Optimisation of scheduled tasks by real-time measurement and correlation

For functional safety, the scheduler should perform all time critical tasks in an order and within predefined deadlines in embedded systems. Scheduling of time critical tasks is determined by estimating their worst-case execution times. To justify the model design of task scheduling, it is required to simulate and visualise the task execution and scheduling maps. This helps to figure out possible problems before deploying the schedule model to real hardware. The simulation tools which are used by companies in an industry perform scheduling simulation and visualisation of all time critical tasks to design and verify the model. All of them lack the capability of comparing simulation results versus real results to achieve the optimised scheduling design. This sometimes leads the overestimated worst-case execution times and increased system cost. The aim of our study is to decrease the system cost with optimisation of scheduled tasks via using the static analysing method. Keywords: Schedule visualisation, scheduler optimisation, functional safety, real-time systems, scheduler.

Statistical analysis of radiomic features in differentiation of glioma grades

Radiomics is an important quantitative feature extraction tool used in many areas such as image processing and computer-aided diagnosis. In this study, the discriminability of brain cancer tumour grades (Grade II and Grade III) with radiomic features were analysed statistically. The data set consists of 121 patients, 77 patients with Grade II tumours and 44 patients with Grade III tumours. A total of 107 radiomic features were extracted, including three groups of radiomic features such as morphological, first-order and texture. Relationships between the characteristics of each group were tested by Spearman’s correlation analysis. Differences between Grade II and Grade III tumour categories were analysed with Mann–Whitney U test. According to the results, it was seen that radiomic features can be used to differentiate the features of tumour levels evaluated in the same category. These results show that by employing radiomic features brain cancer grade detection can help machine learning technologies and radiological analysis. Keywords: Radiomics, glioma, image processing.

Training of ANFIS with simulated annealing algorithm on flexural buckling load prediction of aluminium alloy columns

In this study, we propose a simulated annealing algorithm (SA) to train an adaptive neurofuzzy inference system (ANFIS). We performed different types of optimization algorithms such as genetic algorithm (GA), SA and artificial bee colony algorithm on two different problem types. Then, we measured the performance of these algorithms. First, we applied optimization algorithms on eight numerical benchmark functions which are sphere, axis parallel hyper-ellipsoid, Rosenbrock, Rastrigin, Schwefel, Griewank, sum of different powers and Ackley functions. After that, the training of ANFIS is carried out by mentioned optimization algorithms to predict the strength of heat-treated fine-drawn aluminium composite columns defeated by flexural bending. In summary, the accuracy of the proposed soft computing model was compared with the accuracy of the results of existing methods in the literature. It is seen that the training of ANFIS with the SA has more accuracy. Keywords: Soft computing, ANFIS, simulated annealing, flexural buckling, aluminium alloy columns.

Colour recognition using colour histogram feature extraction and K-nearest neighbour classifier

K-nearest neighbours (KNN) is a widely used neural network and machine learning classification algorithm. Recently, it has been used in the neural network and digital image processing fields. In this study, the KNN classifier is used to distinguish 12 different colours. These colours are black, blue, brown, forest green, green, navy, orange, pink, red, violet, white and yellow. Using colour histogram feature extraction, which is one of the image processing techniques, the features that distinguish these colours are determined. These features increase the effectiveness of the KNN classifier. The training data consist of saved frames and the test data are obtained from the video camera in real-time. The video consists of consecutive frames. The frames are 100 × 70 in size. Each frame is tested with K = 3,5,7,9 and the obtained results are recorded. In general, the best results are obtained when used K = 5. Keywords: KNN algorithm, classifier, application, neural network, image processing, developed, colour, dataset, colour recognition.

Innovative development of key sectors of economy based on the creation of technological parks in the Republic of Azerbaijan

The priorities of stabilisation of the Azerbaijan economy require the search for approaches to the organisation of production and economic activities on a new technological basis within the framework of the construction of structures of the Techno park type. This article is devoted to issues of innovative development of key sectors of economy on the basis of digitalisation and creation of technological parks in the Republic of Azerbaijan. This article examines the current situation of the digital economy, its characteristic features, analyses the state of Techno parks and various approaches to the use of the digital economy, as well as the prospects and trends of its development in the Republic of Azerbaijan. The aim of this article is to develop theoretical and practical issues related to the innovative development of key sectors of the economy on the basis of the introduction of scientific and technical structures of the Techno park type. The main result of this work is the allocation of opportunities for the further successful development of key sectors of the economy on the basis of the creation of technological parks in the Republic of Azerbaijan. The article considers theoretical and practical aspects of innovative development of economic sectors on the basis of introduction of scientific and technical structures of Techno park type. It is determined that one of the main problems of development of the country and its individual regions’ increase of investment attractiveness and innovation activity. It is proved that insufficient use of the scientific and technological potential of the country has been shown to be due to lack of organisational resources and organisational innovation. Keywords: Technopark, digital economy, innovative infrastructure, information technologies.

Innovative technologies and living spaces; Updated living standards according to the evolution of homo sapiens

Homosapiens is the common family name for contemporary human beings. There are different kinds of homo species but the most recent one with the most improved abilities are human beings of the present era, who have adapted themselves to the new technologies and life conditions by improving themselves. The substantial improvements in technology started with the French Revolution in 1799. Initially, technology helped human beings in the production and industry sectors. Thereafter, in the 1990s, technology penetrated living spaces, firstly helping with household duties and then impacting social life, first with the radio and later with the television. Living spaces started to change through the organisation of spaces, and most houses were organised according to location reserved for the television. This is the biggest change brought about by technology in living spaces. The expectations of human beings were on the rise simultaneously with economic welfare and consumption-based demands. In the 2000s, phyisical limitations occurred, while expectations increased even more. These were constraints over time, materials and economy, and the solution came from technology via virtual reality and generated cyber spaces, which were without limits, economical and surpassed the built environments. Due to the lack of physical conditions, built envionments ceded their place to virtual living spaces and virtual cities. In the present study, data collection was undertaken via a study of innovations within living spaces and also via an observation of social lives within living spaces. The present article aims to present what can be foreseen, on the basis of cause and effect, concerning the impacts of the current evolution on the one hand and massive outbreaks of viruses on the other hand, the impacts on the physical spaces of the homosapiens species that have succeeded in adapting to all the changes that they have come across from their beginnings until the present era, the impacts that both phenomena will have on the current living standards and living spaces of humans and what changes human living spaces will undergo in the ongoing process of evolution. Human beings will continue renewing themselves throughout the said phenomena before concluding their process of evolution. Keywords: Innovative, technology, living spaces, living standards, homosapiens.

Classification of brain tumours using radiomic features on MRI

Glioma is one of the most common brain tumours among the diagnoses of existing brain tumours. Glioma grades are important factors that should be known in the treatment of brain tumours. In this study, the radiomic features of gliomas were analysed and glioma grades were classified by Gaussian Naive Bayes algorithm. Glioma tumours of 121 patients of Grade II and Grade III were examined. The glioma tumours were segmented with the Grow Cut Algorithm and the 3D feature of tumour magnetic resonance imaging images were obtained with the 3D Slicer programme. The obtained quantitative values were statistically analysed with Spearman and Mann–Whitney U tests and 21 features with statistically significant properties were selected from 107 features. The results showed that the best performing among the algorithms was Gaussian Naive Bayes algorithm with 80% accuracy. Machine learning and feature selection techniques can be used in the analysis of gliomas as well as pathological evaluations in glioma grading processes. Keywords: Radiomics, glioma, naive bayes.

Determining abbreviations in Kariyer.net domain

In this paper, studies determining abbreviations and their meanings in job texts are explained. The data used in this study consist of job texts stored in the Kariyer.net database. The applied method consists of two separate steps: first, the words and phrases in all job text documents are vectorised with the Word2Vec model. The phrases and abbreviations that are compatible with each other in the proximity of these word vectors are then checked and matched. In the second step, sentences with abbreviations and their meanings in the dataset are defined by the rules determined by Regex. Then, the appropriate abbreviations are collected and added to the dictionary. Keywords: Word embeddings, text mining, abbreviation detection.

A comparative study of different classification algorithms on RNA-Seq cancer data

Gene mutations are the most important reason of cancer diseases, and there are different kind of causing genes across these diseases. RNA-Seq technology enables us to allow for gathering information about many genes simultaneously; hence, RNA-Seq data can be used for cancer diagnosis and classification. In this study, RNA-Seq dataset for renal cell cancer is analysed using three different developed classification methods: random forest (RF), artificial neural network (ANN) and deep learning (DL). The genes in our dataset are related to the following cancer types: kidney renal papillary cell, kidney renal clear cell and kidney chromophore carcinomas. It suggests that the DL method gives the highest accuracy rate compared to RF and ANN for 95.15%, 91.83% and 89.22%, respectively. We believe that the results acquired in this study will make a contribution to the classification of cancer types and support doctors in their processes of decision making. Keywords: Classification, gene-expression, RNA-Seq, DL.

User behaviour analysis and churn prediction in ISP

There is no doubt that customer retention is vital for the service sector as companies’ revenue is significantly based on their customers’ financial returns. The prediction of customers who are at the risk of leaving a company’s services is not possible without using their connection details, support tickets and network traffic usage data. This paper demonstrates the importance of data mining and its outcome in the telecommunication area. The data in this paper are collected from different sources like Net Flow logs, call records and DNS query logs. These different types of data are aggregated together to decrease the missing information. Finally, machine learning algorithms are evaluated based on the customer dataset. The results of this study indicate that the gradient boosting algorithm performs better than other machine learning algorithms for this dataset. Keywords: Data analysis, customer satisfaction, subscriber churn, machine learning, telecommunication.