In a few years, the world will be populated by billions of connected devices that will be placed in our homes, cities, vehicles, and industries. Devices with limited resources will interact with the surrounding environment and users. Many of these devices will be based on machine learning models to decode meaning and behavior behind sensors’ data, to implement accurate predictions and make decisions. The bottleneck will be the high level of connected things that could congest the network. Hence, the need to incorporate intelligence on end devices using machine learning algorithms. Deploying machine learning on such edge devices improves the network congestion by allowing computations to be performed close to the data sources. The aim of this work is to provide a review of the main techniques that guarantee the execution of machine learning models on hardware with low performances in the Internet of Things paradigm, paving the way to the Internet of Conscious Things. In this work, a detailed review on models, architecture, and requirements on solutions that implement edge machine learning on Internet of Things devices is presented, with the main goal to define the state of the art and envisioning development requirements. Furthermore, an example of edge machine learning implementation on a microcontroller will be provided, commonly regarded as the machine learning “Hello World”.

https://www.mdpi.com/1424-8220/20/9/2533/pdf

Edge Machine Learning for AI-Enabled IoT Devices: A Review

While there have been extensive studies of denial of service (DoS) attacks and DDoS attack mitigation, such attacks remain challenging to mitigate. For example, Low-Rate DDoS (LR-DDoS) attacks are known to be difficult to detect, particularly in a software-defined network (SDN). Hence, in this paper we present a flexible modular architecture that allows the identification and mitigation of LR-DDoS attacks in SDN settings. Specifically, we train the intrusion detection system (IDS) in our architecture using six machine learning (ML) models (i.e., J48, Random Tree, REP Tree, Random Forest, Multi-Layer Perceptron (MLP), and Support Vector Machines (SVM)) and evaluate their performance using the Canadian Institute of Cybersecurity (CIC) DoS dataset. The findings from the evaluation demonstrate that our approach achieves a detection rate of 95%, despite the difficulty in detecting LR-DoS attacks. We also remark that in our deployment, we use the open network operating system (ONOS) controller running on Mininet virtual machine in order for our simulated environment to be as close to real-world production networks as possible. In our testing topology, the intrusion prevention detection system mitigates all attacks previously detected by the IDS system. This demonstrates the utility of our architecture in identifying and mitigating LR-DDoS attacks.

/pdf/a-flexible-sdn-based-architecture-for-identifying-and-2h3oonc43x.pdf

A Flexible SDN-Based Architecture for Identifying and Mitigating Low-Rate DDoS Attacks Using Machine Learning

Software-Defined Network (SDN) has become a promising network architecture in current days that provide network operators more control over the network infrastructure. The controller, also called as the operating system of the SDN, is responsible for running various network applications and maintaining several network services and functionalities. Despite all its capabilities, the introduction of various architectural entities of SDN poses many security threats and potential targets. Distributed Denial of Services (DDoS) is a rapidly growing attack that poses a tremendous threat to the Internet. As the control layer is vulnerable to DDoS attacks, the goal of this paper is to detect the attack traffic, by taking the centralized control aspect of SDN. Nowadays, in the field of SDN, various machine learning (ML) techniques are being deployed for detecting malicious traffic. Despite these works, choosing the relevant features and accurate classifiers for attack detection is an open question. For better detection accuracy, in this work, Support Vector Machine (SVM) is assisted by kernel principal component analysis (KPCA) with genetic algorithm (GA). In the proposed SVM model, KPCA is used for reducing the dimension of feature vectors, and GA is used for optimizing different SVM parameters. In order to reduce the noise caused by feature differences, an improved kernel function (N-RBF) is proposed. The experimental results show that compared to single-SVM, the proposed model achieves more accurate classification with better generalization. Moreover, the proposed model can be embedded within the controller to define security rules to prevent possible attacks by the attackers.

/pdf/an-evolutionary-svm-model-for-ddos-attack-detection-in-331am3w47l.pdf

An Evolutionary SVM Model for DDOS Attack Detection in Software Defined Networks

The main task of future networks is to build, as much as possible, intelligent networking architectures for intellectualization, activation, and customization. Software-defined networking (SDN) technology breaks the tight coupling between the control plane and the data plane in the traditional network architecture, making the controllability, security, and economy of network resources into a reality. As one of the important actualization methods of artificial intelligence (AI), machine learning (ML), combined with SDN architecture will have great potential in areas, such as network resource management, route planning, traffic scheduling, fault diagnosis, and network security. This paper presents the network applications combined with SDN concepts based on ML from two perspectives, namely the perspective of ML algorithms and SDN network applications. From the perspective of ML algorithms, this paper focuses on the applications of classical ML algorithms in SDN-based networks, after a characteristic analysis of algorithms. From the other perspective, after classifying the existing network applications based on the SDN architecture, the related ML solutions are introduced. Finally, the future development of the ML algorithms and SDN concepts is discussed and analyzed. This paper occupies the intersection of the AI, big data, computer networking, and other disciplines; the AI itself is a new and complex interdisciplinary field, which causes the researchers in this field to often have different professional backgrounds and, sometimes, divergent research purposes. This paper is necessary and helpful for researchers from different fields to accurately master the key issues.

/pdf/a-survey-of-networking-applications-applying-the-software-24p87ht2ge.pdf

A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning

Measure of image sharpness using eigenvalues

Software Defined Networking (SDN) is a new promising networking concept which has a centralized control over the network and separates the data and control planes. This new approach provides abstraction of lower-level functionality and allows the network administrators to initialize, control, change, and manage network behavior programmatically. The centralized control, being the major advantage of SDN can sometimes also be a major security threat. If the intruder succeeds in attacking the central controller, he would get access to the entire system. The controller is highly vulnerable to Distributed Denial of Service (DDoS) attacks which lead to exhaustion of the system resources which causes non-availability of the services given by the controller. It is critical to detect the attacks in the controller at earlier stage. Many algorithms and techniques have been discovered for this purpose. But less work has been done in the field of SDN networks. Using machine learning algorithms for classifying the connections into legitimate and illegitimate is one such solution. We use two machine learning algorithms namely, the Support Vector Machine (SVM) classifier and the Neural Network (NN) classifier to detect the suspicious and harmful connections.

Detection of distributed denial of service attacks using machine learning algorithms in software defined networks

Real-time vehicle detection, tracking and counting of vehicles is of great interest for researchers and is a need of the society in general for comfortable, smooth and safe movements of vehicles in cities. We propose a video image processing algorithm which detects, tracks and finds the number of vehicles on a road. We convert RGB video frame to HSV color domain, which helps in differentiating the colors of the vehicles more absolutely. The noise is removed from each frame. Detection of the vehicles is purely carried on color features of the vehicles. Vehicle tracking is done using Kalman filter with the data association. The number of vehicles running in a video or in a particular lane is determined. We propose a novel idea to detect, track and count the vehicles on a road and it has been implemented on Raspberry Pi 3 using OpenCV and C++. We have compared the results of the proposed method with that of rear-view vehicle detection and tracking method (Bin et al., 2014) and morphological operation method (Zezhong et al., 2013), and found that the proposed algorithm is more effective in terms of accuracy of vehicle detection and cost.

A novel approach in real-time vehicle detection and tracking using Raspberry Pi

Population explosion leads to an unprecedented increase in the number of physical objects or vehicles on road. As a result, the number of road accidents increases due to a very heavy traffic flow. In this paper, traffic flow is monitored by using computer vision paradigm, where images or sequence of images provides a betterment on the road view. In order to detect vehicles, monitor and estimate traffic flow using low cost electronic devices, this research work utilizes camera module of raspberry pi along with Raspberry Pi 3. It also aims to develop a remote access using raspberry-pi to detect, track and count vehicles only when some variations occur in the monitored area. The proposed system captures video stream like vehicles in the monitored area to compute the information and transfer the compressed video stream for providing video based solution that is mainly implemented in Open CV by Python Programming. The proposed method is considered as an economical solution for industries in which cost-effective solutions are developed for traffic management.

Real Time Vehicle Detection, Tracking and Counting Using Raspberry-Pi

The term Internet of Things [IoT] refers to the ever expanding complex system of basic things that emphasize communication between computing objects, devices and systems by offering connectivity from anyplace and at any time. It is estimated that by the end of 2020, 50 billion devices are said to be connected. IoT technologies play a crucial role to encompass many smart applications in real life. On the other hand, the crosscutting nature of IoT components and systems, introduce new security challenges. IoT covers advantages for various fields like agriculture, industry, healthcare, automobiles and home automation for improving and automating various day-to-day activities. Flood is usually caused either by change in the state of water body or due to the overflow of rivers, dams, etc. Due to advanced civilization and improved human life, environment problems also tend to increase. This paper includes the effective and flexible method for the detection of flood and alerting system. The most advanced technologies like machine learning (ML) provide significant boon to the field of technology are very powerful in monitoring the normal and abnormal behavioral characters of any machine. The objective of this work is to survey on flood issues. Neural networks are most popular, widely used for rainfall forecasting and perform efficiently.

Vishwanath P. Baligar

Papers

Detection of distributed denial of service attacks using machine learning algorithms in software defined networks

A novel approach in real-time vehicle detection and tracking using Raspberry Pi

Real Time Vehicle Detection, Tracking and Counting Using Raspberry-Pi

Low Cost IoT based Flood Monitoring System Using Machine Learning and Neural Networks: Flood Alerting and Rainfall Prediction

High compression and low order linear predictor for lossless coding of grayscale images