The growing need for autonomous systems in offshore industries has contributed to the increased use of machine learning methods. These systems promise to improve safety in operations. However, the methods as enablers of autonomy are susceptible to various failures while interpreting data and making decisions. Several studies have highlighted the lack of research on the reliability and resilience of autonomous systems powered by these standard methods. Recent research provides sets of data interpretation methods. Despite the popularity of machine learning, there is a significant drop in knowledge when these methods result in failures. These failures further support autonomous systems in making wrong decisions. For autonomous systems, resilience and safety management should be an integrated functionality for recovery from risky situations and reporting of incidents. This research proposes an overview of machine learning methods for interpreting sensor data captured by drones operated manually and autonomously. We apply Isolation Forest for anomaly detection analysis and evaluate the Decision tree, Random forest, kNN, Logistic Regression, SVM, and, Naive Bayes for classification analysis. The methods are chosen based on their adequacy and comparative research prevalence. Comparison between the two drone operation modes contributes to understanding the reliability level for autonomously collected data. This research’s results provide an evaluation of machine learning methods’ performance across sensor data.

PURPOSE OF THE STUDY The hip fracture is the leading cause of disability and deaths in elderly. If left untreated, the hip fracture results in inability to walk, and therefore the patient is dependent on the other's people help. The aim of this study was to determine the predictive values of the functional status, present comorbidities, and the types of treatment on the long-term functional status and mortality in patients with the hip fracture. MATERIAL AND METHODS We analyzed the data about the patients with the hip fractures treated in the period between 01.07.2006. and 01.07.2016., with the mean follow-up period between 34.3±4.9 months. The data included radiographs, age, comorbidities, functional status on admission, functional status on discharge, and follow-ups. RESULTS Female sex, increasing age, and poorer functional status upon admission, conservative treatment, trochanteric fracture, the presence of neurological or lung disease, diabetes, were all significant risk factors leading to poorer functional outcomes on the latest follow-up (p < 0.05). On the other hand, the patients who were mobile upon admission had a longer survival (38.1±3.51 months) as compared with the other patients (12.3±5.1 months; χ2=25.202, p = 0.001). Besides, the results of this study revealed that the direct, statistically significant relationship exists between the untreated internal and neurological diseases, and increased mortality and poorer functional outcomes on the latest follow-up. CONCLUSIONS These results are useful for the orthopedic and trauma surgeons, who are treating these patients, the physical medicine and rehabilitation specialists, who are performing the rehabilitation of these patients, but also the health policy makers, who may promote the programmes of healthy aging (treating the diseases, maintaining fitness, etc.) Key words: hip fracture; comorbidity; mortality; functional status.

Background Pharmacogenomics (PGx) testing can reduce toxicities and improve efficacy of several drugs used to treat cancer and associated symptoms. PGx results can be determined from germline whole-exome sequencing (WES), but somatic mutations may cause discordance between tumor and germline DNA. Since clinical diagnostic sequencing in oncology frequently only includes tumor DNA, there would be clinical value in calling germline PGx genotypes from tumor DNA. Thus, the purpose of this study was to assess the feasibility of using somatic WES data to call germline PGx genotypes. Methods Germline and somatic WES data were obtained as part of the clinical workflow for 64 patients treated at the solid molecular tumor board clinic at Indiana University. Aldy v3.3 was implemented in LifeOmic’s Precision Health Cloud™ to call PGx genotypes from somatic WES. Somatic Aldy calls were compared with previously validated Aldy germline calls for 8 genes: CYP2C9, CYP2C19, CYP2D6, CYP3A4, CYP3A5, CYP4F2, DPYD, and TPMT. Somatic read depth was >100x, except for the intronic CYP3A4*22 variant, which was >30x. Results Somatic and germline Aldy calls were compared for a total of 512 genotypes and 56 (11%) calls were discordant. Discordant calls were most common for CYP2B6 (23.4%), followed by CYP2D6 (14.1%), CYP2C19 (10.9%), CYP2C8 (6.3%), and DPYD (6.3%). In contrast, all Aldy calls were concordant for CYP3A5 and TPMT. 38 out of 64 subjects (59%) had discordant calls for at least one gene. The most common first cancer diagnoses in our cohort were colorectal (9.3%), breast (7.8%), and pancreatic (7.8%), and the rates of discordant Aldy calls did not differ by cancer type (p>0.05 for all cancer types). Based on our analyses of discordant calls, we anticipate that adjusting Aldy’s thresholds for variant calling may allow Aldy to determine genotypes from somatic WES data. Conclusion In most cases, genotype calls of drug metabolism genes from tumor DNA reflected the germline genotypes; however, additional work needs to be done to determine if the remaining discordant calls can be corrected by modifying the informatics tools or if they are due to somatic mutations. Citation Format: Wilberforce A. Osei, Tyler Shugg, Reynold C. Ly, Steven M. Bray, Benjamin A. Salisbury, Ryan R. Ratcliff, Victoria M. Pratt, Ibrahim Numanagić, Todd Skaar. Pharmacogenomics genotyping from clinical somatic whole exome sequencing: Aldy, a computational tool [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1151.

Evolving Internet applications, such as immersive multimedia and Industry 4, exhibit stringent delay, loss, and rate requirements. Realizing these requirements would be difficult without advanced dynamic traffic management solutions that leverage state-of-the-art technologies, such as Software-Defined Networking (SDN). Mininet represents a common choice for evaluating SDN solutions in a single machine. However, Mininet lacks the ability to emulate links that have multiple queues to enable differentiated service for different traffic streams. Additionally, performing a scalable emulation in Mininet would not be possible without light-weight application emulators. In this paper, we introduce two tools, namely: QLink and SPEED. QLink extends Mininet API to enable emulating links with multiple queues to differentiate between different traffic streams. SPEED represents a light-weight web traffic emulation tool that enables scalable HTTP traffic simulation in Mininet. Our performance evaluation shows that SPEED enables scalable emulation of HTTP traffic in Mininet. Additionally, we demo the benefits of using QLink to isolate three different applications (voice, web, and video) in a network bottleneck for numerous users.

Reinforcing the polymer with nanoparticles and fibers improves the mechanical, thermal and electrical properties. Owing to this, the functional parts produced by the FDM process of such materials can be used in industrial applications. However, optimal parameters’ selection is crucial to produce parts with optimal properties, such as mechanical strength. This paper focuses on the analysis of influential process parameters on the tensile strength of FDM printed parts. Two statistical methods, RSM and ANN, were applied to investigate the effect the layer thickness, printing speed, raster angle and wall thickness on the tensile strength of test specimens printed with a short carbon fiber reinforced polyamide composite. The reduced cubic model was developed by the RSM method, and the correlation between the input parameters and the output response was analyzed by ANOVA. The results show that the layer thickness and raster angle have the most significant influence on tensile strength. As for machine learning, among the nine different tested ANN topologies, the best configuration was found based on the lowest MAE and MSE test sample result. The results show that the proposed model could be a useful tool for predicting tensile strength. Its main advantage is the reduction in time needed for experiments with the LOSO (leave one subject out) k-fold cross validation scheme, offering better generalization ability, given the small set of learning examples.

Sažetak: Autori u radu analiziraju položaj stečajnog upravitelja prema novom Zakonu o stečaju u Federaciji Bosne i Hercegovine koji je stupio na snagu 15. srpnja 2021. godine. Stečajni upravitelj kao operativno tijelo u stečajnom postupku ima središnju ulogu i od njegovog postupanja ovisi i učinkovitost stečajnog postupka. Položaj stečajnog upravitelja je specifičan jer u sebi objedinjuje dvije funkcije. On je tijelo stečajnog postupka s javnim ovlastima i zastupnik je dužnika po zakonu. Zbog tog specifičnog položaja je iznimno bitno i na koji način je reguliran njegov rad i nadzor nad njegovim postupanjem. Radi jačanja povjerenja u pravosudni sustav izbor i imenovanje stečajnih upravitelja trebao bi biti transparentan. Iako su nove zakonske odredbe unaprijedile sveukupan položaj stečajnih upravitelja, autori daju kritički osvrt na pitanja koja su ostala neregulirana i koja bi stečajni postupak učinila transparentnijim i učinkovitijim. Ključne riječi: stečaj, stečajni postupak, privremeni stečajni upravitelj, stečajni upravitelj, povjerenik

Even though interest in Machine Learning Based Clinical Decision Support Systems (ML-CDSS) has been rapidly growing in recent years, most research and development is exclusively focused on secondary and tertiary care – even though effective diagnostic support in primary care could significantly improve both the circumstances, the process and the outcome of general practice. In this paper, we study the suitability of five supervised machine learning algorithms to the problem of multiclass classification with sparse Boolean features on a primary care data set, and we examine the robustness of the algorithms to incomplete data. We introduce our own classification algorithm, the Artificial Intelligence Based Diagnostic Assistant (AIDA), which is capable of incorporating both symptoms and contextual information into its diagnostic process, thus modeling the decision-making of physicians in a novel and accurate manner. Through our experimental results we show that AIDA is by far the most suitable classification algorithm for ML-CDSS applications in primary care, owing to its high accuracy and outstanding robustness to missing, sparse information.

Biological carbon sequestration is considered an important strategy to mitigate climate change. The energy crop Miscanthus × giganteus has great sequestration potential. The objective of this study was to determine: a) the dry matter yield and carbon content in aboveground and belowground biomass; b) the total carbon balance in the plant and soil pool. The study was conducted in continental Croatia (N 45°51′01.32″; E 16°10′35.85″) by the destructive harvesting of five-year-old Miscanthus × giganteus stands established by rhizomes (MxgR) and seedlings (MxgS) in the spring of 2021. The soil sampling was conducted in 2016 and 2022. The average amount of carbon in the aboveground biomass of MxgR and MxgS is 11.51 t/ha and 9.87 t/ha, respectively, and in the belowground biomass it is 13.18 t/ha and 14.90 t/ha, respectively. The carbon balance in the plant pool of MxgR is three times lower (1.67 t/ha) than that in the plant pool of MxgS (5.03 t/ha). The total soil carbon content increased by 8.7 t/ha under MxgR and by 14.8 t/ha under MxgS during 2016–2022. Therefore, under the studied agroecological conditions, seedlings should be preferred over rhizomes in the selection of planting material. The obtained data represent valuable input data for sequestration modeling.

Family VIII esterases present similarities to class C β‐lactamases, which show nucleophilic serines located at the S‐X‐X‐K motif instead of the G‐X‐S‐X‐G or G‐D‐S‐(L) motif shown by other carboxylesterase families. Here, we report the crystal structure of a novel family VIII (subfamily VIII. I) esterase (EH7; denaturing temperature, 52.6 ± 0.3 °C; pH optimum 7.0–9.0) to deepen its broad substrate range. Indeed, the analysis of the substrate specificity revealed its capacity to hydrolyse nitrocefin as a model chromogenic cephalosporin substrate (40.4 ± 11.4 units·g−1), and a large battery of 66 structurally different esters (up to 1730 min−1), including bis(2‐hydroxyethyl)‐terephthalate (241.7 ± 8.5 units·g−1) and the mycotoxin T‐2 (1220 ± 52 units·g−1). It also showed acyltransferase activity through the synthesis of benzyl 3‐oxobutanoate (40.4 ± 11.4 units·g−1) from benzyl alcohol and vinyl acetoacetate. Such a broad substrate scope is rare among family VIII esterases and lipolytic enzymes. Structural analyses of free and substrate‐bound forms of this homooctamer esterase suggest that EH7 presents a more opened and exposed S1 site having no steric hindrance for the entrance of substrates to the active site, more flexible R1, R2 and R3 regions allowing for the binding of a wide spectrum of substrates into the active site, and small residues in the conserved motif Y‐X‐X containing the catalytic Tyr enabling the entrance of large substrates. These unique structural elements in combination with docking experiments allowed us to gain valuable insights into the substrate specificity of this esterase and possible others belonging to family VIII.

We propose a control protocol based on the prescribed performance control (PPC) methodology for a quadro-tor unmanned aerial vehicle (UAV). Quadrotor systems belong to the class of underactuated systems for which the original PPC methodology cannot be directly applied. We introduce the necessary design modifications to stabilize the considered system with prescribed performance. The proposed control protocol does not use any information of dynamic model parameters or exogenous disturbances. Furthermore, the stability analysis guarantees that the tracking errors remain inside of designer-specified time-varying functions, achieving prescribed performance independent from the control gains’ selection. Finally, simulation results verify the theoretical results.

Objectives To assess the severity of symptoms, duration of infection and viral loads of health-care workers (HCWs) who tested positive for Coronavirus disease 2019 (COVID-19) during Omicron’s prevalence, in regard to vaccination and previous infection. Methods During 2 weeks of highest rate of COVID-19 cases in Bosnia and Herzegovina, the positive nasopharyngeal swabs were analysed in 141 HCWs by reverse transcription quantitative PCR, targeting four different genes: RdRp, E, N and nsp14. Uniformed questionnaire was used to collect relevant sociodemographic and epidemiological data from HCWs divided into four groups: unvaccinated/not previously infected (group 1); unvaccinated/previously infected (group 2); vaccinated/not previously infected (group 3); and vaccinated/previously infected (group 4). Results We observed that occurrence of fever and smell or taste loss were more frequent in group 1 (86.4% and 25%) and group 3 (76.9% and 19.2%), in comparison to group 2 (64.4% and 6.7%) and group 4 (69.2% and 3.8%), ( p  = 0.023 and p  = 0.003). Although statistically not significant, group 2 (61.9%), group 3 (65.4%), and group 4 (70.8%) experienced negativization within 7 days of positive RT-qPCR test, whereas 51.2% of HCWs from group 1 tested negative later on. There is no significant difference between all four groups regarding Ct values of analysed genes. Conclusion During Omicron’s prevalence, the vaccination had less substantial effect on symptomatic disease among HCWs, while fever and loss of smell or taste were considerably less likely to occur upon reinfection. Since viral loads and negativization periods do not seem to significantly vary, irrespective of pre-existing immunity, systemic vaccination and mask-wearing should still be considered among HCWs.