The Research on Rejoining of the Oracle Bone Rubbings Based on Curve Matching

2021 ◽  
Vol 20 (6) ◽  
pp. 1-17
Author(s):  
Yaolin Tian ◽  
Weize Gao ◽  
Xuxing Liu ◽  
Shanxiong Chen ◽  
Bofeng Mo
Keyword(s):  
Good Effect ◽  
Feature Descriptor ◽  
Curve Matching ◽  
Accuracy Rate ◽  
Search Range ◽  
Average Accuracy ◽  
Image Recommendation ◽  
Accuracy Of Results ◽  
Detail Loss ◽  
Target Matching

The rejoining of oracle bone rubbings is a fundamental topic for oracle research. However, it is a tough task to reassemble severely broken oracle bone rubbings because of detail loss in manual labeling, the great time consumption of rejoining, and the low accuracy of results. To overcome the challenges, we introduce a novel CFDA&CAP algorithm that consists of the Curve Fitting Degree Analysis (CFDA) algorithm and the Correlation Analysis of Pearson (CAP) algorithm. First, the orthogonalization system is constructed to extract local features based on the curve features analysis. Second, the global feature descriptor is depicted by using coordinate points sequences. Third, we screen candidate curves based on the features as well as the CFDA algorithm, so the search range of the candidates is narrowed down. Finally, image recommendation libraries for target curves are generated by adopting the CAP algorithm, and the rank for each target matching curve generates simultaneously for result evaluation. With experiments, the proposed method shows a good effect in rejoining oracle bone rubbings automatically: (1) it improves the average accuracy rate of curve matching up to 84%, and (2) for a low-resource task, the accuracy of our method has 25% higher accuracy than that of other methods.

scholarly journals Optimalisasi Prediksi Biaya Komisi Penjualan Mobil Menggunakan Metode Monte Carlo

KOMTEKINFO ◽  
2020 ◽  
Vol 7 (2) ◽  
pp. 140-151
Author(s):  
Zupri Henra Hartomi ◽  
Yuhandri ◽  
Julius Santony
Keyword(s):  
Decision Making ◽  
Monte Carlo ◽  
Accuracy Rate ◽  
Sales Data ◽  
For Profit ◽  
Marketing Performance ◽  
Potential Market ◽  
Average Accuracy ◽  
Car Sales ◽  
The Cost

Sales are the main source of income for every company. Every company in marketing a product, should control the potential market for profit. Predicting the number of sales is important in analyzing sales progress. This study aims to assist companies in predicting car sales and car commission cost budgets based on sales data from the previous year.The data used in the study are car sales data for 2017 and 2018 in the Arengka Automall Pekanbaru Showroom (SAA Pekanbaru).Data processing in research uses the Monte Carlo method.The results of tests that have been carried out state that car sales by Marketing within 1 year resulted in an average accuracy rate of 94% and sales commission fee of Rp 411.000.000.From these results in accordance with calculations performed manually so that with a large accuracy value, the application of the simulation using this Monte Carlo Method feasible to be applied by companies in future decision making to plan the estimated budget for the cost of a car sales commission and as a means to assess Marketing performance at SAA Pekanbaru.

scholarly journals MalDeep: A Deep Learning Classification Framework against Malware Variants Based on Texture Visualization

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Yuntao Zhao ◽  
Chunyu Xu ◽  
Bo Bo ◽  
Yongxin Feng
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Feature Space ◽  
Image Texture ◽  
Accuracy Rate ◽  
Texture Representation ◽  
Malware Classification ◽  
Classification Framework ◽  
Average Accuracy ◽  
New Feature

The increasing sophistication of malware variants such as encryption, polymorphism, and obfuscation calls for the new detection and classification technology. In this paper, MalDeep, a novel malware classification framework of deep learning based on texture visualization, is proposed against malicious variants. Through code mapping, texture partitioning, and texture extracting, we can study malware classification in a new feature space of image texture representation without decryption and disassembly. Furthermore, we built a malware classifier on convolutional neural network with two convolutional layers, two downsampling layers, and many full connection layers. We adopt the dataset, from Microsoft Malware Classification Challenge including 9 categories of malware families and 10868 variant samples, to train the model. The experiment results show that the established MalDeep has a higher accuracy rate for malware classification. In particular, for some backdoor families, the classification accuracy of the model reaches over 99%. Moreover, compared with other main antivirus software, MalDeep also outperforms others in the average accuracy for the variants from different families.

Developing and testing SCoP – a visual hash scheme

2014 ◽  
Vol 22 (4) ◽  
pp. 382-392
Author(s):  
M. Maina Olembo ◽  
Timo Kilian ◽  
Simon Stockhardt ◽  
Andreas Hülsing ◽  
Melanie Volkamer
Keyword(s):  
Design Methodology ◽  
Electronic Voting ◽  
Use Case ◽  
Accuracy Rate ◽  
Content Type ◽  
Average Accuracy ◽  
Follow Up Studies ◽  
Collision Attacks ◽  
Accuracy Rates

Purpose – The purpose of this study was to develop and test SCoP. Users find comparing long meaningless strings of alphanumeric characters difficult. While visual hashes – where users compare images rather than strings – have been proposed as an alternative, people are unable to sufficiently distinguish more than 30 bits, which does not provide adequate security against collision attacks. Our goal is to improve the situation. Design/methodology/approach – A visual hash scheme was developed using shapes, colours, patterns and position parameters. It was evaluated in a series of pilot user studies and improved iteratively, leading to SCoP, which encodes 60 distinguishable bits. We tested SCoP further in two follow-up studies, simulating verifying in remote electronic voting and https certificate validation. Findings – Participants attained an average accuracy rate of 97 per cent with SCoP when comparing two visual hash images, one placed above the other. From the follow-up studies, SCoP was seen to be more promising for the https certificate validation use case, with direct image comparison, while a low average accuracy rate in simulating verifiability in remote electronic voting limits its applicability in an image-recall use case. Research limitations/implications – Participants achieved high accuracy rates in unrealistic situations, where the images appeared on the screen at the same time and in the same size. Studies in more realistic situations are therefore necessary. Originality/value – We identify a visual hash scheme encoding a higher number of distinguishable bits than previously reported in literature, and extend the testing to realistic scenarios.

scholarly journals DWCA-YOLOv5: An Improve Single Shot Detector for Safety Helmet Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhang Jin ◽  
Peiqi Qu ◽  
Cheng Sun ◽  
Meng Luo ◽  
Yan Gui ◽  
...  
Keyword(s):  
Information Dissemination ◽  
Detection Efficiency ◽  
A Priori ◽  
Detection Methods ◽  
Single Shot ◽  
Accuracy Rate ◽  
Average Accuracy ◽  
Head Detection ◽  
Matching Degree ◽  
Complex Construction

Aiming at solving the problem that the detection methods used in the existing helmet detection research has low detection efficiency and the cumulative error influences accuracy, a new algorithm for improving YOLOv5 helmet wearing detection is proposed. First of all, we use the K -means++ algorithm to improve the size matching degree of the a priori anchor box; secondly, integrate the Depthwise Coordinate Attention (DWCA) mechanism in the backbone network, so that the network can learn the weight of each channel independently and enhance the information dissemination between features, thereby strengthening the network’s ability to distinguish foreground and background. The experimental results show as follows: in the self-made safety helmet wearing detection dataset, the average accuracy rate reached 95.9%, the average accuracy of the helmet detection reached 96.5%, and the average accuracy of the worker’s head detection reached 95.2%. Making a comparison with the YOLOv5 algorithm, our model has a 3% increase in the average accuracy of helmet detection, which is in line with the accuracy requirements of helmet wearing detection in complex construction scenarios.

scholarly journals Prediksi Pajak Mineral Non Logam dan Batuan dengan Metode Monte Carlo

2019 ◽  
pp. 32-37
Author(s):  
Julius Santony
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Regional Government ◽  
Test Results ◽  
Accuracy Rate ◽  
Work Plan ◽  
Tax Revenues ◽  
Average Accuracy ◽  
District Government

Regional government in Indonesia annually sets a target for tax revenues of non-metallic minerals and rocks. Setting targets is very important as a guideline in preparing the current year's budget work plan. So far, the target of non-metal mineral and rock tax revenues has been prepared based on a joint agreement between the regional government and the regional legislature. The prediction of non-metal mineral and rock tax revenues using Monte Carlo simulation can be a solution to predict the next few years. This prediction uses data between 2009 - 2018 taken from the tax and retribution management body one of the districts in Indonesia. Testing the results of predictions is done by comparing the results of predictions with data from 2016 - 2018. The test results show that the average accuracy rate reaches 82.05%. So this study greatly helped the district government in setting the target for the acceptance of non-metal minerals and rock taxes.

scholarly journals ECG Arrhythmia Time Series Classification Using 1D Convolution –LSTM Neural Networks

2021 ◽  
Vol 10 (3) ◽  
pp. 1985-1990
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Data Augmentation ◽  
Discrete Wavelet ◽  
Learning Approaches ◽  
Time Series Classification ◽  
Measuring Device ◽  
Average Accuracy ◽  
Accuracy Of Results ◽  
Ecg Arrhythmia

An electrocardiogram (ECG) can be dependablyused as a measuring device to monitor cardiovascular function. The abnormal heartbeat appears in the ECG pattern and these abnormal signals are called arrhythmias. Classification and automatic arrhythmia signals can provide a faster and more accurate result. Several machine learning approaches have been applied to enhance the accuracy of results and increase the speed and robustness of models. This paper proposes a method based on Time-series Classification using deep Convolutional -LSTM neural networks and Discrete Wavelet Transform to classify 4 different types of Arrhythmia in the MIT-BIH Database. According to the results, the suggested method gives predictions with an average accuracy of 97% without needing to do feature extraction or data augmentation.

scholarly journals A Mean-Shift-Based Feature Descriptor for Wide Baseline Stereo Matching

2015 ◽  
Vol 2015 ◽  
pp. 1-14 ◽  
Author(s):  
Yiwen Dou ◽  
Kuangrong Hao ◽  
Yongsheng Ding ◽  
Min Mao
Keyword(s):  
Cross Correlation ◽  
Stereo Matching ◽  
Mean Shift ◽  
Depth Image ◽  
Feature Descriptor ◽  
Feature Points ◽  
Accuracy Rate ◽  
Feature Description ◽  
Feature Scale ◽  
Stable Feature

We propose a novel Mean-Shift-based building approach in wide baseline. Initially, scale-invariance feature transform (SIFT) approach is used to extract relatively stable feature points. As to each matching SIFT feature point, it needs a reasonable neighborhood range so as to choose feature points set. Subsequently, in view of selecting repeatable and high robust feature points, Mean-Shift controls corresponding feature scale. At last, our approach is employed to depth image acquirement in wide baseline and Graph Cut algorithm optimizes disparity information. Compared with the existing methods such as SIFT, speeded up robust feature (SURF), and normalized cross-correlation (NCC), the presented approach has the advantages of higher robustness and accuracy rate. Experimental results on low resolution image and weak feature description in wide baseline confirm the validity of our approach.

Test Of Vowels In Speech Recognition Using Continuous Density Hidden Markov Model And Development Of Phonetically Balanced-Words In The Filipino Language

2014 ◽  
Vol 1 (1) ◽  
pp. 531-536
Author(s):  
Arnel C. Fajardo ◽  
Yoon-joong Kim
Keyword(s):  
Speech Recognition ◽  
Language Processing ◽  
Word List ◽  
Accuracy Rate ◽  
Continuous Density ◽  
Average Accuracy ◽  
Speaker Independent ◽  
Independent Test ◽  
Final Output ◽  
Mel Frequency Cepstral Coefficient

AbstractAn Automatic Speech Recognition (ASR) converts the speech signals into words. The recognized words can be the final output or it can be an input for a natural language processing. In this paper, vowel recognizer using Continuous density HMM and Mel-Frequency Cepstral Coefficient (MFCC) were used for feature extraction for its development, and phonetically balanced words (PBW) in Filipino were developed. Thus, this study is a preparation for Filipino Language ASR using HMM. For vowel recognizer, forty speakers were trained (20 male and 20 female speakers). An average accuracy rate of 94.5% was achieved for speaker-dependent test and 90.8% for speaker independent test. For PBW, 2 word lists were developed consisting of 257 words for the 2-syllable Filipino PBW word list and 212 words for the 3-syllable Filipino PBW word list.

scholarly journals A deep learning technique-based automatic monitoring method for experimental urban road inundation

2021 ◽  
Author(s):  
Hao Han ◽  
Jingming Hou ◽  
Ganggang Bai ◽  
Bingyao Li ◽  
Tian Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Automatic Monitoring ◽  
Water Area ◽  
Detection Accuracy ◽  
Accuracy Rate ◽  
Validation Data ◽  
Monitoring Method ◽  
Urban Flood ◽  
Urban Road ◽  
Average Accuracy

Abstract Reports indicate that high-cost, insecurity, and difficulty in complex environments hinder the traditional urban road inundation monitoring approach. This work proposed an automatic monitoring method for experimental urban road inundation based on the YOLOv2 deep learning framework. The proposed method is an affordable, secure, with high accuracy rates in urban road inundation evaluation. The automatic detection of experimental urban road inundation was carried out under both dry and wet conditions on roads in the study area with a scale of few m2. The validation average accuracy rate of the model was high with 90.1% inundation detection, while its training average accuracy rate was 96.1%. This indicated that the model has effective performance with high detection accuracy and recognition ability. Besides, the inundated water area of the experimental inundation region and the real road inundation region in the images was computed, showing that the relative errors of the measured area and the computed area were less than 20%. The results indicated that the proposed method can provide reliable inundation area evaluation. Therefore, our findings provide an effective guide in the management of urban floods and urban flood-warning, as well as systematical validation data for hydrologic and hydrodynamic models.

Finger Spelling in Air System for Deaf and Dumb

2018 ◽  
Vol 9 (1) ◽  
pp. 28-44
Author(s):  
Urmila Shrawankar ◽  
Shruti Gedam
Keyword(s):  
Real Time ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Human Interaction ◽  
Finger Movements ◽  
Accuracy Rate ◽  
Optical Character ◽  
Average Accuracy ◽  
Bright Color ◽  
Natural Way

Finger spelling in air helps user to operate a computer in order to make human interaction easier and faster than keyboard and touch screen. This article presents a real-time video based system which recognizes the English alphabets and words written in air using finger movements only. Optical Character Recognition (OCR) is used for recognition which is trained using more than 500 various shapes and styles of all alphabets. This system works with different light situations and adapts automatically to various changing conditions; and gives a natural way of communicating where no extra hardware is used other than system camera and a bright color tape. Also, this system does not restrict writing speed and color of tape. Overall, this system achieves an average accuracy rate of character recognition for all alphabets of 94.074%. It is concluded that this system is very useful for communication with deaf and dumb people.

Sign in / Sign up

Export Citation Format

Share Document