Nitte Meenakshi Institute of Technology

The people of all ages are changing the way they live as technology advances, while younger people are experiencing more bone injuries from activity and accidents, seniors are still more prone to broken bones and joint issues. Biomaterials, which are natural or created materials such as titanium, nickel, cobalt, and stainless steel alloys, are used to repair damaged body parts. Stainless steel is a frequently utilized biomaterial due to its ready availability, reasonable price, and ease of shaping. However, it is susceptible to corrosion, suffers from wear, and doesn’t always interact well with the body; furthermore, its properties are considerably altered by the conditions within a human being. Corrosion is particularly dangerous for stainless steel biomaterials, as it releases harmful materials which could damage health and cause numerous serious complications. This analysis offers a thorough evaluation of how stainless steel biomaterials corrode, the specific difficulties with various stainless steel types, and methods to alter the surface of steel to improve durability, corrosion protection, compatibility with the body and how long an implant will last.

Water pollution caused by Methylene blue (MB) dye and the toxic pollutant 4-nitrophenol (4-NP) underscores the need for efficient catalytic reduction methods. In this study, a series of iron sulfide-doped, sulfur-enriched graphitic carbon nitrides (FeS2/S-g-C3N4; FeS-1-4) was synthesized via a one-pot thermal polymerization method, with a constant thiourea concentration and varying iron content. The FeS-1, FeS-2, FeS-3, and FeS-4 catalysts exhibited high efficiency in the reduction of 4-NP to 4-aminophenol (4-AP) in the presence of NaBH4, as well as in the photocatalytic MB degradation using H2O2 under visible-light irradiation. Within 5 min, 4-NP reduction reached similar to 82% with S-g-C3N4 and 98.5% with FeS2/S-g-C3N4 (FeS-4), whose superior performance stems from its modified electronic structure, increased active sites, sulfur vacancies, and improved interfacial contact. Under 150 W mercury lamp illumination, FeS2/S-g-C3N4 achieved 99.1% MB degradation within 35 min, compared to 58.6% in the dark. The enhanced activity was attributed to the FeS2/S-g-C3N4 heterojunction, which promoted charge transfer and improved electron-hole separation, while Fe sites enhanced ROS generation, resulting in nearly complete MB degradation within 35 min with a rate constant (k) similar to 3.6 times higher than in the dark. Scavenger tests indicated that superoxide radicals (O-2 center dot(-)) are the most effective agents for photodegrading MB. Overall, the in-situ synthesized FeS/S-g-C3N4 nanocomposite functions as an efficient catalyst and photocatalyst for removing organic pollutants from water.

The development of online banking has brought about an increase in fraudulent operations, which is a major problem for banks. This study delves into the urgent requirement for interpretable, scalable, and top-notch fraud detection systems by using TabNet, an adaptable deep learning framework, on a Kaggle dataset consisting of actual bank transactions in India. Maximizing operational risk management by improving the accuracy of transaction anomaly detection and ensuring regulatory compliance through transparent models is the goal.We utilize a supervised learning pipeline that incorporates the Synthetic Minority Over-sampling Technique (SMOTE) to ensure that classes are balanced. Subsequently, we conduct thorough exploratory data analysis (EDA) to identify patterns of fraud, both during specific times and across behaviors. On this dataset, five different deep learning architectures are tested: DNN, GRU, LSTM, CNN1D, and TabNet. Assessment of predictive performance was carried out using a 3-fold cross-validation framework. With a ROC-AUC of 0.9739 and an accuracy of 97.39%, TabNet considerably outperformed the competition. The method of sparse feature selection used improved interpretability, generalized better on tabular data, and produced fewer false positives and negatives.Critical insights for operational fraud detection systems and a contribution to the broader literature on explainable AI (XAI) in financial decision-making are offered by the findings. Goals 8 and 16 of the Sustainable Development Agenda are supported by this study, which promotes inclusive economic growth and institutional transparency. Supporting strong, policy-compliant, and interpretable decision-support systems, it also offers practical use for real-time implementation in banking infrastructure.

The effect of GNP loading, printing speed, and the printing temperature on the physicomechanical properties of 3D-printed ABS/GNP composites produced using the FFF process was studied based on a Box–Behnken statistical model. The mechanical properties of the prepared composites, including hardness, tensile, flexural, compressive, and impact strengths, were tested as per the relevant ASTM standards. The study concluded that graphene loading had the highest effect on the mechanical performance of the composites, followed by printing temperature, while the printing speed had the lowest impact. The best combination was 1.5 wt.

Accurate prediction of surface roughness (SR) and material removal rate (MRR) in Wire Electrical Discharge Machining (WEDM) of Al7075/Al2O3 composites remains a critical challenge due to complex, nonlinear interactions among machining parameters and the lack of robust predictive models. Additionally, achieving reliable SR prediction is difficult because of the stochastic nature of the process. In this study, Al7075/Al2O3 composite was fabricated using the stir casting process to ensure uniform particle distribution. The WEDM experiments were systematically designed using Taguchi’s L₁̄8 orthogonal array, where voltage, current, pulse-on time, pulse-off time, and bed speed were varied to evaluate their effects on SR and MRR. This study addresses these issues by developing predictive models using CatBoost, Decision Tree, and Naïve Bayes algorithms. Experiments were designed using Taguchi’s L₁̄8 orthogonal array by varying key parameters. When it comes to predicting MRR and SR, the CatBoost algorithm and the Decision tree method outperform naive Bayes. CatBoost achieved higher prediction accuracy (0.83), precision (1.0), and ROC-AUC (0.83) for MRR compared to other models, indicating its effectiveness in capturing nonlinear relationships without overfitting. Satisfactory accuracy of predictions is obtained using decision tree models, whereas Naïve Bayes gives the least accuracy because of the conditional independence of assumptions made by the algorithm. The lower prediction accuracy for surface roughness (maximum accuracy of 0.5 and ROC-AUC up to 0.5) suggests higher complexity in its prediction, without attributing it solely to randomness or proposing unverified solutions that can be solved by hybrid machine learning models in future. Results show CatBoost outperforms others for MRR prediction, while SR prediction remains less accurate, highlighting the need for advanced hybrid modeling approaches.