scholarly journals Metric Embedding Learning on Multi-Directional Projections

Algorithms ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 133 ◽  
Author(s):  
Gábor Kertész

Image based instance recognition is a difficult problem, in some cases even for the human eye. While latest developments in computer vision—mostly driven by deep learning—have shown that high performance models for classification or categorization can be engineered, the problem of discriminating similar objects with a low number of samples remain challenging. Advances from multi-class classification are applied for object matching problems, as the feature extraction techniques are the same; nature-inspired multi-layered convolutional nets learn the representations, and the output of such a model maps them to a multidimensional encoding space. A metric based loss brings same instance embeddings close to each other. While these solutions achieve high classification performance, low efficiency is caused by memory cost of high parameter number, which is in a relationship with input image size. Upon shrinking the input, the model requires less trainable parameters, while performance decreases. This drawback is tackled by using compressed feature extraction, e.g., projections. In this paper, a multi-directional image projection transformation with fixed vector lengths (MDIPFL) is applied for one-shot recognition tasks, trained on Siamese and Triplet architectures. Results show, that MDIPFL based approach achieves decent performance, despite of the significantly lower number of parameters.

2021 ◽  
Vol 8 (3) ◽  
pp. 533
Author(s):  
Budi Nugroho ◽  
Eva Yulia Puspaningrum

<p class="Abstrak">Saat ini banyak dikembangkan proses pendeteksian pneumonia berdasarkan citra paru-paru dari hasil foto rontgen (x-ray), sebagaimana juga dilakukan pada penelitian ini. Metode yang digunakan adalah <em>Convolutional Neural Network</em> (CNN) dengan arsitektur yang berbeda dengan sejumlah penelitian sebelumnya. Selain itu, penelitian ini juga memodifikasi model CNN dimana metode <em>Extreme Learning Machine</em> (ELM) digunakan pada bagian klasifikasi, yang kemudian disebut CNN-ELM. Dataset untuk uji coba menggunakan kumpulan citra paru-paru hasil foto rontgen pada Kaggle yang terdiri atas 1.583 citra normal dan 4.237 citra pneumonia. Citra asal pada dataset kaggle ini bervariasi, tetapi hampir semua diatas ukuran 1000x1000 piksel. Ukuran citra yang besar ini dapat membuat pemrosesan klasifikasi kurang efektif, sehingga mesin CNN biasanya memodifikasi ukuran citra menjadi lebih kecil. Pada penelitian ini, pengujian dilakukan dengan variasi ukuran citra input, untuk mengetahui pengaruhnya terhadap kinerja mesin pengklasifikasi. Hasil uji coba menunjukkan bahwa ukuran citra input berpengaruh besar terhadap kinerja klasifikasi pneumonia, baik klasifikasi yang menggunakan metode CNN maupun CNN-ELM. Pada ukuran citra input 200x200, metode CNN dan CNN-ELM menunjukkan kinerja paling tinggi. Jika kinerja kedua metode itu dibandingkan, maka Metode CNN-ELM menunjukkan kinerja yang lebih baik daripada CNN pada semua skenario uji coba. Pada kondisi kinerja paling tinggi, selisih akurasi antara metode CNN-ELM dan CNN mencapai 8,81% dan selisih F1 Score mencapai 0,0729. Hasil penelitian ini memberikan informasi penting bahwa ukuran citra input memiliki pengaruh besar terhadap kinerja klasifikasi pneumonia, baik klasifikasi menggunakan metode CNN maupun CNN-ELM. Selain itu, pada semua ukuran citra input yang digunakan untuk proses klasifikasi, metode CNN-ELM menunjukkan kinerja yang lebih baik daripada metode CNN.</p><p class="Abstrak"> </p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>This research developed a pneumonia detection machine based on the lungs' images from X-rays (x-rays). The method used is the Convolutional Neural Network (CNN) with a different architecture from some previous research. Also, the CNN model is modified, where the classification process uses the Extreme Learning Machine (ELM), which is then called the CNN-ELM method. The empirical experiments dataset used a collection of lung x-ray images on Kaggle consisting of 1,583 normal images and 4,237 pneumonia images. The original image's size on the Kaggle dataset varies, but almost all of the images are more than 1000x1000 pixels. For classification processing to be more effective, CNN machines usually use reduced-size images. In this research, experiments were carried out with various input image sizes to determine the effect on the classifier's performance. The experimental results show that the input images' size has a significant effect on the classification performance of pneumonia, both the CNN and CNN-ELM classification methods. At the 200x200 input image size, the CNN and CNN-ELM methods showed the highest performance. If the two methods' performance is compared, then the CNN-ELM Method shows better performance than CNN in all test scenarios. The difference in accuracy between the CNN-ELM and CNN methods reaches 8.81% at the highest performance conditions, and the difference in F1-Score reaches 0.0729. This research provides important information that the size of the input image has a major influence on the classification performance of pneumonia, both classification using the CNN and CNN-ELM methods. Also, on all input image sizes used for the classification process, the CNN-ELM method shows better performance than the CNN method.</em></p>


2005 ◽  
Vol 14 (05) ◽  
pp. 895-921
Author(s):  
ISA SERVAN UZUN ◽  
ABBES AMIRA

Signal and image processing applications require high computational power with the ability to experiment different algorithms involving matrix transforms. Reconfigurable hardware devices in the form of Field Programmable Gate Arrays (FPGAs) have been proposed to obtain high performance at an economical price. However, the users must program FPGAs at a very low level and must have a detailed knowledge of the architecture of the device being used. In trying to reconcile the dual requirements of high performance and the ease of development, this paper reports the design and realization of the Fast Fourier Transforms (FFTs) using a FPGA-based environment, which enables system designer to meet different system requirements (i.e., chip area, speed, memory, etc.) for a range of signal processing and imaging applications. The use of the proposed environment has been proven by the developing a high-level FPGA-based parametrizable image processing system for frequency-domain filtering application. The system achieves real-time image filtering performance exceeding those of currently available solutions by an order of magnitude in frame rate and input image size.


2012 ◽  
Vol 433-440 ◽  
pp. 4468-4474
Author(s):  
Qiang Zheng

The design of exact single pattern string matching algorithm with high performance is the basis of all string matching problems. To overcome the defects of low efficiency of pattern matching, this paper improves one of the fastest exact single pattern matching algorithms known on English text, which is SBNDM2。The simplest form of the BNDM core loop is obtained, in which there are only 5 instructions per-character read by amending the relationship between position in the pattern and bit in the bit mask. And a cross-border protection method is added to the algorithm in order to reduce the cost of cross-border inspection. Two algorithms named S2BNDM and S2BNDM′ are presented. The experimental results indicate that both S2BNDM and S2BNDM′are faster than SBNDM2 in any case.


2021 ◽  
Author(s):  
Francisco J. Castellanos ◽  
Jose J. Valero-Mas ◽  
Jorge Calvo-Zaragoza

AbstractThe k-nearest neighbor (kNN) rule is one of the best-known distance-based classifiers, and is usually associated with high performance and versatility as it requires only the definition of a dissimilarity measure. Nevertheless, kNN is also coupled with low-efficiency levels since, for each new query, the algorithm must carry out an exhaustive search of the training data, and this drawback is much more relevant when considering complex structural representations, such as graphs, trees or strings, owing to the cost of the dissimilarity metrics. This issue has generally been tackled through the use of data reduction (DR) techniques, which reduce the size of the reference set, but the complexity of structural data has historically limited their application in the aforementioned scenarios. A DR algorithm denominated as reduction through homogeneous clusters (RHC) has recently been adapted to string representations but as obtaining the exact median value of a set of string data is known to be computationally difficult, its authors resorted to computing the set-median value. Under the premise that a more exact median value may be beneficial in this context, we, therefore, present a new adaptation of the RHC algorithm for string data, in which an approximate median computation is carried out. The results obtained show significant improvements when compared to those of the set-median version of the algorithm, in terms of both classification performance and reduction rates.


2020 ◽  
Author(s):  
Pengbo Han ◽  
Zeng Xu ◽  
Chengwei Lin ◽  
Dongge Ma ◽  
Anjun Qin ◽  
...  

Deep blue organic-emitting fluorophores are crucial for application in white lighting and full color flat-panel displays but emitters with high color quality and efficiency are rare. Herein, novel deep blue AIE luminogens (AIEgens) with various donor units and an acceptor of cyano substituted tetraphenylbenzene (TPB) cores were developed and used to fabricate non-doped deep blue and hybrid white organic light-emitting diodes (OLEDs). Benefiting from its high emission efficiency and high proportion of horizontally oriented dipoles in the film state, the non-doped deep blue device based on CN-TPB-TPA realized a maximum external quantum efficiency 7.27%, with a low efficiency roll-off and CIE coordinates of (0.15, 0.08). Moreover, efficient two-color hybrid warm white OLEDs (CIE<sub>x,y</sub> = 0.43, 0.45) were achieved using CN-TPB-TPA as the blue-emitting layer and phosphor doped host, which realized maximum current, power, external quantum efficiencies 58.0 cd A<sup>-1</sup>, 60.7 lm W<sup>-1</sup> and 19.1%, respectively. This work provides a general strategy to achieve high performance, stable deep blue and hybrid white OLEDs by construction of AIEgens with excellent horizontal orientation


Author(s):  
Farrikh Alzami ◽  
Erika Devi Udayanti ◽  
Dwi Puji Prabowo ◽  
Rama Aria Megantara

Sentiment analysis in terms of polarity classification is very important in everyday life, with the existence of polarity, many people can find out whether the respected document has positive or negative sentiment so that it can help in choosing and making decisions. Sentiment analysis usually done manually. Therefore, an automatic sentiment analysis classification process is needed. However, it is rare to find studies that discuss extraction features and which learning models are suitable for unstructured sentiment analysis types with the Amazon food review case. This research explores some extraction features such as Word Bags, TF-IDF, Word2Vector, as well as a combination of TF-IDF and Word2Vector with several machine learning models such as Random Forest, SVM, KNN and Naïve Bayes to find out a combination of feature extraction and learning models that can help add variety to the analysis of polarity sentiments. By assisting with document preparation such as html tags and punctuation and special characters, using snowball stemming, TF-IDF results obtained with SVM are suitable for obtaining a polarity classification in unstructured sentiment analysis for the case of Amazon food review with a performance result of 87,3 percent.


Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 574
Author(s):  
Gennaro Tartarisco ◽  
Giovanni Cicceri ◽  
Davide Di Pietro ◽  
Elisa Leonardi ◽  
Stefania Aiello ◽  
...  

In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM–recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.


Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 991
Author(s):  
Yuta Nakahara ◽  
Toshiyasu Matsushima

In information theory, lossless compression of general data is based on an explicit assumption of a stochastic generative model on target data. However, in lossless image compression, researchers have mainly focused on the coding procedure that outputs the coded sequence from the input image, and the assumption of the stochastic generative model is implicit. In these studies, there is a difficulty in discussing the difference between the expected code length and the entropy of the stochastic generative model. We solve this difficulty for a class of images, in which they have non-stationarity among segments. In this paper, we propose a novel stochastic generative model of images by redefining the implicit stochastic generative model in a previous coding procedure. Our model is based on the quadtree so that it effectively represents the variable block size segmentation of images. Then, we construct the Bayes code optimal for the proposed stochastic generative model. It requires the summation of all possible quadtrees weighted by their posterior. In general, its computational cost increases exponentially for the image size. However, we introduce an efficient algorithm to calculate it in the polynomial order of the image size without loss of optimality. As a result, the derived algorithm has a better average coding rate than that of JBIG.


2021 ◽  
Vol 192 ◽  
pp. 109398
Author(s):  
Guan-Yu Ding ◽  
Chun-Xiu Zang ◽  
Han Zhang ◽  
Zhong-Min Su ◽  
Guang-Fu Li ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document