An Emergency Measure Completeness Evaluation Method Based on UGC Data

Complete emergency measures are one of the important guarantees for effective emergency response. An evaluation method based on User-Generated Content (UGC) data is proposed to assess the completeness of emergency measures. To implement this method, UGC data comprising emergency needs from the users and emergency plans comprising emergency measures for specific emergency were firstly collected using a crawler program. A feature template was then established to identify relationships between different features, and a Conditional Random Field (CRF) model was used to extract emergency measures from the emergency plan and emergency needs from UGC data. The Siamese network was applied thereafter to compute the similarity between the emergency measures and emergency needs. The missing emergency measures were obtained based on the similarities, and a quantitative method to calculate the completeness was defined. Finally, using province A as a case study, the emergency measure completeness was evaluated and the emergency measures that need to be strengthened and improved were identified.

IMPLEMENTASI ZONING DAN FITUR ARAH SEBAGAI EKSTRAKSI FITUR PADA PENGENALAN TULISAN TANGAN AKSARA BALI

Character recognition is one of the most researched fields in computer science. Combining the field of digital image processing and pattern recognition is a challenge in determining the most optimal method combination to complete character recognition. Balinese script is one of the regional scripts used in Balinese literary. The challenge with Balinese script is that some of its characters have a degree of similarity. So far, several methods of feature extraction that have been studied for Balinese script are modified direction feature, template matching, image centroid zone and zone centroid zone, local binary pattern. In this research, we combine methods based on zoning and directional features. The methods used are ICZ, ZCZ and freeman chain code to find the characteristics of Balinese script handwriting. The addition of chain code method aims to determine the value around the foreground point. The results of feature extraction will be used as input in the Support Vector Machine for the classification process. The test result shows that the combination of the ICZ, ZCZ and freeman chain code methods produces an accuracy of 89.09%, while the combination of ICZ and ZCZ produces 88.06% of accuracy. The SVM kernels compared use linear kernels.

Robust Iris and Fingerprint Biometric Fusion in Multimodal Feature Template Matching

A fusion scheme in multimodal biometric system is proposed in the name of Multimodal Feature Template Matching (MTM) system derived from the two picture fused values of average point and weighted assessment point. The main objective of MTM algorithm is to design the average point fusion and weighted average point by fusion of Iris and fingerprint features. The MTM algorithm is assigned with avgweights based on their verification accuracy. A hybrid approach of combining biometric image level information id presented. The raw information is merged at image level. This integration addressed, provides a small template and resilience to attacks. However it does not improve the recognition performance, but the performances is also less combination to its unimodal counterpart. Confidence level integration of compatible features of two different uncorrelated biometric traits fingerprint and iris provides sustainable improvement in performance accuracy compared to other integration methods as well as best unimodal system. Fingerprint and iris integration approaches presented in this proposed are more robust and reliable.

GABA, not BOLD, reveals dissociable learning-dependent plasticity mechanisms in the human brain

Experience and training have been shown to facilitate our ability to extract and discriminate meaningful patterns from cluttered environments. Yet, the human brain mechanisms that mediate our ability to learn by suppressing noisy and irrelevant signals remain largely unknown. To test the role of suppression in perceptual learning, we combine fMRI with MR Spectroscopy measurements of GABA, as fMRI alone does not allow us to discern inhibitory vs. excitatory mechanisms. Our results demonstrate that task-dependent GABAergic inhibition relates to functional brain plasticity and behavioral improvement. Specifically, GABAergic inhibition in the occipito-temporal cortex relates to dissociable learning mechanisms: decreased GABA for noise filtering, while increased GABA for feature template retuning. Perturbing cortical excitability during training with tDCs alters performance in a task-specific manner, providing evidence for a direct link between suppression and behavioral improvement. Our findings propose dissociable GABAergic mechanisms that optimize our ability to make perceptual decisions through training.