One of the most important strategies for preventative factory maintenance is anomaly detection without the need for dedicated sensors for each industrial unit. The implementation of sound-data-based anomaly detection is an unduly complicated process since factory-collected sound data are frequently corrupted and affected by ordinary production noises. The use of acoustic methods to detect the irregularities in systems has a long history. Unfortunately, limited reference to the implementation of the acoustic approach could be found in the failure detection of industrial machines. This paper presents a systematic review of acoustic approaches in mechanical failure detection in terms of recent implementations and structural extensions. The 52 articles are selected from IEEEXplore, Science Direct and Springer Link databases following the PRISMA methodology for performing systematic literature reviews. The study identifies the research gaps while considering the potential in responding to the challenges of the mechanical failure detection of industrial machines. The results of this study reveal that the use of acoustic emission is still dominant in the research community. In addition, based on the 52 selected articles, research that discusses failure detection in noisy conditions is still very limited and shows that it will still be a challenge in the future.

As a complex ecosystem composed of flora and fauna, the forest has always been vulnerable to threats. Previous researchers utilized environmental audio collections, such as the ESC-50 and UrbanSound8k datasets, as proximate representatives of sounds potentially present in forests. This study focuses on the application of deep learning models for forest sound classification as an effort to establish an early threats detection system. The research evaluates the performance of several pre-trained deep learning models, including MobileNet, GoogleNet, and ResNet, on the limited FSC22 dataset, which consists of 2,025 forest sound recordings classified into 27 categories. To improve classification capabilities, the study introduces a hybrid model that combines neural network (CNN) with a Bidirectional Long-Short-Term Memory (BiLSTM) layer, designed to capture both spatial and temporal features of the sound data. The research also employs Pareto-Mordukhovich-optimized Mel Frequency Cepstral Coefficients (MFCC) for feature extraction, improving the representation of audio signals. Data augmentation and dimensionality reduction techniques were also explored to assess their impact on model performance. The results indicate that the proposed hybrid CNN-BiLSTM model significantly improved classification loss and accuracy scores compared to the standalone pre-trained models. GoogleNet, with an added BiLSTM layer and augmented data, achieved an average reduced loss score of 0.7209 and average accuracy of 0.7852, demonstrating its potential to classify forest sounds. Improvements in loss score and classification performance highlight the potential of hybrid models in environmental sound analysis, particularly in scenarios with limited data availability.

Reliable integration of LiDAR and photogrammetric point clouds is essential for high-precision 3D mapping, yet systematic evaluations of fusion accuracy under controlled conditions remain limited. This study presents a simulation-based assessment framework for LiDAR–photogrammetry fusion using a neural radiance field (NeRF) representation and iterative closest point (ICP) registration. Experiments were conducted in the CARLA simulator (Town 10), where a drone-mounted multi-sensor platform (RGB, LiDAR, GPS, IMU) generated spatially aligned datasets. Photogrammetric reconstructions were produced using the Nerfstudio–Nerfacto pipeline with varied architectural and sampling configurations to analyze their impact on cross-modal registration. Quantitative evaluation employed Chamfer and cloud-to-cloud (C2C) distances to assess NeRF reconstruction fidelity, and ICP root-mean-square error (RMSE), inlier fitness, and runtime to evaluate registration performance. Results show that tuning NeRF’s hidden dimensions and sampling levels yields up to 25% lower ICP RMSE and faster convergence across object categories. The proposed framework enables reproducible benchmarking of LiDAR–photogrammetry fusion and provides a foundation for extending NeRF-based methods to real-world urban mapping scenarios.