A Survey on Data-driven Network Intrusion Detection

Data-driven network intrusion detection (NID) has a tendency towards minority attack classes compared to normal traffic. Many datasets are collected in simulated environments rather than real-world networks. These challenges undermine the performance of intrusion detection machine learning models by fitting machine learning models to unrepresentative “sandbox” datasets. This survey presents a taxonomy with eight main challenges and explores common datasets from 1999 to 2020. Trends are analyzed on the challenges in the past decade and future directions are proposed on expanding NID into cloud-based environments, devising scalable models for large network data, and creating labeled datasets collected in real-world networks.

Behavior analytic based virtual reality interventions to teach adaptive and functional skills for individuals diagnosed with autism: A systematic review

Virtual reality technologies hold promise for the therapy based on the science of applied behavior analysis as they can replicate real life environments and allow the user to role-play in a simulated environments. This literature review synthesizes the research base evaluating the effects of behavior analytic interventions delivered via virtual reality (VR) technology to teach adaptive and functional skills for individuals with autism. Method: We conducted a systematic search in four databases followed by a reference search for those articles by the systematic database search. We also conducted a quality review using the Evaluative Method for Evaluating and Determining Evidence-Based Practices in Autism (Reichow, 2008). Results: We identified 24 studies with a majority of the studies (n = 18; 75%) utilizing group experimental or quasi-experiment research design, and the remaining (n = 6; 25%) utilizing single-case research design. Of those studies, ten targeted vocational related skills, seven targeted functional behaviors (e.g., problem behavior treatment, hypersensitivity, phobias), four targeted safety skills (e.g., driving, airplane travel, pedestrian safety), two studies targeted general functional skills, and one targeted exercise engagement. Of the 24 studies, 12 met the quality criteria to be classified as “strong” or “adequate” and can offer evidence on the integration of VR technology into the practice of behavior analysis for teaching adaptive or functional skills. Discussion: Taken as a whole, the three studies (Cox et al., 2017; Hu & Han, 2019; Wade et al., 2013) identified as “strong” quality studies were conducted by three different research teams, at three different locations, with 74 different participants and meet the qualifications to be considered a promising practice.

A Simulated Environment for Robot Vision Experiments

Training on simulation data has proven invaluable in applying machine learning in robotics. However, when looking at robot vision in particular, simulated images cannot be directly used no matter how realistic the image rendering is, as many physical parameters (temperature, humidity, wear-and-tear in time) vary and affect texture and lighting in ways that cannot be encoded in the simulation. In this article we propose a different approach for extracting value from simulated environments: although neither of the trained models can be used nor are any evaluation scores expected to be the same on simulated and physical data, the conclusions drawn from simulated experiments might be valid. If this is the case, then simulated environments can be used in early-stage experimentation with different network architectures and features. This will expedite the early development phase before moving to (harder to conduct) physical experiments in order to evaluate the most promising approaches. In order to test this idea we created two simulated environments for the Unity engine, acquired simulated visual datasets, and used them to reproduce experiments originally carried out in a physical environment. The comparison of the conclusions drawn in the physical and the simulated experiments is promising regarding the validity of our approach.

Reduced Simulation: Real-to-Sim Approach toward Collision Detection in Narrowly Confined Environments

Recently, several deep-learning based navigation methods have been achieved because of a high quality dataset collected from high-quality simulated environments. However, the cost of creating high-quality simulated environments is high. In this paper, we present a concept of the reduced simulation, which can serve as a simplified version of a simulated environment yet be efficient enough for training deep-learning based UAV collision avoidance approaches. Our approach deals with the reality gap between a reduced simulation dataset and real world dataset and can provide a clear guideline for reduced simulation design. Our experimental result confirmed that the reduction in visual features provided by textures and lighting does not affect operating performance with the user study. Moreover, by conducting collision detection experiments, we verified that our reduced simulation outperforms the conventional cost-effective simulations in adaptation capability with respect to realistic simulation and real-world scenario.

Augmenting Jurisdiction

<p>Augmenting jurisdiction is a hypothetical scenario I have created, to explore what impact Mixed Reality (MR) could have on the Environmental Court of Aotearoa (EVC A). This Thesis has two equal sides of exploration; Physical and Virtual. The ‘Physical’ in this instance is the hierarchy and organisation of the Environmental Courts of Aotearoa and the ‘Virtual’ are the components and concepts of Mixed Reality. Stage One of the research is exploring the Physical - hierarchy, technological and organisational requirements of EVC A, as set of out by the Ministry of Justice and Courts NZ . Within this stage of research I explore the statutory bodies, resource management act and the compositional structure of the judicial system. I also explore the variable of the Virtual - the concept of MR, as set out by Prof. Paul Milgram, Ph.D., P.Eng. from the ETC lab at the University of Toronto. It explores technologies that are currently under research and development and are not necessarily available to the general public. However these products contain the possibilities for what I am proposing in this paper. Exploring the capabilities of MR delves into products such as “Google Glass” or other Head Mounted Displays (HMD), Heads Up Display (HUD), both material and immaterial video display and graphic simulated environments. Stage Two is extrapolation and interpretation of the Physical and the Virtual constructs. The data from Stage One regulated how I approached the design. The model created in Stage Two is a direct result of the contraints colated in Stage One and the physical parameters of the old Ministry of Defense building, 15 -21 Stout St, Wellington. Stage Two was completed with computer aided design so" ware from companies such as Autodesk, Adobe and others. Stage Three - Exogesis - reflection and evaluation. This stage was to culminate my ideas and research. I would like to thank you for reading this thesis and hope you have a nice day :)></p>

Augmenting Jurisdiction

<p>Augmenting jurisdiction is a hypothetical scenario I have created, to explore what impact Mixed Reality (MR) could have on the Environmental Court of Aotearoa (EVC A). This Thesis has two equal sides of exploration; Physical and Virtual. The ‘Physical’ in this instance is the hierarchy and organisation of the Environmental Courts of Aotearoa and the ‘Virtual’ are the components and concepts of Mixed Reality. Stage One of the research is exploring the Physical - hierarchy, technological and organisational requirements of EVC A, as set of out by the Ministry of Justice and Courts NZ . Within this stage of research I explore the statutory bodies, resource management act and the compositional structure of the judicial system. I also explore the variable of the Virtual - the concept of MR, as set out by Prof. Paul Milgram, Ph.D., P.Eng. from the ETC lab at the University of Toronto. It explores technologies that are currently under research and development and are not necessarily available to the general public. However these products contain the possibilities for what I am proposing in this paper. Exploring the capabilities of MR delves into products such as “Google Glass” or other Head Mounted Displays (HMD), Heads Up Display (HUD), both material and immaterial video display and graphic simulated environments. Stage Two is extrapolation and interpretation of the Physical and the Virtual constructs. The data from Stage One regulated how I approached the design. The model created in Stage Two is a direct result of the contraints colated in Stage One and the physical parameters of the old Ministry of Defense building, 15 -21 Stout St, Wellington. Stage Two was completed with computer aided design so" ware from companies such as Autodesk, Adobe and others. Stage Three - Exogesis - reflection and evaluation. This stage was to culminate my ideas and research. I would like to thank you for reading this thesis and hope you have a nice day :)></p>

Impact of Background Music on the Performance of Laparoscopy Teams

BACKGROUND: Music and noise have different impacts on individuals in the operating room. Their effects on the performance of surgical teams in simulated environments are not well documented. We investigated if laparoscopic teams operating under favorable acoustic conditions would perform better than under noisy conditions.METHODS: We recruited 114 surgical residents and built 57 two-person teams. Each team was required to perform two laparoscopic tasks (object transportation and collaborative suturing) on a simulation training box under musical, neutral, and noisy acoustic conditions. Data were extracted from video recordings of each performance for analysis. Task performance was measured by the duration of time to complete a task and the total number of errors, and objective performance scores. The measures were compared over the three acoustic conditions.RESULTS: A musical environment elicited higher performance scores than a noisy environment for both the object transportation (performance score: 66.3 ± 8.6 vs. 57.6 ± 11.2; p < 0.001) and collaborative suturing tasks (78.6 ± 5.4 vs. 67.2 ± 11.1; p < 0.001). Task times in the musical and noisy environments was subtracted to produce a musical-noisy difference time. Pearson correlation coefficient analysis showed a significant negative relationship between the team experience score and the musical-noisy difference time on the object transportation (r = -0.246, p = 0.046) and collaborative suturing tasks (r = -0.248, p = 0.044). CONCLUSIONS: As to individuals, music enhances the performance of a laparoscopy team while noise worsens performance. The negative correlation between team experience and musical-noisy difference time suggests that laparoscopy teams composed of experienced surgeons are less likely affected by an acoustic distraction than novice teams. Team resistance to acoustic distraction may lead to a new way for assessing team skills.

Learning from Sensors and Past Experience in an Autonomous Oceanographic Probe

The work presented in this paper is part of a multidisciplinary team collaborating in the deployment of an autonomous oceanographic probe with the task of exploring marine regions and take phytoplankton samples for their subsequent analysis in a laboratory. We will describe an autonomous system that, from sensor data, is able to characterize phytoplankton structures. Because the system has to work inboard, a main goal of our approach is to dramatically reduce the dimensionality of the problem. Specifically, our development uses two AI techniques, namely Particle Swarm Optimization and Case-Based Reasoning.We report results of experiments performed with simulated environments.