2022
Постійне посилання на фонд
Переглянути
Перегляд 2022 за Назва
Зараз показуємо 1 - 20 з 42
Результатів на сторінці
Налаштування сортування
Документ Відкритий доступ 1D CNN model for ECG diagnosis based on several classifiers(КПІ ім. Ігоря Сікорського, 2022) Mahmoud M. Bassiouni; Islam Hegazy; Nouhad Rizk; El-Sayed A. El-Dahshan; Abdelbadeeh M. SalemOne of the main reasons for human death is diseases caused by the heart. Detecting heart diseases in the early stage can stop heart failure or any damage related to the heart muscle. One of the main signals that can be beneficial in the diagnosis of diseases of the heart is the electrocardiogram (ECG). This paper concentrates on the diagnosis of four types of ECG records such as myocardial infarction (MYC), normal (N), variances in the ST-segment (ST), and supraventricular arrhythmia (SV). The methodology captures the data from six main datasets, and then the ECG records are filtered using a pre-processing chain. Afterward, a proposed 1D CNN model is applied to extract features from the ECG records. Then, two different classifiers are applied to test the extracted features’ performance and obtain a robust diagnosis accuracy. The two classifiers are the softmax and random forest (RF) classifiers. An experiment is applied to diagnose the four types of ECG records. Finally, the highest performance was achieved using the RF classifier, reaching an accuracy of 98.3%. The comparison with other related works showed that the proposed methodology could be applied as a medical application for the early detection of heart diseases.Документ Відкритий доступ Adaptive hybrid activation function for deep neural networks(КПІ ім. Ігоря Сікорського, 2022) Bodyanskiy, Yevgeniy V.; Kostiuk, Serhii O.Документ Відкритий доступ An explanation of the J. Huber effect, which does not contradict the laws of physics and experimental research(КПІ ім. Ігоря Сікорського, 2022) Silvestrov, Anton M.; Zimenkov, Dmytro K.; Spinul, Liudmyla Yu.; Svyatnenko, Vadym A.Документ Відкритий доступ Analysis of the impact of Russia’s military invasion of Ukraine on the energy independence of European countries(КПІ ім. Ігоря Сікорського, 2022) Zgurovsky, Michael Z.; Kravchenko, Maryna O.; Boiarynova, Kateryna O.; Ilyash, Olha I.; Kopishynska, Kateryna O.; Pyshnograiev, Ivan O.Документ Відкритий доступ Application of beam theory for the construction of twice differentiable closed contours based on discrete noisy points(КПІ ім. Ігоря Сікорського, 2022) Orynyak, I.; Koltsov, D.; Chertov, O.; Mazuryk, R.The smoothing of measured noisy positions of discrete points has considerable significance in various industries and computer graphic applications. The idea of work consists of the employment of the technique of beam with spring supports. The local coordinates systems are established for beam straight line segments, where the initial angles between them are accounted for in the conjugation equations, which provide the angular continuity. The notions of imaginary points are introduced, the purpose of which is to approach the real length of the smoothed contour to the length of the straight chord. Several examples of closed denoised curve reconstruction from an unstructured and highly noisy 2D point cloud are presented.Документ Відкритий доступ Automatic pancreas segmentation using ResNet-18 deep learning approach(КПІ ім. Ігоря Сікорського, 2022) Kakarwal, S. N.; Paithane, Pradip M.Документ Відкритий доступ Clusterization of vector and matrix data arrays using the combined evolutionary method of fish schools(КПІ ім. Ігоря Сікорського, 2022) Bodyanskiy, Ye.; Shafronenko, А.; Pliss, І.The problem of clustering data arrays described in both vector and matrix forms and based on the optimization of data distribution density functions in these arrays is considered. For the optimization of these functions, the algorithm that is a hybrid of Fish School Search, random search, and evolutionary optimization is proposed. This algorithm does not require calculating the optimized function’s derivatives and, in the general case, is designed to find optimums of multiextremal functions of the matrix argument (images). The proposed approach reduces the number of runs of the optimization procedure, finds extrema of complex functions with many extrema, and is simple in numerical implementation.Документ Відкритий доступ Comparative analysis of modified semi-supervised learning algorithms on a small amount of labeled data(КПІ ім. Ігоря Сікорського, 2022) Lyubchyk, L. M.; Yamkovyi, K. S.The paper is devoted to improving semi-supervised clustering methods and comparing their accuracy and robustness. The proposed approach is based on expanding a clustering algorithm for using an available set of labels by replacing the distance function. Using the distance function considers not only spatial data but also available labels. Moreover, the proposed distance function could be adopted for working with ordinal variables as labels. An extended approach is also considered, based on a combination of unsupervised k-medoids methods, modified for using only labeled data during the medoids calculation step, supervised method of k nearest neighbor, and unsupervised k-means. The learning algorithm uses information about the nearest points and classes’ centers of mass. The results demonstrate that even a small amount of labeled data allows us to use semi-supervised learning, and proposed modifications improve accuracy and algorithm performance, which was found during experiments.Документ Відкритий доступ Comparative analysis of the effectiveness of using fine-grained and nested parallelism to increase the speedup of parallel computing in multicore computer systems(КПІ ім. Ігоря Сікорського, 2022) Martell, Valerii V.; Korochkin, Aleksandr V.; Rusanova, Olga V.Документ Відкритий доступ Cost effective hybrid genetic algorithm for workflow scheduling in cloud(КПІ ім. Ігоря Сікорського, 2022) Kumar Bothra, Sandeep; Singhal, Sunita; Goyal, HemlataCloud computing plays a significant role in everyone’s lifestyle by snugly linking communities, information, and trades across the globe. Due to its NP-hard nature, recognizing the optimal solution for workflow scheduling in the cloud is a challenging area. We proposed a hybrid meta-heuristic cost-effective load-balanced approach to schedule workflow in a heterogeneous environment. Our model is based on a genetic algorithm integrated with predict earliest finish time (PEFT) to minimize makespan. Instead of assigning the task randomly to a virtual machine, we apply a greedy strategy that assigns the task to the lowest-loaded virtual machine. After completing the mutation operation, we verify the dependency constraint instead of each crossover operation, which yields a better outcome. The proposed model incorporates the virtual machine’s performance variance as well as acquisition delay, which concedes the minimum makespan and computing cost. One of the most astounding aspects of our cost-effective hybrid genetic algorithm (CHGA) is its capacity to anticipate by creating an optimistic cost table (OCT) while maintaining quadratic time complexity. Based on the results of our meticulous experiments on some real-world workflow benchmarks and comprehensive analysis of some recently successful scheduling algorithms, we concluded that the performance of our CHGA is melodious. CHGA is 14.58188%, 11.40224%, 11.75306%, and 9.78841% cheaper than standard Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Cost Effective Genetic Algorithm(CEGA), and Cost-Effective Loadbalanced Genetic Algorithm (CLGA), respectively.Документ Відкритий доступ Data mining tools for complex socio-economic processes and systems(КПІ ім. Ігоря Сікорського, 2022) Obelets, T. V.The paper considers discovering new and potentially useful information from large amounts of data that actualizes the role of developing data mining tools for complex socio-economic processes and systems based on the principles of the digital economy and their processing using network applications. The stages of data mining for complex socio-economic processes and systems were outlined. The algorithm of data mining was considered. It is determined that the previously used stages of data mining, which were limited to the model-building process, can be extended through the use of more powerful computer technology and the emergence of free access to large amounts of multidimensional data. The available stages of data mining for complex socio-economic processes and systems include the processes of facilitating data preparation, evaluation, and visualization of models, as well as indepth learning. The data mining tools for complex socio-economic processes and systems in the context of technological progress and following the big data paradigm were identified. The data processing cycle has been investigated; this process consists of a series of steps starting with the input of raw data and ending with the output of useful information. The knowledge obtained at the data processing stage is the basis for creating models of complex socio-economic processes and systems. Two types of models (descriptive and predictive) that could be created in the data mining process were outlined. Algorithms for estimating and analyzing data for modeling complex socio-economic processes and systems in accordance with the pre-set task were determined. The efficiency of introducing neural networks and deep learning methods used in data mining was analyzed. It was determined that they would allow effective analysis and use of the existing large data sets for operational human resources management and strategic planning of complex socio-economic processes and systems.Документ Відкритий доступ Development of a hybrid method for calculation of software complexity(КПІ ім. Ігоря Сікорського, 2022) Kazimov, Tofig Hasanaga; Bayramova, Tamilla AdilДокумент Відкритий доступ Dynamic certification and assessment of the buildings life cycle under regular explosive impacts(КПІ ім. Ігоря Сікорського, 2022) Trofymchuk, O. M.; Kaliukh, I. I.; Dunin, V. A.; Kyrash, S. Y.Today in Ukraine, there is no single legalized, generally accepted methodology (at the level of a Ukrainian building standard) for dynamic certification of buildings and structures. A unified approach is proposed as such a technique. It includes four components: visual inspection of buildings; experimental studies of the dynamic response of buildings or structures to explosive effects; mathematical modeling of the stress-strain state of the object under study; synthesis of the results of visual inspection; experimental studies and numerical simulation in order to generalize them systematically. As an approbation, the deterioration of the resource of reinforced concrete structures of residential buildings under the conditions of constant mass industrial explosions with a capacity of 500 to 700 tons in the quarry of Southern GZK (Mining and Processing Plant) in the city of Kryvyi Rih, Ukraine, has been studied. Based on the processing of numerous experimental data and the results of mathematical modeling, a probabilistic model for predicting the deterioration of the technical condition of reinforced concrete structures of the Center for Children and Youth Creativity “Mriya” has been obtained. Calculations of the risks of destruction of the building’s load-bearing elements for its vulnerable areas made it possible to clarify its service life. It decreased by 30 years compared to the standard in 2012.Документ Відкритий доступ Expert system for depression detection in teenagers(КПІ ім. Ігоря Сікорського, 2022) Raharja, Bintang; Samudera, Elfajar Bintang; Lay, Ferry; Hansun, SengДокумент Відкритий доступ Generative time series model based on encoder-decoder architecture(КПІ ім. Ігоря Сікорського, 2022) Nedashkovskaya, Nadezhda I.; Androsov, Dmytro V.Документ Відкритий доступ Hybrid convolution network for medical images processing and breast cancer detection(КПІ ім. Ігоря Сікорського, 2022) Zaychenko, Yuriy P.; Naderan, Maryam; Hamidov, GalibДокумент Відкритий доступ Hybrid GMDH deep learning networks – analysis, optimization and applications in forecasting at financial sphere(КПІ ім. Ігоря Сікорського, 2022) Zaychenko, Yuriy P.; Zaychenko, Helen Yu.; Hamidov, GalibДокумент Відкритий доступ Intelligent decision support systems in the development of megalopolis infrastructure(КПІ ім. Ігоря Сікорського, 2022) Trofymchuk, Oleksandr M.; Stenin, Aleksandr A.; Soldatova, Maria A.; Drozdovich, Irina G.Документ Відкритий доступ Methodological aspects of operative control system intellectualization for dynamic objects(КПІ ім. Ігоря Сікорського, 2022) Melnykov, S. V.; Malezhyk, P. M.; Gasanov, A. S.; Bidyuk, P. I.The problems of intelligent control system organization are considered: determining the number of intellectualization levels, the sequence of actions required for analysis of the control process, adding to the control system new elements providing for enhancement degree of its intellectualization, special features of its structural organization, estimating the possibilities of intellectualization, providing examples of practical intellectualization. The primary purpose of the study is to determine the purposeful organization of intelligent control systems as well as the necessity and usefulness of systemic consideration that takes into consideration the following: requirements of the problem statement, characteristics of the environment, means for acquiring and processing necessary information, working control mechanisms, functional characteristics and experience of user-operator. As a result of the analysis performed, characteristic levels of the intellectual development of a system were determined, the stages of performing intellectualization of a control system were proposed, and the effectiveness of proposed solutions for practical problems was shown.Документ Відкритий доступ Modelling negative thermomechanical effects in reinforced road structures with thermoelastic incompatibility of coating and reinforcement materials(КПІ ім. Ігоря Сікорського, 2022) Gulyayev, Valery I.; Mozgovyy, Volodymyr V.; Shlyun, Nataliia V.; Shevchuk, Lyudmyla V.
- «
- 1 (current)
- 2
- 3
- »