Explore the vast range of titles available.

Unmanned aerial vehicles (UAV), or drones, have gained a lot of popularity over the last decade. The use of autonomous drones appears to be a viable and low-cost solution to problems in many applications. Path planning capabilities are essential for autonomous control systems. An autonomous drone must be able to rapidly compute feasible and energy-efficient paths to avoid collisions. In this study, we review two key aspects of path planning: environmental representation and path generation techniques. Common path planning techniques are analyzed, and their key limitations are highlighted. Finally, we review thirty-five highly cited publications to identify current trends in drone path planning research. We then use these results to identify factors that need to be addressed in future studies in order to develop a practical path planner for autonomous drones.

The ISP (Internet Service Provider) industry relies heavily on internet traffic forecasting (ITF) for long-term business strategy planning and proactive network management. Effective ITF frameworks are necessary to manage these networks and prevent network congestion and over-provisioning. This study introduces an ITF model designed for proactive network management. It innovatively combines outlier detection and mitigation techniques with advanced gradient descent and boosting algorithms, including Gradient Boosting Regressor (GBR), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), CatBoost Regressor (CBR), and Stochastic Gradient Descent (SGD). In contrast to traditional methods that rely on synthetic datasets, our model addresses the problems caused by real aberrant ISP traffic data. We evaluated our model across varying forecast horizons—six, nine, and twelve steps—demonstrating its adaptability and superior predictive accuracy compared to traditional forecasting models. The integration of the outlier detection and mitigation module significantly enhances the model’s performance, ensuring robust and accurate predictions even in the presence of data volatility and anomalies. To guarantee that our suggested model works in real-world situations, our research is based on an extensive experimental setup that uses real internet traffic monitoring from high-speed ISP networks.

Realistic appliance power consumption data are essential for developing smart home energy management systems and the foundational algorithms that analyze such data. However, publicly available datasets are scarce and time-consuming to collect. To address this, we propose HYDROSAFE, a hybrid deterministic-probabilistic model designed to generate synthetic appliance power consumption profiles. HYDROSAFE employs the Median Difference Test (MDT) for profile characterization and the Density and Dynamic Time Warping based Spatial Clustering for appliance operation modes (DDTWSC) algorithm to cluster appliance usage according to the corresponding Appliance Operation Modes (AOMs). By integrating stochastic methods, such as white noise, switch-on surge, ripples, and edge position components, the model adds variability and realism to the generated profiles. Evaluation using a normalized DTW-distance matrix shows that HYDROSAFE achieves high fidelity, with an average DTW distance of ten samples at a 1Hz sampling frequency, demonstrating its effectiveness in producing synthetic datasets that closely mimic real-world data.

With recent advancements in artificial intelligence (AI) and next-generation communication technologies, the demand for Internet-based applications and intelligent digital services is increasing, leading to a significant rise in cyber-attacks such as Distributed Denial-of-Service (DDoS). AI-based DoS detection systems promise adequate identification accuracy with lower false alarms, significantly associated with the data quality used to train the model. Several works have been proposed earlier to select optimum feature subsets for better model generalization and faster learning. However, there is a lack of investigation in the existing literature to identify a common optimum feature set for three main AI methods: machine learning, deep learning, and unsupervised learning. The current works are compromised either with the variation of the feature selection (FS) method or limited to one type of AI model for performance evaluation. Therefore, in this study, we extensively investigated and evaluated the performance of 15 individual FS methods from three major categories: filter-based, wrapper-based, and embedded, and one ensemble feature selection (EnFS) technique. Furthermore, the individual feature subset’s quality is evaluated using supervised and unsupervised learning methods for extracting a common best-performing feature subset. According to our experiment, the EnFS method outperforms individual FS and provides a universal best feature set for all kinds of AI models.

Our increasingly connected world continues to face an ever-growing number of network-based attacks. An Intrusion Detection System (IDS) is an essential security technology used for detecting these attacks. Although numerous Machine Learning-based IDSs have been proposed for the detection of malicious network traffic, the majority have difficulty properly detecting and classifying the more uncommon attack types. In this paper, we implement a novel hybrid technique using synthetic data produced by a Generative Adversarial Network (GAN) to use as input for training a Deep Reinforcement Learning (DRL) model. Our GAN model is trained on the NSL-KDD dataset, a publicly available collection of labeled network traffic data specifically designed to support the evaluation and benchmarking of IDSs. Ultimately, our findings demonstrate that training the DRL model on synthetic datasets generated by specific GAN models can result in better performance in correctly classifying minority classes over training on the true imbalanced dataset.

Objectives: To describe the spectrum of complications of Diabetic Ketoacidosis (DKA) observed in children admitted with severe DKA.Methods: Retrospective review of the medical records of all children admitted with the diagnosis of severe DKA in Pediatric Intensive Care Unit (PICU) of the Aga Khan University Hospital, from January 2010 to December 2015 was done. Data was collected on a structured proforma and descriptive statistics were applied.Results: Total 37 children were admitted with complicated DKA (1.9% of total PICU admission with 1.8% in 2010 and 3.4% in 2015). Mean age of study population was 8.1

Enhancing resiliency in a power grid system is one of the core mandates of electrical distribution companies to provide high-level service. The power resiliency research community has proposed numerous schemes, to detect, classify, and localize fault events. However, the literature still lacks a comprehensive taxonomy of these schemes which can help advance future research. This study aims to provide a compact yet comprehensive review of the state-of-the-art solutions to fault analysis in transmission power systems. We discuss fault types and several fault-analysis methodologies adopted by relevant research works, propose a novel framework to classify these works, and highlight their strengths and limitations. We anticipate that this brief review would be helpful as a literature review and benefit the research community in choosing suitable techniques for fault analysis.

Objectives: To determine the frequency and predictors of outcome of gastrointestinal complications (GIC) in critically ill children. Methods: This descriptive study was prospectively conducted in The Pediatric Intensive Care Unit (PICU), The Aga Khan University Hospital (AKUH), Karachi, from September 2015 to January 2017. After obtaining approval from the Ethical Review Committee of AKUH and informed consent from the parents, all children (aged one month to 18 years), of either gender, admitted to the Pediatric Intensive Care Unit (PICU) during the study period were included. The frequency of the defined GIC: vomiting, high gastric residue volume (GRV), diarrhea, constipation, and gastrointestinal bleed were recorded daily for the first week of the PICU stay. The data was collected by the primary investigator on a predesigned data collection form with inclusion of variables and predictors in light of existing literature and local expertise. The questionnaire was shared with the Pediatric Critical Care Medicine faculty and a consensus was sought on the elements to be incorporated. Results: GIC developed within the first 48 hours of admission in 78 (41%) patients. Of the patients who developed GIC, 37 (47.4%) patients developed high GRV: 31 (39.7%) patients developed constipation, 18 (23.1%) patients developed vomiting, 14 (17.9%) patients developed abdominal distension. With regards to prevalence by occurrence, 32/78 (41%) of patients presented with two GI complications, followed by 21 patients (27%) who presented with a single GIC. Only 11 patients (14%) presented with more than three complications. Median length of stay was higher in patients with GIC (8 days) than with those who did not develop GIC (4 days). The frequency of gastrointestinal complications was significantly higher in children receiving mechanical ventilation, on sedatives and relaxants and those with multiorgan dysfunction syndrome (MODS) and inotropes Conclusion: GI complications are a frequent occurrence in the PICU and are associated with worse clinical outcomes. The use of sedative drugs and the presence of shock with MODS were amongst the important contributing factors. doi: https://doi.org/10.12669/pjms.37.3.3493 How to cite this:Ishaque S, Shakir M, Ladak A, Anwar-Ul-Haque. Gastrointestinal complications in critically ill children: Experience from a resource-limited country. Pak J Med Sci. 2021;37(3):657-662. doi: https://doi.org/10.12669/pjms.37.3.3493 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Objective: To evaluate the clinical and prognostic utility of procalcitonin (PCT), C-reactive protein (CRP), and lactic acid in children admitted to the Pediatric Intensive Care Unit (PICU) of a university teaching hospital. Materials and Methods: Medical records of children (1 month-16 years) tested for serum PCT at the time of admission in the PICU of our hospital from July 1, 2013, to January 15, 2015, were reviewed. Within 24 h of admission, the Pediatric Risk of Mortality Score, blood cultures, white blood cell count, neutrophil counts, serum CRP, plasma lactic acid, and PCT were noted. Patient outcome was assessed at hospital discharge, and the patients were divided into nonsurvivors and survivors. Results: A total of 167 children being admitted to the PICU were enrolled. The median age of the study population was 3 years (0-16 years), with 58.6% being males. Nonsurvivors had significantly higher lactic acid (4.7 mmol/L [2.07-7.6]; P < 0.05) than that of the survivors (2 mmol/L [1.3-3]; P < 0.05). In addition, nonsurvivors (94.4%; P < 0.05) had greater incidence of multiple organ dysfunction syndrome (MODS) than that of the survivors (38.05%; P < 0.05). Binary logistic regression showed age, MODS, and lactic acid to be associated with mortality. Conclusions: This study found that in comparison to PCT and CRP, high plasma lactic acid levels are associated with the development of all-cause MODS and worse outcome in critically ill children admitted in PICU. Prediction of prognosis based on the lactic acid alone may contribute to improve patient management, but further studies are required to endorse our findings.

Objective The goal of this study was to estimate the proportion and causes of potentially preventable mortality among critically ill children admitted to the pediatric intensive care unit (PICU). Methods The medical records of all patients who died in the PICU (age range: one month to 16 years) between January 2014 and December 2015 were evaluated by two independent reviewers to determine whether there had been any delayed recognition of deteriorating conditions, delayed interventions, unintentional/unanticipated harm, medication errors, adverse reactions to transfusions, and hospital-acquired infections that could have resulted in unanticipated death. Preventability was labeled on a 6-point scale. Results During the study period, 92 of 690 patients did not survive [median age: 60 months, interquartile range (IQR): 114]. The median Pediatric Risk of Mortality (PRISM) III score was 17 (IQR: 6). Major diagnostic categories included sepsis (n = 29, 35%), central nervous system diseases (n = 16, 17%), oncological/hematological diseases (n = 6, 6%), cardiac diseases (n = 4, 4%), and miscellaneous conditions. None of the deaths had definitive or strong evidence of preventability. Four (4.3%) patients were in category 4 (i.e., possibly preventable, >50/50 chance), 15 (16.3%) in category 3 (possibly preventable, <50/50 chance), 28 (30.4%) had some evidence of preventability, and 45 (49.0%) were labeled as definitely not preventable. Late identification (diagnostic error) of the worsening condition in four (21.0%) patients, slow intervention in six (31.6.0%), and hospital-acquired infections in 10 (52.6%) were found to be related to potentially preventable mortality. Conclusions Preventable diagnostic errors and nosocomial infections (NIs) are major contributors to preventable mortality. Structured mortality analysis provides actionable information for future preventive strategies. Improvement in care processes, including clinical decision support systems, could help reduce preventable mortality rates.