An Advanced Artificial Fish School Algorithm to Update Decision Tree for NLOS Acoustic Localization Signal Identification with the Dual-Receiving Method

Abstract

For indoor sensor systems, it is essential to implement an extra supporting area notification part. To inform the real-time coordinates, the time difference of arrival (TDOA) algorithm can be introduced. For these indoor localization systems, their main processes are often built based on the line of sight (LOS) scenario. However, obstacles make the off-the-shelf localization system unable to play its due role in the flexible non-line of sight (NLOS) scenario. So, it is necessary to adjust the signals according to the NLOS identification results. However, the NLOS identification methods before were not effective enough. To address these challenges, on the one hand, this paper proposes an adaptive strategy for a dual-receiving signal processing method. On the other hand, the system is matched with the homologous NLOS identification method based on a novel artificial fish school algorithm (AFSA) and the decision tree model. According to our experiments, our novel AFSA optimization method can obtain a better effect and take less time. The NLOS acoustic signal identification accuracy can be improved significantly in flexible scenarios compared with other methods. Based on these processes, the system will achieve more accurate localization results in flexible NLOS situations.

Indoor Human Action Recognition Based on Dual Kinect V2 and Improved Ensemble Learning Method

“…On the one hand, to assist in the mechanism, it turns out to be tremendous to cope with the NLOS transmission path issues. As for the Chirp (Linear Frequency Modulation, LFM) signals in indoor localization systems, it can be clearly found that the Chirp signal used in the system does not bring extra environmental noise and is beneficial for improving the filtering effect due to its significant difference in frequency distribution in the real-world situation [33,34]. As for each acoustic anchor, we consult some conclusions in [33,50].…”

“…The conversion from coordinates to weights is obtained through the combination of coordinates and radians using geometric principles. The indoor localization system from [33,34,50] can be adopted and it will provide the localization results required for the dual Kinect V2 system. In certain instances, it may be necessary to affix or stabilize some IoT devices [33].…”

“…Micro-Electro-Mechanical System (MEMS) microphones can also be introduced to achieve necessary interaction with various acoustic anchors. The core circuit of the anchors and other modules required for the head-worn microphone can be referred to [33,34,[51][52][53]]. In our system, users have the authority to decide whether to use the indoor localization process and the adaptive weight-adjusting mechanism or not.…”

“…BERT-GAN [2 MotionBERT [29] have achieved significant results in HAR tasks, while GAN methods [28,30] have been proposed to address imbalanced multi-classi applications in different situations. It is undeniable that the methods mentioned and datasets including NTU-60, NTU-120 and others [31][32][33][34][35][36][37][38][39][40][41], which contain actions, have also played a crucial role in facilitating research. This is not only refle the application scenario for a single-person issue but also in the application scen multiple persons working simultaneously.…”

“…The descriptions are as follows (Fi In complex situations, additional measures and processes are required to other multimodal information in the system. A heightened emphasis on a localization signals, as derived from Kinect and other IoT devices, is imperat 22,33,34]. If dynamic obstacles appear in the transmission path, NLOS scenari occur in an indoor localization system.…”