Tanmay Bhowmik

Stress has an impact, not only on a person’s physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.

Discovering vulnerabilities is an information-intensive task that requires a developer to locate the defects in the code that have security implications. The task is difficult due to the growing code complexity and some developer's lack of security expertise. Although tools have been created to ease the difficulty, no single one is sufficient. In practice, developers often use a combination of tools to uncover vulnerabilities. Yet, the basis on which different tools are composed is under explored. In this paper, we examine the composition base by taking advantage of the tool design patterns informed by foraging theory. We follow a design science methodology and carry out a three-step empirical study: mapping 34 foraging-theoretic patterns in a specific vulnerability discovery tool, formulating hypotheses about the value and cost of foraging when considering two composition scenarios, and performing a human-subject study to test the hypotheses. Our work offers insights into guiding developers' tool usage in detecting software vulnerabilities.

In order to mitigate the ever-increasing trend in software failures with far reaching consequences, research has suggested close coordination of requirements engineering (RE) and testing. The literature also advocates the notion of requirements-based testing (RBT) focusing on checking both the quality attributes and implementation of requirements. As requirements reside in the environment comprised of certain problem domain phenomena, the environment assertions connecting some of these phenomena in the indicative mood play a critical part in determining the correctness of a software solution. For formulating environment assertions, current literature provides manual techniques that are extremely time consuming and highly dependent on an individual's domain knowledge. In addition, developers often struggle to formulate good assertions from scratch. To address this issue, our work develops a boilerplate with certain placeholders that can be replaced with relevant attributes to formulate individual environment assertions. Leveraging this boilerplate, we further present a framework to capture environment assertions in an automated manner. An empirical study, involving 45 developers and 56 different software systems from 13 application domains, suggests that our framework captures useful environment assertions that are also relevant to software providing similar features in other application domains. Our work, to that end, opens new avenues for further coordination between RE and testing.