No abstract

This research includes an analytical study of the administrative and scientific work in departments, branchs and units of the Kirkuk University Presidency. It aims to convert the traditional routine work to the electronic work at the university by applying E-Management technique as one of the required modern logical solutions most commonly used to facilitate the difficulty of managing the vast amount of documents and delaying workflow that facing most institutions and organizations. In view of the increasing and urgent need for the use of E-Management systems throughout all the departments of the university presidency, the Electronic Distributed Kirkuk University Management System (E-DKUMS) is designed by using of Distributed Databases (DDB) technique, as well as using of electronic network infrastructure (LAN) that connects all the university configurations. The results of system implementation demonstrated that it is distinguished with high performance and speed, very high reliability and security, as well as very few employment cost. Test and evaluation results proved the ability of the system to facilitate the progress of managerial functions, reduce the time and effort, and capability of restructuring the administrative structure because of its excellence with flexibility in the creation and deletion departments, branches, and units for the system; in addition to easily troubleshot and fast execution.

Neuroevolutionary algorithms, such as NeuroEvolution of Augmenting Topologies (NEAT) in Machine Learning (ML) methods, are utilized for training and playing computer games due to increased research in Artificial Intelligence (AI) field. NEAT is a genetic algorithm for the generation of evolving artificial neural networks. In this paper, a new study is presented. A Dama board game is designed, and the NEAT algorithm is implemented to develop and train the populations of neural networks for playing the game efficiently. Different inputs and outputs for the network are used, and various network sizes are tried for the game to reach or pass the human level. This paper aims to make a neural network that plays a Dama game like humans or is close by training different neural networks for many generations. The experimental results show that neural networks have been trained for several thousands of generations, and they have played more than one million games. It is concluded that using more input to handle information is better for the learning process. It is also found that a set of values for NEAT parameters is suitable for extensive neural networks like those used in this paper. Povzetek: je predstavljena nova študija. Zasnovana je tradicionalna igra, imenovana "Dama", in implementiran je algoritem NEAT za razvoj in usposabljanje populacij nevronskih omrežij, da igrajo igro, prvič, na način, ki presega človeške zmožnosti.

The key target of Distributed Denial-of-Service (DDoS) attacks is to interrupt and suspend any available online services either executed for professional or personal gains. These attacks originate from the fast advancement in the number of insecure technologies. The attacks are caused due to the easy access to internet and advent of technology resulting to exponential growth of traffic volumes. DDoS attack remains most leading security risks to provisioning services. Also, the current embraced security mechanism for defense lacks flexibility and adequate resources to combat these attacks. Hence, there is need to embrace various other critical resources, where they can share the problem of mitigation. In addition, emerging technologies for instance smart contracts and blockchain offers for the sharing of these potential attacks information in an entirely automated and distributed manner. This paper recommends for a blockchain design which combines smart contracts and Machine Learning (ML) technologies, by presenting new ideal opportunities towards efficient DDoS mitigation solutions in variety of cooperative domains. Furthermore, the key advantage and benefits of this structure is deployment of still existing distributed and public infrastructure to blacklisted IP address or even advertise white, and the application of such an infrastructure with further defense mechanisms to current attacks of DDoS, deprived of considering distribution mechanisms or specialized registries, which facilitates the implementation of procedures across diverse domains. This paper further presents the demonstration and implementation features of this blockchain structure, discussion and study findings over these smart contracts and ML technologies. The study further concludes by recommending use of smart contract in collaborative block-chain design with ML for mitigating future attack of DDoS.Povzetek: Ta dokument priporoča zasnovo blockchain, ki združuje nastajajoča orodja s pametnimi pogodbami in tehnologijami strojnega učenja, ki predstavlja nove idealne priložnosti za učinkovite rešitve za ublažitev DDoS-jev na različnih področjih sodelovanja.

No abstract