Smartphones are context-aware devices that provide a compelling platform for ubiquitous computing and assist users in accomplishing many of their routine tasks anytime and anywhere, such as sending and receiving emails. The nature of tasks conducted with these devices has evolved with the exponential increase in the sensing and computing capabilities of a smartphone. Due to the ease of use and convenience, many users tend to store their private data, such as personal identifiers and bank account details, on their smartphone. However, this sensitive data can be vulnerable if the device gets stolen or lost. A traditional approach for protecting this type of data on mobile devices is to authenticate users with mechanisms such as PINs, passwords, and fingerprint recognition. However, these techniques are vulnerable to user compliance and a plethora of attacks, such as smudge attacks. The work in this paper addresses these challenges by proposing a novel authentication framework, which is based on recognizing the behavioral traits of smartphone users using the embedded sensors of smartphone, such as Accelerometer, Gyroscope and Magnetometer. The proposed framework also provides a platform for carrying out multi-class smart user authentication, which provides different levels of access to a wide range of smartphone users. This work has been validated with a series of experiments, which demonstrate the effectiveness of the proposed framework.

Smartphones are a promising platform for continuous monitoring of human behavior. However, the ability to capture people's behavioral patterns in-the-wild is a challenge, as the user's behavior and physical activities can vary, given the variability of settings and environments. Modeling and understanding of human activity in-the-wild must not overlook a user's behavioral context, which is just as crucial as recognizing the range of physical activities. The work in this paper presents a novel framework for context-aware human activity recognition by incorporating human behavioral contexts with physical activities. The proposed framework utilizes a series of machine learning classifiers to validate the efficiency of the proposed method.

Recent developments in mobile brain-body imaging (MoBI) technologies have enabled studies of human locomotion where subjects are able to move freely in more ecologically valid scenarios. In this study, MoBI was employed to describe the behavioural and neurophysiological aspects of three different commonly occurring walking conditions in healthy adults. The experimental conditions were self-paced walking, walking while conversing with a friend and lastly walking while texting with a smartphone. We hypothesised that gait performance would decrease with increased cognitive demands and that condition-specific neural activation would involve condition-specific brain areas. Gait kinematics and high density electroencephalography were recorded whilst walking around a university campus. Conditions with dual tasks were accompanied by decreased gait performance. Walking while conversing was associated with an increase of theta () and beta (β) neural power in electrodes located over left-frontal and right parietal regions, whereas walking while texting was associated with a decrease of β neural power in a cluster of electrodes over the frontal-premotor and sensorimotor cortices when compared to walking whilst conversing. In conclusion, the behavioural ‘signatures’ of common real-life activities performed outside the laboratory environment were accompanied by differing frequency-specific neural ‘biomarkers’. The current findings encourage the study of the neural biomarkers of disrupted gait control in neurologically impaired patients.

Pattern recognition is seen as a major challenge within the field of data mining and knowledge discovery. For the work in this paper, we have analyzed a range of widely used algorithms for finding frequent patterns with the purpose of discovering how these algorithms can be used to obtain frequent patterns over large transactional databases. This has been presented in the form of a comparative study of the following algorithms: Apriori algorithm, Frequent Pattern (FP) Growth algorithm, Rapid Association Rule Mining (RARM), ECLAT algorithm and Associated Sensor Pattern Mining of Data Stream (ASPMS) frequent pattern mining algorithms. This study also focuses on each of the algorithm's strengths and weaknesses for finding patterns among large item sets in database systems