scholarly journals Unsupervised Clustering of Hyperspectral Paper Data Using t-SNE

2020 ◽  
Vol 6 (5) ◽  
pp. 29
Author(s):  
Binu Melit Devassy ◽  
Sony George ◽  
Peter Nussbaum
Keyword(s):  
Imaging Systems ◽  
High Dimensional ◽  
Electromagnetic Spectrum ◽  
Discrimination Power ◽  
Vast Number ◽  
Clustering Quality ◽  
The Subject ◽  
Non Destructive

For a suspected forgery that involves the falsification of a document or its contents, the investigator will primarily analyze the document’s paper and ink in order to establish the authenticity of the subject under investigation. As a non-destructive and contactless technique, Hyperspectral Imaging (HSI) is gaining popularity in the field of forensic document analysis. HSI returns more information compared to conventional three channel imaging systems due to the vast number of narrowband images recorded across the electromagnetic spectrum. As a result, HSI can provide better classification results. In this publication, we present results of an approach known as the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm, which we have applied to HSI paper data analysis. Even though t-SNE has been widely accepted as a method for dimensionality reduction and visualization of high dimensional data, its usefulness has not yet been evaluated for the classification of paper data. In this research, we present a hyperspectral dataset of paper samples, and evaluate the clustering quality of the proposed method both visually and quantitatively. The t-SNE algorithm shows exceptional discrimination power when compared to traditional PCA with k-means clustering, in both visual and quantitative evaluations.

Ignorantia juris non excusat: The trial and the affirmation of the Italian legal thriller

2019 ◽  
Vol 53 (2) ◽  
pp. 532-543
Author(s):  
Francesco Bratos
Keyword(s):  
20Th Century ◽  
Literary Tradition ◽  
The Political ◽  
Literary Genre ◽  
Complex Relationship ◽  
Vast Number ◽  
Literary Movement ◽  
The Subject ◽  
Unique Style

The complex relationship between literature and law has been widely debated. Over the last 20 years, the judicial novel has been the subject of renewed consideration from critics. Numerous studies have pointed out how literary and judicial practices seem characterized by common methods of narrative organization and communication of experiences. Beyond the controversy on the classification of the judicial novel as literary genre, the representation of courtrooms has undeniably become one of the recurring tropes of the 20th-century novel. Within this multifaceted literary movement, the unique style of Italian judiciary literature warrants its articulation as a distinct genre. The working hypothesis of this article is that the political and cultural centrality acquired by the Italian Magistratura, as result of a longstanding confrontation with the political powers, is essential in studying the success of the Italian judiciary novel, together with the emergence of a vast number of jurist-writers. Analyzing specifically the work of the jurist-writer Gianrico Carofiglio, I will demonstrate how the Italian legal thriller transforms the representation of the trial, dealing with the literary tradition as well as with law’s own representation.

scholarly journals USING PROFESSIONAL CONTENT PROBLEMS IN THE MATHEMATICAL TRAINING PROCESS OF SPECIALISTS IN ECONOMIC SPECIALTIES

2017 ◽  
Vol 8 (17) ◽  
pp. 44
Author(s):  
О. М. Tokarchuk
Keyword(s):  
Teaching Methods ◽  
Training Process ◽  
Subject Field ◽  
Problem Book ◽  
Interdisciplinary Problems ◽  
Economic Profile ◽  
The Subject ◽  
Different Characteristics

The article deals with the problem of improving the quality of mathematical training of future specialists in economic specialties through the use of problems with professional content. The categorical apparatus of the research has been  revealed. The issues of classification of problems with professional content on the basis of different characteristics have been considered: according to educational purpose, teaching methods, time, etc. The characteristics of the problems with professional content have been specified. The functions that are fulfilled by such problems have been singled out: educational, developmental, up-bringing, control. The advantages of using problems with professional content in the process of mathematical training of economic specialties students of colleges have been revealed. Requirements for the selection, development and compilation of problems with professional content have been defined. The subject field of interdisciplinary problem book, developed for mathematical training of specialists in colleges of economic profile, has been presented.Key words: mathematical training, specialists in economic specialties, colleges, problems with professional content, interdisciplinary problems.

scholarly journals FEATURES OF DETERMINATION OF THE COST OF PLANTS CERTAIN KINDS WHEN CARRYING OUT FORENSIC MERCHANDISING EXAMINATIONS

2017 ◽  
Vol 17 ◽  
pp. 351-359
Author(s):  
О. S. Obolentseva-Krasivska
Keyword(s):  
Ornamental Plants ◽  
Biological Properties ◽  
Planting Material ◽  
The Subject ◽  
Definition Of ◽  
The Cost ◽  
Market Relations

Flowers, ornamental plants, planting material (saplings) and other plants with regard to which the market with possibility of carrying out independent adequate marketing was formed, are the subject of evaluation by the experts in field of forensic merchandising. With the development of the market and market relations such goods as flowers, planting material and others are increasingly encashed in the market of Ukraine and become the objects of forensic merchandising examinations and expert researches. Special feature of merchandising researches of the plant origin objects is the use of the comprehensive approach to the estimation of their quality and cost. Researches are carried out with the purpose of determination of properties, consumer value, conformity to standards and specifications of plants certain kinds. When studying a considerable variety of flower plants, one distinguishes scientific and industrial classifications. In merchandising flowers industrial classification of flower ornamental plants which provides distribution of flower plants to the separate groups similar on biological properties, the agricultural technician of cultivation and practical application in gardening is used. During carrying out merchandising examinations on an establishment of consumer properties of certain kinds plants, namely establishments organoleptic indicators of quality and quantity of flower decorative production given for research, the expert checks conformity of this production to requirements of normative and technical documents. Requirements to quality of flower production are normalised by standards depending on production kind – cutf lowers, pottery blossoming plants, pottery decorative sheet plants, sprouts of flower decorative production, planting material, seeds of flower ornamental plants. At carrying out merchandising researches of flower decorative production, plants and saplings it’s necessary for merchandising experts to pay special attention on definition of quality indicators and a grade of plants according to standards, and also to consider data concerning age of a plant, novelty of a grade and origin country of production.

scholarly journals An Improvement of Quality of the Rear Cover of Bearing Turbine with the use of Selected Methods

2019 ◽  
Vol 1 (1) ◽  
pp. 456-463
Author(s):  
Andrzej Pacana ◽  
Dominika Siwiec
Keyword(s):  
Current Approach ◽  
Ishikawa Diagram ◽  
Fluorescent Method ◽  
Control Actions ◽  
Wide Range ◽  
Unit Character ◽  
The Subject ◽  
Non Destructive ◽  
Made In

Abstract The analyses of the nonconformity of products are made in order to achieve the desired level of their quality. This is also the case in the analyzed enterprise located in south-eastern Poland. Due to production character in this enterprise to identify the incompatibilities of products the non-destructive tests are used. In the current approach to quality after identified the nonconformities the cause her arise were determined, it was noted in order to use by statistical analyzes. Unfortunately, no deeper qualitative analyzes were made which could specify the source of its creation. Therefore, it was considered that it is necessary to propose to use (near current actions according to non-destructive tests) the sequence of quality management instruments. In order to improve the quality control actions, the sequence of techniques which complement each other, i.e. non-destructive tests, Ishikawa diagram and 5Why method, was proposed. To demonstrate the effectiveness of the proposed sequence, the rear cover of the bearing turbine was selected as the subject of the analysis. The choice was conditioned by the unit character of production, which till now was discouraged a detailed analysis of sources of nonconformities. After analyzed the product with used the fluorescent method the nonconformities were identified on the rear cover of the bearing turbine, which was the porosity cluster. In order to identify the causes these nonconformities the Ishikawa diagram was drawn up. Next, the selected main causes (i.e. supplier of the product and nonconformities created during the production of the product) were analyzed the 5Why method in order to identify the source cause of the problem. In this case, it was the nonconformity material from the supplier. The proposed sequence, which uses the minimal resources let to show the wide range of information, which should be used to the improvement of quality. The presented the set of activities can be practised in each of the enterprises to analyze quality problems in order to identify the nonconformities and their causes.

scholarly journals Navel Orange Maturity Classification by Multispectral Indexes Based on Hyperspectral Diffuse Transmittance Imaging

2017 ◽  
Vol 2017 ◽  
pp. 1-7
Author(s):  
Xuan Wei ◽  
Jin-Cheng He ◽  
Da-Peng Ye ◽  
Deng-Fei Jie
Keyword(s):  
Multispectral Imaging ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Low Cost ◽  
Imaging Systems ◽  
Correct Classification Rate ◽  
Discriminate Analysis ◽  
Classification Rate

Maturity grading is important for the quality of fruits. Nondestructive maturity detection can be greatly beneficial to the consumer and fruit industry. In this paper, a hyperspectral image of navel oranges was obtained using a diffuse transmittance imaging based system. Multispectral indexes were built to identify the maturity with the hyperspectral technique. Five indexes were proposed to combine the spectra at wavelengths of 640, 760 nm (red edges), and 670 nm (for chlorophyll content) to grade the navel oranges into three maturity stages. The index of (T670+T760-T640)/(T670+T760+T640) seemed to be more appropriate to classify maturity, especially to distinguish immature oranges that can be straightly identified in accordance with the value of this index ((T670+T760-T640)/(T670+T760+T640)). Different indexes were used as the input of linear discriminate analysis (LDA) and of k-nearest neighbor (k-NN) algorithm to identify the maturity, and it was found that k-NN with (T670+T760-T640)/(T670+T760+T640) could reach the highest correct classification rate of 96.0%. The results showed that the built index was feasible and accurate in the nondestructive classification of oranges based on the hyperspectral diffuse transmittance imaging. It will greatly help to develop low-cost and real-time multispectral imaging systems for the nondestructive detection of fruit quality in the industry.

scholarly journals Thoughts for Foods: Imaging Technology Opportunities for Monitoring and Measuring Food Quality

2021 ◽  
Author(s):  
Ayman Eissa ◽  
Lajos Helyes ◽  
Elio Romano ◽  
Ahmed Albandary ◽  
Ayman Ibrahim
Keyword(s):  
Food Quality ◽  
Advanced Technology ◽  
Imaging Systems ◽  
Electromagnetic Spectrum ◽  
Quality And Safety ◽  
Imaging Technology ◽  
Multiple Imaging ◽  
Technology Applications ◽  
Food Quality And Safety

In recent decades, the quality and safety of fruits, vegetables, cereals, meats, milk, and their derivatives from processed foods have become a serious issue for consumers in developed as well as developing countries. Undoubtedly, the traditional methods of inspecting and ensuring quality that depends on the human factor, some mechanical and chemical methods, have proven beyond any doubt their inability to achieve food quality and safety, and thus a failure to achieve food security. With growing attention on human health, the standards of food safety and quality are continuously being improved through advanced technology applications that depend on artificial intelligence tools to monitor the quality and safety of food. One of the most important of these applications is imaging technology. A brief discussion in this chapter on the utilize of multiple imaging systems based on all different bands of the electromagnetic spectrum as a principal source of various imaging systems. As well as methods of analyzing and reading images to build intelligence and non-destructive systems for monitoring and measuring the quality of foods.

scholarly journals AN ANALYSIS OF STUDENTS READING FINAL EXAMINATION BY USING ITEM ANALYSIS PROGRAM ON ELEVENTH GRADE OF SMA NEGERI 8 MEDAN

2019 ◽  
Vol 1 (1) ◽  
pp. 13-19
Author(s):  
Dewi Manalu ◽  
Kammer Tuahman Sipayung ◽  
Febrika Dwi Lestari
Keyword(s):  
Quantitative Research ◽  
Item Analysis ◽  
Multiple Choice ◽  
Final Examination ◽  
Multiple Choice Questions ◽  
Discrimination Power ◽  
Reliability Level ◽  
The Subject ◽  
Program Version

The purpose of this study was to determine the quality of the reading final examination in SMA N8 Medan grade eleventh in terms of reliability, level difficulty, discrimination power and level of distractor. This research is qualitative-quantitative research. The subject of research are the grade XI of SMA N8 Medan. Data is analyzed by ANATES program version 4.0.9. The analysis shows that: (1) items of multiple choice question that can be said as valid are 14 items ( 56%), while the invalid items amounted to 11 items ( 44%). (2) Items mutiple choice question can said as reliable because it equal 0,90 so it can said reliable. (3) items of multiple choice questions that categorized easy are 3 items (12%), satisfactory category 7 ( 28%) difficult category 2 (8%) and the other calculate categorized very easy 3 items (12%) and very difficult 3 (12%). (4) items of multiple choice questions that categorized poor are 12 items (48%),average category are 2 items (8%), good items category 1 items (4%) and excellent items are 8 items (32%).

scholarly journals Classification of soybean tempe quality using deep learning

2021 ◽  
Vol 924 (1) ◽  
pp. 012022
Author(s):  
Y Hendrawan ◽  
B Rohmatulloh ◽  
I Prakoso ◽  
V Liana ◽  
M R Fauzy ◽  
...  
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Low Cost ◽  
Confusion Matrix ◽  
Learning Rate ◽  
Traditional Food ◽  
Quality Classification ◽  
Non Destructive

Abstract Tempe is a traditional food originating from Indonesia, which is made from the fermentation process of soybean using Rhizopus mold. The purpose of this study was to classify three quality levels of soybean tempe i.e., fresh, consumable, and non-consumable using a convolutional neural network (CNN) based deep learning. Four types of pre-trained networks CNN were used in this study i.e. SqueezeNet, GoogLeNet, ResNet50, and AlexNet. The sensitivity analysis showed the highest quality classification accuracy of soybean tempe was 100% can be achieved when using AlexNet with SGDm optimizer and learning rate of 0.0001; GoogLeNet with Adam optimizer and learning rate 0.0001, GoogLeNet with RMSProp optimizer, and learning rate 0.0001, ResNet50 with Adam optimizer and learning rate 0.00005, ResNet50 with Adam optimizer and learning rate 0.0001, and SqueezeNet with RSMProp optimizer and learning rate 0.0001. In further testing using testing-set data, the classification accuracy based on the confusion matrix reached 98.33%. The combination of the CNN model and the low-cost digital commercial camera can later be used to detect the quality of soybean tempe with the advantages of being non-destructive, rapid, accurate, low-cost, and real-time.

scholarly journals Assessing the quality of higher education:

Dixi ◽  
2021 ◽  
Vol 23 (1) ◽  
pp. 1-11
Author(s):  
Oleg Bululukov ◽  
Anatolii Dmitrievich Marushev ◽  
Ivan Vladimirovich Kubariev ◽  
Inesa Anatoliivna Shumilo
Keyword(s):  
Higher Education ◽  
Education Quality ◽  
Educational Institutions ◽  
Quality Of Higher Education ◽  
Scientific Analysis ◽  
The Subject ◽  
Definition Of ◽  
International Experts

Introduction: For the educational world to achieve its existence and taste of creation and existence, there is always that need to promote and expect quality education, and this can only be realized through the analysis of its basic concept and formalities put in place. It is in this lane that an article and research is considered necessary. Purpose: To recognize the undeniable importance of creating a reliable and transparent system of accreditation of educational institutions, the introduction of an independent system of education quality assessment, by the way of scientific analysis and comparison. The subject matter of the article consists in the concepts and forms of the quality of higher education. Methodology: Based on the analysis of scientific points of view, the authors have suggested their own definition of the concepts of “quality of higher education” and “form of assessing the quality”. The classification of forms of assessing the quality of education has been provided and its procedural forms have been defined. Conclusions: The authors have formulated propositions for improving the accreditation process in Ukraine. It has been noted that the issues related to the process of providing education in Ukraine are currently under close attention of both state authorities and international experts and public organizations.

Non-Negative Based Locally Sparse Representation for Classification

2013 ◽  
Vol 677 ◽  
pp. 502-507
Author(s):  
Kang Hua Hui ◽  
Chun Li Li ◽  
Xiao Rong Feng ◽  
Xue Yang Wang
Keyword(s):  
Sparse Representation ◽  
Image Data ◽  
High Dimensional ◽  
Locally Linear Embedding ◽  
Discrimination Power ◽  
Knn Classifier ◽  
Reduction Methods ◽  
Linear Embedding ◽  
Low Dimensional

In this paper, a new method is proposed, which can be considered as the combination of sparse representation based classification (SRC) and KNN classifier. In detail, with the assumption of locally linear embedding coming into existence, the proposed method achieves the classification goal via non-negative locally sparse representation, combining the reconstruction property and the sparsity of SRC and the discrimination power included in KNN. Compared to SRC, the proposed method has obvious discrimination and is more acceptable for the real image data without those preconditions difficult to satisfy. Moreover, it is more suitable for the classification of low dimensional data dimensionally reduced by dimensionality reduction methods, especially those methods obtaining the low dimensional and neighborhood preserving embeddings of high dimensional data. The experiments on MNIST is also presented, which supports the above arguments.

Sign in / Sign up

Export Citation Format

Share Document