Logo

Publikacije (37601)

Nazad
Li Zhang, Jun Wu, Shahid Mumtaz, Jianhua Li, H. Gačanin, J. Rodrigues

With the development of smart cities, the demand for artificial intelligence (AI) based services grows exponentially. The existing works just focus on cloud- edge or edge-device cooperative AI which suffers low learning efficiency of AI, while edge-to-edge cooperative AI is still an unresolved issue. Moreover, the existing researches concentrate on the computation offloading of the AI-based task, ignoring that it is a brain-like task performing sophisticated processing to raw data, which leads to the high latency and low quality of the learning services. To address these challenges, this paper proposes an on-demand learning offloading mechanism for edge-to-edge cooperative AI. Firstly, the principle of the learning capability and its offloading are proposed for the formal description of the learning resources migration. Secondly, the proposed mechanism realizes the bilateral learning offloading utilizing edge-to-edge and cloud-edge collaborations to handle AI-based tasks with high learning efficiency and resource utilization rate. Moreover, we model the edge-to-edge learning offloading allocation based on the concatenation of deep neural network (DNN) subtasks and their heterogeneous requirement of learning resources. Simulation results indicate the rationality and efficiency of the proposed mechanism.

Six Sigma is a version, a philosophy, a strategy and a set of tools for improvement of the quality services and processes. Till now, this method was mostly used in the world of manufacture. Telecommunication is the industry that is based on the service, where the customers are the main focus, and their needs very often seem unpredictable. In this work, a critical review had been given to the application of the Six Sigma methodology in the department of customers support of a telecom company. Through SWOT analysis, given is a review of the opportunities and challenges of this methodology, and also what is necessary to be changed for this methodology to have a purpose and application in one telecommunication company.

The action of forces in the back and abdomen under conditions of loading of different external forces at different bending angles is unexplored area. This paper presents a methodology that enables calculation of the magnitudes of forces in the back and abdominal muscles using the combined techniques of the CATIA software system, appropriate mathematical model and polynomial regression analysis. The person of 180cm in height and 85 kg in weight is loaded with 5 + 5 kg of cargo in both hands, and three cases of bending angles of 150, 300 and 600 relative to the vertical axis are analysed.

In this paper, an analytical calculation of load on bridge crane carts winch wheel loads was performed based on which FEM analysis and topological wheel optimization were performed. After the calculation, a standard wheel diameter was adopted. During FEM analysis in the CAD system, SolidWorks noted that certain surface areas had extremely low stress values, which was the main reason for the topological optimization of the wheel. The topological optimization of the geometric 3D model of the wheel is made in the CAESS ProTOp software, resulting in optimized 3D geometric wheel model. These models offer a number of advantages, such as saving materials to produce, reducing their own weight, balance stress conditions and easy customization model optimized technologies of additive manufacturing. This model of analysis and optimization was performed on the laboratory model of the bridge crane and it is applicable to all types of cranes.

Sejfo Papić, Fuad Klisura, Safet Velić

<p style="text-align: justify;">Bearing in mind that the wheel sleeves of motor vehicles are exposed to strong dynamic loads, and knowing that these are very responsible parts of the constructions, the need for permanent researches of the influence of certain variables on the process of production of them is imposed. The prepared part which, in this case, is obtained by forging from the appropriate steel has an important role. The process of forging, implies the appearance of certain errors that can manifest in many ways. Such mistakes, despite rigorous control, are difficult to eliminate completely. The paper deals with prepared parts with errors and their impact on the consistency of the tools, as well as the analysis of the influence of the change in the percentage of some elements on the same.</p>

This chapter examines the concept of digital assets from an angle that has not yet been explored in legal scholarship around digital death and the transmission of digital assets on death. Digital death is conceived herein as the death of an individual who leaves behind various digital fragments of their identity, either in the form of digital assets broadly or as digital biographies, dossiers, autobiographies and archives. Digital death causes uncertainty as to what happens in this dispersed, interconnected and often unregulated digital space, which Kasket lucidly entitles The New Elysium. Most legal scholars have considered digital assets either from a perspective of ‘hard law’ of succession and probate or the intersection of property, contracts and intellectual property; sometimes referring to data protection, jurisdiction or cybercrime. The scholars have not ventured into exploring theory that goes beyond theories of property, intellectual property and privacy. The chapter begins by examining classical conceptualisations of digital assets as property and the ‘”new” new property’, exploring whether this is the correct way to perceive digital assets conceptually. It will then go on to examine post-mortem privacy in the context of digital assets, and introduce a novel link with the Floridian concept of informational bodies. In the attempt to offer a comprehensive framework and a more nuanced normative support for future policy and law, the chapter interrelates all of the concepts with the ideas of postmortal society, introducing a new concept of ‘postmortal privacy’. Finally, the author uses this conceptualisation to test some of the existing legal regimes in the area of the transmission of digital assets. Suggestions from this chapter remain mainly at an abstract level, due to the scope and the nature of the framework it introduces.

J. Husić, Sabina Baraković, Seudin Kasumović

The rapid growth in subscribers and usage of multimedia services enlarges the volume of Session Initiation Protocol (SIP) call control signalling creating a need to understand Quality of Experience (QoE) in this case and improve it. This paper provides an analysis of influence of SIP call control signalling on QoE for Voice over Internet Protocol (VoIP) service. The aim was to investigate whether SIP call control signalling load has the influence on the human perception of SIP signalling performances and QoE, and to identify the importance of distinct SIP-based signalling performance metrics. Moreover, the intention was to determine whether SIP call control signalling load changes its impact if previously proposed algorithm for differentiated treatment of SIP messages is activated, and quantify mutual relationships of considered user perceptions and QoE. The findings show that SIP call control signalling load has a strong and negative impact on dependent variables and that the proposed algorithm improves QoE and human perception of SIP signalling performances.

Enida Cero Dinarevic, J. Barakovic, Sabina Baraković

Human activity recognition (HAR) is a classification process that is used for recognizing human motions. A comprehensive review of currently considered approaches in each stage of HAR, as well as the influence of each HAR stage on energy consumption and latency is presented in this paper. It highlights various methods for the optimization of energy consumption and latency in each stage of HAR that has been used in literature and was analyzed in order to provide direction for the implementation of HAR in health and wellbeing applications. This paper analyses if and how each stage of the HAR process affects energy consumption and latency. It shows that data collection and filtering and data segmentation and classification stand out as key stages in achieving a balance between energy consumption and latency. Since latency is only critical for real-time HAR applications, the energy consumption of sensors and devices stands out as a key challenge for HAR implementation in health and wellbeing applications. Most of the approaches in overcoming challenges related to HAR implementation take place in the data collection, filtering and classification stages, while the data segmentation stage needs further exploration. Finally, this paper recommends a balance between energy consumption and latency for HAR in health and wellbeing applications, which takes into account the context and health of the target population.

Nema pronađenih rezultata, molimo da izmjenite uslove pretrage i pokušate ponovo!

Pretplatite se na novosti o BH Akademskom Imeniku

Ova stranica koristi kolačiće da bi vam pružila najbolje iskustvo

Saznaj više