Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts.

Recently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps for resource allocation. This study proposes a reliable hybrid dynamic bandwidth slice forecasting framework that combines the long short-term memory (LSTM) neural network and local smoothing methods to improve the network forecasting model. Moreover, the proposed framework can dynamically react to all the changes occurring in the data series. Backbone traffic was used to validate the proposed method. As a result, the forecasting accuracy improved significantly with the proposed framework and with minimal data loss from the smoothing process. The results showed that the hybrid moving average LSTM (MLSTM) achieved the most remarkable improvement in the training and testing forecasts, with 28% and 24% for long-term evolution (LTE) time series and with 35% and 32% for the multiprotocol label switching (MPLS) time series, respectively, while robust locally weighted scatter plot smoothing and LSTM (RLWLSTM) achieved the most significant improvement for upstream traffic with 45%; moreover, the dynamic learning framework achieved improvement percentages that can reach up to 100%.

Molecular Analysis of the Antibiotic Resistant NDM-1 Gene in Clinical Isolates of Enterobacteriaceae.

BACKGROUND: The emergence of the New Dehli metallo-beta-lactamase (NDM) gene in Enterobacteriaceae is responsible for multidrug resistance responsible for severe infections and serious morbidity in patients. Our study aimed to define the molecular characteristics and antibiogram of the NDM-1 producing Enterobacteriaceae. METHODS: We isolated 370 individual enterobacteria from the clinical specimens collected from the two tertiary hospitals in Sakaka, Saudi Arabia. Bacterial isolation was performed using standard microbiological techniques and the Phoenix and Microscan WalkAway Plus automated analyzers. Bacterial strains were characterized by phenotypic methods and PCR, and DNA sequencing was used for the molecular characterization of NDM genes. RESULTS: The blaNDM gene was detected among the 68 members of the Enterobacteriaceae including a single case of rarely reported Cedecea lapagei. Of these 68, 43 isolates (63.2%) were blaNDM-1 and 25 (36.8%) were blaNDM variants. A statistically significant relationship between the NDM-1 and Klebsiella pneumoniae (p = 0.004) was seen, and the relationship between the NDM variants was significantly associated with Citrobacter freundii (p = 0.02) and Escherichia coli (p = 0.03). The in vitro minimum inhibitory concentrations (MICs) of NDM-producing Enterobacteriaceae revealed a very high rate of antibiotic resistance against several groups of antibiotics. These bacterial strains were less resistant to two aminoglycosides, gentamicin (39; 57.3%) and amikacin (27; 39.7%), and showed minimum resistance to tigecycline (25; 36.8%). CONCLUSIONS: The emergence of a large number of NDM-1 enterobacteria in our study identifies a substantial public concern, both within hospitals and the wider community, and leaves us a narrow choice of therapeutic options: the aminoglycosides, co-trimoxazole, and tigecycline.