Ying Jin

Conference Title: 2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science (IRI) Conference Start Date: 2022, Aug. 9 Conference End Date: 2022, Aug. 11 Conference Location: San Diego, CA, USAWith the recent changes in college admissions, Advance Placement (AP) courses become ever more critical in demonstrating student academic performance in college applications. Teens feel the pressure of taking more AP courses and performing well on AP exams. Stress is one important factor that contributes to psychological disorders. It is valuable to understand and analyze teens' emotions toward AP courses using real-world data; however, there is a lack of research in the literature. Considering the feasibility and limitations of the traditional questionnaire approach, this research collects real world data from social media. Students' emotional states, such as enjoyment and stress, are analyzed from Twitter's tweets using various deep learning models with different text augmentation techniques. We summarize the analysis results as word clouds and emotion charts in each month in an academic year. Students can use the research results to prepare for the self-adjustment of emotions over time when taking AP courses. Parents, school counselors, and psychologists can use this empirical study to better understand students' sentiments and trends during different time periods, and help teens to thrive.

It is important to consider water constraints when making decisions for future energy allocations, as some promising renewable energy sources have a high demand for water and are restricted by water availability. The Energy-Water-Emissions Dashboard (EWED) project is an information exchange system of the United State Energy-Water Nexus. Our previous publication describes our approach of using machine learning models to predict future electricity generation, water consumption, and water withdrawal of different types of power plants across the United States. The performance of water consumption prediction is less desirable than that of electricity generation and water withdrawal. This paper describes a novel two-phase approach to improve the prediction of water consumption. The first phase uses Recurrent Neural Network (RNN) to predict future water consumption based on time series. The predicted result is then fed into the second phase as a new feature to produce the final water consumption prediction using Artificial Neural Network (ANN). Compared to our previous ANN prediction, Root Mean Square Error (RMSE) decreased 6.9% and Mean Absolute Error (MAE) decreased 21%. Compared with the conventional coefficient method used by EWED, RMSE decreased 53%. The performance evaluation is comprehensive with five statistical measures and is accurate with k-fold cross-validation.

In an active rule-based system, users define reactions to events by specifying active rules. The system executes rules upon occurrences of events automatically. Events can be primitive that is raised by a single database operation, such as insert, delete, and replace. Users can also define composite events that are grouped by multiple primitive events. The composition of those events can trigger one or more rules. In this paper, we present our approach of supporting composite events in a fuzzy XML database system. Fuzzy logic allows people to specify vague information directly. Our research has built a fuzzy active rule-based database system on top of traditional XML databases, while allows manipulation of fuzzy data, as well as execution of fuzzy active rules. The paper describes the language structure of composite events and the rules. We also talk about the event logs and how to process composite events at run time.

Fuzzy logic reflects human nature to express and evaluate the world in a vague manner. This paper describes our approach to incorporate fuzzy logic into XML database systems. The system was built on top of traditional XML databases, while allows the storage of fuzzy data as well as crisp data. The paper describes the structure of the system, starting with the critical architectural component named fuzzy meta- knowledge base, which records different types of fuzzy distributions for database attributes. Next, a fuzzy query language is presented that is based on the XQuery standard, while allowing fuzzy expressions in any condition in a query. A query processor was built to allow the processing and execution of a fuzzy query over both fuzzy and crisp XML data.

Active database rules provide event management capability to database systems by signaling events and handling events automatically. Active rules play important roles in data management such as database integrity checking and database integration. Our past research has reported an active rule scheduling algorithm, named IRS, to schedule the execution of concurrently triggered rules to achieve the confluence property. The confluence property allows rule execution to produce the same final result regardless of the execution order of simultaneously triggered rules. The IRS algorithm schedules rules at static time with rules triggered by primitive events. This paper describes our research on extending the IRS algorithm, named CIRS algorithm, to incorporate composite events. We define a new triggering graph to represent composite events, and convert the new graph to apply the data access sub-algorithm and priority graph generation sub-algorithm. Using the CIRS algorithm, rules triggered by composite events can be scheduled at static time that guarantees the confluent execution of simultaneously triggered rules.

Triggers have played an important role in integrity constraint management for relational database systems. More research projects and commercial systems are working on supporting triggers in XML database systems in recent years. This paper describes our approach to incorporate fuzziness into XML triggers. By adding a thin layer to an existing database, fuzzy expressions can be used within triggers to specify application level constraints declaratively. Our system provides support to fuzziness over traditional XML databases, while the underlying XML data remains crisp. As a result, any existing application will not be affected and is not required to be altered when using our approach. To the best of our knowledge, this is the only research reported to support fuzzy triggers in XML database systems. This paper describes the language of the fuzzy trigger, the system architecture, and the implementation with a motivating example.

Database triggers allow database users to specify integrity constraints and business logics by describing the reactions to events. Traditional database triggers can handle mutating events such as insert, update, and delete. This paper describes our approach to incorporate timer-triggers to handle temporal events that are generated at a given time or at certain time intervals. We propose a trigger language, named FZ-Trigger, to allow fuzziness in database triggers. FZ-Triggers allow fuzzy expressions in the condition part of a trigger with either a mutating event or a temporal event. This paper describes the generation of temporal events, the language of FZ-Triggers, and the system implementation. We also present a motivating example that illustrates the use of FZ-Trigger in the case of reacting to temporal events.

High throughput biological experiments produce a large amount of biological data that can be updated by time. Inconsistent data stored in the same or different databases may lead to serious biological research problems. Constraint management is important to ensure biological data integrity. Some existing databases were built for the easy use for biologists; however the database management system (DBMS) may not have a sufficient constraint management system. In this paper, we propose an XML-based active rule language, named BioRL, to enforce constraints on existing databases without changing the original system structures or the underlying databases. In BioRL language, biological semantics are represented declaratively in active rules by using XQuery expressions and functions. This paper presents the syntax of the BioRL language, with examples that illustrate the use of BioRL in an application environment. This paper also presents the BioRule system to support the specification and execution of BioRL, focusing on the architectural components of the BioRL parser and the BioRL repository.

XML is becoming one of the most common means to exchange data throughout the internet. Biological research is advancing at very high rates as a result of the large amounts of information that can be passed to researchers throughout the world, thereby increasing collaboration and reducing redundancy. There are limitations to the use of this data if there is no ability to verify it. This paper presents our BioRule system that uses active rules to verify the integrity of XML data. This system consists of a language named BioRL and an execution environment that supports event detection and rule processing. The paper discusses the language, architecture, and implementation to enforce constraints over XML documents being manipulated within a native XML database.

Constraints are important to ensure consistency and validity of biological data to computerize biological findings. Incorrect data could lead to serious scientific problems when conducting further biology research and experiments. We propose an XML-based active rule system named BioRule to enforce constraints on top of existing data sources. The BioRule system serves as a middleware to filter inconsistent data before populating or updating data sources. Biological semantics are specified in active rules, while the validation can be enforced by the BioRule system automatically according to the defined rules. To facilitate and simplify the specification of active rules, we developed a web-based user-friendly tool to guide end-users. Rule examples, over an existing biology application, are also provided in this paper to illustrate the specification of active rules though web-based interfaces for constraint validation.