In this project, students will explore the fundamentals of machine learning applied to a space weather example through a hands-on activity. By using the space weather domain, this lesson can also be applied to general science standards. Using Google's Teachable Machine, students create an image classification model that can recognize and differentiate between key space weather phenomena such as auroras, solar flares, and sunspots. This accessible approach introduces real-world applications of AI in science while helping students build practical skills in data analysis and pattern recognition. Students then deploy their models using a simple web application built with HTML and JavaScript. This combined assignment allows students to gain firsthand experience with advanced machine learning concepts, including model inference, confidence scores, and integrating models into digital tools. Designed for high school and introductory computer science courses, the project requires minimal technical setup and is adaptable to various levels. Students not only learn the basics of machine learning, such as how training data works, why class balance matters, and how to test with new examples, but also strengthen their coding skills by customizing and debugging their own web apps. For more advanced students, optional extension activities introduce topics such as user interface design, artificial intelligence ethics, and the impact of space weather on the technology we rely on every day.

In this lightning talk, we discuss the creation of an initial G6-12 unit that traces how fundamentals of coding have evolved in response to socio-economic-political and technological motivators. The unit employed unplugged strategies to enhance students' grasp of core computer science principles and spark deeper engagement and conceptual understanding. Lessons were designed. We designed the unit so lessons can be used alone or part of a larger experience. While these lessons were created separately and used independently, the cohort collaboratively reflected and observed that technological advancements consistently build upon prior practices and habits, revealing interconnected developments that unfold over time. The impetus for this research has also been influenced by Meadow's work on communication throughout the ages, which explains coding in a similar manner. The complexity of communications progressively increases, yet the systems developed rely on simple, repeatable patterns regardless of whether they appear in the historical timeline. Examples of these communications include smoke signals, Morse code, and spectral imaging. Even binary code, a basic language composed of only two characters (0s and 1s), enables the creation of complex and sophisticated communication technologies. For example, the computational spectral imaging lesson immerses students in binary code and data representation through unplugged pixel art activities that simulate the transmission of satellite images, illustrating how simple patterns form the foundation of complex computing systems. In addition, the lesson supports the unifying theme by connecting historical communication methods to modern coding practices, revealing the continuity of technological evolution across time.

We propose to incorporate three interpretable methods, namely SHAP (SHapley Additive exPlanations), PDP (partial dependence plots) and Anchors, into a deep learning-based model, called SolarFlareNet, for operational flare forecasting. SolarFlareNet takes as input a sample of SHARP (Space-weather HMI Active Region Patches) magnetic parameters and predicts as output whether a solar flare would occur within the next 24 hours. We analyze flare events that occurred from May 2010 to December 2022 using the Geostationary Operational Environmental Satellite's X-ray flare catalogs and construct a database of flares with identified active regions in the catalogs. This database, together with the SHARP magnetic parameters, is used to train and test the SolarFlareNet model. Our experimental results describe the use of the three proposed methods (SHAP, PDP, and Anchors) to interpret the SolarFlareNet model and demonstrate the effectiveness of the methods.

In today's rapidly changing technological landscape, it is becoming increasingly evident that solar weather, simulations, and artificial intelligence (AI) are topics that can be and should be integrated into middle school education. Solar weather events can create massive problems with climate, communication, and technology, problems that can be alleviated by prediction. These events generate massive amounts of data that AI can use for such prediction. These topics can be introduced through simulations. How can we integrate solar weather data and simulations with AI-driven models to create interactive and educational software? This paper reviews lessons and pedagogical approaches used to teach about solar weather, AI and incorporate simulations to integrate CS concepts into other middle school subject areas. The research supports year one of a three-year project. The length of the project allows time to develop a progression to introduce CS concepts and the development of a simulation that can be used in a variety of middle school classrooms.

Guided by grounded theory and using a drawing task, this study aimed to analyze how education stakeholders, including K-8 teachers and school administrators, perceive and conceptualize the work of computer scientists. Twenty-eight participants completed the draw-a-computer-scientist task and underwent a six-session summer professional development workshop at a major university in New Jersey. The content analysis of the collected drawing data revealed various stereotypical images people hold of computer scientists, especially male computer scientists. The study findings also highlighted that a few participants contemplated the traditional view of a computer scientist and demonstrated their enhanced understanding of the computer science field. Considering the existence of deep-rooted stereotypes regarding the computer science field and computer scientists, this study identified important implications for how well-designed professional development workshops can address the lack of awareness about and broaden the perspectives of the computer science field.

States are moving to adopt Computer Science (CS) education standards to help K-12 teachers adapt and integrate computing /computational thinking (CT) concepts into the curriculum. These approaches also rely heavily on training current and pre-service teachers and creating opportunities to learn CS while also managing the rigors of their education career. This poster presents elements of the collaboration between the Department of CS and Department of Teaching and Learning at Montclair State University (MSU) to bring CS to pre- and in-service educators. Here we will highlight our curriculum work and professional development (PD) series. The New Jersey (NJ) Department of Education has adopted CS Education standards for K-12 and distinctly funded curriculum development and faculty formation programs. MSU has built programs that support teachers through PD experiences in CT and CS. In the 10-month period ending March 2023, we will offer 30 PD opportunities for a CS and CS education. To date, more than 200 educators have received PD to address their educational needs regarding CS curricula.

There has been extensive research about the CS1 course. Much less has been written about the CS2 course, which is often a gateway course for CS majors. CS2 classes often reflect a second semester course in programming, yet when studying this course many universities have different purposes for this course. This poster shows the programming languages used in CS2 courses by the CS programs on the 28th Reid List of First Programing Languages. The languages used in CS1 and CS2 courses are discussed and the transitions between languages as students progress from their first course to their second. The analysis will then be discussed.

Contact: [email protected] The United States does not produce sufficient numbers of well-qualified professionals in STEM, and in computing/ technology in particular. The number of students pursuing undergraduate degrees in computer science or related field continues to grow but is still not pacing industry growth. Employers repeatedly suggest that good professional and technical competencies, including "soft skills", are a major factor in both obtaining and succeeding in STEM careers. Moreover, both the Council on Graduate Studies and the National Science Board in the NSF 2018 STEM Trends report support the need of such skills for success in STEM. These competencies comprise (1) communication, oral and written, and in technical, business and general settings; (2) working in and leading teams, in varying roles; (3) managing business and professional relationships; (4) planning, problem solving, and critical thinking; (5) mathematical capabilities including numeracy; and (6) an understanding of ethical, social, managerial, and economic perspectives; plus, responding to recent developments in science and science careers, (7) an interdisciplinary perspective and overview understanding of data science. In this poster we present a proposal for a post baccalaureate certificate curriculum, which we suggest also assists students transitioning from other fields, and can be applied more widely across STEM.

The CS1 course is arguably the most important course offered in a Computer Science major; if students struggle in the course, they are likely to drop out of the major, and if certain key topics are covered, they may struggle in other courses later in their undergraduate program. For this reason, it is not surprising that the programming language used in a CS1 course as well as the teaching methodology is frequently a contentious subject. Richard Reid of Michigan State University kept a list of programming languages used in CS1 courses from the early 1990s until his retirement in 1999, and Reid's former student, Frances Van Scoy, continued compiling the List until 2006. Siegfried et al. updated the List in 2011 and 2015. The historical data shows the different languages (and in some cases, approaches) used by the schools reported on the Reid List. Additionally, in compiling the last two lists, there were trends spotted, with some feedback from faculty at the Reid List schools, stating the reasons for changes that they made as well as why they currently use and previously used the various languages.

With current trends in integrating phylogenetic analysis into pharma-research, computing systems that integrate the two areas can help the drug discovery field. DrugTree is a tool that overlays ligand data on a protein-motivated phylogenetic tree. While initial tests of DrugTree are successful, it has been noticed that there are a number of lags concerning querying the tree. Due to the interleaving nature of the data, query optimization can become problematic since the data is being obtained from multiple sources, integrated and then presented to the user with the phylogenetic imposed upon the phylogenetic analysis layer. This poster presents our initial methodologies for addressing the query optimization issues. Our approach applies standards as well as uses novel mechanisms to help improve performance time.

Pyruvate kinase is an enzyme that catalyzes the formation of pyruvate from phosphenolpyruvate in glycolysis. There is a wealth of data on the activity of certain molecules and their effects on pyruvate kinase. This project aims to create an application that uses a pyruvate kinase dataset to determine the nature of unidentified molecules; whether or not they would be activators or inhibitors of this enzyme. This application uses an Apriori algorithm to identify or predict modulators of pyruvate kinase. This initial study focuses on simplified molecular input line entry specification (SMILES) text as target data to be mined. The three dimensional structure of pyruvate kinase is known and accessible though the Protein Data Bank (e.g., PDB code IA3W).

In this poster we propose a method for addressing the genomic nomenclature problem by using phylogenetic tools along with the BIO-AJAX data cleaning framework.

Support vector machines (SVMs) are a state-of-the-art machine learning tool widely used in speech recognition, image processing and biological sequence analysis. An essential step in SVMs is to devise a kernel function to compute the similarity between two data points in Euclidean space. In this paper we present a new kernel that takes advantage of both global and local structural information in RNAs and uses the information together to classify RNAs with support vector machines. Experimental results demonstrate the good performance of the new kernel and show that it outperforms existing kernels when applied to classifying non-coding RNA sequences.

No abstract available.

In this paper, we describe a new interdisciplinary B.S. degree in Science Informatics at Montclair State University, a multipurpose public institution that includes a substantial General Education component. Beginning in the freshmen year, the Science Informatics curriculum contains 16 semester hours of interdisciplinary science informatics courses including a freshmen experience, internships, a research component, ethics, and a concentration currently in bioinformatics, cheminformatics, or computer science as well as core science and mathematics courses.

Currently, phylogenetic tree techniques are being used in multiple areas, from Tree of Life problems to pathogen recognition to drug discovery. With all of these applications for phylogenetic tree techniques, methods are needed to exploit the knowledge modeled in phylogenetic trees more thoroughly. One such information point of interest is the behavior of frequent patterns in phylogenetic trees. While there are many techniques that look at maximal, consensus and supertreepatterns, there are few techniques that look at frequent, but not maximal pattern. This demonstration paper presents PhyloMiner, a tool that automatically discovers frequent agreement subtrees from multiple phylogenies. It introduces this topic of frequent agreement subtrees and then concludes with describing the PhyloMiner tool that implements these concepts and is available freely on the World Wide Web.

XML is increasingly important in data exchange and information management. A large amount of efforts have been spent in developing efficient techniques for storing, querying, indexing and accessing XML documents. In This work we propose a new approach to clustering XML data. In contrast to previous work, which focused on documents defined by different DTDs, the proposed method works for documents with the same DTD. Our approach is to extract features from documents, modeled by ordered labeled trees, and transform the documents to vectors in a high-dimensional Euclidean space based on the occurrences of the features in the documents. We then reduce the dimensionality of the vectors by principal component analysis (PCA) and cluster the vectors in the reduced dimensional space. The PCA enables one to identify vectors with co-occurrent features, thereby enhancing the accuracy of the clustering. Experimental results based on documents obtained from Wisconsin's XML data bank show the effectiveness and good performance of the proposed techniques.

Phylogenetic trees are essential for understanding the relationships among organisms or taxa. Many of the current techniques for searching phylogenetic repositories allow the user to perform a keyword-type search or an aligned sequence data search, or to browse a hierarchical list of taxa. Here we describe a new search engine that allows the user to present an example phylogeny, or a query tree, and then searches a phylogenetic database for trees that contain the query structure. The presented search engine is fully operational and is available on the World Wide Web.

XML's tree structure provides a rich background for complicated structural searches. In this paper we present a new system, called XML Query by Example (XML QBE) that allows the user to query XML documents exploiting their inherent tree structure. We present some interesting queries and describe the underlying query processing algorithms. We also describe the system's architecture and report its implementation status. Finally we conclude the paper by pointing out some future work.