Browsing by Author "Dr. Abbas Javed, Assistant Profesor [Supervisor]"

Now showing 1 - 2 of 2

Mechine And Learning Based IoT Instruion Detection
(Publisher COMSATS University Islambad Lahore Campus, 2018) Muhammad Saad Sarfraz Khan; , SP16-REE-006; Dr. Abbas Javed, Assistant Profesor [Supervisor]; LHR TP 6439
In today’s world, technological advancements are gradually increasing, so small scale to large scale companies use the internet for business purposes. Other than that Internet of Things (IoT) is a current trend in the world. Most companies try to improve their companies by making them smart premises since this will give a lot of advantages; some are increasing customer satisfaction, saving time, control expenses, monitoring, and many more. So, with the rise of these technological advancements, diverse types of security issues like DDoS, malware, virus, worms, and many other issues occurs as well because of the software or device vulnerabilities. These are harmful to organizations’ sensitive data due to the violation of integrity, confidentiality, and availability. IoT devices have been extensively implemented in many different applications in recent years, such as smart homes, medical, heavy industry, agriculture, networks, security, transportation, etc. An adversary can capture the network traffic of IoT devices and analyze it to reveal user activities even if the traffic is encrypted. Due to the increasing number of cyber-attacks, we need IoT security solutions. The majority of the attacks are extended versions of previously known attacks and bypass the conventional firewall system. An Intrusion Detection System (IDS) performed an incredibly significant part to figure out the novel types of attacks by analyzing the network traffic. Machine Learning (ML) and Deep Learning (DL) based techniques such as Random Forest (RF), Support Vector Machine (SVM), J48, Naïve Bayes (NB), Logistic Regression (LR), etc. are used as a classifier to categorize the network traffic as normal and attack class. The objective of this research is to compare the impact of different Feature Selection (FS) techniques such as Information Gain (IG), Chi-Square, Correlation-based Feature Selection (CFS) subsets evaluator, Classifier based attributes, and other techniques on the accuracy, computational time and confusion matrix of ML & DL based techniques and identify the attack categories. FS methods and classifiers have been implemented on four different data sets NSL KDD, UNSW-15, CIC IDS2017, and TON_IoT and a comparative assessment of the outcome is presented. By applying our proposed comparative model, we will be able to trace out the malicious attacks i.e., DoS, DDoS, routing attacks, Man-in-The-Middle (MITM), etc. in the realm of IoT networks. This model detects the attacks with high accuracy and consumes less time as compared to the other methods.
Real-Time Air Pollution Monitoring Using Machine
(COMSATS University Islamabad Lahore Campus, 2020) Rana Ahtisham Ali,; SP18-REE-015; Dr. Abbas Javed, Assistant Profesor [Supervisor]; LHR TP 7466
According to World Health Organization (WHO), the air in Lahore, Pakistan, has an annual average of 68 µg/m3 of PM 2.5 particles which are 6.8 times more than safe levels recommended by WHO. In December 2016, the amount of PM2.5 went above 100 µg/m3 which was more than 10 times safe levels set by WHO. Currently, there is no network for real time air pollution prediction available in Lahore, nor Pakistan. In this research, an Internet of Things (IoT) based low cost/low power outdoor air quality monitoring system has been developed. We developed the wireless sensor nodes for the monitoring and prediction of the PM2.5 particles in the air. The nodes comprised of different sensors for measuring PM2.5, SO2, O3, CO, NH3, NO2, humidity, and temperature values and Long Range (LoRa) transceiver for uploading the data on the cloud. The coverage range of LoRa gateway has been tested in Lahore, Pakistan and it is found that coverage range of the sensor node is around 2.7 KM in densely populated areas. Five different artificial neural network models are used for the prediction ahead of 1hr, 2hr, 3hr, 4hr, 5hr and 6hr. We obtained the accuracy of 99% for tested model of LSTM. The accuracy of LSTM model for 1hr ahead is 13% more than FFNN, 2% than Elman NN, 0.41% than NARX and 0.45% than layer recurrent. The accuracy of LSTM model to predict 6hr ahead is above 95%. For 6hr ahead prediction, accuracy of LSTM is 15% better than FFN, 12% than Elam NN, 7% than layer recurrent and 9% than NARX NN. Results show that the LSTM model outclass all other models. The computational time of LSTM model to predict 6hr ahead is 150.22565msec. While FFN takes 30 msec, Elman NN takes 60msec, NARX takes 80msec and layer recurrent take 90 msec. The 1hr ahead predicted model of feed-forward NN embedded in all nodes and placed at different places for real-time testing. The dataset collected at the server side analyzed and it is found that our air pollution monitoring system is capable of accurately predicting the future (1 hour ahead) concentration of PM 2.5 in outdoor air. Its accuracy for 1hr ahead prediction is up-to 90% and its algorithm takes 0.642 micro seconds computational time for the prediction level of PM2.5.