LightSEEN: Real-Time Unknown Traffic Discovery via Lightweight Siamese Networks

With the increase in the proportion of encrypted network traffic, encrypted traffic identification (ETI) is becoming a critical research topic for network management and security. At present, ETI under closed world assumption has been adequately studied. However, when the models are applied to the realistic environment, they will face unknown traffic identification challenges and model efficiency requirements. Considering these problems, in this paper, we propose a lightweight unknown traffic discovery model LightSEEN for open-world traffic classification and model update under practical conditions. The overall structure of LightSEEN is based on the Siamese network, which takes three simplified packet feature vectors as input on one side, uses the multihead attention mechanism to parallelly capture the interactions among packets, and adopts techniques including 1D-CNN and ResNet to promote the extraction of deep-level flow features and the convergence speed of the network. The effectiveness and efficiency of the proposed model are evaluated on two public data sets. The results show that the effectiveness of LightSEEN is overall at the same level as the state-of-the-art method and LightSEEN has even better true detection rate, but the parameter used in LightSEEN is 0.51 % of the baseline and its average training time is 37.9 % of the baseline.

Finding an optimal distance of social distancing for COVID 19

Social distancing is a non-pharmaceutical infection prevention and control approach that is now being utilized in the COVID-19 scenario to avoid or restrict the transmission of illness in a community. As a consequence, the disease transmission, as well as the morbidity and mortality associated with it are reduced. The deadly coronavirus will circulate if the distance between the two persons in each site is used. However, coronavirus exposure must be avoided at all costs. The distance varies due to different nations' political rules and the conditions of their medical embassy. The WHO established a social distance of 1 to 2 metres as the standard. This research work has developed a computational method for estimating the impact of coronavirus based on various social distancing metrics. Generally, in COVID – 19 situations, social distance ranging from long to extremely long can be a good strategy. The adoption of extremely small social distance is a harmful approach to the pandemic. This calculation can be done by using deep learning based on crowd image identification. The proposed work has been utilized to find the optimal social distancing for COVID – 19 and it is identified as 1.89 meter. The purpose of the proposed experiment is to compare the different types of deep learning based image recognition algorithms in a crowded environment. The performance can be measured with various metrics such as accuracy, precision, recall, and true detection rate.

Design and Implementation of the Voice Command Recognition and the Sound Source Localization System for Human–Robot Interaction

SUMMARY Human–robot interaction (HRI) is becoming more important nowadays. In this paper, a low-cost communication system for HRI is designed and implemented on the Scout robot and a robotic face. A hidden Markov model-based voice command detection system is proposed and a non-native database has been collected by Persian speakers, which contains 10 desired English commands. The experimental results confirm that the proposed system is capable to recognize the voice commands, and properly performs the task or expresses the right answer. Comparing the system with a trained system on the Julius native database shows a better true detection (about 10%).

Method for detecting R-waves of an ECG signal based on wavelet decomposition

Increasing the efficiency of cardiological diagnostics based on the analysis of human heart rate variability necessitates the development of accurate methods for detecting the R-waves of the electrocardiosignal (ECG signal). A technique for detecting R-waves of an ECG signal based on the wavelet multiresolution analysis (WMRA). The proposed technique for detecting R-waves includes sequential stages of digital processing of an ECG signal: WMRA; a set of nonlinear operators; adaptive algorithm for detecting signal peaks. A comparative analysis of the proposed technique with existing approaches to the detection of R-waves of the ECG signal has been carried out. To obtain quantitative characteristics of evaluating the efficiency of detecting R-waves, we used imitation modeling of an ECG signal containing noises and interferences of various intensity and nature of occurrence. The effectiveness of the considered approaches to the detection of R-waves of the ECG signal was investigated for clinical recordings of ECG signal. The absolute error of measuring the RR-interval durations for model signals with different noise levels is estimated. It is shown that the proposed method for detecting R-waves of an ECG signal based on WMRA is characterized by small errors in measuring the duration of RR-intervals, high rates of true detection and small errors of false detection and omission.

Is Fault Detection and Diagnosis in Pneumatic Actuator A Topic of Concern?

The present civilization highly depends on industrial products and hence there is an increased demand for the same. Therefore, each industry is trying to increase its production output without hindering the quality. Maintenance of plant health is essential to improve the production rate without any loss. Industrial processes require monitoring of every element as their consistent behavior is a fundamental concern. Any deviation in the working of these components may alter the quality of the end product, causing a huge loss for the industry. Therefore, monitoring and finding the root cause for irregular behavior of industrial processes is a requisite for avoiding any future loss. In this paper, an attempt is made to present types of faults, types of pneumatic actuator faults, and different techniques used for the detection and isolation of faults. Simulation work is carried out to generate stiction behavior in the control valve using the Choudhury stiction model. Valve stiction behavior for different values of stick band and jump values are discussed in this paper. A comparison of several techniques used for the detection of faults based on two performance indices namely true detection rate and false alarm rate has been given at the end of this paper. From these techniques, it is observed that these indices are interdependent, such that an increase in the detection rate increases the false detection rate and increases detection time.

Robust estimates of the true (population) infection rate for COVID-19: a backcasting approach

Differences in COVID-19 testing and tracing across countries, as well as changes in testing within each country over time, make it difficult to estimate the true (population) infection rate based on the confirmed number of cases obtained through RNA viral testing. We applied a backcasting approach to estimate a distribution for the true (population) cumulative number of infections (infected and recovered) for 15 developed countries. Our sample comprised countries with similar levels of medical care and with populations that have similar age distributions. Monte Carlo methods were used to robustly sample parameter uncertainty. We found a strong and statistically significant negative relationship between the proportion of the population who test positive and the implied true detection rate. Despite an overall improvement in detection rates as the pandemic has progressed, our estimates showed that, as at 31 August 2020, the true number of people to have been infected across our sample of 15 countries was 6.2 (95% CI: 4.3–10.9) times greater than the reported number of cases. In individual countries, the true number of cases exceeded the reported figure by factors that range from 2.6 (95% CI: 1.8–4.5) for South Korea to 17.5 (95% CI: 12.2–30.7) for Italy.

CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.

Deep autoencoder for false positive reduction in handgun detection

In an object detection system, the main objective during training is to maintain the detection and false positive rates under acceptable levels when the model is run over the test set. However, this typically translates into an unacceptable rate of false alarms when the system is deployed in a real surveillance scenario. To deal with this situation, which often leads to system shutdown, we propose to add a filter step to discard part of the new false positive detections that are typical of the new scenario. This step consists of a deep autoencoder trained with the false alarm detections generated after running the detector over a period of time in the new scenario. Therefore, this step will be in charge of determining whether the detection is a typical false alarm of that scenario or whether it is something anomalous for the autoencoder and, therefore, a true detection. In order to decide whether a detection must be filtered, three different approaches have been tested. The first one uses the autoencoder reconstruction error measured with the mean squared error to make the decision. The other two use the k-NN (k-nearest neighbors) and one-class SVMs (support vector machines) classifiers trained with the autoencoder vector representation. In addition, a synthetic scenario has been generated with Unreal Engine 4 to test the proposed methods in addition to a dataset with real images. The results obtained show a reduction in the number of false positives between 22.5% and 87.2% and an increase in the system’s precision of 1.2%$$-47$$ - 47 % when the autoencoder is applied.

Real Time Monitoring and Fire Detection using Internet of Things and Cloud based Drones

Smart cities with smart infrastructure is a rapidly flourishing field of research in the modern days. Open areas, agricultural land, forests, office, homes and several areas can have occurrences of fire accidents leading to loss of significant resources. Unmanned Aerial Vehicle (UAV) and wireless sensor network technologies are used fir detection of fire at an early stage in this paper. This helps in avoiding serious fire accidents. The environmental parameters are monitored using the sensor architecture. The sensors uses IoT based applications for processing the gathered environmental data. Cloud computing, IoT sensors, wireless technology and UAVs are combined for the purpose of fire detection in this paper. In order to improve the accuracy of the system, integration of image processing schemes is done in this system. The rules are formulated such that the true detection rate is improved. The existing state-of-the-art models are compared with the proposed system. The simulation results show that the rate of fire detection of the proposed system is improved for up to 98% when compared to the traditional models.