Towards Self-supervised Learning for Multi-function Radar Behavior State Detection and Recognition

<div>The analysis of intercepted multi-function radar (MFR) signals has gained considerable attention in the field of cognitive electronic reconnaissance. With the rapid development of MFR, the switch between different work modes is becoming more flexible, increasing the agility of pulse parameters. Most of the existing approaches for recognizing MFR behaviors heavily depend on prior information, which can hardly be obtained in a non-cooperative way. This study develops a novel hierarchical contrastive self-supervise-based method for segmenting and clustering MFR pulse sequences. First, a convolutional neural network (CNN) with a limited receptive field is trained in a contrastive way to distinguish between pulse descriptor words (PDW) in the original order and the samples created by random permutations to detect the boundary between each radar word and perform segmentation. Afterward, the K-means++ algorithm with cosine distances is established to cluster the segmented PDWs according to the output vectors of the CNN’s last layer for radar words extraction. This segmenting and clustering process continues to go in the extracted radar word sequence, radar phase sequence, and so on, finishing the automatic extraction of MFR behavior states in the MFR hierarchical model. Simulation results show that without using any labeled data, the proposed method can effectively mine distinguishable patterns in the sequentially arriving PDWs and recognize the MFR behavior states under corrupted, overlapped pulse parameters.</div>

Towards Self-supervised Learning for Multi-function Radar Behavior State Detection and Recognition

<div>The analysis of intercepted multi-function radar (MFR) signals has gained considerable attention in the field of cognitive electronic reconnaissance. With the rapid development of MFR, the switch between different work modes is becoming more flexible, increasing the agility of pulse parameters. Most of the existing approaches for recognizing MFR behaviors heavily depend on prior information, which can hardly be obtained in a non-cooperative way. This study develops a novel hierarchical contrastive self-supervise-based method for segmenting and clustering MFR pulse sequences. First, a convolutional neural network (CNN) with a limited receptive field is trained in a contrastive way to distinguish between pulse descriptor words (PDW) in the original order and the samples created by random permutations to detect the boundary between each radar word and perform segmentation. Afterward, the K-means++ algorithm with cosine distances is established to cluster the segmented PDWs according to the output vectors of the CNN’s last layer for radar words extraction. This segmenting and clustering process continues to go in the extracted radar word sequence, radar phase sequence, and so on, finishing the automatic extraction of MFR behavior states in the MFR hierarchical model. Simulation results show that without using any labeled data, the proposed method can effectively mine distinguishable patterns in the sequentially arriving PDWs and recognize the MFR behavior states under corrupted, overlapped pulse parameters.</div>

An Empirical Study on the Impact of Prior Information Provision Methods on Participants’ Perceptions in Tasting Marketing

Tasting events are a typical example of a tourism experience that utilizes alcohol. However, it has not been sufficiently demonstrated how the prior information given to customers at tasting events affects their perception of the tasting and its marketing effects. In this study, we conducted a tasting experiment of a new Japanese sake product in California, the USA to clarify how information given to participants in advance can affect their perception of the tasting, satisfaction, and word-of-mouth intention related to the new sake product, and compared the effects of the following types of prior information: 1) no information, 2) written information, 3) video explained by a man, and 4) video explained by a woman. The results show that presenting information makes a difference in its impact as opposed to providing no information. When prior information was presented in written form, various perspectives significantly influenced the satisfaction and recommended intention more than in the cases of video. On the other hand, in the cases of video, the number of significant paths was reduced, but the influence on word-of-mouth intention was greater than in the case of written information. This study contributes to the development of a theory and empirical evidence that takes into account prior information in tasting marketing in tourism.

Image Segmentation for Review of Cerebral Apoplexy

Brain computed tomography (CT) provides a medical imaging tool for reviewing cerebral apoplexy. It is of strong clinical significance to study the key techniques for lesion segmentation and feature selection of cerebral apoplexy. Most of the previous research fail to fully utilized the other prior information, or apply to the changing feature analysis on multiple lesion images generated in the rehabilitation process. Therefore, this paper aims to develop an image segmentation method for review of cerebral apoplexy. Based on the correlation between image series, the authors proposed a segmentation method for CT images of cerebral apoplexy, and developed a way to extract and select the changing lesion features, which assists with the diagnosis of cerebral apoplexy rehabilitation. The image segmentation and feature selection results were obtained through experiments, revealing the effectiveness of our method.

PEMODELAN SISTEM ANTREAN PELAYANAN BUS JALUR BARAT TERMINAL TIRTONADI KOTA SURAKARTA DENGAN METODE BAYESIAN

Tirtonadi is the largest bus station in Surakarta City. The departure line is devided into two lines, namely west line and east line. The west line serves buses to the west of Surakarta City. The number of buses that enter and leave the station every day causes bus queues. Modeling the queue system and analyzing the system performance measure aims to determine wether the bus service system is good or not. The queue system model is obtained by finding the distribution of arrival patterns and service patterns using the Bayesian method. This method is used because it combines the information from the current research and the prior information from the previous research. The queueing condition of the five lanes in the west line meets steady state conditions because the utility value is less than 1. The queue displant is First Come First Service (FCFS) with unlimited customers and unlimited calling sources. Based on the posterior distribution, the queue system of service bus is (GAMM/IG/1):(GD/∞/∞) for Solo-Jakarta-Bandung lane and Pedesaan lane, while for Solo-Purwokerto-Cilacap, Solo-Yogyakarta, and Solo-Semarang has the queue system (GAMM/GAMM/1):(GD/∞/∞). The queue system of service bus for each lane has good services based on the value of system performance measure.

Entropy-Based Variational Scheme with Component Splitting for the Efficient Learning of Gamma Mixtures

Finite Gamma mixture models have proved to be flexible and can take prior information into account to improve generalization capability, which make them interesting for several machine learning and data mining applications. In this study, an efficient Gamma mixture model-based approach for proportional vector clustering is proposed. In particular, a sophisticated entropy-based variational algorithm is developed to learn the model and optimize its complexity simultaneously. Moreover, a component-splitting principle is investigated, here, to handle the problem of model selection and to prevent over-fitting, which is an added advantage, as it is done within the variational framework. The performance and merits of the proposed framework are evaluated on multiple, real-challenging applications including dynamic textures clustering, objects categorization and human gesture recognition.

The what and where of synchronous sound perception

Sound localization and identification are challenging in acoustically rich environments. The relation between these two processes is still poorly understood. As natural sound-sources rarely occur exactly simultaneously, we wondered whether the auditory system could identify ('what') and localize ('where') two spatially separated sounds with synchronous onsets. While listeners typically report hearing a single source at an average location, one study found that both sounds may be accurately localized if listeners are explicitly being told two sources exist. We here tested whether simultaneous source identification (one vs. two) and localization is possible, by letting listeners choose to make either one or two head-orienting saccades to the perceived location(s). Results show that listeners could identify two sounds only when presented on different sides of the head, and that identification accuracy increased with their spatial separation. Notably, listeners were unable to accurately localize either sound, irrespective of whether one or two sounds were identified. Instead, the first (or only) response always landed near the average location, while second responses were unrelated to the targets. We conclude that localization of synchronous sounds in the absence of prior information is impossible. We discuss that the putative cortical 'what' pathway may not transmit relevant information to the 'where' pathway. We examine how a broadband interaural correlation cue could help to correctly identify the presence of two sounds without being able to localize them. We propose that the persistent averaging behavior reveals that the 'where' system intrinsically assumes that synchronous sounds originate from a single source.

Deconvolution of fission-track length distributions and its application to dating and separating pre- and post-depositional components

To enable the separation of pre- and postdepositional components of the length distribution of (partially annealed) horizontal confined fission tracks, the length distribution is corrected by deconvolution. Probabilistic least-squares inversion corrects natural track length histograms for observational biases, considering the variance in data, modelization, and prior information. The corrected histogram is validated by its variance–covariance matrix. It is considered that horizontal track data can exist with or without measurements of angles to the c axis. In the latter case, 3D histograms are introduced as an alternative to histograms of c-axis-projected track lengths. Thermal history modelling of samples is not necessary for the calculation of track age distributions of corrected tracks. In an example, the age equations are applied to apatites with predepositional (inherited) tracks in order to extract the postdepositional track length histogram. Fission tracks generated before deposition in detrital apatite crystals are mixed with post-depositional tracks. This complicates the calculation of the post-sedimentary thermal history, as the grains have experienced different thermal histories prior to deposition. Thereafter, the grains share a common thermal history. Thus, the extracted post-depositional histogram without inherited tracks may be used for thermal history calculation.