28 April 2022 in Computational Intelligence and Neuroscience
The early diagnosis of stress symptoms is essential for preventing various mental disorder such as depression. Electroencephalography (EEG) signals are frequently employed in stress detection research and are both inexpensive and noninvasive modality. This paper proposes a stress classification system by utilizing an EEG signal. EEG signals from thirty-five volunteers were analysed which were acquired using four EEG sensors using a commercially available 4-electrode Muse EEG headband. Four movie clips were chosen as stress elicitation material. Two clips were selected to induce stress as it contains emotionally inductive scenes. The other two clips were chosen that do not induce stress as it has many comedy scenes. The recorded signals were then used to build the stress classification model. We compared the Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) for classifying stress and nonstress group. The maximum classification accuracy of 93.17% was achieved using two-layer LSTM architecture.
2 October 2020 in Journal of Statistics and Management Systems
With the rapid growth in on-line based recruiting system, candidates apply for job on web portal by uploading their resumes. Due to internet based recruiting systems, candidates participate in large volumes and hence it becomes a challenge task for recruiter to filter candidates for the required role. The resumes uploaded by the candidate are varied in format such as font, colour, font size, etc. and it is difficult for the recruiters to find the best match for a job role. Natural Language Processing (NLP) helps to deal with such problems and help recruiters to extract detailed information of the candidates required to carry forward their candidature. In this work, we propose to use named entity recognition of Stanford CoreNLP system to extract information relevant for recruiting process. Moreover, on the basis of skills set of candidate, the resume of the candidate is assigned a genre such as Computer Science, Statistics, Business Development etc. In this paper we propose to design an intelligent resume parser system capable of converting the unstructured data into a structured format which enables the recruiter to filter the right candidates for the desired job role. The overall resume prediction of our system is 91.47%.
1 January 2023 in International Journal of Critical Infrastructures