Machine learning (ML) has made significant advancements in predictive modelling across many engineering sectors. However, predicting the bearing capacity of pre-bored grouted planted nodular (PGPN) piles remains a relatively unexplored area due to complexity load-bearing mechanism, pile-soil interactions, and multiple variables involved. The study utilises state-of-the-art ML techniques such as extreme gradient boosting (XGBoost), random forest (RF), machines (GBMs), deep learning-based...

In this study machine learning models are used that forecast the compressive strength of self-compacting concrete (SCC) depending on percentage replacement cement by supplementary cementitious material. order to predict mechanical property SCC, a hybrid artificial neural network (ANN) along with metaheuristic optimization techniques and two traditional were employed which comprised 300 datasets. Several input factors in modelling process, including cement, water-binder ratio, coarse...

Uncertainty and variability are inherent to pile design consequently, there have been considerable researches in quantifying the reliability or probability of failure structures. This paper aims at examining comparing applicability adaptability Minimax Probability Machine Regression (MPMR), Emotional Neural Network (ENN), Group Method Data Handling (GMDH), Adaptive Neuro-Fuzzy Inference System (ANFIS) analysis embedded cohesionless soil proposes an AI-based prediction method for bearing...

The complexity of concrete's composition makes it difficult to predict its compressive strength, which is a highly valuable and desired characteristic. Traditional methods for prediction are expensive time-consuming, resulting in limited data availability. However, modern soft-computing models have emerged as reliable solution accurately forecasting strength. research proposes novel Deep Neural Network (DNN), Multivariate Adaptive Regression Splines (MARS) Extreme Learning Machine (ELM)...

Determining the bearing capacity of a strip footing under inclined loading is crucial in designing foundations. Due to complex correlations, subject area remains predominantly unexplored, or it has been simulated using only limited datasets. This paper presents development prediction model based on machine learning (ML), leveraging advanced hybrid artificial neural network (ANN) models for estimating footings loading. The ANN are hybridized with four different optimization algorithms, ant...

The nature of soil varies horizontally as well vertically, owing to the process formation soil. Thus, ensuring safe design geotechnical structures has been a major challenge. In shallow foundations, conducting field tests is expensive and time-consuming often conducted on significantly scaled-down models. Empirical models, too, have found be least reliable in literature. study proposes AI-based techniques predict bearing capacity foundation, simulated using datasets obtained experiments...

Cervical cancer is a severe and pervasive disease that poses significant health threat to women globally. The Pap smear test an efficient effective method for detecting cervical in its early stages. However, manual screening labor-intensive requires expert cytologists, leading potential delays inconsistencies diagnosis. Deep Learning-based Computer-Aided Diagnosis (CAD) has shown results can ease the problem of screening. one single model sometimes insufficient capture complex data pattern...

AUTOSAR, an open standard for automotive software, is currently being exploited by the industry. Although mainly focuses on software architecture, it also provides a development methodology. Unfortunately, methodology in its current form insufficient industrial exploitation because describes only incomplete set of activities, work products and their dependencies. Specifically, (1) activities to support COTS-based are missing even though AUTOSAR encourages use COTS components; (2) does not...

This paper presents work on a recommendation system for Knowledge assisted Agile Requirements Evolution (K-gileRE). We treat requirements engineering as special case of knowledge and emphasize the fact that providing domain edge can impart agility to definition exercise. The approach differs from existing agile methods in it seamlessly incorporates base into an framework explicitly provides requirement analysts, relevant online specific recommendations based underlying ontologies. 'domain...

One of the major problems that cause continual trouble in deep learning networks is training a large network requires massive labelled datasets. The preparation dataset cumbersome task and lot human interventions. This paper proposes novel generator ‘Sim2Real’ transfer recent fast-developing field machine used to bridge gap between simulated real data. Training with datasets often converges due its size but fails generalize real-world applications. Simulated can be train test models, enables...

Advancement in the satellite imaging techniques has produced wider applications disaster reduction and management. Considering crucial role of rapid detection landslides management, this research paper exploits capability sentinel-1A imagery landslide detection. In image processing feature techniques, machine learning based classification methods have gained popularity by proving its potential mapping susceptible landslides. Therefore, primary objective is automatic identification using...

Because of the rapid propagation wireless devices, Mobile ad hoc Networking (MANET) is considered as an emerging technology. MANET's are more susceptible to attacks because it lack centralized monitoring and has dynamic changing network. In order detect in MANET, network activities analyzed through Intrusion Detection System (IDS) identify known unknown attacks. this article, efficient IDS system based on data mining techniques proposed which suspicious MANET Initially, a created various The...

Envisioned speech captured by EEG signals is a fascinating area of research as this useful in bio-medical applications for the patients suffering from motor neuron diseases and also those areas where silent desirable. This work examines possibility better feature extraction techniques which robust model with help classifier can be built. Results showed that Common Spatial Patterns (CSP) filter coefficients combination statistical features Random Forest turn out to suitable choice. Three...