Vigorous IDS on Nefarious Operations and Threat Analysis Using Ensemble Machine Learning

The geometric increase in the usage of computer networking activities poses problems with the management of network normal operations. These issues had drawn the attention of network security researchers to introduce different kinds of intrusion detection systems (IDS) which monitor data flow in a network for unwanted and illicit operations. The violation of security policies with nefarious motive is what is known as intrusion. The IDS therefore examine traffic passing through networked systems checking for nefarious operations and threats, which then sends warnings if any of these malicious activities are detected. There are 2 types of detection of malicious activities, misuse detection, in this case the information about the passing network traffic is gathered, analyzed, which is then compared with the stored predefined signatures. The other type of detection is the Anomaly detection which is detecting all network activities that deviates from regular user operations. Several researchers have done various works on IDS in which they employed different machine learning (ML), evaluating their work on various datasets. In this paper, an efficient IDS is built using Ensemble machine learning algorithms which is evaluated on CIC-IDS2017, an updated dataset that contains most recent attacks. The results obtained show a great increase in the rate of detection, increase in accuracy as well as reduction in the false positive rates (FPR).

A ten-year cross-national examination of the dance between intuition and rationality in entrepreneurial processes

Entrepreneurs rely, to a degree, on intuition while they also rely on rationality. Both are associated with formation of expectations for new venture creation as well as perseverance of efforts in managing the new venture and its creation. Global Entrepreneurship Monitor data from three distinct countries over a ten-year period are used in logistic regression analysis to find, not unexpectedly, that intuition and rationality vary in impact across countries and over time. While the findings confirm past findings, they also provide intriguing new insights into the dance between intuition and rationality in entrepreneurial processes.

Abstract 13737: Enhanced Prehospital End-Tidal CO2 Monitor Data Analysis for Intubated Severe Traumatic Brain Injury: Striking Findings From the EPIC Study

Background: Studies show that EMS patients are often inadvertently hyperventilated (HV), resulting in hypocapnia. In TBI, HV markedly increases mortality. We evaluated continuous prehospital ETCO2 data in intubated TBI patients. Methods: Analysis of monitor data files (Philips MRx™) from a sample of intubated TBI cases in the EPIC Study (NIH-R01NS071049). Results: Among hundreds of cases, graphical display of continuous ETCO2 from 3 subjects dramatically exemplified commonly-occurring inadvertent HV. Fig 1 shows unrecognized HV lasting nearly 15 min. Fig 2 reveals nearly 14 min of increasing ventilatory rate and progressively worsening hypocapnia. Fig 3 shows nearly 4 min of HV that ends abruptly with clear, sudden recognition and slowing of ventilatory rate that leads to restoration of normal ETCO2 in only a few breaths. The corresponding EMS patient care records (PCR) failed to document the presence, severity, and duration of HV. Conclusions: In a study emphasizing prevention of HV, subsequent evaluation of continuous ETCO2 data revealed many cases of unintentionally rapid manual ventilation and severe hypocapnia, often occurring for long periods. These findings, even in the face of explicit guideline-based training, demonstrate a clear need for routine access to continuous monitor data among intubated patients for quality improvement and in clinical studies. Review of PCRs does not reliably identify mismanagement of ventilation. Furthermore, these findings make it likely that real-time audiovisual feedback technology would improve ventilatory management by alerting providers to unidentified HV that results from the frequent distractions occurring during EMS care.

Is Wrist Accelerometry Suitable for Threshold Scoring? A Comparison of Hip-Worn and Wrist-Worn ActiGraph Data in Low-Active Older Adults with Obesity

Background Hip- and wrist-worn ActiGraph accelerometers are widely used in research on physical activity as they offer an objective assessment of movement intensity across the day. Herein we characterize and contrast key structured physical activities and common activities of daily living via accelerometry data collected at the hip and wrist from a sample of community-dwelling older adults. Methods Low-active, older adults with obesity (age 60+ years) were fit with an ActiGraph GT3X+ accelerometer on their non-dominant wrist and hip before completing a series of tasks in a randomized order, including sitting/standing, sweeping, folding laundry, stair climbing, ambulation at different intensities, and cycling at different intensities. Participants returned a week later and complete the tasks once again. Vector magnitude counts/second were time-matched during each task and then summarized into counts/minute (CPM). Results Monitors at both wear locations similarly characterized standing, sitting, and ambulatory tasks. A key finding was that light home chores (sweeping, folding laundry) produced higher and more variable CPM values than fast walking via wrist ActiGraph. Regression analyses revealed wrist CPM values were poor predictors of hip CPM values, with devices aligning best during fast walking (R 2=.25) and stair climbing (R 2=.35). Conclusion As older adults spend a considerable portion of their day in non-exercise activities of daily living, researchers should be cautious in the use of simply acceleration thresholds for scoring wrist-worn accelerometer data. Methods for better classifying wrist-worn activity monitor data in older adults are needed.

Design and Development of Water Distribution Monitoring System in Regional Drinking Water Companies (PDAM) Based On Internet Of Things

The purpose of this study is to create a prepaid PDAM clean water distribution system using a microcontroller based on the Internet of Things (IoT). The hardware used to realize the system consists of ultrasonic sensors, water flow sensors, relays, LCD buzzers and Arduino. ESP 8266 01 for delivery to the Thingspeak app. From the test results obtained HC-SR04 ultrasonic sensor reading error occurs when the water level is low and too high, the maximum measurable water level is 95%. When calculating the comparison between the water discharge that is read by the sensor and that measured by the measuring cup, the results are always not the same. The error when testing the water flow sensor at the water level is less than 49% this is influenced by the speed of the water fired by the pump, where the pump will be under low pressure when the water level is below that value. The system can monitor data readings from the water flow sensor using the ESP8266 monitored on the thinkspeak web server using a smartphone. Overall the tool can function well.

Livin' on the edge: precision yield data shows evidence of ecosystem services from field boundaries.

Field boundaries can provide ecosystem services to crops by creating better abiotic conditions for crop growth, and can also act as habitat for beneficial arthropods. This suggests that crop boundaries may create an intermediate hump-shaped increase in crop yield, where negative edge effects are cancelled out by increased ecosystem services from the field boundary. However, there is little large-scale evidence showing this, largely because plot-scale crop yields are costly and time-consuming to measure. Precision yield data from combine yield monitors has huge potential in this respect, as the equipment is widespread and data is frequently recorded by growers. In this study, we used 252 field-years of yield monitor data from three common crops - wheat (Triticum aestivum), canola (Brassica napus), or peas (Pisum sativum) - recorded across Alberta, Canada, and examined how yield varied with distances from common crop boundary types. Average crop yield tended to increase with distance from crop boundaries before plateauing at about 50 m, and yield variation (SD) tended to decrease with distance. There was evidence of an intermediate increase in yield for wheat away from shelterbelts, and a weak increase in canola, but this was not seen for other crop types or boundary types. This study represents one of the first uses of precision yield data to measure ecosystem service provision at large spatial scales.

A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction

Smart sensors are an integral part of the Fourth Industrial Revolution and are widely used to add safety measures to human–robot interaction applications. With the advancement of machine learning methods in resource-constrained environments, smart sensor systems have become increasingly powerful. As more data-driven approaches are deployed on the sensors, it is of growing importance to monitor data quality at all times of system operation. We introduce a smart capacitive sensor system with an embedded data quality monitoring algorithm to enhance the safety of human–robot interaction scenarios. The smart capacitive skin sensor is capable of detecting the distance and angle of objects nearby by utilizing consumer-grade sensor electronics. To further acknowledge the safety aspect of the sensor, a dedicated layer to monitor data quality in real-time is added to the embedded software of the sensor. Two learning algorithms are used to implement the sensor functionality: (1) a fully connected neural network to infer the position and angle of objects nearby and (2) a one-class SVM to account for the data quality assessment based on out-of-distribution detection. We show that the sensor performs well under normal operating conditions within a range of 200 mm and also detects abnormal operating conditions in terms of poor data quality successfully. A mean absolute distance error of 11.6mm was achieved without data quality indication. The overall performance of the sensor system could be further improved to 7.5mm by monitoring the data quality, adding an additional layer of safety for human–robot interaction.

Method of automatic correction of neutron monitor data for precipitation in the form of snow in real time

We have carried out an experimental study of the influence of precipitation in the form of snow on measurements of the neutron flux intensity near Earth's surface. We have examined the state of the snow cover and its density, and found out that the density depends on the depth of the snow cover. Using the experimental results, we estimate the neutron absorption path in the snow. Changes in snow cover by 10–12 cm at a depth of 80 cm are shown to cause variations in the monitor count rate with an amplitude of 0.9 %. At the snow depth of 80 cm, the neutron monitor count rate decreases by about 8 %. The observed variations should be attributed to the meteorological effects of cosmic rays. The absorption coefficient of neutrons in the snow was also found from the correlation between the count rate of the neutron monitor and the amount of snow above the detector. We propose a real-time correction of the neutron monitor data for precipitation in the form of snow. For this purpose, we implement continuous monitoring of the amount of snow cover. The monitoring is provided by a snow meter made using a laser rangefinder module. We discuss the results obtained.