ERASMUS+ project The Future is in Applied Artificial Intelligence (FAAI) aims to increase the quality and relevance of students' and graduates' knowledge and skills in AI/ML-specific topics based on skills needed in the labor market. This paper presents the results of the survey that was conducted in the context of the FAAI project to assess the needs of employers in project participants' countries in graduates' competencies in Artificial Intelligence, Machine Learning, and Data Science in general for the purpose of training specialists in the field of Applied AI. The survey was filled in by 38 companies and consisted of 31 questions related to general required competencies, type of machine learning problems solved, AI libraries used in companies, required soft skills, employers' satisfaction with the level of preparedness of master's degree graduates in the field of AI.
In this paper we analyze a user-centric handover procedure, which can be used to improve the downstream communication from low Earth orbit satellite network to end-users, in presence of shadowed-Rician fading. We consider usage of DVB-S2X protocol and numerically express the improvement, measured by average spectral efficiency and data loss rate, achievable with employment of multiple satellites. The improvement is a consequence of the proposed strategy to predict the signal-to-noise ratio in the considered communication channel.
This paper presents a design sensitivity analysis for microwave power amplifiers (PAs). Specifically, the variation of matching circuit elements within a given range is taken into account during the design process using a multi-objective interactive visualization method. The method is illustrated on the example of a 5-W peak power GaN MMIC intended to operate around 8-14 GHz over a range of drain supply voltages for envelope tracking. In this circuit, the measured performance is shifted to higher frequencies compared to the design. Applying a sensitivity analysis method demonstrates how a ±20% variation of capacitors used in the process affects performance. We demonstrate that the method can be used to analyze trade-offs between multiple output performance metrics in PA design, additionally demonstrating a design sensitivity metric that can be included in future designs.
This study conducts a comparative survey of some outstanding works on non-anthropomorphic robotic hands over the past four decades. In this research, the specific features of these works are identified by describing and evaluating their structures. In addition, the possibility of the practical application of these hands is provided. As a result, some comparative comments were also figured out. All these analyses and evaluations serve as the basis for the author's design of the non-anthropomorphic hand. The paper concludes with a brief on the author's design.
The work is devoted to designing a manufacturing network incorporating logistic-production sites that are located at the nodes of the squared lattice with the help of the AI technique. We focused on qualitative analysis of the dynamic behavior of the dynamic lattice model. The model includes rate constants and initial conditions affecting the trajectories of the model which can be classified either as a stable node, limit cycle, or chaotic attractor. We aim to solve the problem of the model qualitative behavior as an AI classification problem. The training dataset is constructed with the help of Monte-Carlo simulation with high-performance computing in Julia. The AI model is built as a C5.0 decision tree. The work was fulfilled with the framework of Erasmus+ Project No. 2022-1-PL01-KA220-HED000088359 entitled "The Future is in Applied Artificial Intelligence" (FAAI) and offers a use case to be studied during the applied AI training course.
This paper presents an overview of the recent advances we made in the field of microwave sensors. Sensors for different physical quantities are presented, ranging from structures for the retrieval of the electric and magnetic characteristics of materials, to devices for the determination of position and angular rotation. These sensors are based on various fabrication technologies, including planar structures, additive manufacturing, and hybrid solutions, which take advantage of the best features of different technologies.
The work is fulfilled within the framework of Erasmus+ project "The Future is in Applied Artificial Intelligence" (FAAI) and devoted to the development the methodology for collecting and analyzing good practices in the field of applied artificial intelligence (AAI) regarding the competences, training, existing solutions and real cases, which can be used for developing training courses of competence based education. Here we propose the definition of good practice in the field of AAI together with the corresponding criteria and features. The offered methodology uses system research based on the data gathered from existing training courses in AAI, labor market, surveys filled in by academics, students and employers, AAI use cases in science and industry.
A new feeding method of the crossed slot antenna is introduced in this paper. The crossed slot antenna consists of two identical rectangular parts slots positioned at the right angle, at the upper side of the substrate. It is fed by microstrip line on the opposite bottom substrate side without the influence on the desired radiation pattern of the slot antenna. This new method of feeding is compared with uniplanar feeding method by coplanar waveguide line (CPW). A new feeding method enables almost 2.5 times greater operating range of the crossed slot antenna, defined by S 11 parameter, than CPW feeding. Also, feeding by microstrip line has a potential advantage in design of crossed slot antenna arrays with incorporated tapered distribution requested for high gain antenna with low side lobe suppression, as well as scanning antennas with corresponding delay lines which are separated from radiating elements.
This article is fulfilled within the framework of Erasmus+ project "The Future is in Applied Artificial Intelligence (FAAI). It gives overview of current job market related to the field of Applied Artificial Intelligence. The data is obtained from online survey, and it gives highlights of several aspects of labor market divided into research and analysis of the market, and specific requirements necessary. Regarding research and analysis, the data provided deals with:-positions offered in the market.-machine learning problems occurring.-models being developed while resolving the real-world problem.-machine learning tasks to be solved.The collected data in the domain of job market requirements gives highlight about:-required programming languages.-educational requirements.-required competencies.Results given can serve as a guide to which competencies are necessary in the field of AAI and provide information for both professionals and curriculum creators.
This article is devoted to the development of ways to solve one of the main problems of all modern blockchain platforms – the problem of scaling. The authors consider using the segmentation of the blockchain network for this purpose by dividing it into separate segments – the so-called shards. Each shard is, in fact, a separate blockchain with its state. Sharding is undoubtedly one of the most difficult solutions, but also the most promising solution to ensure linear performance growth of modern blockchain platforms.
The paper presents results of analysis aimed to increase gain of planar PCB antenna arrays through combining fewer complex arrays into bigger antenna systems. Analysis starts from 256-antenna elements arrays and investigates various aspects of combining few such antennas into bigger arrays - like number of antennas, topology, efficient low loss microwave power transfer and combining, current distribution aspects etc. Analysis shows that there is a room to increase gain of planar PCB antenna arrays to levels above ~30dBi and proposed approach could be used to fulfill requirements for nowadays demanding perimeter surveillance and security radar applications.
This study focuses on analyzing historical data to forecast future trends in Bitcoin prices due to its influence on the business landscape. Its high volatility attracted attention to understanding the influencing factors for its price. This paper presents an empirical investigation using time-series data of various exogenous and endogenous variables. Closing prices of Bitcoin and Ethereum, along with the daily volume of Bitcoin-related tweets are examined for Bitcoin closing price prediction by a long-short term memory (LSTM) network, fine-tuned by a hybrid adaptive reptile search algorithm. The analysis covers a three-year period, in which data is divided into training, validation, and testing sets. Comparative analysis against LSTM networks tuned by other high-performing metaheuristic algorithms demonstrates that the novel approach outperforms competitors in terms of standard regression metrics.
To find the future directions for the anti-drone radar (ADR) industry, we compare 14 commercial off-the-shelf (COTS) ADR by 14 criteria, and classify them by 3 criteria. Our analysis shows that COTS ADR manufacturers could benefit from focusing on passive ADR, multiple-input multiple-output ADR, and classification based on machine learning.
The influence of the mobile phone position on the electromagnetic field distribution inside the biological tissues of the user's head is discussed in the paper. The case of voice transmission was simulated at the frequency of 0.8 GHz. Numerical models of a child's head and a smartphone have been used. The distribution of the magnetic field within user's head tissues for different positions of the mobile phone is considered.
The localization represents human and devices position determination. In fingerprinting technique, the machine learning algorithms are used to estimate the position based on comparison of the new and required position. In this paper the accuracy and confusion matrices of five machine learning algorithms were analysed to find the most suitable.
With the increased demand for additional bandwidth, when it comes to the Metropolitan Area Networks, there is also a growing need to keep the local traffic local. Preventing the traffic of local origin from "spilling" over the MAN borders, or maybe even country borders become one of the very important tasks. This is where local Internet Exchange Points can help. This paper illustrates possibilities local IXP implementation has to offer (city of Nis, Serbia in this case) and improvements that can come out of it.
In this paper we are concerned with the low probability of detection (LPD) and covert radars employing optical incoherent sources. Key idea of our proposed LPD/covert radar concept is to hide the radar signal in solar radiation by employing the broadband (>30 nm) Erbium-doped fiber amplifier source, modulating such source output beam with a constant amplitude modulation format at high-speed, and detect the presence of the target by the cross-correlation method. To demonstrate the proposed concept we developed an outdoor free-space optical (FSO) testbed at the University of Arizona campus. To improve the tolerance to atmospheric turbulence effects the adaptive optics is used. We demonstrate that the LPD/covert radar concept over strong turbulent FSO channel is feasible in a desert environment.
Achieved spectral efficiency is one of the most important metrics in mobile communication systems performance assessment. In this paper methodology on how to assess it in 5G/NR systems is discussed, as well as examples of relevant network performance analysis from commercially deployed network, through underperforming channels identification and troubleshooting. It is shown that proposed methodology provides valuable network insights.
This paper overviews the most recent advances in the unstructured Transmission Line Modelling method that is uniquely placed for modeling advanced photonic applications with multi-scale features. The paper focuses on the holistic approach that needs to be taken when considering these applications which involves not just the electromagnetic solver, but also important aspects of the unstructured mesh generation and geometry definition. The capability of the UTLM is demonstrated on the complex geometry of a photonic polarization splitter that incorporates diverse components namely tapers, multimoded waveguides and a photonic crystal region.
