Research Papers

Check me out on ResearchGateORCID iD iconORCiD, or Google Scholar!


Simulation of Neural Responses to Classical Music Using Organoid Intelligence Methods
Jul. 2024 - DOI: 10.48550/arxiv.2407.18413
ABSTRACT: Music is a complex auditory stimulus capable of eliciting significant changes in brain activity, influencing cognitive processes such as memory, attention, and emotional regulation. However, the underlying mechanisms of music-induced cognitive processes remain largely unknown. Organoid intelligence and deep learning models show promise for simulating and analyzing these neural responses to classical music, an area significantly unexplored in computational neuroscience. Hence, we present the PyOrganoid library, an innovative tool that facilitates the simulation of organoid learning models, integrating sophisticated machine learning techniques with biologically inspired organoid simulations. Our study features the development of the Pianoid model, a "deep organoid learning" model that utilizes a Bidirectional LSTM network to predict EEG responses based on audio features from classical music recordings. This model demonstrates the feasibility of using computational methods to replicate complex neural processes, providing valuable insights into music perception and cognition. Likewise, our findings emphasize the utility of synthetic models in neuroscience research and highlight the PyOrganoid library's potential as a versatile tool for advancing studies in neuroscience and artificial intelligence.

Links:

Doctoral Dissertation
Choral Music Generation: A Deep Hybrid Learning Approach
Mar. 2024 - DOI: 10.13140/RG.2.2.10418.62400 - ProQuest: 31296228
ABSTRACT: Despite advancements in AI and machine learning, the creation of AI-generated music that captures the complexity and nuance of classical choral arrangements has remained largely unexplored. This gap is significant, considering the intricate compositional techniques and sophisticated music theory knowledge required for classical choral music. My research is motivated by the quest to bridge this gap, aiming to develop an AI model capable of producing realistic choral compositions that adhere to the rich traditions of classical music. Additionally, I explore how AI-generated music is perceived across different listener groups, contributing insights into the intersection of AI and human perception in the arts. This study seeks to address three primary research questions: the feasibility of current machine learning architectures in generating SATB choral music, the ability of a hybrid AI model to produce compositions indistinguishable from human-created music by the general public, and the varying perception of AI-generated classical music among individuals with varying musical backgrounds. This dissertation presents the “Choral-GTN” system: a novel architecture combining a Generative Transformer Network with a rule-based post-processing system, alongside the curated “CHORAL” dataset to address the challenge of generating realistic four-part (SATB) choral music. My comprehensive approach integrates advanced deep learning techniques with sophisticated musical theory insights to produce compositions that closely mimic those created by human composers. Through a meticulously designed survey and rigorous statistical analysis, I evaluate the realism and indistinguishability of my AI-generated music across varied listener groups. The findings demonstrate that this model successfully created music that was largely indistinguishable from human compositions, achieving a significant milestone in AI-assisted music composition and music perception.

Links:

Deep Learning for Protein Structure Prediction: Advancements in Structural Bioinformatics
Apr. 2023 - DOI: 10.1101/2023.04.26.538026
ABSTRACT:
Motivation: Accurate prediction of protein structures is crucial for understanding protein function, stability, and interactions, with far-reaching implications in drug discovery and protein engineering. As the fields of structural bioinformatics and artificial intelligence continue to converge, a standardized model for protein structure prediction is still yet to be seen as even large models like AlphaFold continue to change architectures. To this end, we provide a comprehensive literature review highlighting the latest advancements and challenges in deep learning-based structure prediction, as well as a benchmark system for structure prediction and visualization of amino acid protein sequences.
Results: We present ProteiNN, a Transformer-based model for end-to-end single-sequence protein structure prediction, motivated by the need for accurate and efficient methods to decipher protein structures and their roles in biological processes and a system to perform prediction on user-input protein sequences. The model leverages the transformer architecture’s powerful representation learning capabilities to predict protein secondary and tertiary structures directly from integer-encoded amino acid sequences. Our results demonstrate that ProteiNN is effective in predicting secondary structures, though further improvements are necessary to enhance the model’s performance in predicting higher-level structures. This work thus showcases the potential of transformer-based architectures in structure prediction and lays the foundation for future research in structural bioinformatics and related fields.

Links:

A Novel Dataset and Deep Learning Benchmark for Classical Music Form Recognition and Analysis
Dec. 2022 - DOI: 10.5281/zenodo.7416689
ABSTRACT: Automated computational analysis schemes for Western classical music analysis based on form and hierarchical structure have not received much attention in the literature so far. One reason, of course, is the paucity of labeled datasets — which, if available, could be used to train machine learning approaches. Dataset curation cannot be crowdsourced; one needs trained musicians to devote sizable effort to carry out such annotations. Further, such an analysis is not simple for beginners; obtaining labeled data that can capture the nuances of a musician's reasoning acquired over years of practice is fraught with challenges. To this end, we provide a system for computational analysis of classical music, both for machine learning and music researchers. First, we introduce a labeled dataset containing 200 classical music pieces annotated by form and phrases. Then, by leveraging this dataset, we show that deep learning-based methods can be used to learn Form Classification as well as Phrase Analysis and Classification, for which few (if any) results have been reported yet. Taken together, we provide the community with a unique dataset as well as a toolkit needed to analyze classical music structure, which can be used or extended to drive applications in both commercial and educational settings.

Links:

Graph Compression: Toward a Generalized Algorithm
May. 2022 - DOI: 10.5281/zenodo.6600816
ABSTRACT: Currently, most graph compression algorithms focus on in-memory compression (such as for web graphs) – few are feasible for external compression, and there is no generalized approach to either task. These compressed representations are versatile and can be applied to a great number of different applications, with the most common being social network and search systems. We present a new set of compression approaches, both lossless and lossy, for external memory graph compression. These new algorithms may also be applicable for runtime usage (i.e., running graph algorithms on the compressed representation).

Links:

Master Thesis
Deep Learning for Musical Form: Recognition and Analysis
Apr. 2022 - DOI: 10.13140/RG.2.2.33554.12481
ABSTRACT: Musical form analysis is a rigorous task that frequently challenges the expertise of human analysts and signal processing algorithms alike. While numerous systems have been proposed to perform the tasks of musical segmentation, genre classification, and single-label segment classification in popular music, none have specifically focused on the analytical process used by classical musicians. Classical music form analysis facilitates a combination of these tasks, including form classification, structural segmentation, and multilabel large- and small-segment classification – tasks that lack feasible algorithms, machine learning models, and extensive research. Form analysis has many applications in the world of music, and a viable analytical system would greatly benefit performing musicians and academic researchers, both in musicology and signal processing. As well, current datasets used for related research tasks lack standardized analytical conventions, including form classification, and suffer from erroneous annotations and extensibility due to the data sources used for the music. In this thesis, we propose a new system to perform the task of automatic musical form analysis using deep learning models, as well as a new standardized dataset.

Links:

Emotion Recognition of the Singing Voice: Toward a Real-Time Analysis Tool for Singers
May. 2021 - DOI: 10.48550/arxiv.2105.00173
ABSTRACT: Current computational-emotion research has focused on applying acoustic properties to analyze how emotions are perceived mathematically or used in natural language processing machine learning models. With most recent interest being in analyzing emotions from the spoken voice, little experimentation has been performed to discover how emotions are recognized in the singing voice — both in noiseless and noisy data (i.e., data that is either inaccurate, difficult to interpret, has corrupted/distorted/nonsense information like actual noise sounds in this case, or has a low ratio of usable/unusable information). Not only does this ignore the challenges of training machine learning models on more subjective data and testing them with much noisier data, but there is also a clear disconnect in progress between advancing the development of convolutional neural networks and the goal of emotionally cognizant artificial intelligence. By training a new model to include this type of information with a rich comprehension of psycho-acoustic properties, not only can models be trained to recognize information within extremely noisy data, but advancement can be made toward more complex biofeedback applications — including creating a model which could recognize emotions given any human information (language, breath, voice, body, posture) and be used in any performance medium (music, speech, acting) or psychological assistance for patients with disorders such as BPD, alexithymia, autism, among others. This paper seeks to reflect and expand upon the findings of related research and present a stepping-stone toward this end goal.

Links:

Optimizing Data Cube Visualization for Web Applications: Performance and User-Friendly Data Aggregation
Dec. 2020 - DOI: 10.48550/arxiv.2101.00171
ABSTRACT: Current open source applications which allow for cross-platform data visualization of OLAP cubes feature issues of high overhead and inconsistency due to data oversimplification. To improve upon this issue, there is a need to cut down the number of pipelines that the data must travel between for these aggregation operations and create a single, unified application which performs efficiently without sacrificing data, and allows for ease of usability and extension.

Links:

Generative Deep Learning for Virtuosic Classical Music: Generative Adversarial Networks as Renowned Composers
Dec. 2020 - DOI: 10.48550/arxiv.2101.00169
ABSTRACT: Current AI-generated music lacks fundamental principles of good compositional techniques. By narrowing down implementation issues both programmatically and musically, we can create a better understanding of what parameters are necessary for a generated composition nearly indistinguishable from that of a master composer.

Links:

Visualization Techniques with Data Cubes: Utilizing Concurrency for Complex Data
Oct. 2020 - DOI: 10.48550/arxiv.2101.00170
ABSTRACT: With web and mobile platforms becoming more prominent devices utilized in data analysis, there are currently few systems which are not without flaw. In order to increase the performance of these systems and decrease errors of data oversimplification, we seek to understand how other programming languages can be used across these platforms which provide data and type safety, as well as utilizing concurrency to perform complex data manipulation tasks.

Links:

Chunk List
Feb. 2017 - DOI: 10.48550/arxiv.2101.00172
ABSTRACT: Chunking data is obviously no new concept; however, I had never found any data structures that used chunking as the basis of their implementation. I figured that by using chunking alongside concurrency, I could create an extremely fast run-time in regards to particular methods as searching and/or sorting. By using chunking and concurrency to my advantage, I came up with the chunk list - a dynamic list-based data structure that would separate large amounts of data into specifically sized chunks, each of which should be able to be searched at the exact same time by searching each chunk on a separate thread. As a result of implementing this concept into its own class, I was able to create something that almost consistently gives around 20x-300x faster results than a regular ArrayList. However, should speed be a particular issue even after implementation, users can modify the size of the chunks and benchmark the speed of using smaller or larger chunks, depending on the amount of data being stored.

Links:


Books and Monographs

Check me out on Amazon, Lulu Publishing, Google Books, or wherever else you get your books!


Introduction to Organoid Intelligence: Lecture Notes on Computer Science
Aug. 2024 - Paperback

ISBN: 978-1-304-10774-9

Description: This text provides a comprehensive introduction to Organoid Intelligence (OI), an emerging and interdisciplinary field at the intersection of biology, computation, neuroscience, and engineering. These notes are intended to act as a course companion (which may be designed based on the following syllabus), not necessarily a standalone text for self-study unless the reader already has some familiarity with studying computational neuroscience and artificial intelligence. It is designed for advanced undergraduate and graduate students (e.g., a 500/600-level course) who are already familiar with linear algebra, programming, and AI concepts such as machine learning and deep learning. The text begins by establishing the necessary biological background, covering essential topics like cell biology, neurogenesis, computational neuroscience, and the development of brain organoids. From there, it explores how these biological foundations intersect with computational models to form the basis of OI. Through practical projects using the PyOrganoid Python library, students will learn to create and simulate Deep Organoid Learning models, applying theoretical concepts in a hands-on environment. Furthermore, the text is designed to prepare students for more advanced studies and experimental work in Organoid Intelligence, particularly in contexts where real brain organoids are combined with AI models for cutting-edge research and applications.

Links:

Introduction to Real-Time Audio Programming Using Sonic Pi and ChucK: Lecture Notes on Computer Science
Aug. 2024 - Paperback

ISBN: 978-1-304-12225-4

Description: This text offers a comprehensive set of lecture notes introducing live audio programming through the use of Sonic Pi and ChucK, two powerful and versatile tools for creating music with code. These notes are intended to act as a course companion, not necessarily a standalone text for self-study unless the reader already has some familiarity with studying programming languages. Students will first develop a solid foundation in Ruby programming before diving into Sonic Pi, where they will explore the basics of sound synthesis, rhythm, melody, harmony, sample manipulation, and effects. Throughout the course, students will learn advanced techniques in live coding, sound design, and generative music, along with integrating external tools like MIDI and OSC for collaborative performances. The latter end of the course will focus on ChucK, where students will further refine their skills in sound synthesis, real-time audio processing, and advanced programming concepts. The course culminates in a final project where students will combine their knowledge of Sonic Pi and ChucK to create and perform a live audio programming piece. Likewise, this text includes a set of appendices containing applied course assignments and supplemental notes on music theory (excluding classical voice leading) — hence, students should be expected to have prerequisite knowledge of introductory music theory and computer programming (e.g., in Python or Ruby, ideally).

Links:

Mathematical Notation Reference for Computer Science
Dec. 2023 - Paperback

ISBN: 978-1-304-80795-3

Description: This text contains a comprehensive reference for many commonly seen mathematical notations used frequently in Computer Science, including symbols (or other relevant notation), names, meanings, and programming equivalents (in Python, if any), alongside the most frequently used alphabets (i.e., Latin and Greek) and Latin abbreviations and phrases commonly used in academic literature.

Links:

Introduction to Java: Lecture Notes for AP Computer Science A
Dec. 2022 - Paperback

ISBN: 978-1-387-37972-9

Description: This text consists of a set of succinct lecture notes introducing computer programming in Java for AP Computer Science A students. These notes are intended to act as a course companion, not necessarily a standalone text for self-study unless the reader already has some familiarity with studying programming languages. The text covers all ten units of the AP Computer Science A exam from the Fall 2020 edition of the Course and Exam Description (the most recent as of the publication of this work), a brief introductory unit on setting up and installing Java, and a code editor, and a bonus unit on extra concepts from beyond the AP subset that are especially useful in real-world applications. Some key topics that may be covered include basic programming concepts, such as variables, data types, control structures, and functions, Object-Oriented Programming principles (encapsulation, inheritance, and polymorphism), using Java libraries, parsing data, algorithms and data structures (searching and sorting), and advanced Java features such as generic typing and Functional Programming. Overall, this text provides a thorough foundation in programming concepts and techniques, as well as the skills and knowledge needed to succeed in the AP Computer Science A course and exam, including pitfalls that students should learn to avoid.

Links:

Jazz and Politics: Connections Between Black Ethnic Struggles and Jazz History
Jul. 2021 - Hardcover

ISBN: 978-1-105-83510-0

Description: This research seeks to answer how the history of black ethnic struggles in the United States and the history of jazz are connected. The following issues are discussed:
-Black culture in a white society during the twentieth century,
-The role of jazz musicians, both black and white, in advancing integration, fighting for civil rights, and using their music as a voice,
-Specific examples of musicians, music, and incidents that illustrate your points,
-How the progress of jazz styles reflects the cultural changes of the century, and,
-How the general ethos of dominant culture is evident in the world of jazz.

Links:

An Introduction to Film Scoring in Horror Movies
Jan. 2020 - Paperback

ISBN: 978-1-794-89921-6

Description: The horror movie genre is one of complexity, both in design and story. The style of screenwriting and use of visual and aural nuances has developed into a rich, exciting form of entertainment that plays on the viewer's mind, body, and morals. In terms of visuals, horror movies play on classic psychological fears and utilize them in ways that may be gruesome or traumatizing, yet impossible to look away from. However, one of the biggest tools used to create the sense of fear in the movies is of course the specific use of sound and music to build and develop tension and emphasize horrific scenes. From the usage of drums to imitate a pounding heartbeat to strings playing harsh, discordant and unexpected sounds meant to imitate the screams of frightened animals, and the crashing, staccato chords that strike into instinctive fears, the composer/film scorer of the horror genre plays an extremely important role in delivering the full effect of the film that often goes unnoticed.

Links:

Undergraduate Musicology Research: Studies in Music History
Nov. 2019 - Paperback

ISBN: 978-1-794-73135-6

Description: This book contains a collection of three research papers during undergraduate coursework by Daniel Szelogowski. The works recall three lesser-known composers: Francesco Landini, Frederic Chopin, and Karol Szymanowski — all of which have many sources of misinformation or lack of information overall.

Links:

Menu