Ticket Collection with Destination Prediction in Bus Services in Urban Areas using Time Based Predictive Algorithm

In the new age of automation and machine assisted function of the human way of life people still tend to notice verification and checking of tickets in local land transport such as trains and buses to still be operated by man. This project is a proposal of a new platform and method to book these tickets of buses on a local level. This can lead to decrease in the overcrowding of buses, easy time management of commuters, and smooth functioning of the bus business. Initially the bank details of the passenger must be linked to the app.Machine learning predictive parsing algorithm in combination with data mining features enable the prediction of the passengers to and fro details on a daily and timely basis. Then a SMS alert for ticket payment proof is sent to the user. In admin side, they calculate amount details using this application. Per day amount details of specific route or bus can be calculated by accessing the database. There is also a provision where the IMEI numbers of the consumers is collected. Through GPS system the IMEI numbers of the mobiles inside the bus is checked with the IMEI numbers of those in the database. Ticket defaulters are identified if the IMEI numbers are not present in the database. The entire trail of the transit is on a non-paper sever.

Incremental, Predictive Parsing with Psycholinguistically Motivated Tree-Adjoining Grammar

Psycholinguistic research shows that key properties of the human sentence processor are incrementality, connectedness (partial structures contain no unattached nodes), and prediction (upcoming syntactic structure is anticipated). There is currently no broad-coverage parsing model with these properties, however. In this article, we present the first broad-coverage probabilistic parser for PLTAG, a variant of TAG that supports all three requirements. We train our parser on a TAG-transformed version of the Penn Treebank and show that it achieves performance comparable to existing TAG parsers that are incremental but not predictive. We also use our PLTAG model to predict human reading times, demonstrating a better fit on the Dundee eye-tracking corpus than a standard surprisal model.

Aplikasi Piranti Lunak Penganalisis Sintaksis Kalimat Bahasa Indonesia

Indonesian has a vast variety in structures and sentence types that brings about difficulty in using the language correctly and accurately. This research aims for producing a software application for syntax analysis and error checking for Indonesian sentences. The method used in developing the application is rapid prototyping method which consists of several phases: system requirement analysis, design, coding, implementation and evaluation while the method used in syntax analysis process is regular expression and predictive parsing method. Despite some existing limitations, the application produced is able to check the syntax error of various Indonesian sentence types.