, predictive maintenance, process optimization, improved product quality, and reduced human error. The study also shows that digital manufacturing enhances production efficiency, machine utilization, flexibility, and sustainability. Overall, digital manufacturing plays a significant role in transforming traditional industries into smart, competitive, and data-driven manufacturing systems..

The study “Dynamic Modeling and Analysis of Mechanical Systems Using Simulation Techniques” focuses on the analysis of mechanical system behavior under dynamic loading conditions. Mechanical systems experience motion, vibration, force, damping, and changing operational conditions during actual working processes. Dynamic modeling helps represent these systems through mathematical equations, while simulation techniques allow their performance to be tested virtually. The study analyzes displacement, velocity, acceleration, vibration response, stability, and operational efficiency using simulation-based methods. The results indicate that simulation improves design accuracy, reduces physical testing, identifies faults early, and supports safer and cost-effective mechanical system optimization..

This study focuses on machine learning-based noise reduction techniques for improving the performance of wireless communication systems. Wireless signals are often affected by thermal noise, interference, fading, and multipath distortion, which reduce signal quality and increase transmission errors. Machine learning methods such as Artificial Neural Networks, Autoencoders, and Deep Learning models help identify noise patterns and separate useful signal components from unwanted disturbances. The study shows that these techniques improve signal-to-noise ratio, reduce bit error rate, increase data accuracy, and enhance communication reliability. Therefore, machine learning provides an adaptive and efficient solution for future wireless networks..

This study evaluates the performance of wireless communication systems using advanced digital modulation techniques. Modulation schemes such as BPSK, QPSK, 16-QAM, 64-QAM, and OFDM were examined on the basis of bit error rate, signal-to-noise ratio, throughput, bandwidth efficiency, and noise immunity. The study found that lower-order modulation techniques offer better reliability in noisy channels, while higher-order QAM techniques provide higher data rates under good channel conditions. OFDM showed balanced performance by reducing multipath fading and improving broadband transmission. The study concludes that adaptive modulation improves speed, reliability, and spectrum utilization in modern wireless communication systems..

Automated Quality Inspection Systems using Machine Vision Techniques provide an advanced solution for improving quality control in manufacturing industries. The system uses cameras, sensors, lighting devices, and image-processing software to inspect products automatically and detect defects such as cracks, scratches, dimensional errors, missing components, and surface irregularities. Compared with manual inspection, machine vision offers higher accuracy, faster inspection speed, better consistency, and reduced human error. It also supports real-time monitoring, waste reduction, and improved production efficiency. Therefore, machine vision-based inspection is an effective technology for smart manufacturing and reliable industrial quality management..

The rapid growth of large-scale data has created a pressing need for intelligent frameworks that support efficient decision-making and resource management. This study presents a machine learning-based predictive analytics framework designed for processing high-dimensional data and providing decision support in dynamic environments. The framework integrates models such as Random Forests, LSTMs, and reinforcement learning to forecast workloads, detect anomalies, and optimize resource allocation proactively. Results demonstrate improved prediction accuracy, enhanced system efficiency, and reduced operational costs. The approach enables data-driven, scalable, and automated decision-making suitable for cloud computing, industrial systems, and IoT-driven environments..

This study investigates sentiment analysis of social media data using deep learning and Natural Language Processing (NLP) techniques. Three models—CNN, LSTM, and BERT—were implemented to classify textual posts into positive, neutral, and negative sentiments. Data pre-processing, including cleaning, tokenization, and embedding generation, ensured quality input for training. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. Results indicate that transformer-based BERT outperforms CNN and LSTM due to its bidirectional contextual understanding and ability to capture nuanced sentiment. The study highlights the practical utility of deep learning for real-time sentiment monitoring and informed decision-making..

This study proposes a secure data transmission framework integrating advanced cryptographic algorithms and machine learning-based attack detection. Symmetric (AES-256) and asymmetric (ECC-256) encryption ensure data confidentiality, integrity, and authentication, while digital signatures protect against tampering. The machine learning module, including hybrid 1D-CNN-LSTM and ensemble models, monitors network traffic in real time to detect known and zero-day attacks with high accuracy, precision, recall, and F1-score. Experimental results demonstrate that the framework achieves secure, efficient, and proactive data protection suitable for IoT, cloud, and enterprise networks. The approach offers a scalable solution for resilient cybersecurity in dynamic digital environments..

Seismic performance assessment of reinforced concrete (RC) buildings is critical for ensuring structural safety in earthquake-prone regions. This study employed AI-based predictive models integrated with numerical simulations to evaluate storey displacement, inter-storey drift, base shear, demand-to-capacity ratios, and performance indices of a ten-storey RC structure. Machine learning algorithms, including artificial neural networks, support vector machines, and ensemble learning, were utilized to predict structural responses and identify vulnerable areas. Optimization techniques facilitated performance-driven retrofitting strategies. Results demonstrated high accuracy of AI predictions compared to simulations, enabling efficient decision-making and prioritization of interventions, thereby enhancing building resilience and seismic safety..

This study presents a hybrid Finite Element and Artificial Intelligence (FEM-AI) modeling approach for predicting structural behavior under varying loads and conditions. FEM simulations were used to generate detailed data on displacement, stress, strain, and load capacity, which trained an Artificial Neural Network to predict structural responses efficiently. The hybrid model demonstrated high accuracy, closely matching FEM and experimental results, while significantly reducing computational time. This methodology enables rapid evaluation, performance-based design, and real-time structural health monitoring. The approach provides a reliable and intelligent framework for analyzing complex structures and optimizing infrastructure safety and efficiency..

Seismic retrofitting of existing buildings is crucial to enhance structural safety, resilience, and serviceability, particularly in older reinforced concrete and masonry structures. This study investigates the application of artificial intelligence (AI) in optimizing retrofitting strategies using predictive modeling, machine learning, and optimization algorithms. AI-driven approaches enable precise determination of fiber-reinforced polymer (FRP) placement, material usage, and reinforcement configuration, significantly improving flexural and axial capacity, stiffness, ductility, and seismic performance. Comparative analyses reveal substantial reductions in deflection, crack width, and expected seismic damage. The findings highlight AI as an effective, sustainable, and cost-efficient tool for enhancing the performance and longevity of existing infrastructure..

This study explores the integration of Building Information Modeling (BIM) with Finite Element Method (FEM) and predictive frameworks for structural design and lifecycle management in sustainable infrastructure development. BIM provides a multidimensional, data-rich platform enabling accurate modeling, interdisciplinary collaboration, and optimization of material use, while FEM facilitates detailed analysis of axial forces, shear forces, bending moments, and lateral displacements. Lifecycle assessment within BIM supports early-stage sustainability evaluation, including embodied carbon reduction, energy efficiency, and maintenance planning. The results demonstrate that BIM-based workflows enhance safety, performance, cost-efficiency, and environmental responsibility, establishing BIM as a transformative tool for resilient and sustainable structural engineering..

Self-healing concrete (SHC) has emerged as an innovative solution for improving the durability and sustainability of reinforced concrete structures. This study investigates biological, capsule-based, and mineral-based self-healing mechanisms, along with the integration of Fibre Reinforced Polymer (FRP) retrofitting, to enhance structural performance. Experimental results demonstrated significant improvements in compressive strength, crack-healing efficiency, ductility, stiffness, and durability compared to conventional concrete. FRP-based SHC systems achieved up to 75% self-healing efficiency and extended service life from 8.6 years to over 25 years. The findings highlight SHC as a sustainable, eco-friendly approach for resilient and long-lasting infrastructure development..

This study focused on machine learning-based damage detection and crack identification in reinforced concrete structures. Reinforced concrete structures often develop cracks due to loading, corrosion, shrinkage, temperature variation, and environmental effects. Traditional inspection methods are time-consuming, subjective, and less reliable for large structures. Therefore, machine learning techniques were applied to detect cracks automatically from concrete surface images and classify damage severity. Models such as SVM, Random Forest, ANN, and CNN were used for analysis. The study found that CNN-based methods provided higher accuracy and faster detection, supporting structural health monitoring, preventive maintenance, and improved infrastructure safety..

This study focused on the development of smart concrete using nano-materials to enhance structural strength and durability. Nano-materials such as nano-silica, nano-titanium dioxide, graphene oxide, and carbon nanotubes were incorporated into concrete mixes to improve internal bonding, pore refinement, hydration, and crack resistance. The results showed that nano-modified concrete performed better than conventional concrete in terms of compressive strength, tensile strength, and water absorption resistance. Graphene oxide and carbon nanotube concrete showed the highest improvement. The study concluded that nano-material-based smart concrete is suitable for durable, sustainable, and high-performance modern infrastructure..

This study focuses on the application of Remote Sensing and GIS techniques for structural damage assessment after earthquakes. Earthquakes often cause severe damage to buildings, roads, bridges, and urban infrastructure, making rapid assessment essential for rescue and rehabilitation. Remote sensing helps identify collapsed structures, debris, surface deformation, and damaged zones through satellite, SAR, and drone imagery. GIS supports spatial analysis by integrating damage data with building footprints, population density, road networks, and seismic intensity maps. The study shows that these techniques improve damage classification, emergency response planning, and long-term reconstruction strategies..

This study focused on the development of machine learning-based traffic flow prediction models for congestion reduction and efficient urban traffic management. The model analyzed historical and real-time traffic data, including vehicle count, average speed, road occupancy, travel time, and peak-hour movement. Various machine learning techniques such as Linear Regression, Decision Tree, Random Forest, Support Vector Machine, Artificial Neural Network, and LSTM were considered for prediction. The findings showed that advanced models improved forecasting accuracy and helped identify congestion-prone areas. Overall, the study supported smart traffic control, reduced delays, improved route planning, and promoted sustainable urban mobility..

This study assessed the life cycle cost and carbon footprint of highway pavement systems using sustainable construction materials. It compared conventional pavement with alternatives such as reclaimed asphalt pavement, warm mix asphalt, recycled concrete aggregate, and fly ash/slag-modified pavement. The assessment considered material production, transportation, construction, maintenance, rehabilitation, and end-of-life stages. Results showed that sustainable pavement systems reduced overall construction cost, lowered carbon emissions, conserved natural resources, and improved long-term environmental performance. The study concluded that life cycle-based evaluation is essential for selecting cost-effective and low-carbon pavement materials for sustainable highway infrastructure development..

This study examined road traffic accident analysis and severity prediction using machine learning techniques and statistical modelling. The research focused on identifying major factors responsible for accident severity, including speed, road condition, weather, lighting, vehicle type, traffic density, and driver behaviour. Statistical modelling was used to understand the relationship between accident variables and severity levels, while machine learning models were applied to classify accidents into minor, serious, and fatal categories. The result showed that Random Forest performed better than other models due to its strong prediction capability. The study supports road safety planning, black-spot identification, and emergency response improvement..

This study focused on the development of Artificial Neural Network models for pavement performance prediction and maintenance planning. Pavement condition was influenced by traffic load, pavement age, climatic variation, cracking, rutting, roughness, and previous maintenance history. The ANN model was designed to identify nonlinear relationships among these factors and predict future pavement deterioration more accurately than traditional methods. The predicted results helped classify road sections into routine maintenance, preventive maintenance, rehabilitation, and reconstruction categories. The study concluded that ANN-based prediction improved maintenance prioritization, reduced cost, enhanced road safety, and supported sustainable pavement management..

The present study analyzed the comparative structural and functional performance of rigid and flexible pavements under heavy traffic loading conditions. It examined major parameters such as load-carrying capacity, deflection resistance, rutting resistance, riding quality, maintenance requirement, and durability. The study found that rigid pavement performed better under repeated heavy axle loads due to its high stiffness, flexural strength, and wider load distribution capacity. Flexible pavement offered lower initial cost and better early riding comfort but required frequent maintenance due to rutting, fatigue cracking, and surface deformation. Overall, rigid pavement was more suitable for long-term heavy traffic conditions..

This study focused on GIS-based transportation network planning and accessibility analysis for sustainable urban mobility development. It examined road connectivity, public transport coverage, travel time efficiency, service accessibility, last-mile connectivity, and sustainable mobility indicators. GIS tools helped identify well-connected zones, underserved areas, congestion points, and accessibility gaps within the urban transport system. The findings showed that strong road networks and improved service accessibility supported better mobility, while weak last-mile connectivity required planning attention. The study concluded that GIS provides a scientific and spatial framework for efficient, inclusive, and environmentally sustainable urban transport planning..

This study focused on machine learning-based prediction of road accident black spots for improved traffic safety planning. Accident data, road characteristics, traffic volume, weather conditions, and location-based factors were analyzed to identify high-risk road segments. Machine learning models helped classify locations into low, medium, high, and very high-risk zones. The findings showed that poor road geometry, inadequate lighting, speeding, unsafe intersections, and heavy traffic flow contributed significantly to accident occurrence. The study concluded that predictive models can support authorities in prioritizing safety measures, reducing accident risks, and improving sustainable road safety management..

This study evaluated the performance of modified bitumen for improving the durability of flexible pavements under heavy traffic and varying climatic conditions. Conventional bitumen often showed limitations such as rutting, cracking, stripping, and premature pavement failure. To overcome these problems, suitable modifiers were added to enhance binder properties. Laboratory tests indicated that modified bitumen improved softening point, stability, moisture resistance, fatigue resistance, and overall pavement life. The modified mix showed better load-bearing capacity and resistance to deformation than conventional bitumen. Therefore, modified bitumen was found suitable for durable, economical, and sustainable flexible pavement construction..

Sustainable Road construction using industrial by-products is an important approach for reducing environmental impact and conserving natural resources. This study focuses on the use of waste materials such as fly ash, steel slag, blast furnace slag, waste plastic, foundry sand, recycled asphalt pavement, and construction and demolition waste in road construction. These materials can partially replace conventional aggregates, soil, bitumen, and cement in pavement layers. Their use helps reduce landfill waste, carbon emissions, quarrying activities, and construction costs. The study concludes that industrial by-products can support durable, economical, and eco-friendly road infrastructure development..

This study presents a Life Cycle Cost Analysis of flexible and rigid pavement systems under varying traffic conditions. The analysis compares both pavement types by considering initial construction cost, maintenance cost, rehabilitation cost, user cost, service life, and long-term performance. The result shows that flexible pavement is more economical for low and medium traffic roads due to its lower initial cost and easy maintenance. However, rigid pavement becomes more cost-effective under high traffic and heavy commercial vehicle conditions because of its durability, longer service life, and reduced maintenance frequency..

This study evaluates the performance of stabilized soil techniques for sustainable rural road construction. Weak rural road soils often have low strength, high plasticity, and poor load-bearing capacity, leading to early pavement failure and frequent maintenance. The study examines different stabilization methods using lime, cement, fly ash, quarry dust, and lime–fly ash combinations. Results show that stabilized soil improves California Bearing Ratio, compressive strength, compaction, and durability compared with untreated soil. Among the techniques, lime–fly ash stabilization provides the best overall performance. Therefore, soil stabilization is an economical, durable, and eco-friendly solution for rural road development..

This study focuses on sustainable transportation infrastructure planning for rapidly growing urban areas. Rapid urbanization has increased traffic congestion, pollution, fuel consumption, road accidents, and pressure on existing transport systems. The study highlights the need for integrated transport planning that includes public transport improvement, pedestrian facilities, cycling infrastructure, electric mobility, smart traffic management, and proper land-use coordination. The findings show that sustainable transport planning can reduce private vehicle dependency, improve mobility efficiency, lower environmental impact, and support inclusive urban development. Overall, sustainable transportation is essential for creating safe, efficient, green, and livable cities..

This study focuses on the optimization of urban traffic signal timing using Artificial Intelligence algorithms to minimize traffic delay and fuel consumption. Rapid urbanization and increasing vehicle density have created serious congestion problems at signalized intersections. Traditional fixed-time signals often fail to respond to changing traffic conditions, resulting in longer queues, excessive waiting time, fuel wastage, and higher emissions. The proposed AI-based approach uses traffic parameters such as vehicle flow, queue length, waiting time, and arrival rate to generate adaptive signal timings. The study concludes that AI-optimized signals improve traffic efficiency, reduce fuel use, and support sustainable urban transportation..

This study investigates the performance of bituminous mixes modified with waste plastic for improving pavement strength and durability. Waste plastic was cleaned, shredded, and added to hot aggregates in different proportions before mixing with bitumen. Marshall mix design was used to evaluate stability, flow value, density, and air voids. The results showed that the addition of waste plastic improved aggregate-bitumen bonding and increased load-bearing capacity. The optimum performance was observed at 8% plastic content by weight of bitumen. Thus, waste plastic-modified bituminous mix provides an eco-friendly and sustainable solution for durable pavement construction..

This study evaluates the performance of green concrete prepared by using nano-silica and industrial waste materials as partial replacement of conventional cement. The main objective is to improve concrete strength and durability while reducing environmental impact. Industrial waste materials such as fly ash, GGBS, silica fume, and waste foundry sand help in minimizing cement consumption and waste disposal problems. Nano-silica improves the microstructure of concrete by filling pores and increasing calcium silicate hydrate formation. The results indicate that the optimum mix with nano-silica and industrial waste provides better compressive strength, reduced water absorption, and improved durability..

This study examines the use of Building Information Modeling (BIM) for structural planning and construction optimization. BIM provides a digital platform for creating accurate 3D structural models, improving visualization, coordination, and decision-making. The study highlights how BIM supports clash detection, quantity estimation, project scheduling, cost control, and resource management. Compared with traditional methods, BIM reduces design errors, rework, material wastage, and construction delays. It also improves communication among architects, engineers, contractors, and project managers. Overall, BIM is an effective tool for achieving efficient, economical, sustainable, and high-quality construction project delivery..

This study focuses on structural design and analysis using Building Information Modeling and Finite Element Techniques. BIM was used to develop a detailed digital model of structural components such as beams, columns, slabs, and foundations. Finite Element Analysis was applied to evaluate stress, displacement, deformation, bending moment, shear force, and load distribution under different loading conditions. The results showed that BIM-FEA integration improved design accuracy, visualization, clash detection, material optimization, and construction coordination. This approach reduced design errors and supported safer, economical, and sustainable structural planning for modern construction projects..

This study focuses on machine learning-based network traffic classification for efficient network management. The main aim is to identify and classify different types of traffic such as browsing, streaming, file transfer, VoIP, gaming, and suspicious traffic. Network traffic data were processed through feature extraction, data cleaning, and model training. Machine learning algorithms such as Naïve Bayes, Decision Tree, Support Vector Machine, Random Forest, and Artificial Neural Network were applied and compared. The result showed that Random Forest achieved the highest accuracy, proving its effectiveness in traffic classification, bandwidth management, congestion control, and network security improvement..

This study examines the stress, fatigue, and failure behaviour of mechanical components using numerical simulation techniques. Mechanical components are often subjected to static and cyclic loads, which may cause stress concentration, deformation, fatigue damage, crack initiation, and final failure. Finite Element Analysis was used to evaluate von Mises stress, total deformation, fatigue life, damage factor, and safety factor. The results showed that critical failure zones usually occur near holes, sharp edges, fillets, supports, and load application points. The study concludes that numerical simulation improves design accuracy, reduces testing cost, and enhances component reliability and service life..

This study examines the fatigue life and crack propagation behavior of welded joints in steel truss bridges subjected to repeated traffic loading. Welded joints are highly vulnerable to fatigue damage due to stress concentration, residual stresses, weld defects, and continuous cyclic loading. The study focuses on identifying critical crack initiation zones, evaluating fatigue damage, and predicting remaining service life using stress-life and fracture mechanics principles. The results indicate that weld toe, weld root, and gusset plate joints are the most fatigue-sensitive locations. Regular inspection, crack monitoring, and timely strengthening are essential for improving bridge safety and durability..

This study focuses on the development of intelligent structural analysis systems using artificial intelligence techniques for improving accuracy, speed, and reliability in structural engineering. The proposed system applies machine learning and neural network models to analyse structural data, predict stress, strain, deflection, load capacity, and damage conditions. It helps engineers identify structural behaviour more efficiently than conventional methods. The study shows that AI-based systems support early damage detection, optimized design, faster analysis, and better decision-making. Overall, artificial intelligence provides a smart and effective approach for safer, economical, and sustainable structural performance evaluation..

This study examines the application of digital twin-based simulation for evaluating the structural performance of civil engineering structures. A digital twin creates a dynamic virtual model of a physical structure by integrating sensor data, BIM, finite element analysis, and predictive analytics. The study focuses on assessing stress, displacement, vibration, damage detection, maintenance planning, and service-life prediction under different loading and environmental conditions. The results indicate that digital twin technology improves monitoring accuracy, supports early damage identification, reduces maintenance uncertainty, and enhances infrastructure safety. Therefore, digital twins provide an intelligent and sustainable approach for life-cycle structural management..

This study focuses on the design optimization of steel plate girder bridges using finite element modelling under dynamic traffic and environmental loads. A detailed finite element model was developed to analyse stress distribution, deflection, vibration response, fatigue behaviour, and material utilization. Dynamic moving traffic loads and environmental effects such as wind, temperature variation, and corrosion were considered to represent realistic bridge conditions. Design variables including web thickness, flange dimensions, girder depth, and stiffener spacing were optimized. Results showed reduced steel weight, lower stress, improved stiffness, enhanced fatigue resistance, and better dynamic stability..

This study focuses on the strengthening of reinforced concrete beams and columns using Fiber Reinforced Polymer (FRP) composites. FRP materials are widely used in structural rehabilitation due to their high tensile strength, light weight, corrosion resistance, and easy application. The study shows that FRP bonding and wrapping significantly improve flexural strength, shear resistance, axial load capacity, ductility, stiffness, and energy absorption of reinforced concrete members. FRP strengthening also helps in reducing crack propagation and delaying structural failure. Therefore, FRP composites provide an economical, durable, and sustainable solution for repairing and upgrading damaged or weak concrete structures..

Bridge pier scour in tidal environments is a major concern for the safety and durability of coastal and estuarine bridges. The study examines how tidal current velocity, flow reversal, wave-current interaction, sediment type, and storm surge influence scour depth around bridge piers. Results indicate that scour depth increases under high ebb tide, combined wave-current action, and storm surge conditions. Sandy beds show faster erosion, while cohesive sediments resist initial scour. The study highlights the need for site-specific hydraulic analysis, bathymetric survey, sediment testing, and protective measures to ensure long-term bridge foundation stability in tidal regions..

This study focuses on the design and simulation of advanced digital communication systems using MATLAB-based models. The work analyzes different modulation techniques such as BPSK, QPSK, 16-QAM, and OFDM under noisy channel conditions. MATLAB simulation was used to generate digital data, modulate signals, transmit them through an Additive White Gaussian Noise channel, and evaluate receiver performance. The results showed that BPSK achieved the lowest bit error rate, while OFDM provided better bandwidth efficiency and resistance to multipath effects. The study confirms that MATLAB is an effective tool for communication system analysis..

This study evaluates the performance of an OFDM-based communication system under noisy channel conditions. The analysis focuses on how Additive White Gaussian Noise affects signal quality, Bit Error Rate, and overall transmission reliability. Different modulation schemes such as BPSK, QPSK, 16-QAM, and 64-QAM are compared at various Signal-to-Noise Ratio levels. The results show that BER decreases as SNR increases, indicating improved system performance under better channel conditions. Lower-order modulation schemes provide higher reliability, while higher-order schemes support greater data rates but are more noise-sensitive..

This study focuses on machine learning-based fault detection and classification in electrical power systems. Power system faults such as line-to-ground, line-to-line, double-line-to-ground, and three-phase faults can disturb stability, damage equipment, and interrupt electricity supply. Machine learning techniques analyze voltage, current, frequency, and transient signal features to identify and classify faults accurately. Algorithms such as Decision Tree, Support Vector Machine, Random Forest, K-Nearest Neighbour, and Artificial Neural Network were considered for comparative evaluation. The study shows that machine learning improves fault detection accuracy, reduces response time, and supports reliable smart grid protection..

Electrical load forecasting is essential for efficient power system planning, grid stability, and energy management. This study focuses on predicting future electricity demand using artificial intelligence and time series modelling techniques. Historical load data, weather conditions, seasonal patterns, and peak demand factors were considered for model development. Traditional ARIMA and AI-based models such as ANN, SVM, Random Forest, and LSTM were compared. The result showed that LSTM achieved the highest forecasting accuracy due to its ability to learn sequential load patterns. The study concludes that AI-based forecasting improves reliability, reduces operational cost, and supports smart grid management..

This study focuses on power system stability analysis using artificial intelligence-based predictive models. Modern power systems face stability challenges due to load variation, faults, renewable energy integration, and complex grid operations. Traditional stability methods are often slow for real-time prediction, whereas AI models can quickly learn system behaviour from historical and real-time data. Techniques such as Artificial Neural Networks, Random Forest, Deep Learning, and Hybrid AI models help classify stable, marginally stable, and unstable conditions with higher accuracy. The study concludes that AI-based predictive models improve reliability, response time, and preventive decision-making in smart power systems..

Artificial Intelligence (AI)-based transportation demand forecasting has emerged as a critical tool for sustainable urban planning and intelligent mobility management. Rapid urbanization, population growth, and increasing mobility demands have created complex transportation challenges, including congestion, travel time uncertainty, and inefficient resource allocation. Traditional forecasting methods often fail to capture nonlinear, dynamic, and spatial-temporal interactions inherent in modern transport systems. AI-driven approaches, incorporating machine learning, deep learning, graph neural networks, and hybrid predictive models, enable accurate, real-time demand estimation for both passenger and freight transport. .

Economic Load Dispatch (ELD) is a fundamental problem in power system operation, focused on determining optimal generation schedules to meet load demand at minimal cost while satisfying operational and technical constraints. Traditional methods often struggle with nonlinearities, prohibited operating zones, ramp-rate limits, and variability introduced by renewable energy sources. This study explores the application of advanced optimization techniques, including Genetic Algorithms (GA), Particle Swarm Optimization (PSO), hybrid metaheuristics, and Reinforcement Learning (RL), to enhance ELD performance. Simulation results demonstrate that these methods significantly reduce total generation costs, improve system efficiency, lower transmission losses, and increase renewable energy utilization compared to conventional approaches. .

Artificial Intelligence-based smart manufacturing systems are transforming industrial operations in the era of Industry 4.0 by enabling predictive maintenance, process optimization, and intelligent decision-making. By integrating IoT sensors, Digital Twin technology, and machine learning algorithms, these systems enhance operational efficiency, reduce downtime, and lower maintenance costs across multiple industrial sectors. AI-driven analytics and Robotic Process Automation improve production flexibility, quality, and sustainability while supporting adaptive and data-driven manufacturing workflows. Despite challenges such as cybersecurity and workforce adaptation, AI-enabled smart manufacturing provides a resilient, cost-effective, and future-ready framework for modern industrial ecosystems..

Pressure vessels are critical components in industrial applications, requiring high structural integrity under elevated pressures and thermal loads. This study presents a hybrid design optimization approach combining Finite Element Analysis (FEA) with computational techniques, including Particle Swarm Optimization, Genetic Algorithms, Response Surface Methodology, and machine learning-based predictive models, to enhance structural performance while minimizing material usage and cost. Both metallic and composite overwrapped pressure vessels (COPVs) were analysed, optimizing geometry, material properties, and ply configurations. The results demonstrate improved burst pressure, reduced stress concentration, and weight savings, confirming that integrated FEA and optimization frameworks enable efficient, safe, and cost-effective pressure vessel design..

This study focuses on the performance evaluation and optimization of CNC machining processes using advanced computational techniques, specifically Particle Swarm Optimization (PSO). A MATLAB-based simulation and GUI platform was developed to analyze the effects of spindle speed, feed rate, and depth of cut on Material Removal Rate (MRR), surface roughness, tool wear, energy consumption, and machining cost. The results demonstrate significant improvements in productivity and overall efficiency while maintaining acceptable trade-offs in surface quality and operational parameters. The integrated multi-objective optimization framework ensures sustainable, cost-effective, and high-performance CNC operations, providing a practical foundation for Industry 4.0 manufacturing applications..

This study presents a Digital Image Processing (DIP)-based approach for crack detection and structural damage assessment in concrete structures. Concrete infrastructures are prone to deterioration due to environmental and mechanical factors, leading to crack formation that compromises safety. Traditional inspection methods are often subjective and inefficient, whereas DIP provides an automated and accurate alternative. The proposed method includes image acquisition, preprocessing, segmentation, edge detection, and morphological operations to extract crack features. Results show improved accuracy in identifying cracks compared to conventional techniques. This approach enhances structural health monitoring, enabling early detection, reduced maintenance costs, and improved infrastructure safety..

This study investigates the structural performance of reinforced concrete (RC) buildings using advanced digital simulation techniques based on Finite Element Analysis (FEA). With increasing complexity in modern construction and exposure to multiple loading conditions such as seismic, wind, and gravity loads, accurate evaluation of structural behaviour has become essential. The study models an RC building using nonlinear material properties to capture realistic responses including cracking, yielding, and deformation patterns. Key performance parameters such as displacement, inter-story drift, stress distribution, shear force, and bending moment are analysed under different load combinations. The results indicate that all structural responses remain within permissible design limits, ensuring safety and stability. Critical stress concentrations are observed at beam-column joints, highlighting the need for proper reinforcement design. The findings confirm that digital simulation techniques provide higher accuracy and better predictive capability compared to conventional methods, supporting safer and more efficient structural design practices in modern civil engineering..

The growing demand for sustainable and eco-friendly road infrastructure has encouraged the use of industrial waste materials in flexible pavement construction. This study evaluates the performance of flexible pavements incorporating waste materials such as fly ash, ground granulated blast furnace slag (GGBFS), waste plastic, and crumb rubber as partial replacements or modifiers in bituminous mixes. The main objective is to assess improvements in mechanical strength, durability, and resistance to pavement distresses. Laboratory investigations were conducted using the Marshall Mix design method, and performance parameters such as Marshall Stability, flow value, rutting resistance, fatigue life, and moisture susceptibility were analysed. Results indicate that modified mixes significantly outperform conventional mixes in terms of load-bearing capacity, resistance to deformation, and durability. Waste plastic and crumb rubber showed the highest improvement in performance characteristics. The study confirms that industrial waste incorporation enhances pavement sustainability while reducing environmental pollution and construction costs. .

Pavement design plays a critical role in ensuring structural integrity, durability, and cost-efficiency of roadway infrastructure. This study presents a comparative evaluation of four widely used pavement design methods: IRC, AASHTO, Mechanistic-Empirical, and AI-Based Optimized, using a MATLAB-based graphical user interface (GUI) to facilitate systematic analysis. Key performance indicators, including pavement thickness, cost index, deflection, fatigue life, and overall performance score, were assessed under identical input conditions representing traffic load, subgrade strength, and design life. Results indicate that traditional methods such as AASHTO and IRC prioritize structural safety and durability, exhibiting higher thickness, lower deflection, and superior fatigue life, while AI-based optimization reduces material usage and cost at the expense of slightly lower structural performance. Mechanistic-Empirical methods provide balanced outcomes. The study underscores the importance of selecting appropriate design methodologies based on project-specific requirements and demonstrates the utility of computational tools in optimizing pavement design decisions..

Transportation systems are major contributors to energy consumption, carbon emissions, and operational costs, posing significant challenges for sustainable urban development. This study presents a comprehensive framework for modelling and optimizing transportation energy consumption using a MATLAB-based platform. The approach integrates computational modelling, multi-objective optimization, and scenario analysis to evaluate baseline and optimized transportation scenarios for 1000 passengers traveling 25 km per day. Optimization priorities considered include balanced sustainability, minimum energy, and minimum emissions..