No abstract

No abstract

Traffic Analysis has been a problem that city planners have dealt with for years. Smarter ways are being developed to analyze traffic and streamline the process. Analysis of traffic may account for the number of vehicles in an area per some arbitrary time period and the class of vehicles. People have designed such mechanism for decades now but most of them involve use of sensors to detect the vehicles i.e. a couple of proximity sensors to calculate the direction of the moving vehicle and to keep the vehicle count. Even though over the time these systems have matured and are highly effective, they are not very budget friendly. The problem is such systems require maintenance and periodic calibration. Therefore, this study has purposed a vision based vehicle counting and classification system. The system involves capturing of frames from the video to perform background subtraction in order detect and count the vehicles using Gaussian Mixture Model (GMM) background subtraction then it classifies the vehicles by comparing the contour areas to the assumed values. The substantial contribution of the work is the comparison of two classification methods. Classification has been implemented using Contour Comparison (CC) as well as Bag of Features (BoF) and Support Vector Machine (SVM) method.

Continuous health monitoring for an infant is crucial for detecting and preventing several diseases. Recent advancement in wearable technology has given rise to the development of wearable infant health monitoring systems (WIHMSs). These systems provide an edge over conventional infant health monitoring systems which are not only bulky and uncomfortable for the infants but are also limited to the clinical settings. This study reviews some state-of-the-art WIHMS, mentions the advantages, limitations and the challenges faced by such systems. This study, for the first time, contributes an appraisal of research prototypes and commercially available systems for WIHMS, which is the need of the day.

Social media have become a very viable medium for communication, collaboration, exchange of information, knowledge, and ideas. However, due to anonymity preservation, the incidents of hate speech and cyberbullying have been diversified across the globe. This intimidating problem has recently sought the attention of researchers and scholars worldwide and studies have been undertaken to formulate solution strategies for automatic detection of cyberaggression and hate speech, varying from machine learning models with vast features to more complex deep neural network models and different SN platforms. However, the existing research is directed towards mature languages and highlights a huge gap in newly embraced resource poor languages. One such language that has been recently adopted worldwide and more specifically by south Asian countries for communication on social media is Roman Urdu i-e Urdu language written using Roman scripting. To address this research gap, we have performed extensive preprocessing on Roman Urdu microtext. This typically involves formation of Roman Urdu slang- phrase dictionary and mapping slangs after tokenization. We have also eliminated cyberbullying domain specific stop words for dimensionality reduction of corpus. The unstructured data were further processed to handle encoded text formats and metadata/non-linguistic features. Furthermore, we performed extensive experiments by implementing RNN-LSTM, RNN-BiLSTM and CNN models varying epochs executions, model layers and tuning hyperparameters to analyze and uncover cyberbullying textual patterns in Roman Urdu. The efficiency and performance of models were evaluated using different metrics to present the comparative analysis. Results highlight that RNN-LSTM and RNN-BiLSTM performed best and achieved validation accuracy of 85.5 and 85% whereas F1 score was 0.7 and 0.67 respectively over aggression class.