The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Multi-instance learning is a new machine learning framework following supervised learning, unsupervised learning and reinforcement learning. In order to solve the complex computing problems of many dimensions and large amount of samples better in multi-instance learning, a multi-instance learning algorithm based on multi-side is put forward in this paper. The algorithm selects the feature attributes...
Calligraphy classification of the ancient manuscripts gives useful information to paleographers. Researches on digital paleography using calligraphy are done on the manuscripts to identify unidentified place of origin, number of writers, and the date of ancient manuscripts. Information that are used are features from characters, tangent value and features known as Grey-Level Co-occurrence Matrix (GLCM)...
FPGA interconnects are typically utilized as digital resources to connect the logical building blocks of an FPGA. Because of the flexibility in the FPGA interconnect, all of the wires in the interconnect will never be simultaneously utilized. These unutilized wires can combined into a single net on the FPGA while retaining a specific physical shape. When this shape is excited, energy is emitted from...
Actions consist of short shape-motion fragments which recur in a seemingly unique sequence. We propose that these short fragments may constitute a concise vocabulary for actions. Models based on such “words” sometimes use the bag of words paradigm, which ignores sequence information. Also, despite the well-known utility of Fourier and similar features for temporal modelling, Fourier models have not...
Dr. Karl Berger was a Swiss researcher whose work on Mt. St. Salvatore rates him the title of “father of direct lightning research.” He documented his findings in an article published in ELECTRA magazine in 1975. Some 40 years later the IEC immortalized that work by characterizing it as the closest representation of the actual lightning flash and using it as the basis for the parameters of the 10/350...
One-class classification is an important problem with applications in several different areas such as outlier detection and machine monitoring. In this paper we propose a novel method for one-class classification which also implements prototype reduction. The main feature of the proposed method is to analyze every limit of all the feature dimensions to find the true border which describes the normal...
In this paper, we introduce a Goodness-of-Fit test for the Multivariate Exponential Power (MEP) distribution, a multivariate extension of the Generalized Gaussian, which has recently gained considerable interest as a model for wavelet coefficients in the context of color image retrieval and spread-spectrum watermarking. We present a size and power study of this test and show Goodness-of-Fit results...
Characters extracted from images or graphics pose a challenge for traditional character recognition techniques. The high degree of intraclass variation along with the presence of clutter makes accurate recognition difficult, yet the semantic information conveyed by sections of text within images or graphics makes their recognition an important problem. Previous work has shown that, on the two most...
In this paper, we present a template based approach to the segmentation of touching components in handwritten text lines. Local patches around touching components are identified and a dictionary is created consisting of template patches together with their correct segmentations. We use two shape context based methods to compute similarity between input patches and dictionary templates to find the...
In this paper, we propose a method for classifying textual entities of bilingual documents written in Chinese and English. In contrast to earlier works that performed classification on the level of text lines or documents, we apply our method to the level of textual components, as we must first identify Chinese components before merging them into intact characters and sending the latter characters...
To solve the problems of complexity and low robustness that exist in present image shape feature detection and description methods, a new image shape feature detection and description method is proposed. First, salient regions are detected using a method based on connected component. Then, a descriptor composed of Hu's moment invariants and eccentricity is used to descript the detected regions. Experiments...
Abrasion resistance mechanism and factors of concrete were studied, common concrete abrasion resistance performance test methods were analyzed, the principle of rotating-jet mode concrete abrasion resistance performance test was studied, and in accordance with this principle, the rotating-jet mode concrete abrasion resistance performance testing machine was developed. Through comparing with existing...
Localization is an important ability in autonomous vehicle application. This paper reports the implementation of localization system using single wireless camera as visual sensor and an augmented reality computer vision library, ARToolkit, for executing tracking activity. Augmented reality tag were used as landmarks to be tracked which are placed arround within 2×2 metres testing environment. The...
On the questions that the area to detect is big and the examination environment is wicked for the pressure vessel and other large-scale equipment welded joint, proposed an examination method by using acoustic emission diagnosis technology to monitor crack's sketchy position, then again using the ultrasonic testing to determinate crack's accurate position, the size and the shape, discussed in detail...
Our study investigates the generalization capability of fuzzy rule-based trading systems and conducted an empirical study on Taiwan's stock market during 1991/1/1–2010/12/31. The empirical conclusions are as follows (1) The investment performance in the training period is much better than that in the testing period, which exhibits over-learning. (2) The symmetry rules approach demonstrates that the...
The viability of producing BEGe-type detectors from isotopically modified germanium for the GERDA experiment is demonstrated by a complete test of the supply chain. GERDA is built to search for neutrinoless double beta (Ovββ) decay of Ge using high-purity germanium detectors made of material enriched in 76Ge. To reach a sensitivity for Ovββ decay of <1.4·1026 years, new active background suppression...
The application of GA to structural damage identification is an effective method, it is easy to implement and no special requirement concerning the initial values of unknown parameters is needed. In the paper, a nondestructive global damage identification method, an improved Genetic algorithm, is proposed to identify damage location and severity of the structure, which is verified by a number of damage...
Quantification of viscoelastic properties of soft fibrous protein gels and tissue biopsies is vital to the study of disease progression and wound healing, among other research areas. The aim of this work is to establish a method of testing irregularly-shaped and anisotropic biological samples. This method has been tested with samples that have G' in the range of 10-500 Pa and sizes of approximately...
The Arabic web content is growing rapidly and the need for its efficient management is gaining importance and the morphological complexity of Arabic raises many challenges in this regard. This paper reports on some of our work aimed at designing text mining and query pre-processing tools that are able to efficiently process and search large quantities of Arabic web data. In our research we try to...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.