In this work, classification of cellular structures in the high resolutional histopathological images and the discrimination of cellular and non-cellular structures have been investigated. The cell classification is a...
详细信息
In this work, classification of cellular structures in the high resolutional histopathological images and the discrimination of cellular and non-cellular structures have been investigated. The cell classification is a very exhaustive and time-consuming process for pathologists in medicine. The development of digital imaging in histopathology has enabled the generation of reasonable and effective solutions to this problem. Morever, the classification of digital data provides easier analysis of cell structures in histopathological data. Convolutional neural network (CNN), constituting the main theme of this study, has been proposed with different spatial window sizes in RGB color spaces. Hence, to improve the accuracies of classification results obtained by supervised learning methods, spatial information must also be considered. So, spatial dependencies of cell and non-cell pixels can be evaluated within different pixel neighborhoods in this study. In the experiments, the CNN performs superior than other pixel classification methods including SVM and k-Nearest Neighbour (k-NN). At the end of this paper, several possible directions for future research are also proposed.
Renovation of business-critical software is becoming increasingly important. We identify fundamental notions and techniques to aid in system renovation and sketch some basic techniques: generic language technology to ...
详细信息
orthogonal and quasi-orthogonal matrices with a limited number of element values and structured in some way are of considerable interest for many technical applications related to image processing and signal coding. T...
orthogonal and quasi-orthogonal matrices with a limited number of element values and structured in some way are of considerable interest for many technical applications related to image processing and signal coding. The paper classifies and considers cyclic matrices and matrices with cyclic blocks. Descriptions of noise-resistant encoding methods of images and their protective masking using such matrices are given. Based on the analysis of the autocorrelation functions of new code sequences obtained from strings of modified cyclic quasi-orthogonal matrices and the simulation performed, numerical values of the quality parameters of the new code sequences are given. It is shown that their application makes it possible to reduce the maximum level of the side lobe of the aperiodic autocorrelation function, which allows us to conclude that their application is promising and that signal coding algorithms can be revised.
The first implementation of the programming language FX-87, a polymorphic typed functional language based on a system for static program analysis, is described. This polymorphic effect system integrates type checking ...
详细信息
The first implementation of the programming language FX-87, a polymorphic typed functional language based on a system for static program analysis, is described. This polymorphic effect system integrates type checking and side-effect analysis into a single framework and allows the automatic detection of parallelizable expressions at compile-time. In FX-87, every expression has two static properties: a type and an effect. Type and effect polymorphism permits the behavior of first-class procedures to be statically modeled. The integration of type and effect analysis has resulted in the first system that is able (by accurate modeling of the side-effects of procedure values and masking of unobservable effects in the heap) to detect a compile-time, parallelizable constructs in both functional and imperative programs.< >
the issue of ensuring the reliability of the functioning of global systems of remote online monitoring of the condition of patients is considered. Remote monitoring is in demand when supervision the health status of d...
the issue of ensuring the reliability of the functioning of global systems of remote online monitoring of the condition of patients is considered. Remote monitoring is in demand when supervision the health status of disabled people with cardiovascular diseases, pregnant women and children. It is especially in demand in the context of a pandemic and the accompanying restrictions on movement. Monitoring is carried out “transparently” for the patient, without involving him in the subtleties of the process of interaction with a medical institution, ensuring the preservation of his mobility due to the proposed concept of implementing a wearable online monitor device. The procedures of the online monitor initialization and distribution of functions in it are considered. Threats to the normal functioning of distributed systems with online monitors are presented, including existing problems of a general nature related mainly to global communications. Solutions are offered to ensure reliable operation of wearable devices as part of online monitors.
Finding a document that is similar to a specified query document within a large document database is one of important issues in the Big Data era, as most data available is in the form of unstructured texts. Our testin...
详细信息
Construction of complex array operations by composition of more basic ones allows for abstract and concise specifications of algorithms. Unfortunately, naïve compilation of such specifications leads to creation o...
详细信息
Heart disease, known as cardiovascular disease has been one of the main causes of death worldwide in recent years. It is affected by various risk factors such as high blood pressure, high cholesterol, diabetes, smokin...
详细信息
暂无评论