Classification of Computer Graphic Images and Photographic Images Based on Fusion of Color and Texture Features

With the rapid advancement in digital image rendering techniques, allows the user to create surrealistic computer graphic (CG) images which are hard to distinguish from photographs captured by digital cameras. In this paper, classification of CG images and photographic (PG) images based on fusion of global features is presented. Color and texture of an image represents global features. Texture feature descriptors such as gray level co-occurrence matrix (GLCM) and local binary pattern (LBP) are considered. Different combinations of these global features are investigated on various datasets. Experimental results show that, fusion of color and texture features subset can achieve best classification results over other feature combinations.

The Rediscovered Watermark in the Drawing Leda and the Swan by Raphael Kept at Windsor Castle

This article presents an in-depth study of Raphael’s drawing of Leda and the Swan (RCIN 912759), preserved at Windsor Castle. The research aims to make the paper’s physical properties accessible and extend the information on the watermark. The methodology follows an artistic–design-oriented approach. The data extraction process uses a back-lighting photographic technique combined with image post-processing operations. The work catalogues in scientific terms the complete paper mould lines of the Windsor sheet according to the International Standard of Paper Classification (IPH). Based on comparisons with a series of drawings by Leonardo da Vinci, the contribution suggests a chronological and provenance estimate of the paper used by Raphael.

Topic space trajectories

The annual number of publications at scientific venues, for example, conferences and journals, is growing quickly. Hence, even for researchers it becomes harder and harder to keep track of research topics and their progress. In this task, researchers can be supported by automated publication analysis. Yet, many such methods result in uninterpretable, purely numerical representations. As an attempt to support human analysts, we present topic space trajectories, a structure that allows for the comprehensible tracking of research topics. We demonstrate how these trajectories can be interpreted based on eight different analysis approaches. To obtain comprehensible results, we employ non-negative matrix factorization as well as suitable visualization techniques. We show the applicability of our approach on a publication corpus spanning 50 years of machine learning research from 32 publication venues. In addition to a thorough introduction of our method, our focus is on an extensive analysis of the results we achieved. Our novel analysis method may be employed for paper classification, for the prediction of future research topics, and for the recommendation of fitting conferences and journals for submitting unpublished work. An advantage in these applications over previous methods lies in the good interpretability of the results obtained through our methods.

Sustainable Transport Packaging: Evaluation and Feasibility for Different Use Cases

The continuous increase in e-commerce shipping is causing a critical amount of transport packaging waste. The aim of this paper is a comprehensive presentation of different types of innovations for sustainable transport packaging. Within the paper, classification and evaluation of 37 sustainable packaging solutions are presented, including customized on-demand packaging, alternative materials and closed-loop systems. A multi-criteria evaluation scheme covering a wide range of economic, ecological, operational and social indicators was used to assess the feasibility of the packaging options in different cases. Depending on the degree of innovation and implementation risk, packaging options are proposed as a “Quick Win”, “Go Green” or “Thought Leadership” solution. In the conclusion chapter of this paper, recommendations are made for three different use cases, namely grocery, fashion and textiles and electronic goods.

PERKEMBANGAN PENELITIAN LITERASI SAINS DALAM PEMBELAJARAN FISIKA DI INDONESIA

THE DEVELOPMENT OF SCIENTIFIC LITERACY RESEARCH IN PHYSICS LEARNING IN INDONESIAAbstractScientific literacy is one topic that is starting to get much attention in the academic field. Mastering the ability of scientific literacy is essential for everyone to solve problems. Scientific literacy in physics is very important for life in the era of science and technology. This study aims to provide an overview of research related to scientific literacy in learning physics in Indonesia. This study is to determine the distribution and description of scientific literacy research that has been done so that it is expected to provide direction in conducting further research, improvement, and policy. This research used a descriptive content analysis study method. The instrument used the adopted Paper Classification Form or PCF by Kizilaslan et al. Analysis was carried out on 59 articles relating to the scientific literacy in physics published in 2012-2019. Scientific literacy research in physics in Indonesia continues to increase until its peak in 2018, dominated by topics research in media development, teaching materials, or other learning components that aim to develop student scientific literacy. High school students become a sample that is often used in research, with most using a sample size of 51-100. Types of quantitative research methods and test instruments become more dominant than others. The definition of scientific literacy that is widely used in physics education research in Indonesia is the definition of scientific literacy by PISA. AbstrakLiterasi sains merupakan salah satu topik yang mulai banyak mendapat perhatian dalam bidang akademik. Hal ini dikarenakan penguasaan kemampuan literasi sains yang penting bagi semua orang untuk menyelesaikan masalah. Literasi sains pada fisika sangat penting untuk kehidupan di era sains dan teknologi. Tujuan dari penelitian ini untuk memberikan tinjauan umum terkait penelitian literasi sains dalam pembelajaran fisika di Indonesia. Hal ini untuk mengetahui distribusi dan deskripsi penelitian literasi sains yang telah dilakukan, sehingga diharapkan dapat memberi arahan dalam melakukan penelitian, perbaikan maupun kebijakan lebih lanjut. Penelitian ini menggunakan metode descriptive content analysis study. Instrumen yang digunakan mengadopsi Paper Classification Form atau PCF oleh Kizilaslan et al. Analisis dilakukan terhadap 59 artikel berkaitan dengan literasi sains fisika yang dipublikasikan dalam rentang 2012-2019. Penelitian literasi sains fisika di Indonesia terus mengalami peningkatan hingga puncaknya pada tahun 2018, didominasi oleh topik penelitian pengembangan media, bahan ajar, atau komponen pembelajaran lainnya yang bertujuan untuk mengembangkan literasi sains siswa. Siswa SMA menjadi sampel yang sering digunakan dalam penelitian, dengan sebagian besar menggunakan ukuran sampel 51–100. Jenis metode penelitian quantitative dan instrument tes mendominasi dibandingkan lainnya. Definisi literasi sains yang banyak digunakan dalam penelitian literasi sains fisika di Indonesia yakni definisi literasi sains menurut PISA.

Analysis and Examination of Heart distress from ECG signal using Artificial Intelligence.

Health data analysis is usually based on a comparison of derived health measures to predefined thresholds. Symptoms can be observed if a value is above or below a threshold. Early detection of signs of heart failure allows the prediction of strokes of heart failure and can therefore prevent these. So identifying “accurate” criteria is the most important task. The accuracy of an experiment depends strongly on the accuracy of the criteria used. Congestive heart failure (CHF) occurs when the heart can not pump sufficient blood for a stable physiological condition. CHF usually occurs when the coronary artery blockage causes the heart tissue to become acidic. The data used to analyze data such as Linear Regression, Missing Enrollment Data, Search Signal, Clinical Data Protection Programs, and Early Adaptive Alarm. The proposed system involves models including server and data warehouse processing, pre-processing, extraction classification characterization in this paper. Classification of heart defects and prediction of heart failure by using applied classifier for hybridization, guideline for treating patients as a gym, level of stress management. In this article, the program tracks the heart disease patients, predicts atrial fibrillation and ventricular fibrillation, and alerts patients when the critical condition occurs.

Effect of the paper surface properties on the ink transfer parameters in offset printing

Paper has a crucial impact on the qualitative properties of printed product as properties of the paper’s surface directly impact the ink transfer, consequently, basic optical properties of the print. Although same ISO paper type, papers possess variable surface properties leading to different influence on the ink transfer. The aim of this research was to analyse influence of the surface properties of the paper, including surface free energy, smoothness and gloss of some standard papers used in lithography on the ink transfer while matching the colorimetric values defined by ISO 12647-2:2013. Determination of amount of the ink transfer, optical density, mottling and colour difference of prints were performed to evaluate paper-ink interactions. Results have shown that produced prints differ in the investigated properties. Furthermore, there are significant correlations between the surface free energy of the paper and paper smoothness and the ink transfer. In addition, amount of ink used to produce a standardized print varies for different paper types (even in the same ISO paper classification), meaning difference in ink costs. This research proved the high influence of paper’s certain parameters on the ink transfer by strong correlation coefficients. This enables better process control and optimization of the printing.