This thesis performs an empirical analysis of Word2Vec by comparing its output to WordNet, a well-known, human-curated lexical database. It finds that Word2Vec tends to uncover more of certain types of semantic relations than others -- with Word2Vec returning more hypernyms, synonomyns and hyponyms than hyponyms or holonyms. It also shows the probability that neighbors separated by a given cosine distance in Word2Vec are semantically related in WordNet. This result both adds to our understanding of the still-unknown Word2Vec and helps to benchmark new semantic tools built from word vectors.

Secondary structure (SS) refers to the local spatial organization of the polypeptide backbone atoms of a protein. Accurate prediction of SS is a vital clue to resolve the 3D structure of protein. SS has three different components- helix (H), beta (E) and coil (C). Most SS predictors are imbalanced as their accuracy in predicting helix and coil are high, however significantly low in the beta. The objective of this thesis is to develop a balanced SS predictor which achieves good accuracies in all three SS components. We proposed a novel approach to solve this problem by combining a genetic algorithm (GA) with a support vector machine. We prepared two test datasets (CB471 and N295) to compare the performance of our predictors with SPINE X. Overall accuracy of our predictor was 76.4% and 77.2% respectively on CB471 and N295 datasets, while SPINE X gave 76.5% overall accuracy on both test datasets.

Presently, self-tracking applications are used to help patients with chronic illness management. For example, applications ask users to track mood through online diaries or snap photos of their food content in order to analyze patterns correlated to their chronic disease. Although these health care applications are on the market today, there still exists a fundamental challenge in motivating participants to consistently update and enter information. Therefore, the focus of this thesis is on reducing the fatigue from using these applications. Pulling from user social media data will almost completely eliminate the capture burden placed on participants, since users will only have to continue to use social media as they regularly do. Instead of analyzing manually inputted data, patterns can be found between social media data and chronic diseases. A Microsoft Research team found indicators in public user Twitter data associated with the onset of a depressive episode. They were able to create a predictor tool, predicting the onset of a depressive episode, with 70 percent accuracy. Using this research alongside expert feedback, our aim is to design an interface used by both clinician and patient that will provide them with a timeline marking spikes in Twitter indicators correlated to a patient’s depressive episode.

This thesis discusses image processing and filtering techniques with emphasis on Mean filter, Median filter, and different versions of the Iterative Truncated Arithmetic Mean (ITM) filter. Specifically, we review in detail the ITM algorithms (ITM1 and ITM2) proposed by Xudong Jiang. Although filtering is capable of reducing noise in an image, it usually also results in smoothening or some other form of distortion of image edges and file details. Therefore, maintaining a proper trade off between noise reduction and edge/detail distortion is key. In this thesis, an improvement over Xudong Jiang’s ITM filters, namely ITM3, has been proposed and tested for different types of noise and for different images. Each of the two original ITM filters performs better than the other under different conditions. Experimental results demonstrate that the proposed filter, ITM3, provides a better trade off than ITM1 and ITM2 in terms of attenuating different types of noise and preserving fine image details and edges.

Given mobile devices’ weak computational power, game programmers must learn to create games with simple graphics that are engaging and easy to play. Though seldom created for phones and tablets, puzzle games are a perfect fit. In recent years, the genre has gained a following and even won some acclaim. Games like Myst, The Seventh Guest and Portal all engage gamers with challenging puzzles and then reward them with story components upon task fulfillment. Few such games have been created for mobile devices, in part due to the difficulty of developing for devices with different operating systems. Android, WebIOS and Windows Phone all have different software development kits that produce a final product incompatible with operating systems other than what it was developed for. One promising solution is to use browser technology to deliver games since all devices are geared to interact with the Web through browsers such as Internet Explorer, Mozilla Firefox, and Google Chrome. The aim of this project was to build a puzzle game that can be run on any digital device. The project can be accessed without any plug-ins and was created by using web technologies such as JQuery, Touch Punch, local storage, and WebGL. JQuery allows drag and drop functionality and Touch Punch allows the JQuery functionality intended for a mouse to work on a touch interface. Local storage provides storage on a user’s device, as opposed to a server, and WebGL enables graphics processing on a user’s tablet or phone through web commands.

In recent years, mobile devices have played a significant role in daily life. As a result, Mobile Applications have become very popular. An increasing number of people are using mobile applications to handle an increasing number of personal tasks, as well as for amusement. To date, there are thousands of mobile applications available for a variety of purposes. However, there are very few specifically designed for local church use. Mobile applications are potentially more convenient and easier to operate than normal website for parishioners. Designing and implementing a mobile application for Crest Community Church, in Riverside, based on Android Developer Tools (ADT) and Android Software Development Kit (Android SDK) is this project’s primary objective. The objective of this project is to provide a communications platform where members of Crest Community Church can share news, discuss coming church events, promote and enhance the connectivity of this worship community, and provide mobile access to information not available on their present systems. A distinct feature of this project allows for communication between mobile application and webserver by creating a HTTP URL Connection. As a result, church members can publish news and events in a discussion forum as well as a dialog with other church members in a near real time format. The Crest users can also indicate that posted prayer request has been prayed for. In addition, this new application displays general church information, and provides the address and driving direction for potential visitors. Church members can also check the church’s calendar of events, special meetings and information about the Passion Center for Children ministry. This project has the ability to store and track pertinent information about each user, the content of all discussions, and retains member’s key contact data. This project successfully implemented a church mobile application. It demonstrated that a tailored mobile application can enhance the sense of community via internet for this congregation. It feather shows that mobile applications can greatly assist churches in community with members as well as visitors. The application also expanded the internet footprint of Crest Community Church, and offers other churches an avenue to improve their connectivity for the future.

Data clustering is a data analysis technique that groups data based on a measure of similarity. When data is well clustered the similarities between the objects in the same group are high, while the similarities between objects in different groups are low. The data clustering technique is widely applied in a variety of areas such as bioinformatics, image segmentation and market research. This project conducted an in-depth study on data clustering with focus on density-based clustering methods. The latest density-based (CFSFDP) algorithm is based on the idea that cluster centers are characterized by a higher density than their neighbors and by a relatively larger distance from points with higher densities. This method has been examined, experimented, and improved. These methods (KNN-based, Gaussian Kernel-based and Iterative Gaussian Kernel-based) are applied in this project to improve (CFSFDP) density-based clustering. The methods are applied to four milestone datasets and the results are analyzed and compared.

CoyoteLab is an exploration in the use of Linux container technology as a means to simplify the way students in computing fields access and complete laboratory work in their educational career. This project provides two main benefits: creating a simple way for students to log in and access their coursework without anything more than their web browser, and providing course instructors a way to verify that assigned work is completed successfully. Thanks to advances in container technology and the advent of WebSockets, this becomes a middle layer between a WebSocket opened up on the client’s browser and the SSH daemon running in the user’s container on a remote server.

Hospitals are the largest and most complex organizations where health care is provided. Safe and effective patient care services in hospitals depend on the efficient decisions made by hospital executives. The main task of hospital executives is to ensure the hospital can provide high quality patient care and services. “Android Mobile Application For Hospital Executives” is an Android application used for displaying hospital performance metrics on a daily basis. This application allows hospital executives to review and monitor hospital operational data with ease of access and in a portable manner. Thus, reducing the effort of the hospital executives to perform their tasks.

At California State University San Bernardino, students can ordinarily register online and join waiting lists when a course is full. However, the system does not support waiting lists when a course has associated laboratory sections. This project addresses this problem.