Search results

The purpose of this paper is geared towards the capture and analysis of network traffic using an array ofmachine learning (ML) and deep learning (DL) techniques to classify network traffic into different classes and predict network traffic parameters.

The classifier models include k-nearest neighbour (KNN), multilayer perceptron (MLP) and support vector machine (SVM), while the regression models studied are multiple linear regression (MLR) as well as MLP. The analytics were performed on both a local server and a servlet hosted on the international business machines cloud. Moreover, the local server could aggregate data from multiple devices on the network and perform collaborative ML to predict network parameters. With optimised hyperparameters, analytical models were incorporated in the cloud hosted Java servlets that operate on a client–server basis where the back-end communicates with Cloudant databases.

Regarding classification, it was found that KNN performs significantly better than MLP and SVM with a comparative precision gain of approximately 7%, when classifying both Wi-Fi and long term evolution (LTE) traffic.

Collaborative regression models using traffic collected from two devices were experimented and resulted in an increased average accuracy of 0.50% for all variables, with a multivariate MLP model.

In this chapter, a general introduction on artificial intelligence (AI) is given as well as an overview of the advances of AI in different engineering disciplines, including its effectiveness in driving the United Nations Sustainable Development Goals (UN SDGs). This chapter begins with some fundamental definitions and concepts on AI and machine learning (ML) followed by a classification of the different categories of ML algorithms. After that, a general overview of the impact which different engineering disciplines such as Civil, Chemical, Mechanical, Electrical and Telecommunications Engineering have on the UN SDGs is given. The application of AI and ML to enhance the processes in these different engineering disciplines is also briefly explained. This chapter concludes with a brief description of the UN SDGs and how AI can positively impact the attainment of these goals by the target year of 2030.

The purpose of this paper is to develop a blockchain-based data capture and transmission system that will collect real-time power consumption data from a household electrical appliance and transfer it securely to a local server for energy analytics such as forecasting.

The data capture system is composed of two current transformer (CT) sensors connected to two different electrical appliances. The CT sensors send the power readings to two Arduino microcontrollers which in turn connect to a Raspberry-Pi for aggregating the data. Blockchain is then enabled onto the Raspberry-Pi through a Java API so that the data are transmitted securely to a server. The server provides real-time visualization of the data as well as prediction using the multi-layer perceptron (MLP) and long short term memory (LSTM) algorithms.

The results for the blockchain analysis demonstrate that when the data readings are transmitted in smaller blocks, the security is much greater as compared with blocks of larger size. To assess the accuracy of the prediction algorithms data were collected for a 20 min interval to train the model and the algorithms were evaluated using the sliding window approach. The mean average percentage error (MAPE) was used to assess the accuracy of the algorithms and a MAPE of 1.62% and 1.99% was obtained for the LSTM and MLP algorithms, respectively.

A detailed performance analysis of the blockchain-based transmission model using time complexity, throughput and latency as well as energy forecasting has been performed.

The purpose of this paper is to perform a comparative analysis of the delay associated in running two real-time machine learning-based applications, namely, a video quality assessment (VQA) and a phishing detection application by using the edge, fog and cloud computing paradigms.

The VQA algorithm was developed using Android Studio and run on a mobile phone for the edge paradigm. For the fog paradigm, it was hosted on a Java server and for the cloud paradigm on the IBM and Firebase clouds. The phishing detection algorithm was embedded into a browser extension for the edge paradigm. For the fog paradigm, it was hosted on a Node.js server and for the cloud paradigm on Firebase.

For the VQA algorithm, the edge paradigm had the highest response time while the cloud paradigm had the lowest, as the algorithm was computationally intensive. For the phishing detection algorithm, the edge paradigm had the lowest response time, and the cloud paradigm had the highest, as the algorithm had a low computational complexity. Since the determining factor for the response time was the latency, the edge paradigm provided the smallest delay as all processing were local.

The main limitation of this work is that the experiments were performed on a small scale due to time and budget constraints.

A detailed analysis with real applications has been provided to show how the complexity of an application can determine the best computing paradigm on which it can be deployed.

This chapter provides an overview of the potential use of Intelligent Transport Systems (ITS) and associated artificial intelligence (AI) techniques in the land transport sector in an attempt to achieve related United Nations Sustainable Development Goals (SDGs) targets. ITS applications that have now been extensively tested worldwide and have become part of the everyday transport toolkit available to practitioners have been discussed. AI techniques applied successfully in specific ITS applications such as automatic traffic control systems, real-time image processing, automatic incident detection, safety management, road condition assessment, asset management and traffic enforcement systems have been identified. These methods have helped to provide traffic engineers and transport planners with novel ways to improve safety, mobility, accessibility and efficiency in the sector and thus move closer to achieving the various SDG targets pertaining to transportation.

Intelligent real-time systems are significantly impacting several of the UN Sustainable Development Goals (SDGs) by revolutionising processes in several areas such as Industry 4.0, smart cities, transportation, agriculture, renewable energy, climate change and other economic activities. Given that much of the work to achieve the SDGs relies on information and communication technology, cybersecurity has a potentially immense role to play towards achieving these outcomes. Moreover, cyberattacks have emerged as a new functional threat for interconnected, smart manufacturers and digital supply networks, employed in intelligent real-time systems for the Fourth Industrial Revolution. The effects of cyberattacks can be much more widespread than ever before due to the interconnected nature of Industry 4.0-driven operations. Blockchain can be really useful in such situations as it provides edge protection and allows authentication of the machine-to-machine and human–machine operations, stable data share, life cycle management, access control compliance of devices and self-sustaining operations. Moreover, blockchain can be applied for tracking and tracing transactions through devices, which are performed during the operation, as well as to encrypt and transmit data securely. It is vital to establish complete trust in a technology that is being adopted so that its full potential can be exploited. It is consequently critical that the organisational and information technology strategy fully integrates secure, vigilant and resilient cybersecurity strategies such as blockchain. This will ensure that cyber risks are properly managed in the age of Industry 4.0. This chapter, therefore, analyses the application of blockchain in intelligent real-time systems such as Industry 4.0 so that the opportunities these systems present for the SDGs can be exploited safely with minimum risks to society.

Energy production and distribution is undergoing a revolutionary transition with the advent of disruptive technologies such as the Internet of Energy (IoE), 5G and artificial intelligence (AI). IoE essentially involves automating and enhancing the energy infrastructure: the power grid from grid operators to energy generators and distribution utilities. The IoE also relies on powerful connectivity networks such as 5G, big data analytics and AI to optimise its operation. By incorporating the technology that employs ubiquitous devices such as smartphones, tablets or smart electric vehicles, it will be possible to fully exploit the potential of IoE using 5G networks. 5G networks will provide high speed connections between devices such as drones, tractors and cloud networks, to transfer huge amounts of sensor data. Additionally, there are many sources of isolated data across the main energy production units (generation, transmission and distribution), and the data is increasing at phenomenal rates. By applying AI to these data, major improvements can be brought at each stage of the energy production chain. Tying renewable energy to the telecommunications sector and leveraging on the potential of data analytics is something which is gaining major attention among researchers and industry experts. This chapter therefore explores the combination of three of the most promising technologies i.e. IoE, 5G and AI for achieving affordable and clean energy, which is SDG 7 in the UN Sustainable Development Goals (SDGs).

There is an urgent need to develop climate-smart agrosystems capable of mitigating climate change and adapting to its effects. Conventional agricultural practices prevail in Mauritius, whereby synthetic chemical fertilizers, pesticides and insecticides are used. It should be noted that Mauritius remains a net-food importing developing country of staple food such as cereals and products, roots and tubers, pulses, oil crops, vegetables, fruits and meat (FAO, 2011). In Mauritius, the agricultural sector faces extreme weather conditions like drought or heavy rainfall. Moreover, to increase the crop yields, farmers tend to use 2.5 times the prescribed amount of fertilizers in their fields. These excess fertilizers are washed away during heavy rainfall and contaminate lakes and river waters. By using smart irrigation and fertilization system, a better management of soil water reserves for improved agricultural production can be implemented. Soil Nitrogen, Phosphorus and Potassium (NPK) content, humidity, pH, conductivity and moisture data can be monitored through the cloud platform. The data will be processed at the level of the cloud and an appropriate mix of NPK and irrigation will be used to optimise the growth of the crops. Machine learning algorithms will be used for the control of the land drainage, fertilization and irrigation systems and real time data will be available through a mobile application for the whole system. This will contribute towards the Sustainable Development Goals (SDGs): 2 (Zero Hunger), 11 (Sustainable cities and communities), 12 (Responsible consumption and production) and 15 (Life on Land). With this project, the yield of crops will be boosted, thus reducing the hunger rate (SDG 2). On top of that, this will encourage farmers to collect the waters and reduce fertilizer consumption thereafter sustaining the quality of the soil on which they are cultivating the crops, thereby increasing their yields (SDG 15).

Adsorption parameters (e.g. Langmuir constant, mass transfer coefficient and Thomas rate constant) are involved in the design of aqueous-media adsorption treatment units. However, the classic approach to estimating such parameters is perceived to be imprecise. Herein, the essential features and performances of the ant colony, bee colony and elephant herd optimisation approaches are introduced to the experimental chemist and chemical engineer engaged in adsorption research for aqueous systems. Key research and development directions, believed to harness these algorithms for real-scale water treatment (which falls within the wide-ranging coverage of the Sustainable Development Goal 6 (SDG 6) ‘Clean Water and Sanitation for All’), are also proposed. The ant colony, bee colony and elephant herd optimisations have higher precision and accuracy, and are particularly efficient in finding the global optimum solution. It is hoped that the discussions can stimulate both the experimental chemist and chemical engineer to delineate the progress achieved so far and collaborate further to devise strategies for integrating these intelligent optimisations in the design and operation of real multicomponent multi-complexity adsorption systems for water purification.