The highly dynamic wireless communication environment poses a challenge for many applications (e.g., adaptive multimedia streaming services). Providing accurate TP can significantly improve performance of these applications. The scheduling algorithms in cellular networks consider various PHY metrics, (e.g., CQI) and throughput history when assigning resources for each user. This article explains how AI can be leveraged for accurate TP in cellular networks using PHY and application layer metrics. We present key architectural components and implementation options, illustrating their advantages and limitations. We also highlight key design choices and investigate their impact on prediction accuracy using real data. We believe this is the first study that examines the impact of integrating network-level data and applying a deep learning technique (on PHY and application data) for TP in cellular systems. Using video streaming as a use case, we illustrate how accurate TP improves the end user's QoE. Furthermore, we identify open questions and research challenges in the area of AI-driven TP. Finally, we report on lessons learned and provide conclusions that we believe will be useful to network practitioners seeking to apply AI.

This paper presents an empirical validation of a polarized channel model for off-body communications with dynamic users, based on wideband indoor measurements at 5.8 GHz with a 500 MHz bandwidth. The model is based on geometrical optics, and takes the signal depolarization and influence of user dynamics into account. By considering a scenario with the user walking towards an access point with co-located vertical and horizontal dipole antennas, the simulated receiver (Rx) power is compared against measurements for wearable antenna placements on the chest, wrist and lower leg. The obtained root mean square error is found to be within 2.8 dB for the vertical off-body antenna polarization, and within 3.2 dB for the horizontal one. Fairly matching Rx power values are obtained even when only free space propagation is considered in the simulator, with the error being below 3.4 dB in most cases.

This paper analyses the impact of the human body on antenna radiation characteristics, with a focus on the polarization aspect. The effect of the body tissues on a wrist-worn ultra-wideband double loop antenna radiation characteristics is investigated at 3, 4 and 5 GHz, based on numerical full-wave simulations complemented with a voxel model of a hand. Results show a strong influence of the body on the gain and polarization characteristics; the radiation in the direction towards the body is suppressed by 20 dB or more, and the antenna polarization changes from a linear to an elliptical one. By simulating an off-body communications scenario with the user walking at a fixed distance from the off-body antenna, up to 6.5 dB lower received power is obtained by using the wearable antenna radiation pattern simulated with the hand phantom, compared to the case when the antenna in free space.

Despite the rapid improvements in the field of microgrid protection, it continues to be one of the most important challenges faced by the distribution system operators. With the introduction of this new operation concept, the existing protection devices are not able to successfully identify, classify and localize different types of faults that occur in the microgrids due to their dynamic behaviour, especially in the islanded mode of operation. This paper presents a methodology that provides the station protection functionalities that include detection and classification of faults, isolation of the faulty feeder and fault location estimation. The proposed method is based on discrete wavelet transform and artificial neural networks. The test system based on the real data, completely developed in MATLAB Simulink, is used to demonstrate the accuracy of all functionalities of the station protection algorithm that can be easily applied in microgrids. The presented results demonstrated the method accuracy and showed that it can be used as an upgrade of the existing protection equipment for the future implementation of the advanced microgrid station protection system.

This paper presents a data visualization method in 3D space that includes actual positions, volumes and space relations of the chunks of data that are being visualized. Data that is being visualized is real-time information provided by the smart warehouse management system about packages distributed on pallet places within a warehouse. Three different visualizations are shown: qualitative, quantitative and cumulative. The method is graded for the time needed to determine the location of all pallet places that fulfill searched criteria and getting the exact value of searched information for each pallet place. Challenges in presenting this data and interacting with resulting visualizations are discussed. It is concluded that showing actual positions of chunks of data greatly increases the speed of acquiring searched values and positions at the same time for outliers but has issues with clusters and multiple types of queried data.

Previous transcriptome-wide association studies (TWAS) have identified breast cancer risk genes by integrating data from expression quantitative loci and genome-wide association studies (GWAS), but analyses of breast cancer subtype-specific associations have been limited. In this study, we conducted a TWAS using gene expression data from GTEx and summary statistics from the hitherto largest GWAS meta-analysis conducted for breast cancer overall, and by estrogen receptor subtypes (ER+ and ER−). We further compared associations with ER+ and ER− subtypes, using a case-only TWAS approach. We also conducted multigene conditional analyses in regions with multiple TWAS associations. Two genes, STXBP4 and HIST2H2BA, were specifically associated with ER+ but not with ER− breast cancer. We further identified 30 TWAS-significant genes associated with overall breast cancer risk, including four that were not identified in previous studies. Conditional analyses identified single independent breast-cancer gene in three of six regions harboring multiple TWAS-significant genes. Our study provides new information on breast cancer genetics and biology, particularly about genomic differences between ER+ and ER− breast cancer.

The paper presents an online web-oriented system named SOLARS, which is aimed at calculating the feasibility of building the photovoltaic (PV) systems. SOLARS currently enables potential investors to calculate the technical and financial feasibility of building the PV systems in the Republic of Srpska (Bosnia and Herzegovina). Very intuitive GUI design enables investors to obtain feasibility calculations in three simple steps: (i) selection of a geographical location, (ii) specification of technical parameters, and (iii) specification of financial parameters. A usage scenario is illustrated by a real feasibility calculation example.

The effective collection and management of personal data of rapidly migrating populations is important for ensuring adequate healthcare and monitoring of a displaced peoples' health status. With developments in ICT data sharing capabilities, electronic personal health records (ePHRs) are increasingly replacing less transportable paper records. ePHRs offer further advantages of improving accuracy and completeness of information and seem tailored for rapidly displaced and mobile populations. Various emerging initiatives in Europe are seeking to develop migrant-centric ePHR responses. This paper highlights their importance and benefits, but also identifies a number of significant ethical, legal and social issues (ELSI) and challenges to their design and implementation, regarding (1) the kind of information that should be stored, (2) who should have access to information, and (3) potential misuse of information. These challenges need to be urgently addressed to make possible the beneficial use of ePHRs for vulnerable migrants in Europe.

The rapid development of financial markets results in data variability and unpredictability. Anomaly detection in financial data is a very important issue. Finding anomalies can result in error reduction and corrections in due time. The main aim of this research was to find anomalies in general ledgers of a real company in Bosnia and Herzegovina. Anomalies are defined as input errors of accountants. Main concepts of anomaly detection are defined, a summary of the current progress is given, and challenges of future work are presented. Cluster-based and histogram-based anomaly detections were performed on a real-life dataset of a microcredit organization. Results of algorithms were presented, as well as results achieved using synthetic data.

Postural orthostatic tachycardia syndrome (POTS) is a chronic, debilitating condition characterized by heterogeneous symptoms, such as lightheadedness, palpitations, pre-syncope, syncope, and weakness or heaviness, especially of the legs. It is frequently associated with hypermobile joints or conditions such as chronic fatigue syndrome, chronic abdominal pain, migraine headache, and diabetes mellitus. Described is a case of POTS, which though it is not rare, is rarely diagnosed. It can be diagnosed quickly with simple methods.