scholarly journals A Machine Learning Method Based on 3D Local Surface Representation for Recognizing the Inscriptions on Ancient Stele

2021 ◽  
Vol 11 (12) ◽  
pp. 5758
Author(s):  
Sheriff Murtala ◽  
Ye-Chan Choi ◽  
Kang-Sun Choi
Keyword(s):  
Reference Point ◽  
Surface Characteristics ◽  
Surface Region ◽  
Surface Point ◽  
Principal Curvatures ◽  
Local Surface ◽  
Background Region ◽  
K Nearest Neighbors ◽  
Class Labels ◽  
Better Than

It is challenging to extract reliefs from ancient steles due to their rough surfaces which contain relief-like noise such as dents and scratches. In this paper, we propose a method to segment relief region from 3D scanned ancient stele by exploiting local surface characteristics. For each surface point, four points that are apart from the reference point along the direction of the principal curvatures of the point are identified. The spin images of the reference point and the four relative points are concatenated to provide additional local surface information of the reference point. A random forest model is trained with the local surface features and thereafter, used to classify 3D surface point as relief or non-relief. To effectively distinguish relief from the degraded surface region containing relief-like noise, the model is trained using three-class labels consisting of relief, background, and degraded surface region. The initial three-class result obtained from the model is refined using the k-nearest neighbors algorithm, and finally, the degraded region is re-labeled to background region. Experimental results show that the proposed method performed better than the state-of-the-art, SVM-based method with a margin of 0.68%, 3.53%, 2.25%, and 2.36%, in accuracy, precision, F1 score, and SIRI, respectively. When compared with the height- and curvature-based methods, the proposed method outperforms these existing methods with an accuracy, precision, F1 score, and SIRI of over 4%, 20%, 11%, and 12%, respectively.

scholarly journals Variety Identification of Orchids Using Fourier Transform Infrared Spectroscopy Combined with Stacked Sparse Auto-Encoder

Molecules ◽  
2019 ◽  
Vol 24 (13) ◽  
pp. 2506 ◽  
Author(s):  
Yunfeng Chen ◽  
Yue Chen ◽  
Xuping Feng ◽  
Xufeng Yang ◽  
Jinnuo Zhang ◽  
...  
Keyword(s):  
Fourier Transform ◽  
Principal Component ◽  
Fourier Transform Infrared ◽  
Spectroscopic Technique ◽  
Variety Identification ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Discriminant Models ◽  
The Fourier Transform ◽  
Better Than

The feasibility of using the fourier transform infrared (FTIR) spectroscopic technique with a stacked sparse auto-encoder (SSAE) to identify orchid varieties was studied. Spectral data of 13 orchids varieties covering the spectral range of 4000–550 cm−1 were acquired to establish discriminant models and to select optimal spectral variables. K nearest neighbors (KNN), support vector machine (SVM), and SSAE models were built using full spectra. The SSAE model performed better than the KNN and SVM models and obtained a classification accuracy 99.4% in the calibration set and 97.9% in the prediction set. Then, three algorithms, principal component analysis loading (PCA-loading), competitive adaptive reweighted sampling (CARS), and stacked sparse auto-encoder guided backward (SSAE-GB), were used to select 39, 300, and 38 optimal wavenumbers, respectively. The KNN and SVM models were built based on optimal wavenumbers. Most of the optimal wavenumbers-based models performed slightly better than the all wavenumbers-based models. The performance of the SSAE-GB was better than the other two from the perspective of the accuracy of the discriminant models and the number of optimal wavenumbers. The results of this study showed that the FTIR spectroscopic technique combined with the SSAE algorithm could be adopted in the identification of the orchid varieties.

DS-kNN

2021 ◽  
Vol 15 (2) ◽  
pp. 131-144
Author(s):  
Redha Taguelmimt ◽  
Rachid Beghdad
Keyword(s):  
Intrusion Detection ◽  
False Positive ◽  
Detection Rate ◽  
Nearest Neighbors ◽  
The Other ◽  
Intrusion Detection Systems ◽  
K Nearest Neighbors ◽  
Detection Systems ◽  
Knn Classifier ◽  
Better Than

On one hand, there are many proposed intrusion detection systems (IDSs) in the literature. On the other hand, many studies try to deduce the important features that can best detect attacks. This paper presents a new and an easy-to-implement approach to intrusion detection, named distance sum-based k-nearest neighbors (DS-kNN), which is an improved version of k-NN classifier. Given a data sample to classify, DS-kNN computes the distance sum of the k-nearest neighbors of the data sample in each of the possible classes of the dataset. Then, the data sample is assigned to the class having the smallest sum. The experimental results show that the DS-kNN classifier performs better than the original k-NN algorithm in terms of accuracy, detection rate, false positive, and attacks classification. The authors mainly compare DS-kNN to CANN, but also to SVM, S-NDAE, and DBN. The obtained results also show that the approach is very competitive.

A test of prospect theory

2005 ◽  
Vol 21 (4) ◽  
pp. 511-516 ◽  
Author(s):  
David Feeny ◽  
Ken Eng
Keyword(s):  
Total Hip Arthroplasty ◽  
Prospect Theory ◽  
Reference Point ◽  
Standard Gamble ◽  
Health States ◽  
Current Health ◽  
Current State ◽  
Direction Opposite ◽  
Better Than ◽  
Utility Scores

Objectives: Prospect theory (PT) hypothesizes that people judge states relative to a reference point, usually assumed to be their current health. States better than the reference point are valued on a concave portion of the utility function; worse states are valued on a convex portion. Using prospectively collected utility scores, the objective is to test empirically implications of PT.Methods: Osteoarthritis (OA) patients undergoing total hip arthroplasty periodically provided standard gamble scores for three OA hypothetical states describing mild, moderate, and severe OA as well as their subjectively defined current state (SDCS). Our hypothesis was that most patients improved between the pre- and postsurgery assessments. According to PT, scores for hypothetical states previously > SDCS but now < SDCS should be lower at the postsurgery assessment.Results: Fourteen patients met the criteria for testing the hypothesis. Predictions were confirmed for 0 patients; there was no change or mixed results for 6 patients (42.9 percent); and scores moved in the direction opposite to that predicted by PT for 8 patients (57.1 percent).Conclusions: In general, the direction and magnitude of the changes in hypothetical-state scores do not conform to the predictions of PT.

scholarly journals Climate Fiction and the Ethics of Existentialism

2021 ◽  
Vol 12 (1) ◽  
pp. 167-178
Author(s):  
Jens Kramshøj Flinker
Keyword(s):  
Climate Change ◽  
Reference Point ◽  
Narrative Ethics ◽  
Ethical Standards ◽  
Reading Practice ◽  
Ethical System ◽  
Positive Side ◽  
Climate Fiction ◽  
Better Than

        The purpose of this article is twofold: Existentialism as a philosophical discipline and ethical reference point seems to be a rare guest in ecocriticism. Based on an analysis of Lyra Koli's climate fiction Allting Växer (2018) this article argues that existentialism has something to offer to the ecocritical field. I make use of an econarratological approach, drawing on James Phelan's narrative ethics. Thus, I emphasize the article's second purpose, as narrative ethics is about reconstructing narratives own ethical standards rather than the reader bringing a prefabricated ethical system to the narrative. This reading practice can help to question the idea that some ethical and philosophical standards are better than others within ecocriticism—by encouraging scholars in ecocriticism to relate to what existentialism has to do with climate change in this specific case. In continuation of my analysis, I argue that Allting Växer is pointing at a positive side of existentialist concepts such as anxiety or anguish, that is, that there is a reflecting and changing potential in these moods or experiences. This existentialist framework contrasts with the interpretation of "Anthropocene disorder" (Timothy Clark) as the only outcome when confronting the complexity of the Anthropocene.

scholarly journals Validation and Comparison of MODIS C6.1 and C6 Aerosol Products over Beijing, China

2018 ◽  
Vol 10 (12) ◽  
pp. 2021 ◽  
Author(s):  
Xinpeng Tian ◽  
Qiang Liu ◽  
Xiuhong Li ◽  
Jing Wei
Keyword(s):  
Optical Properties ◽  
Urban Areas ◽  
Surface Characteristics ◽  
Complex Surface ◽  
Deep Blue ◽  
Spatial Coverage ◽  
Moderate Resolution ◽  
Moderate Resolution Imaging Spectroradiometer ◽  
Beijing China ◽  
Better Than

The operational Moderate Resolution Imaging Spectroradiometer (MODIS) Aerosol Products (APs) have provided long-term and wide-spatial-coverage aerosol optical properties across the globe, such as aerosol optical depth (AOD). However, the performance of the latest Collection 6.1 (C6.1) of MODIS APs is still unclear over urban areas that feature complex surface characteristics and aerosol models. The aim of this study was to validate and compare the performance of the MODIS C6.1 and C6 APs (MxD04, x = O for Terra, x = Y for Aqua) over Beijing, China. The results of the Dark Target (DT) and Deep Blue (DB) algorithms were validated against Aerosol Robotic Network (AERONET) ground-based observations at local sites. The retrieval uncertainties and accuracies were evaluated using the expected error (EE: ±0.05 + 15%) and the root-mean-square error (RMSE). It was found that the MODIS C6.1 DT products performed better than the C6 DT products, with a greater percentage (by about 13%–14%) of the retrievals falling within the EE. However, the DT retrievals collected from two collections were significantly overestimated in the Beijing region, with more than 64% and 48% of the samples falling above the EE for the Terra and Aqua satellites, respectively. The MODIS C6.1 DB products performed similarly to the C6 DB products, with 70%–73% of the retrievals matching within the EE and estimation uncertainties. Moreover, the DB algorithm performed much better than DT algorithm over urban areas, especially in winter where abundant missing pixels were found in DT products. To investigate the effects of factors on AOD retrievals, the variability in the assumed surface reflectance and the main optical properties applied in DT and DB algorithms are also analyzed.

scholarly journals You can’t be better than me: The role of the reference point in modulating people’s pursuit of wealth

2013 ◽  
Vol 37 ◽  
pp. 65-76 ◽  
Author(s):  
Andrea Pittarello ◽  
Enrico Rubaltelli ◽  
Rino Rumiati
Keyword(s):  
Reference Point ◽  
Better Than

Geometric Features Sensitive Mesh Segmentation Orient to Patch-Based Fitting

2011 ◽  
Vol 130-134 ◽  
pp. 2081-2085
Author(s):  
Xiang Jun Zhao ◽  
Mei Lu ◽  
Jian Hua Gong
Keyword(s):  
Optimization Technique ◽  
Surface Region ◽  
Surface Structures ◽  
Mesh Segmentation ◽  
Geometric Features ◽  
Principal Curvatures ◽  
Shape Approximation ◽  
Rotating Surface ◽  
Fitting In ◽  
Novel Algorithm

Segmenting meshes into natural regions is useful for patch-based mesh fitting. In this paper, we present a novel algorithm for segmenting meshes into characteristic patches and provide a corresponding geometric proxy for each patch. We extend the powerful optimization technique of variational shape approximation by allowing for several different primitives to represent the geometric proxy of a surface region. Our method has the particular advantage of robustness. As the principal curvatures of the surfaces become more equal, the returned results are become closer to the surfaces of geometry primitives, i.e. planes, cylinders, or cones, or rotating surface which are the most common patch types in the reverse engineering. The expected result that we recover surface structures more robustly and thus get better approximations, is validated and demonstrated on a number of examples.

scholarly journals Javanese Character Feature Extraction Based on Shape Energy

2017 ◽  
Vol 5 (1) ◽  
pp. 154-169 ◽  
Author(s):  
Galih Hendra Wibowo ◽  
Riyanto Sigit ◽  
Aliridho Barakbah
Keyword(s):  
Feature Extraction ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Performance Test ◽  
Test Results ◽  
K Nearest Neighbors ◽  
Method Performance ◽  
Feature Extraction Method ◽  
Character Feature ◽  
Better Than

Javanese character is one of Indonesia's noble culture, especially in Java. However, the number of Javanese people who are able to read the letter has decreased so that there need to be conservation efforts in the form of a system that is able to recognize the characters. One solution to these problem lies in Optical Character Recognition (OCR) studies, where one of its heaviest points lies in feature extraction which is to distinguish each character. Shape Energy is one of feature extraction method with the basic idea of how the character can be distinguished simply through its skeleton. Based on the basic idea, then the development of feature extraction is done based on its components to produce an angular histogram with various variations of multiples angle. Furthermore, the performance test of this method and its basic method is performed in Javanese character dataset, which has been obtained from various images, is 240 data with 19 labels by using K-Nearest Neighbors as its classification method. Performance values were obtained based on the accuracy which is generated through the Cross-Validation process of 80.83% in the angular histogram with an angle of 20 degrees, 23% better than Shape Energy. In addition, other test results show that this method is able to recognize rotated character with the lowest performance value of 86% at 180-degree rotation and the highest performance value of 96.97% at 90-degree rotation. It can be concluded that this method is able to improve the performance of Shape Energy in the form of recognition of Javanese characters as well as robust to the rotation.

Partial retrieval of CAD models based on local surface region decomposition

2013 ◽  
Vol 45 (11) ◽  
pp. 1239-1252 ◽  
Author(s):  
Songqiao Tao ◽  
Zhengdong Huang ◽  
Lujie Ma ◽  
Shunsheng Guo ◽  
Shuting Wang ◽  
...  
Keyword(s):  
Surface Region ◽  
Local Surface ◽  
Cad Models ◽  
Partial Retrieval

scholarly journals A Novel Categorical Data Attribute Split Technique in Decision Tree Learning

2020 ◽  
Vol 9 (1) ◽  
pp. 1607-1612
Keyword(s):  
Decision Tree ◽  
Categorical Data ◽  
Ease Of Use ◽  
Decision Tree Learning ◽  
Current Node ◽  
Categorical Attributes ◽  
Categorical Attribute ◽  
A New Technique ◽  
Class Labels ◽  
Better Than

A new technique is proposed for splitting categorical data during the process of decision tree learning. This technique is based on the class probability representations and manipulations of the class labels corresponding to the distinct values of categorical attributes. For each categorical attribute aggregate similarity in terms of class probabilities is computed and then based on the highest aggregated similarity measure the best attribute is selected and then the data in the current node of the decision tree is divided into the number of sub sets equal to the number of distinct values of the best categorical split attribute. Many experiments are conducted using this proposed method and the results have shown that the proposed technique is better than many other competitive methods in terms of efficiency, ease of use, understanding, and output results and it will be useful in many modern applications.

Sign in / Sign up

Export Citation Format

Share Document