Inderscience Publishers: publishers of distinguished academic, scientific and professional journals.

As the social applications are gaining the more popularity, different kinds of social media platform are ready to publish and express the emotions in the form of reviews. In which, detecting the concealed sentiment patterns and discovering knowledge in the huge user-generated inputs is a challenging task and has greater social significance value. In traditional sentiment analysis approaches, statistical correlation between words is considered. Whereas, dependency factor between aspects and the sentiment words are ignored, which has a greater impact factor on overall sentiment analysis. In this paper, we propose a new supervised topic level sentiment model (SSM), which is capable of handling overall sentiment analysis problems. Belief maximisation algorithm is used in SSM model, and Dirichlet distribution is used to estimate aspects and sentiment words. In order to prepare and modernise new documents, a hyperparameter Gibbs sampling method is used. We conducted experiments on reviews related to different products in multiple documents and the results state that the SSM model outperforms the on-hand algorithm in terms of aspect recognition and overall sentiment prediction accuracy.

Self-driving vehicles such as autonomous cars are manufactured mostly with smart sensors and IoT devices with artificial intelligence (AI) techniques. In most of the cases, smart sensors are networked with IoT devices to transmit the data in real-time. IoT devices transmit the sensor data to the processing unit to do necessary actions based on sensor output data. The processing unit executes the tasks based on pre-defined instructions given to the processor with embedded and AI coding techniques. Continuous streaming of sensors raw data to the processing unit and for cloud storage are creating a huge load on cloud devices or on servers. In order to reduce the amount of stream data load on the cloud, fog computing, or fogging technology, helps a lot. Fogging is nothing but the pre-processing of the data before deploying it into the cloud. In fog environment, data optimization and analytical techniques take place as a part of data processing in a data hub on IoT devices or in a gateway.