Frequency weighting to evaluate the feeling of pressure and/or vibration caused by low-frequency noise: Re-analysis of an existing study

Low-frequency noise may create specific perceptions, which might cause various health effects. The present study aimed to identify exposure–response relationships between low-frequency noise and perceptions by re-analysing an experimental study. We investigated the predominant perceptions of ‘feeling bothered’ and ‘feeling of pressure and/or vibration’ using multivariate logistic regression analysis. A significant interaction between 1/3 octave-band sound pressure level and frequency was indicated for ‘feeling bothered’ but not ‘feeling of pressure and/or vibration’, suggesting that the ‘feeling of pressure and/or vibration’ does not originate in cochlear. A mathematical model indicating resonance at approximately 50 Hz fitted the results well. A frequency weighting derived from the mathematical model could be applied to broad-band low-frequency noise to evaluate the perception and health effects. However, further investigations on the weighting for the perception are necessary because the results were obtained only from the existing study.

Application of loudness level to temporally varying sounds

Most of the environmental noises are temporally varying and include various frequency components. Various methods for evaluating the environmental noises have been proposed. Among them, the method for calculating loudness level was first standardized in 1975 as ISO 532, including Stevens' and Zwicker's methods. Unfortunately, these methods can only be applied to steady state sounds. On the other hand, Aeq (Equivalent Continuous A-weight Sound Pressure Level) is standardized for the evaluation of level fluctuating environmental sounds as ISO 1996. In , the energy mean and A-weighting are used for averaging temporal fluctuation and frequency weighting, respectively. The present authors with their colleagues have conducted many psychological experiments using artificial sounds and actual sounds since 1970's and have being introduced that p (Loudness-based Method), which is a combination of ISO 532 for frequency weighting and ISO 1996 for temporal level fluctuation, is a good method for evaluating various kinds of environmental sounds. ISO 532-1 (Zwicker's method) has been revised including the temporal fluctuation into consideration in 2017, in which p has been adopted as a note. The merit of p will be introduced in this paper presenting many examples.

Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks

Brain structure segmentation on magnetic resonance (MR) images is important for various clinical applications. It has been automatically performed by using fully convolutional networks. However, it suffers from the class imbalance problem. To address this problem, we investigated how loss weighting strategies work for brain structure segmentation tasks with different class imbalance situations on MR images. In this study, we adopted segmentation tasks of the cerebrum, cerebellum, brainstem, and blood vessels from MR cisternography and angiography images as the target segmentation tasks. We used a U-net architecture with cross-entropy and Dice loss functions as a baseline and evaluated the effect of the following loss weighting strategies: inverse frequency weighting, median inverse frequency weighting, focal weighting, distance map-based weighting, and distance penalty term-based weighting. In the experiments, the Dice loss function with focal weighting showed the best performance and had a high average Dice score of 92.8% in the binary-class segmentation tasks, while the cross-entropy loss functions with distance map-based weighting achieved the Dice score of up to 93.1% in the multi-class segmentation tasks. The results suggested that the distance map-based and the focal weightings could boost the performance of cross-entropy and Dice loss functions in class imbalanced segmentation tasks, respectively.

Development of Frequency Weighted Model Reduction Algorithm with Error Bound: Application to Doubly Fed Induction Generator Based Wind Turbines for Power System

The state-space representations grant a convenient, compact, and elegant way to examine the induction and synchronous generator-based wind turbines, with facts readily available for stability, controllability, and observability analysis. The state-space models are used to look into the functionality of different wind turbine technologies to fulfill grid code requirements. This paper deals with the model order reduction of the Variable-Speed Wind Turbines model with the aid of improved stability preserving a balanced realization algorithm based on frequency weighting. The algorithm, which is in view of balanced realization based on frequency weighting, can be utilized for reducing the order of the system. Balanced realization based model design uses a full frequency spectrum to perform the model reduction. However, it is not possible practically to use the full frequency spectrum. The Variable-Speed Wind Turbines model utilized in this paper is stable and includes various input-output states. This brings a complicated state of affairs for analysis, control, and design of the full-scale system. The proposed work produces steady and precise outcomes such as in contrast to conventional reduction methods which shows the efficacy of the proposed algorithm.

Fault Diagnosis for Vehicle on-Board Equipments of High-Speed Railway Based on GA-ANFIS Model

Vehicle on-board equipment is the most important train control equipment in high-speed railways. Due to the low efficiency and accuracy of manual detection, in this paper, we propose an intellectualized fault diagnosis method based on adaptive neuro-fuzzy inference system (ANFIS) network. Firstly, we collect the fault information sheets that are recorded by electrical personnel, using frequency weighting factor and principal component analysis (PCA) to realize the data extraction and dimension reduction; Then, in order to improve the fault diagnosis rate of the model, using genetic algorithm (GA) to optimize the parameters of the ANFIS network; Finally, using the fault data of a high-speed railway line in 2019 to test the model, the optimized ANFIS model can achieve 96% fault diagnosis rate for vehicle on-board equipments, which indicating the method is effective and accurate.

Tree, Shrub, and Grass Classification Using Only RGB Images

In this work, a semantic segmentation-based deep learning method, DeepLabV3+, is applied to classify three vegetation land covers, which are tree, shrub, and grass using only three band color (RGB) images. DeepLabV3+’s detection performance has been studied on low and high resolution datasets that both contain tree, shrub, and grass and some other land cover types. The two datasets are heavily imbalanced where shrub pixels are much fewer than tree and grass pixels. A simple weighting strategy known as median frequency weighting was incorporated into DeepLabV3+ to mitigate the data imbalance issue, which originally used uniform weights. The tree, shrub, grass classification performances are compared when all land cover types are included in the classification and also when classification is limited to the three vegetation classes with both uniform and median frequency weights. Among the three vegetation types, shrub is found to be the most challenging one to classify correctly whereas correct classification accuracy was highest for tree. It is observed that even though the median frequency weighting did not improve the overall accuracy, it resulted in better classification accuracy for the underrepresented classes such as shrub in our case and it also significantly increased the average class accuracy. The classification performance and computation time comparison of DeepLabV3+ with two other pixel-based classification methods on sampled pixels of the three vegetation classes showed that DeepLabV3+ achieves significantly higher accuracy than these methods with a trade-off for longer model training time.