Faheem Zafari

Microlocation for Internet-of-Things-Equipped Smart Buildings

Microlocation is the process of locating any entity with a very high accuracy (possibly in centimeters), whereas geofencing is the process of creating a virtual fence around a point of interest (PoI). In this paper, we present an insight into various microlocation enabling technologies, techniques, and services. We also discuss how they can accelerate the incorporation of Internet of Things (IoT) in smart buildings. We argue that micro-location-based location aware solutions can play a significant role in facilitating the tenants of an IoT-equipped smart building. Also, such advanced technologies will enable the smart building control system through minimal actions performed by the tenants. We also highlight the existing and envisioned services to be provided by using microlocation enabling technologies. We describe the challenges and propose some potential solutions, such that microlocation enabling technologies and services are thoroughly integrated with IoT-equipped smart building.

Enhancing iBeacon Based Micro-Location with Particle Filtering

The advent of Bluetooth Low Energy (BLE) enabled Beacons is poised to revolutionize the indoor contextual aware services to the users. Due to the lower energy consumption and higher throughput, BLE could therefore be an integral pillar of an Internet of Things (IoT) Location Based Service (LBS). Tracking a user with high accuracy is known as Micro-Location. This is a requirement of many IoT user-centric applications for indoor environments. Although several technologies have been used for tracking purposes, the accuracy has always been a serious issue. At the same time, each vendor would install different technologies. In this work, we propose to use the cutting edge and commercially available Apples iBeacon protocol and iBeacon BLE sensors for micro-location. We propose to leverage a control theoretic approach, namely particle filtering, in order to increase the tracking accuracy in an indoor environment. We performed extensive experiments and our results show that the proposed beacon based micro-location system can be used to locate a user in an indoor environment with an error as low as 0.27 meters.

Enhancing the accuracy of iBeacons for indoor proximity-based services

Proximity-based Services (PBS) require high detection accuracy, energy efficiency, wide reception range, low cost and availability. However, most existing technologies cannot satisfy all these requirements. Apples Bluetooth Low Energy (BLE), named iBeacon, has emerged as a leading candidate in this domain and has become an almost industry standard for PBS. However, it has several limitations. It suffers from poor proximity detection accuracy due to its reliance on Received Signal Strength Indicator (RSSI). To improve proximity detection accuracy of iBeacons, we present two algorithms that address the inherent flaws in iBeacons current proximity detection approach. Our first algorithm, Server-side Running Average (SRA), uses the path-loss model-based estimated distance for proximity classification. Our second algorithm, Server-side Kalman Filter (SKF), uses a Kalman filter in conjunction with SRA. Our experimental results show that SRA and SKF perform better than the current moving average approach utilized by iBeacons. SRA results in about a 29% improvement while SKF results in about a 32% improvement over the current approach in proximity detection accuracy.

Predicting network attack patterns in SDN using machine learning approach

An experimental setup of 32 honeypots reported 17M login attempts originating from 112 different countries and over 6000 distinct source IP addresses. Due to decoupled control and data plane, Software Defined Networks (SDN) can handle these increasing number of attacks by blocking those network connections at the switch level. However, the challenge lies in defining the set of rules on the SDN controller to block malicious network connections. Historical network attack data can be used to automatically identify and block the malicious connections. There are a few existing open-source software tools to monitor and limit the number of login attempts per source IP address one-by-one. However, these solutions cannot efficiently act against a chain of attacks that comprises multiple IP addresses used by each attacker. In this paper, we propose using machine learning algorithms, trained on historical network attack data, to identify the potential malicious connections and potential attack destinations. We use four widely-known machine learning algorithms: C4.5, Bayesian Network (BayesNet), Decision Table (DT), and Naive-Bayes to predict the host that will be attacked based on the historical data. Experimental results show that average prediction accuracy of 91.68% is attained using Bayesian Networks.

Very Short Term Load Forecasting Using Cartesian Genetic Programming Evolved Recurrent Neural Networks (CGPRNN)

Forecasting the electrical load requirements is an important research objective for maintaining a balance between the demand and generation of electricity. This paper utilizes a neuro-evolutionary technique known as Cartesian Genetic Programming evolved Recurrent Neural Network (CGPRNN) to develop a load forecasting model for very short term of half an hour. The network is trained using historical data of one month on half hourly basis to predict the next half hour load based on the 12 and 24 hours data history. The results demonstrate that CGPRNN is superior to other networks in very short term load forecasting in terms of its accuracy achieving 99.57 percent. The model was developed and evaluated on the data collected from the UK Grid station.

Electrical load forecasting using fast learning recurrent neural networks

A new recurrent neural network model which has the ability to learn quickly is explored to devise a load forecasting and management model for the highly fluctuating load of London. Load forecasting plays an significant role in determining the future load requirements as well as the growth in the electricity demand, which is essential for the proper development of electricity infrastructure. The newly developed neuroevolutionary technique called Recurrent Cartesian Genetic Programming evolved Artificial Neural Networks (RCGPANN) has been used to develop a peak load forecasting model that can predict load patterns for a complete year as well as for various seasons in advance. The performance of the model is evaluated using the load patterns of London for a period of four years. The experimental results demonstrate the superiority of the proposed model to the contemporary methods presented to date.

Future Clients' Requests Estimation for Dynamic Resource Allocation in Cloud Data Center Using CGPANN

Cloud computing is an emerging and rapid growing field of Infrastructure as a Service (IaaS), it has to deal with resource allocation and power management issues. This paper proposes CGPANN to accurately forecast the clients requests for a very short term duration of 1 second. A forecasting accuracy as high as 99.81% has been attained that verifies the accuracy of the proposed model. The experimental results show that the model outperforms all the contemporary models proposed in past.

Evolving Recurrent Neural Network using Cartesian Genetic Programming to Predict The Trend in Foreign Currency Exchange Rates

Forecasting the foreign exchange rate is an uphill task. Numerous methods have been used over the years to develop an efficient and reliable network for forecasting the foreign exchange rate. This study utilizes recurrent neural networks (RNNs) for forecasting the foreign currency exchange rates. Cartesian genetic programming (CGP) is used for evolving the artificial neural network (ANN) to produce the prediction model. RNNs that are evolved through CGP have shown great promise in time series forecasting. The proposed approach utilizes the trends present in the historical data for its training purpose. Thirteen different currencies along with the trade-weighted index (TWI) and special drawing rights (SDR) is used for the performance analysis of recurrent Cartesian genetic programming-based artificial neural networks (RCGPANN) in comparison with various other prediction models proposed to date. The experimental results show that RCGPANN is not only capable of obtaining an accurate but also a computationally efficient prediction model for the foreign currency exchange rates. The results demonstrated a prediction accuracy of 98.872 percent (using 6 neurons only) for a single-day prediction in advance and, on average, 92% for predicting a 1000 days’ exchange rate in advance based on ten days of data history. The results prove RCGPANN to be the ultimate choice for any time series data prediction, and its capabilities can be explored in a range of other fields.

Joint Data Compression and Caching: Approaching Optimality with Guarantees

We consider the problem of optimally compressing and caching data across a communication network. Given the data generated at edge nodes and a routing path, our goal is to determine the optimal data compression ratios and caching decisions across the network in order to minimize average latency, which can be shown to be equivalent to maximizing the compression and caching gain under an energy consumption constraint. We show that this problem is NP-hard in general and the hardness is caused by the caching decision subproblem, while the compression sub-problem is polynomial-time solvable. We then propose an approximation algorithm that achieves a

Dynamic feedback neuro-evolutionary networks for forecasting the highly fluctuating electrical loads

(1-1/e)