The introduction of OpenAI's ChatGPT in 2022 kickstarted the release of Generative Artificial Intelligence (GAI) applications to the public domain. Such chat interfaces are based on large language models (LLMs) and possess a vast array of abilities spanning conversation, the writing and debugging of code, the writing of papers, and the creation of images, music, and songs. With students now having access to a myriad of GAI tools, academia has been permanently altered. Our proposed system, named Code Analysis and Education Tutor (CAET), integrates GAI into early Computer Science education by providing students with an ethical alternative to existing GAI tools. CAET is designed to assist students with programming tasks in a manner tailored to their individual needs without jeopardizing the integrity of their learning. A point of uniqueness from existing works is CAET's ability to display or hide generated code based on its pertinence to the problem at hand. After subjecting multiple GAI models to common programming errors and queries, we settled on OpenAI's GPT-3.5 Turbo model due to its comprehensive capabilities and cost-effectiveness. Overall, CAET underscored the model's conversational dynamics and provided insights for creating a more personalized learning experience for students in an introductory computer science course.

ABSTRACT:Preventing medication errors remains a priority in nursing education. The implementation of Barcode Medication Administration (BCMA) systems is one strategy that has been used to reduce medication errors. Practice using BCMA in simulated settings may enhance the transfer of these skills to the clinical practice setting. However, the purchase of BCMA educational products available for nursing students can be cost prohibitive for many nursing programs. To overcome the barrier of cost, an interdisciplinary and innovative collaborative approach was used to create a fully functional low-cost BCMA system.

Using algorithms to compose creative and pleasing music has been an ambitious research goal since the 1950s. This trend continues to this day with the help of widely accessible, highly sophisticated music research tools created by big companies, such as Google’s Magenta. Due to the sequential nature of musical pieces, Recurrent Neural Networks (RNNs), as well as advanced variants such as Long-Short Term Memory networks (LSTMs), have been successfully employed for this purpose. Music scores data is made up of features like duration, pitch, rhythm, chords, etc. As more music features are integrated into the composition process, the space of encodings required to represent possible feature combinations grows significantly, making the process computationally infeasible. This consideration becomes of huge significance in situations with polyphonic pieces, where additional features such as harmonies and multiple voices are present. With an emphasis on efficiency without sacrificing quality, this research aims to further demonstrate the effectiveness of LSTMs for automated music generation by learning from existing music scores data. More specifically, we show that training separated models to learn individual music features and combining results to generate new music is, overall, superior to the common practice of learning resource-intensive complex models that simultaneously incorporate multiple desired features.

Creating aesthetically pleasing music via algorithmic composition has continually been an ambitious goal of music research. Memory-based neural networks have shown to be particularly suited for this type of sequential learning. Music scores data is commonly used to represent different music features–such as durations and pitches–which when combined, make up the entirety of a music piece. As more music features are integrated into the music composition process, the space of labels required to represent possible feature combinations in a neural network grows significantly and rather quickly making the process computationally challenging, to say the least. This consideration bears special importance in situations with polyphonic pieces, where additional features such as harmonies and multiple voices are present. This research highlights the potential benefits of feature separation in music composition from music scores data. More specifically, we demonstrate the effectiveness of neural networks for automated music composition by learning music features separately; we start by creating separate simple models, one for each desired music feature, and then combine results from the simple models to compose new music. This is in contrast to the common practice of employing a single complex model trained over multiple features simultaneously. Case study evaluation results show significant time savings for our proposed approach with similar music “quality” compared to the complex model.

Privacy and anonymity are important concepts in the field of communication. Internet users seek to adopt protective measures to ensure the privacy and security of the data transmitted over the network. Encryption is one technique to secure critical information and protect its confidentiality. Although there exist many encryption algorithms, hiding the identity of the sender can only be achieved through an anonymous network. Different classifications of anonymous networks exist. Latency level and system model architecture are two essential criteria. In this paper, we present a description of a set of anonymous systems including NetCamo, TOR, I2P and many others. We will show how these systems work and contrast the advantages and disadvantages of each one of them.

In the age of BigData, producing results quickly while oper- ating over vast volumes of data has become a vital require-ment for data mining and machine learning applications to a degree that traditional serial algorithms can no longer keep up with these constraints. This paper applies different forms of parallelization techniques to popular instance-based classifiers (cid:177) namely, a special form of naive Bayes and k -nearest neighbors (cid:177) in an attempt to compare performance and make broad conclusions applicable to instance-based classifiers. Overall, our experimental results strongly indicate that par- allelism over test instances provides the most speedup in most cases compared to other forms of parallelism.

Advancements in speech recognition and voice-to-text technologies have made these topics more popular as of late. When analyzing certain types of time-series data, it is important to properly preprocess the data in order to deal with varied-length instances. In this work we study the influence of three different data preprocessing techniques on the quality of patterns extracted from a dataset of Arabic digits spoken by native speakers. Our ultimate objective is to determine which data preprocessing technique is most effective in producing strong patterns from this dataset which we accomplish by clustering the preprocessed datasets and measuring the quality of the produced clusters. Our experiments underscore the benefits of using the proposed polynomial fitting preprocessing technique to produce desirable results.

Source code plagiarism is easy to commit but difficult to catch. Many approaches have been proposed in the literature to automate its detection; however there is little consensus on what works best. In this paper, we propose two new measures for determining the accuracy of a given technique and describe an approach to convert code files into strings which can then be compared for similarity in order to detect plagiarism. We then compare several string comparison techniques, heavily utilised in the area of biological sequence alignment, and compare their performance on a large collection of student source code containing various types of plagiarism. Experimental results show that the compared techniques succeed in matching a plagiarised file to its original files upwards of 90% of the time. Finally, we propose a modification for these algorithms that drastically improves their runtimes with little or no effect on accuracy. Even though the ideas presented herein are applicable to most programming languages, we focus on a case study pertaining to an introductory-level Visual Basic programming course offered at our institution.

With an overwhelming amount of genetic data now becoming publicly available, there is a growing need to develop more effective gene prediction methods that produce reliable results. Although prediction of the stop codon location for genes in prokaryotic organisms is largely considered to be a solved problem, accurate prediction of the exact start codon location continues to lag behind because of the ambiguity for these start codons in the genetic code. This paper will detail a new approach to predicting more precise gene locations for both the start and stop codon in prokaryotic organisms. This approach uses gene prediction results from other prediction programs to find consistently predicted gene locations. It then uses these “consistent genes” as a training set for Naive Bayesian classification to improve accuracy in the “ambiguous genes,” those in which there is some variability or inconsistency in predicted locations between the prediction programs.

There have been many attempts for clustering categorical data such as market basket dataset. However, most of categorical clustering approaches belong to partitional clustering which requires at least one input parameter (e.g., the minimum intra-cluster similarity or the desired number of clusters). In this paper, we propose a parallelised hierarchical clustering approach for categorical data (PH-clustering) using vertical data structures. In order to minimise the impact of low support items, we devise a weighted confidence (WC) affinity function to compute the similarity between clusters. Based on our analysis of the major clustering steps, we adopt a partial local and partial global approach to reduce computation time as well as to keep network communication at minimum. Load balance issues are addressed especially during the data partitioning phase. Our experimental results on standardised market basket data show that the proposed weighted confidence affinity measure is more accurate than other contemporary affinity measures in the literature and that our parallel clustering approach provides magnitudes of time improvements over sequential clustering especially over larger data sizes. Our results also indicate that the number of items/attributes in the dataset has a more drastic impact on performance than the number of transactions/tuples.

Since the invention of the printing press, text has been the predominate mode for collecting, storing and disseminating a vast, rich range of information. With the unprecedented increase of electronic storage and dissemination, document collections have grown rapidly, increasing the need to manage and analyze this form of data in spite of its unstructured or semistructured form. Text-data analysis (Hearst, 1999) has emerged as an interdisciplinary research area forming a junction of a number of older fields like machine learning, natural language processing, and information retrieval (Grobelnik, Mladenic, & Milic-Frayling, 2000). It is sometimes viewed as an adapted form of a very similar research field that has also emerged recently, namely, data mining, which focuses primarily on structured data mostly represented in relational tables or multidimensional cubes. This article provides an overview of the various research directions in text-data analysis. After the “Introduction,” the “Background” section provides a description of a ubiquitous text-data representation model along with preprocessing steps employed for achieving better text-data representations and applications. The focal section, “Text-Data Analysis,” presents a detailed treatment of various text-data analysis subprocesses such as information extraction, information retrieval and information filtering, document clustering and document categorization. The article closes with a “Future Trends” section followed by a “Conclusion” section.

In this day and age, conducting a biological experiment is presumably a very expensive procedure largely owing to the highly sophisticated and expensive equipment necessitated by the process. Conceivably, being capable of isolating and focusing on a smaller set of imperative genes or gene products that are of high relevance to the experiment, pathway, or biological system under investigation is very desirable largely owing to the potential savings in experimental costs. In this work, we propose an intelligent information system capable of generating a ranked list of genes and gene products that are most pertinent to a given biological pathway, experiment or system (referred to as a biological context henceforth). We assume that the biological context of interest can be described by various textual query terms and phrases from the biological domain which, in turn, relate to various molecular functions, biological processes and cellular components of genes and their products. Intelligent text-based analyses and mining are utilised for this purpose by using the published literature, in the form of publication abstracts downloaded from PubMed, with the intention of ranking genes and gene products having identified relationships to the specified description terms based on the gene ontology (GO) standard. At this stage, our approach is capable of producing promising results given all surrounding restrictions, one of which is the lack of similar work in the literature. For demonstration purposes, we report experimental results on the molting regulation pathway in Drosophila melanogaster (fruit fly).

Data clustering is a discovery process that partitions a data set into groups (clusters) such that data points within the same group have high similarity while being very dissimilar to points in other groups (Han & Kamber, 2001). The ultimate goal of data clustering is to discover natural groupings in a set of patterns, points, or objects without prior knowledge of any class labels. In fact, in the machine-learning literature, data clustering is typically regarded as a form of unsupervised learning as opposed to supervised learning. In unsupervised learning or clustering, there is no training function as in supervised learning. There are many applications for data clustering including, but not limited to, pattern recognition, data analysis, data compression, image processing, understanding genomic data, and market-basket research.

Data clustering has been proven to be a promising data mining technique. Recently, there have been many attempts for clustering market-basket data. In this paper, we propose a parallelized hierarchical clustering approach on market-basket data (PH-Clustering), which is implemented using MPI. Based on the analysis of the major clustering steps, we adopt a partial local and partial global approach to decrease the computation time meanwhile keeping communication time at minimum. Load balance issue is always considered especially at data partitioning stage. Our experimental results demonstrate that PH-Clustering speeds up the sequential clustering with a great magnitude. The larger the data size, the more significant the speedup when the number of processors is large. Our results also show that the number of items has more impact on the performance of PH-Clustering than the number of transactions.

This paper analyses annotated genome data by applying a very central data-mining technique known as Association Rule Mining (ARM) with the aim of discovering rules and hypotheses capable of yielding deeper insights into this type of data. In the literature, ARM has been noted for producing an overwhelming number of rules. This work proposes a new technique capable of using domain knowledge in the form of queries in order to efficiently mine only the subset of the associations that are of interest to investigators in an incremental and interactive manner.

The new interdisciplinary field of Data Mining emerged in the early 1990s as a response to the profusion of digital data generated in numerous fields such as biology, chemistry, astronomy, advertising, banking and finance, retail market, stock market, and the WWW. In this paper, I describe an undergraduate course in Data Mining offered at the College of Saint Benedict and Saint John's University in Spring of 2007 as a CSCI-317-upper-division "Topics in Computer Science"- course, entitled "Data Intelligence." One of the main objectives of the course was to engage students in experimental computing research through a number of carefully planned research activities resulting in better understanding of the course contents and deeper insights into the challenges faced by the data mining community.