The lift-plus-cruise electric vertical takeoff and landing (eVTOL) aircraft represents a major eVTOL configuration. However, the reliability of its lift powertrain has attracted increasing research attention because of its complex redundant architecture and dynamic failure behaviors. This paper proposes a reliability assessment framework for the lift powertrain of a lift-plus-cruise eVTOL in which a dynamic fault tree (DFT) model is mapped onto a generalized stochastic Petri net (GSPN) model, and a discrete event simulation (DES)-based GSPN quantitative analysis algorithm is developed. Based on this framework, the reliability of the lift powertrain is evaluated, and the effectiveness of the proposed algorithm is validated through comparison with results from a Monte Carlo simulation (MCS)-based DFT. The simulation results indicate that the high-voltage battery is the most critical component affecting system reliability. Reducing its failure rate leads to substantially greater improvement in system reliability compared to improving other components, providing quantitative guidance for lift powertrain architecture optimization.

Reliability analysis of multistate systems in multistate environments presents a significant challenge, particularly when considering proof testing parameters. This paper introduces a novel reliability assessment framework for multistate systems subjected to periodic inspection testing, utilizing Multiphase Markov Chains (MMC). The approach effectively represents system behavior across various degradation states while integrating the effects of proof testing. By modeling distinct operational phases, including normal operation, degraded states, and proof test interventions, this method improves the estimation of multistate systems unavailability. A case study illustrates the impact of key proof test parameters, such as test efficiency and risk of inducing failures, on overall multistate system reliability. Additionally, two simulation cases are conducted to examine the influence of various inspection test factors and highlight the advantages of maintenance strategies.

Emotion identification using audio is a significant difficulty in interactions between humans and computers, as emotional indicators within speech are usually complex and dependent on context. Conventional techniques encounter difficulties in precise classification owing to high-dimensional characteristics and restricted predictability. This paper is devoted to the recognition of emotions from audio with a novel approach based on a hybrid ResNet single-channel feature-tailored architecture. The elicitation of emotions by the suggested predication system is an indicator of robust classification error. The suggested methodology is a dimensionality reduction methodology based on Principal Component Analysis and takes advantage of ANOVA to provide detailed statistical validation to improve feature selection and general performance of the model. The model possesses a high accuracy of 94.50% in addition to high precision, recall and F1 scores, indicating that the model is well able to identify emotional states. When comparing our study with previous literature, it is evident that our model has superior performance, and it is more effective than both traditional machine learning approaches and other approaches of deep learning. It is a part of the speech emotion recognition method development that may be used in personalized music recommendation systems and other human-computer interaction technologies.

CBIR systems work well with clean query images but are highly degraded by real-world noise such as Gaussian blur, salt-and-pepper noise, compression artifacts, and haze. In this paper, NRGAN-HFF (Noise-Resilient GAN with Hybrid Feature Fusion) is proposed as a new CBIR framework that addresses noisy query-image retrieval. The framework incorporates a DnCNN-based Generative Adversarial Network (GAN) to do adaptive query denoising as well as a Synergistic Hybrid Feature Fusion (HFF) module that fuses handcrafted descriptors (Color Moments, LBP, HOG, SIRF) with deep CNN features (fine-tuned VGG16 and pre-trained ResNet50), and then features are selected by LightGBM as well as dimensionality reduction by PCA. A standardized Noisy Query Generation Pipeline (NQGP) effectively uses four types of noise at three intensity levels, which result in 12 variants of corruption for each image to be evaluated objectively. The experiments that were performed on a merged dataset of 19,680 images of Caltech-101, Stanford-40 Actions, and Corel-1K also prove that NRGAN-HFF has an average Noise Robustness Score (NRS) of 94.1%, regardless of the type and severity of noise, which is evidence that the framework is dual-performable with respect to both retrieval and operational resilience in adverse conditions.

This research work deals with the challenges in software fault prediction (SFP) such as class imbalance in benchmark datasets, noisy features, and high-dimensional feature spaces. To overcome the above limitations, we propose a novel hybrid feature selection framework, FS-BWOA-COA, which incorporates Coati Optimization Algorithm (COA) for local exploitation and Beluga Whale Optimization Algorithm (BWOA) for global exploration. The two-phase optimization approach helps to avoid duplication and improves the stability of the classifier, while also helping to maintain the balance between exploration and exploitation. The framework was tested using several classifiers such as Decision Tree, SVM, KNN, and Naïve Bayes on eleven NASA PROMISE datasets. The hybrid outperforms single BWOA and COA, with an average accuracy of 0.9033 and peak values of 0.95 on the MC1 and JM1 datasets. The results of the statistical validation using the Friedman test, Wilcoxon signed-rank test, and paired t-tests confirm the same.

For long-horizon machine learning, there is a need to process large amounts of contextual data and perform reasoning over long sequences of time or knowledge. The traditional monolithic machine learning architectures have shown limitations in terms of scalability, accessibility of knowledge, and efficient utilization of resources in cloud computing. The paper aims to introduce a Hybrid Retrieval-Augmented Microservices Architecture (HRAMA), which can be used to enhance the efficiency of machine learning architectures in cloud computing. The hybrid retrieval mechanism integrates semantic vector similarity search with metadata-based filtering to improve the relevance of the extracted information. The architecture is based on a machine learning pipeline that is decomposed into independent microservices, which are then deployed using containerized cloud computing. The performance of the proposed architecture is validated using experimental results that show improved retrieval accuracy, system throughput, and scalability, along with reduced inference latency. The proposed HRAMA framework is efficient for long horizon cloud machine learning applications.