No abstract

the work aims at the optimization of the output feed rate of a Stationary Hook Hopper Feeder so that the best possible set of parameters affecting it can be selected to get the desired output. For this purpose the effect of various parameters on the feeder output is studied. To facilitate the study and detailed analysis, a statistical model is constructed which is used to predict and optimize the performance of the system. Efficient feed rate optimization determines the input variable settings to adjust the feed rate of the feeder according to the consumption of the parts in the next phase of production. The Stationary Hook Hopper Feeder, whose performance is to be studied, consists of a rotating circular plate and a guiding hook fixed at the centre and running up to the periphery of the plate. As the plate rotates, the parts follow the trajectory of the hook, orient themselves and then eventually are delivered through the delivery chute, tangentially to the plate. The factors influencing the feeder's performance include the speed of rotation of the disc, the population of the parts in the hopper and the size of parts to be fed. A series of experiments is performed on the three process parameters to investigate their effect on the feed rate. To study the interaction among the factors a full 23 factorial experiment approach has been adopted using the two basic principles of experimental designreplication and randomization. The process model was formulated based on Analysis of variance (ANOVA) using Minitab® statistical package. The outcome is represented graphically and in the form of empirical model which defines the performance characteristics of the Stationary Hook Hopper Feeder.Index Terms-ANOVA, design of experiments, full factorial design, stationary hook hopper feeder.

With the ever-increasing rate of information dissemination and absorption, "Fake News" has become a real menace. People these days often fall prey to fake news that is in line with their perception. Checking the authenticity of news articles manually is a time-consuming and laborious task, thus, giving rise to the requirement for automated computational tools that can provide insights about degree of fake ness for news articles. In this paper, a Natural Language Processing (NLP) based mechanism is proposed to combat this challenge of classifying news articles as either fake or real. Transfer learning on the Bidirectional Encoder Representations from Transformers (BERT) language model has been applied for this task. This paper demonstrates how even with minimal text pre-processing, the fine-tuned BERT model is robust enough to perform significantly well on the downstream task of classification of news articles. In addition, LSTM and Gradient Boosted Tree models have been built to perform the task and comparative results are provided for all three models. Fine-tuned BERT model could achieve an accuracy of 97.021% on NewsFN data and is able to outperform the other two models by approximately eight percent.

A novel system for measuring the user experience of any user interface by measuring the feedback directly from the brain through Electroencephalography (EEG) is described. We developed an application that records data for different emotions of the user while using any interface and visualises the data for any interval during the task, as well as presenting various statistics and insight about the data. The application also provides the points of mouse movement on any interface as different coloured dots, where the colour represents the mental load at those points. This makes it easier to identify the user experience based on emotions at exact points on the user interface.In experiments, the brain activity of participants was recorded while they performed tasks on both a well-designed and poorly designed user interface. Screen and mouse cursor position were recorded, along with the values of several facial expressions and emotions extracted from the EEG. Users were interviewed after the study to share their experiences. For each study session analysis was done by comparing EEG, screen recording and interview data. Results showed that frustration, furrow and excitement values reflect user experience.

Traditionally, searching for videos on popular streaming sites like YouTube is performed by taking the keywords, titles, and descriptions that are already tagged along with the video into consideration. However, the video content is not utilized for searching of the user’s query because of the difficulty in encoding the events in a video and comparing them to the search query. One solution to tackle this problem is to encode the events in a video and then compare them to the query in the same space. A method of encoding meaning to a video could be video captioning. The captioned events in the video can be compared to the query of the user, and we can get the optimal search space for the videos. There have been many developments over the course of the past few years in modeling video-caption generators and sentence embeddings. In this paper, we exploit an end-to-end video captioning model and various sentence embedding techniques that collectively help in building the proposed video-searching method. The YouCook2 dataset was used for the experimentation. Seven sentence embedding techniques were used, out of which the Universal Sentence Encoder outperformed over all the other six, with a median percentile score of 99.51. Thus, this method of searching, when integrated with traditional methods, can help improve the quality of search results.