The new barrier mode in Apache Spark allows embedding distributed deep learning training as a Spark stage to simplify the distributed training workflow. In Spark, a task in a stage doesn’t depend on any other tasks in the same stage, and hence it can be scheduled independently. However, several algorithms require more sophisticated inter-task communications, similar to the MPI paradigm. By combining distributed message passing (using asynchronous network IO), OpenJDK’s new auto-vectorization and Spark’s barrier execution mode, we can add non-map/reduce based algorithms, such as Cannon’s distributed matrix multiplication to Spark. We document an efficient distributed matrix multiplication using Cannon’s algorithm, which improves significantly on the performance of the existing MLlib implementation. Used within a barrier task, the algorithm described herein results in an up to 24% performance increase on a 10,000x10,000 square matrix with a significantly lower memory footprint. Applications of efficient matrix multiplication include, among others, accelerating the training and implementation of deep convolutional neural network based workloads, and thus such efficient algorithms can play a ground-breaking role in faster, more efficient execution of even the most complicated machine learning tasks

Disease-related data and information collected by physicians, patients, and researchers seem insignificant at first glance. Still, the same unorganized data contain valuable information that is often hidden. The task of data mining techniques is to extract patterns to classify the data accurately. One of the various Data mining and its methods have been used often to diagnose various diseases. In this study, a machine learning (ML) technique based on distributed computing in the Apache Spark computing space is used to diagnose diabetics or hidden pattern of the illness to detect the disease using a large dataset in real-time. Implementation results of three ML techniques of Decision Tree (DT) technique or Random Forest (RF) or Support Vector Machine (SVM) in the Apache Spark computing environment using the Scala programming language and WEKA show that RF is more efficient and faster to diagnose diabetes in big data.

Bark beetles are one of the major causes of tree mortality in coniferous forests worldwide. The large-scale disturbances by beetle outbreaks have strongly increased in Honduras and other countries, leading to significant ecological, economic, and social consequences. However, the taxonomy, local distribution, and environmental aspects of most bark beetles and their biological predators remain poorly studied. Here, we applied a morphological approach to identify Scolytinae individuals across different forest areas in Honduras. Moreover, the barcoding approach was used by amplifying and sequencing the mitochondrial COI gene. The intraspecific genetic diversity of Ips apache was also analyzed. 1,131 individuals were examined, and 27 genera were identified. Most of the specimens were identified as belonging to the genus Ips, accounting for 53.2% of the total. Xyleborus accounted for 16.5% and Temnoscheila accounted for 10%. Less than four individuals were found for fifteen genera. Ips, Temnoscheila, Xyleborus, Hypothenemus and Pityophthorus exhibited the most extensive geographic distribution among the sampled sites. At the genus level, Olancho, El Paraíso, and Copán displayed the highest diversity. This study is the first report of two genera (Xylomeira and Stephanopachys) in Honduran pine forests. Among individuals of I. apache, there was evidence of intraspecific genetic diversity, but no population structure was detected. While our findings update the list of bark beetles and biological predators associated with Honduran coniferous forests, more taxonomic inventories and ecological studies are required to understand the spread of bark beetles in pine forests.

Deep learning neural networks require an immense amount of computation, especially in the training phase of the network when networks with multiple layers of intermediate neurons need to be built. In this paper, we will focus on the PSO algorithm with the aim of significantly accelerating the DLNN training phase by taking advantage of the GPGPU architecture and the Apache Spark analytics engine for large-scale data processing tasks. PSO is a bio-inspired stochastic optimization method whose goal is to iteratively improve the solution to a (usually complex) problem by attempting to approximate a given objective. However, parallelizing an efficient PSO is not a straightforward process due to the complexity of the computations performed on the swarm of particles and the iterative execution of the algorithm until a solution close to the objective with minimal error is achieved. In the present work, two parallelizations of the PSO algorithm have been implemented , both designed for a distributed execution environment. The synchronous parallel PSO implementation ensures consistency at the cost of potential idle time due to global synchronization, while the asynchronous parallel PSO approach improves execution time by reducing the need for global synchronization, making it more suitable for large datasets and distributed environments such as Apache Spark. Both variants of PSO have been implemented to distribute the computational load supported by this algorithm –due to the costly fitness evaluation and updating of particle positions– across the different Spark cluster executor nodes to effectively achieve coarse-grained parallelism, resulting in a significant performance increase over current sequential variants of PSO.

Background: Multi-drug resistance organisms (MDRO) often cause increased morbidity, mortality, and length of stays (LOS). However, there is uncertainty whether the infection of MDRO increase the morbidity, mortality, and ICU-LOS. Objective: This study performed to determine the prevalence of MDRO in ICU, site of infection and the association of MDRO or site of infection with mortality. Secondary outcome was determined by ascertaining the association of MDRO or site of infection with (ICU-LOS). Methods: A retrospective cohort study was performed with adult sepsis patients in ICU. Univariate and multivariate (MVA) logistic regression with cox regression modeling were performed to compute the association of MDRO on ICU-mortality. MVA modelling was performed for ICU-LOS predictors. Results: Out of 228 patients, the isolated MDRO was 97 (42.5%) of which 78% were gram-negative bacteria. The mortality rate among those with MDRO was 85 (37.3%). The hospital acquired infection (HAI) was significantly predictor for ICU-LOS in univariate linear regression (R² = 0.034, P=0.005). In MVA linear regression, both Enterococcus faecalis infection and acinetobacter baumannii (AC) -MDRO were predictors for ICU-LOS with (R² = 0.478, P<0.05). In the univariate cox regression, only the infection with AC- MDRO was a risk factor for ICU-mortality with [ HR =1.802 (95% CI: 1.2 – 2.706; P = 0.005)]. Conclusions: Identifying risk factors for MDRO highlight the appropriate administration of empirical antibiotics and effectively control of source of infection which would reduce mortality and ICU-LOS. The usage of broad- spectrum antibiotics should be limited for those having substantial risk factors to acquire MDRO.

In the domain of financial trading, where accuracy and swift response to data discrep- ancies are paramount for maintaining clienttrust, our research paper delves into the development of a real-time alert system utilizing SpringBoot, a framework renowned for its robustness and adaptability in enterprise applications. We embark on a comprehensive journey, beginning with addressing thefoundational challenges inherent in monitoring trade inquiries - the necessity for real-time processing, unwavering data accuracy,and ensuring unwavering system reliability. The study then methodically transitions to the architectural design, where we explore howSpringBoot’s capabilities are optimally utilized to meet these challenges. Following this, we delve into the im- -plementationphase, detailing the strategic selection of compatible technologies and methods for effective data management and discrepancydetection. The paper culminates in a thorough evalu- ation of the system, where we assess performance across various operationalscenarios, scrutinize the accuracy of the discrepancy detection mechanisms, and integrate real-world feedback from users in thetrading sector. This holistic approach not only highlights the versatility and efficiency of SpringBoot in creating reliable alert systems in the high-stakes world of financial trading but also serves as a detailed guide for similar endeavors in this field