Farhan Aadil

Efficient Car Alarming System for Fatigue Detection during Driving

Driver inattention is one of the main causes of traffic accidents. Monitoring a driver to detect inattention is a complex problem that involves physiological and behavioral elements. Different approaches have been made, and among them Computer Vision has the potential of monitoring the person behind the wheel without interfering with his driving. A computer vision system for driving monitoring uses face location and tracking as the first processing stage. On the next stage the different facial features are extracted and tracked for monitoring the drivers vigilance. In this thesis I have developed a system that can monitor the alertness of drivers in order to prevent people from falling asleep at the wheel. The other main aim of this algorithm is to have efficient performance on low quality webcam and without the use of infrared light which is harmful for the human eye. Motor vehicle accidents cause injury and death, and this system will help to decrease the amount of crashes due to fatigued drivers. The proposed algorithm will work in three main stages. In first stage the face of the driver is detected and tracked. In the second stage the facial features are extracted for further processing. In last stage the most crucial parameter is monitored which is eyes status. In this last stage it is determined that whether the eyes are closed or open. On the basis of this result the warning is issued to the driver to take a break.

CACONET: Ant Colony Optimization (ACO) Based Clustering Algorithm for VANET

A vehicular ad hoc network (VANET) is a wirelessly connected network of vehicular nodes. A number of techniques, such as message ferrying, data aggregation, and vehicular node clustering aim to improve communication efficiency in VANETs. Cluster heads (CHs), selected in the process of clustering, manage inter-cluster and intra-cluster communication. The lifetime of clusters and number of CHs determines the efficiency of network. In this paper a Clustering algorithm based on Ant Colony Optimization (ACO) for VANETs (CACONET) is proposed. CACONET forms optimized clusters for robust communication. CACONET is compared empirically with state-of-the-art baseline techniques like Multi-Objective Particle Swarm Optimization (MOPSO) and Comprehensive Learning Particle Swarm Optimization (CLPSO). Experiments varying the grid size of the network, the transmission range of nodes, and number of nodes in the network were performed to evaluate the comparative effectiveness of these algorithms. For optimized clustering, the parameters considered are the transmission range, direction and speed of the nodes. The results indicate that CACONET significantly outperforms MOPSO and CLPSO.

Grey wolf optimization based clustering algorithm for vehicular ad-hoc networks

Abstract In vehicular ad-hoc network (VANETs), frequent topology changes occur due to fast moving nature of mobile nodes. This random topology creates instability that leads to scalability issues. To overcome this problem, clustering can be performed. Existing approaches for clustering in VANETs generate large number of cluster-heads which utilize the scarce wireless resources resulting in degraded performance. In this article, grey wolf optimization based clustering algorithm for VANETs is proposed, that replicates the social behaviour and hunting mechanism of grey wolfs for creating efficient clusters. The linearly decreasing factor of grey wolf nature enforces to converge earlier, which provides the optimized number of clusters. The proposed method is compared with well- known meta-heuristics from literature and results show that it provides optimal outcomes that lead to a robust routing protocol for clustering of VANETs, which is appropriate for highways and can accomplish quality communication, confirming reliable delivery of information to each vehicle.

Implementation of VANET-based Warning Generation System using Cellular Networks, GPS, and Passive RFID Tags

Vehicular communication systems are a key part of an intelligent transportation system, while vehicle safety communication is a major target of vehicular communication. Other features that augment vehicular ad hoc networks are enhanced driving experience, including but not limited to, active navigation and weather information, real-time traffic information and a plethora of other autonomous and automated systems. However, our focus will be warning generation systems, which can help reduce fatalities if deployed in an efficient and fail-safe manner on motorways and highways. This paper describes a collective information system for collection and delivery of traffic information aimed at supporting fast, efficient and secure travel of people and transport of goods. Based on that information, authorities are able to assess vehicles’ sudden motion and movement changes and can generate warning/alert messages (for emergency/police vehicles) for post-accident scenarios. In this paper, the use of a radio frequency identification (RFID) system for vehicular communication has been proposed and an extended RFID system and infrastructure for vehicle safety communication through emergency phone towers (EPTs) and cell phones is suggested. In order to communicate, vehicles may be equipped with a cellular phone, RFID, and/or a global positioning system (GPS), whereas RFID readers may be mounted on EPTs, which are already installed on motorways. It also provides a demonstration on flow of information within the system; the simulation results are also included.

Clustering algorithm for internet of vehicles (IoV) based on dragonfly optimizer (CAVDO)

Internet of vehicles (IoV) is a branch of the internet of things (IoT) which is used for communication among vehicles. As vehicular nodes are considered always in motion, hence it causes the frequent changes in the topology. These changes cause major issues in IoV like scalability, dynamic topology changes, and shortest path for routing. Clustering is among one of the solutions for such type of issues. In this paper, the stability of IoV topology in a dynamic environment is focused. The proposed metaheuristic dragonfly-based clustering algorithm CAVDO is used for cluster-based packet route optimization to make stable topology, and mobility aware dynamic transmission range algorithm (MA-DTR) is used with CAVDO for transmission range adaptation on the basis of traffic density. The proposed CAVDO with MA-DTR is compared with the progressive baseline techniques ant colony optimization (ACO) and comprehensive learning particle swarm optimization (CLPSO). Numerous experiments were performed keeping in view the transmission dynamics for stable topology. CAVDO performed better in many cases providing minimum number of clusters according to current channel condition. Considerable important parameters involved in clustering process are: number of un-clustered nodes as a re-clustering criterion, clustering time, re-clustering delay, dynamic transmission range, direction, and speed. According to these parameters, results indicate that CAVDO outperformed ACO-based clustering and CLPSO in various network settings. Additionally, to improve the network availability and to incorporate the functionalities of next-generation network infrastructure, 5G-enabled architecture is also utilized.

A Route Optimized Distributed IP-Based Mobility Management Protocol for Seamless Handoff across Wireless Mesh Networks

A Wireless Mesh Network (WMN) can provide Internet connectivity to end users through heterogenous access network technologies. However, the mobility of mobile nodes across these access networks in WMNs results in service disruption. Existing mobility management protocols are designed for single hop networks and are centralized in nature. A Distributed IP-based Mobility Management Protocol (DIMMP) is proposed in this paper that provides seamless mobility with service continuation for mobile nodes when they roam across WMNs. Instead of relying on a centralized mobility anchor, the mobility functionality is distributed at multiple nodes in the WMN, in order to reduce the chances of potential single point of failure. The proposed protocol manages both types of mobilities i.e. intra-WMN and inter-WMN and uses a new enhanced route optimization procedure. Simulation results show that this work has contributed by improving the performance of handoff procedure with respect to handoff latency, packet loss and signalling overhead, as compared to the existing protocols.

A dimensionality reduction-based efficient software fault prediction using Fisher linear discriminant analysis (FLDA)

AbstractSoftware quality is an important factor in the success of software companies. Traditional software quality assurance techniques face some serious limitations especially in terms of time and budget. This leads to increase in the use of machine learning classification techniques to predict software faults. Software fault prediction can help developers to uncover software problems in early stages of software life cycle. The extent to which these techniques can be generalized to different sizes of software, class imbalance problem, and identification of discriminative software metrics are the most critical challenges. In this paper, we have analyzed the performance of nine widely used machine learning classifiers—Bayes Net, NB, artificial neural network, support vector machines, K nearest neighbors, AdaBoost, Bagging, Zero R, and Random Forest for software fault prediction. Two standard sampling techniques—SMOTE and Resample with substitution are used to handle the class imbalance problem. We further used FLDA-based feature selection approach in combination with SMOTE and Resample to select most discriminative metrics. Then the top four classifiers based on performance are used for software fault prediction. The experimentation is carried out over 15 publically available datasets (small, medium and large) which are collected from PROMISE repository. The proposed Resample-FLDA method gives better performance as compared to existing methods in terms of precision, recall, f-measure and area under the curve.

Energy Aware Cluster-Based Routing in Flying Ad-Hoc Networks

Flying ad-hoc networks (FANETs) are a very vibrant research area nowadays. They have many military and civil applications. Limited battery energy and the high mobility of micro unmanned aerial vehicles (UAVs) represent their two main problems, i.e., short flight time and inefficient routing. In this paper, we try to address both of these problems by means of efficient clustering. First, we adjust the transmission power of the UAVs by anticipating their operational requirements. Optimal transmission range will have minimum packet loss ratio (PLR) and better link quality, which ultimately save the energy consumed during communication. Second, we use a variant of the K-Means Density clustering algorithm for selection of cluster heads. Optimal cluster heads enhance the cluster lifetime and reduce the routing overhead. The proposed model outperforms the state of the art artificial intelligence techniques such as Ant Colony Optimization-based clustering algorithm and Grey Wolf Optimization-based clustering algorithm. The performance of the proposed algorithm is evaluated in term of number of clusters, cluster building time, cluster lifetime and energy consumption.

Social media signal detection using tweets volume, hashtag, and sentiment analysis

Social Media is a well-known platform for users to create, share and check the new information. The world becomes a global village because of the utilization of internet and social media. The data present on Twitter contains information of great importance. There is a strong need to extract valuable information from this huge amount of data. A key research challenge in this area is to analyze and process this huge data and detect the signals or spikes. Existing work includes sentiment analysis for Twitter, hashtag analysis, and event detection but spikes/signal detection from Twitter remains an open research area. From this line of research, we propose a signal detection approach using sentiment analysis from Twitter data (tweets volume, top hashtag and sentiment analysis). In this paper, we propose three algorithms for signal detection in tweets volume, tweets sentiment and top hashtag. The algorithms are the- Average moving threshold algorithm, Gaussian algorithm, and hybrid algorithm. The hybrid algorithm is a combination of the average moving threshold algorithm and Gaussian algorithm. The proposed algorithms are tested over real-time data extracted from Twitter and two large publically available datasets- Saudi Aramco dataset and BP America dataset. Experimental results show that hybrid algorithm outperforms the Gaussian and average moving threshold algorithm and achieve a precision of 89% on real-time tweets data, 88% on Saudi Aramco dataset and 81% on BP America dataset with the recall of 100%.

Optimized Gabor Feature Extraction for Mass Classification Using Cuckoo Search for Big Data E-Healthcare

Widespread use of electronic health records is a major cause of a massive dataset that ultimately results in Big Data. Computer-aided systems for healthcare can be an effective tool to automatically process such big data. Breast cancer is one of the major causes of high mortality rate among women in the world since it is difficult to detect due to lack of early symptoms. There is a number of techniques and advanced technologies available to detect breast tumors nowadays. One of the common approaches for breast tumour detection is mammography. The similarity between the normal (unaffected) tissues and the masses (affected) tissues is often very high that leads to false positives (FP). In the field of medicine, the sensitivity to false positives is very high because it results in false diagnosis and can lead to serious consequences. Therefore, it is a challenge for the researchers to correctly distinguish between the normal and affected tissues to increase the detection accuracy. Radiologists use Gabor filter bank for feature extraction and apply it to the entire input image that yields poor results. The proposed system optimizes the Gabor filter bank to select most appropriate Gabor filter using a metaheuristic algorithm known as “Cuckoo Search”. The proposed algorithm is run over sub-images in order to extract more descriptive features. Moreover, feature subset selection is used to reduce feature size because feature extracted from the segmented region of interest will be high dimensional and cannot be handled easily. This algorithm is more efficient, fast, and less complex and spawns improved results. The proposed method is tested on 2000 mammograms taken from DDSM database and outperforms some of the best techniques used for mammogram classification based on Sensitivity, Specificity, Accuracy, and Area under the curve (ROC).