Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

2023

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 901 - 930 of 3503

Full-Text Articles in Computer Sciences

An Assessment Of The Consistency Gap In Developing Countries: A Case Of Zimbabwe’S Ict Regulatory Framework, Casper Chigwedere Sep 2023

An Assessment Of The Consistency Gap In Developing Countries: A Case Of Zimbabwe’S Ict Regulatory Framework, Casper Chigwedere

African Conference on Information Systems and Technology

An effective Information and Communications Technology (ICT) regulatory system is expected to advance regulatory consistency, independence, pro-competitiveness, consistency, competency, and accountability. These qualities will inspire investor confidence, sectoral growth, and customer satisfaction. Since we considered regulatory independence elsewhere, this paper investigates the level of regulatory consistency in developing countries. This is done using data from Zimbabwe a developing country in Sub-Saharan Africa. The study employs a Qualitative methodology, and Heeks’ (2002) Design Reality Gap (DRG) model under an interpretivist paradigm. Data collection employed in-depth interviews with purposively selected stakeholders and the analysed using Nvivo (release 1.6.1 (1136)) and thematic analysis …


Towards Safe Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja Sep 2023

Towards Safe Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution. We present our ongoing work on automated refactoring that assists developers in specifying whether …


Revealing Gene Regulation-Based Neural Network Computing In Bacteria, Samitha S. Somathilaka, Sasitharan Balasubramaniam, Daniel P. Martins, Xu Li Sep 2023

Revealing Gene Regulation-Based Neural Network Computing In Bacteria, Samitha S. Somathilaka, Sasitharan Balasubramaniam, Daniel P. Martins, Xu Li

School of Computing: Faculty Publications

Bacteria are known to interpret a range of external molecular signals that are crucial for sensing environmental conditions and adapting their behaviors accordingly. These external signals are processed through a multitude of signaling transduction networks that include the gene regulatory network (GRN). From close observation, the GRN resembles and exhibits structural and functional properties that are similar to artificial neural networks. An in-depth analysis of gene expression dynamics further provides a new viewpoint of characterizing the inherited computing properties underlying the GRN of bacteria despite being non-neuronal organisms. In this study, we introduce a model to quantify the gene-to-gene interaction …


A Novel Fuzzy Relative-Position-Coding Transformer For Breast Cancer Diagnosis Using Ultrasonography, Yanhui Guo, Ruquan Jiang, Xin Gu, Heng-Da Cheng, Harish Garg Sep 2023

A Novel Fuzzy Relative-Position-Coding Transformer For Breast Cancer Diagnosis Using Ultrasonography, Yanhui Guo, Ruquan Jiang, Xin Gu, Heng-Da Cheng, Harish Garg

Computer Science Faculty and Staff Publications

Breast cancer is a leading cause of death in women worldwide, and early detection is crucial for successful treatment. Computer-aided diagnosis (CAD) systems have been developed to assist doctors in identifying breast cancer on ultrasound images. In this paper, we propose a novel fuzzy relative-position-coding (FRPC) Transformer to classify breast ultrasound (BUS) images for breast cancer diagnosis. The proposed FRPC Transformer utilizes the self-attention mechanism of Transformer networks combined with fuzzy relative-position-coding to capture global and local features of the BUS images. The performance of the proposed method is evaluated on one benchmark dataset and compared with those obtained by …


Bare-Bones Based Salp Swarm Algorithm For Text Document Clustering, Mohammed Azmi Al-Betar, Ammar Kamal Abasi, Ghazi Al-Naymat, Kamran Arshad, Sharif Naser Makhadmeh Sep 2023

Bare-Bones Based Salp Swarm Algorithm For Text Document Clustering, Mohammed Azmi Al-Betar, Ammar Kamal Abasi, Ghazi Al-Naymat, Kamran Arshad, Sharif Naser Makhadmeh

Machine Learning Faculty Publications

Text Document Clustering (TDC) is a challenging optimization problem in unsupervised machine learning and text mining. The Salp Swarm Algorithm (SSA) has been found to be effective in solving complex optimization problems. However, the SSA’s exploitation phase requires improvement to solve the TDC problem effectively. In this paper, we propose a new approach, known as the Bare-Bones Salp Swarm Algorithm (BBSSA), which leverages Gaussian search equations, inverse hyperbolic cosine control strategies, and greedy selection techniques to create new individuals and guide the population towards solving the TDC problem. We evaluated the performance of the BBSSA on six benchmark datasets from …


Towards Safe Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja Sep 2023

Towards Safe Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution. We present our ongoing work on automated refactoring that assists developers in specifying whether …


Multiple Structural And Functional Annotations Based In-Silico Characterization Of Q9brx8 Protein, Eiman Zahid, Muhammad Farhan Sarwar Sep 2023

Multiple Structural And Functional Annotations Based In-Silico Characterization Of Q9brx8 Protein, Eiman Zahid, Muhammad Farhan Sarwar

Karbala International Journal of Modern Science

Numerous proteins found in humans are poorly understood because there is a dearth of experimental evidence. Hypothetical proteins (HPs) or uncharacterized proteins are the terms used to describe these proteins. In this work, one of these proteins, Q9BRX8, is investigated using in-silico or bioinformatics tools to reveal its significant properties. In this regard, NCBI for the sequence retrieval, ProtParam tool for analysis of physiochemical properties, SOPMA for secondary structure prediction, SWISS-Model for homology modelling, STRING for protein-protein interaction and HDOCK for protein-protein docking analysis among other tools, were incorporated. The physiochemical characteristics indicated that Q9BRX8, which has an instability score …


Pura Vida Neutrosophic Algebra, Ranulfo Paiva Barbosa (Sobrinho), Florentin Smarandache Sep 2023

Pura Vida Neutrosophic Algebra, Ranulfo Paiva Barbosa (Sobrinho), Florentin Smarandache

Neutrosophic Systems with Applications

We introduce Pura Vida Neutrosophic Algebra, an algebraic structure consisting of neutrosophic numbers equipped with two binary operations namely addition and multiplication. The addition can be calculated sometimes with the function min and other times with the max function. The multiplication operation is the usual sum between numbers. Pura Vida Neutrosophic Algebra is an extension of both Tropical Algebra (also known as Min-Plus, or Min-Algebra) and Max-Plus Algebra (also known as Max-algebra). Tropical and Max-Plus algebras are algebraic structures included in semirings and their operations can be used in matrices and vectors. Pura Vida Neutrosophic Algebra is included in Neutrosophic …


Trigonometric Similarity Measures Of Pythagorean Neutrosophic Hypersoft Sets, Ramya G, Francina Shalini A Sep 2023

Trigonometric Similarity Measures Of Pythagorean Neutrosophic Hypersoft Sets, Ramya G, Francina Shalini A

Neutrosophic Systems with Applications

In our daily life, most problems stem from the wrong decisions. Similarity measures (SMs) are very helpful in making good decisions. In this paper, distinct similarities of Pythagorean Neutrosophic Hypersoft Sets (PNHSSs) and its properties are presented. Finally, the proposed SMs applied for converting plastic waste into energy source problems. Comparing various suggested similarities makes decision-making simple, easy, and accurate.


A Comparative Analysis Of Proactive And Reactive Methods For Privacy-Aware Interleaved Dnn Offloading, Jamie Cotter Sep 2023

A Comparative Analysis Of Proactive And Reactive Methods For Privacy-Aware Interleaved Dnn Offloading, Jamie Cotter

Department of Computer Science Publications

Deep Neural Networks (DNNs) are increasingly used on the edge in mobile and other resource-constrained devices for inference tasks ranging from object detection and image recognition to video processing. Many of these tasks have low latency requirements that cannot be satisfied if they are processed locally due to their high computational complexity. Offloading computation to the edge and cloud offers a way to alleviate this computational latency. Doing so introduces communication delays, which makes offloading a balancing act between the benefits of reduced processing time and the communication delays incurred. Existing algorithms for DNN offloading based on DNN partitioning are …


Trigonometric Similarity Measures Of Pythagorean Neutrosophic Hypersoft Sets, Ramya G, Francina Shalini A Sep 2023

Trigonometric Similarity Measures Of Pythagorean Neutrosophic Hypersoft Sets, Ramya G, Francina Shalini A

Neutrosophic Systems with Applications

In our daily life, most problems stem from the wrong decisions. Similarity measures (SMs) are very helpful in making good decisions. In this paper, distinct similarities of Pythagorean Neutrosophic Hypersoft Sets (PNHSSs) and its properties are presented. Finally, the proposed SMs applied for converting plastic waste into energy source problems. Comparing various suggested similarities makes decision-making simple, easy, and accurate.


Pura Vida Neutrosophic Algebra, Ranulfo Paiva Barbosa (Sobrinho), Florentin Smarandache Sep 2023

Pura Vida Neutrosophic Algebra, Ranulfo Paiva Barbosa (Sobrinho), Florentin Smarandache

Neutrosophic Systems with Applications

We introduce Pura Vida Neutrosophic Algebra, an algebraic structure consisting of neutrosophic numbers equipped with two binary operations namely addition and multiplication. The addition can be calculated sometimes with the function min and other times with the max function. The multiplication operation is the usual sum between numbers. Pura Vida Neutrosophic Algebra is an extension of both Tropical Algebra (also known as Min-Plus, or Min-Algebra) and Max-Plus Algebra (also known as Max-algebra). Tropical and Max-Plus algebras are algebraic structures included in semirings and their operations can be used in matrices and vectors. Pura Vida Neutrosophic Algebra is included in Neutrosophic …


A Study On Feature Selection Using Multi-Domain Feature Extraction For Automated K-Complex Detection, Yabing Li, Xinglong Dong, Kun Song, Xiangyun Bai, Hongye Li, Fakhreddine Karray Sep 2023

A Study On Feature Selection Using Multi-Domain Feature Extraction For Automated K-Complex Detection, Yabing Li, Xinglong Dong, Kun Song, Xiangyun Bai, Hongye Li, Fakhreddine Karray

Machine Learning Faculty Publications

Background: K-complex detection plays a significant role in the field of sleep research. However, manual annotation for electroencephalography (EEG) recordings by visual inspection from experts is time-consuming and subjective. Therefore, there is a necessity to implement automatic detection methods based on classical machine learning algorithms. However, due to the complexity of EEG signal, current feature extraction methods always produce low relevance to k-complex detection, which leads to a great performance loss for the detection. Hence, finding compact yet effective integrated feature vectors becomes a crucially core task in k-complex detection. Method: In this paper, we first extract multi-domain features based …


A Neutrosophic Approach For B-Spline Curve By Using Interpolation Method, Siti Nur Idara Binti Rosli, Mohammad Izat Emir Bin Zulkifly Sep 2023

A Neutrosophic Approach For B-Spline Curve By Using Interpolation Method, Siti Nur Idara Binti Rosli, Mohammad Izat Emir Bin Zulkifly

Neutrosophic Systems with Applications

This study introduces a B-spline curve interpolation model based on the neutrosophic set technique. To begin, the neutrosophic notion is used to define the neutrosophic control point relation. After that, the neutrosophic control point is combined with the B-spline basis function. Besides, the neutrosophic B-spline curve interpolation model is illustrated using the interpolation method. Furthermore, an example and the methods are shown for creating the right curve.


A New Approach For The Statistical Convergence Over Non-Archimedean Fields In Neutrosophic Normed Spaces, Jeyaraman M., Iswariya S. Sep 2023

A New Approach For The Statistical Convergence Over Non-Archimedean Fields In Neutrosophic Normed Spaces, Jeyaraman M., Iswariya S.

Neutrosophic Systems with Applications

The goal of the research involves elaborating on the topics of statistical convergence, including statistical Cauchy sequences within non-Archimedean Neutrosophic normed spaces, as well as achieving specific useful conclusions. The present research shows how, within a non-Archimedean field, certain sections of statistically convergent sequences that could not be true often become true. Likewise, we created statistically complete and statistically continuous spaces for such regions that demonstrated certain essential facts. κ indicates a complete field of non-Archimedean and non-trivially valued research.


An Analysis Of Obesity In School Children During The Pandemic Covid-19 Using Plithogenic Single Valued Fuzzy Sets, S. P. Priyadharshini, F. Nirmala Irudayam Sep 2023

An Analysis Of Obesity In School Children During The Pandemic Covid-19 Using Plithogenic Single Valued Fuzzy Sets, S. P. Priyadharshini, F. Nirmala Irudayam

Neutrosophic Systems with Applications

The objective of this research is to examine the perception that school children with obesity, when excluded from organized academic performance and constrained to their residences during the coronavirus epidemic 2019, will reveal negative consequences in health behaviors. To meet the objective, the concept of Plithogenic Single valued fuzzy sets (PSFS) and their aggregation operators were introduced. Based on the proposed theory, an analysis is presented with the case study to highlight its practicality and preciseness.


Fixed Point Results In Neutrosophic Rectangular Extended B-Metric Spaces, Naeem Saleem, Umar Ishtiaq, Khaleel Ahmad, Salvatore Sessa, Ferdinando Di Martino Sep 2023

Fixed Point Results In Neutrosophic Rectangular Extended B-Metric Spaces, Naeem Saleem, Umar Ishtiaq, Khaleel Ahmad, Salvatore Sessa, Ferdinando Di Martino

Neutrosophic Systems with Applications

In this manuscript, we establish the notion of neutrosophic rectangular extended b-metric spaces and derive some fixed point results for contraction mappings. Also, we provide several non-trivial examples. Our results are more generalized with respect to the existing ones in the literature. At the end of the paper, we provide an application to non-linear fractional differential equations to test the validity of the results.


Graphical Method For Solving Neutrosophical Nonlinear Programming Models, Maissam Jdid, Florentin Smarandache Sep 2023

Graphical Method For Solving Neutrosophical Nonlinear Programming Models, Maissam Jdid, Florentin Smarandache

Neutrosophic Systems with Applications

An important method for finding the optimal solution for linear and nonlinear models is the graphical method, which is used if the linear or nonlinear mathematical model contains one, two, or three variables. The models that contain only two variables are among the most models for which the optimal solution has been obtained graphically, whether these models are linear or non-linear in references and research that are concerned with the science of operations research, when the data of the issue under study is classical data. In this research, we will present a study through, which we present the graphical method …


Mfa-Dvr: Direct Volume Rendering Of Mfa Models, Jianxin Sun, David Lenz, Hongfeng Yu, Tom Peterka Sep 2023

Mfa-Dvr: Direct Volume Rendering Of Mfa Models, Jianxin Sun, David Lenz, Hongfeng Yu, Tom Peterka

School of Computing: Faculty Publications

3D volume rendering is widely used to reveal insightful intrinsic patterns of volumetric datasets across many domains. However, the complex structures and varying scales of volumetric data can make efficiently generating high-quality volume rendering results a challenging task. Multivariate functional approximation (MFA) is a new data model that addresses some of the critical challenges: high-order evaluation of both value and derivative anywhere in the spatial domain, compact representation for largescale volumetric data, and uniform representation of both structured and unstructured data. In this paper, we present MFA-DVR, the first direct volume rendering pipeline utilizing the MFA model, for both structured …


A Neutrosophic Approach For B-Spline Curve By Using Interpolation Method, Siti Nur Idara Binti Rosli, Mohammad Izat Emir Bin Zulkifly Sep 2023

A Neutrosophic Approach For B-Spline Curve By Using Interpolation Method, Siti Nur Idara Binti Rosli, Mohammad Izat Emir Bin Zulkifly

Neutrosophic Systems with Applications

This study introduces a B-spline curve interpolation model based on the neutrosophic set technique. To begin, the neutrosophic notion is used to define the neutrosophic control point relation. After that, the neutrosophic control point is combined with the B-spline basis function. Besides, the neutrosophic B-spline curve interpolation model is illustrated using the interpolation method. Furthermore, an example and the methods are shown for creating the right curve.


Fixed Point Results In Neutrosophic Rectangular Extended B-Metric Spaces, Naeem Saleem, Umar Ishtiaq, Khaleel Ahmad, Salvatore Sessa, Ferdinando Di Martino Sep 2023

Fixed Point Results In Neutrosophic Rectangular Extended B-Metric Spaces, Naeem Saleem, Umar Ishtiaq, Khaleel Ahmad, Salvatore Sessa, Ferdinando Di Martino

Neutrosophic Systems with Applications

In this manuscript, we establish the notion of neutrosophic rectangular extended b-metric spaces and derive some fixed point results for contraction mappings. Also, we provide several non-trivial examples. Our results are more generalized with respect to the existing ones in the literature. At the end of the paper, we provide an application to non-linear fractional differential equations to test the validity of the results.


A New Approach For The Statistical Convergence Over Non-Archimedean Fields In Neutrosophic Normed Spaces, Jeyaraman M., Iswariya S. Sep 2023

A New Approach For The Statistical Convergence Over Non-Archimedean Fields In Neutrosophic Normed Spaces, Jeyaraman M., Iswariya S.

Neutrosophic Systems with Applications

The goal of the research involves elaborating on the topics of statistical convergence, including statistical Cauchy sequences within non-Archimedean Neutrosophic normed spaces, as well as achieving specific useful conclusions. The present research shows how, within a non-Archimedean field, certain sections of statistically convergent sequences that could not be true often become true. Likewise, we created statistically complete and statistically continuous spaces for such regions that demonstrated certain essential facts. κ indicates a complete field of non-Archimedean and non-trivially valued research.


An Analysis Of Obesity In School Children During The Pandemic Covid-19 Using Plithogenic Single Valued Fuzzy Sets, S. P. Priyadharshini, F. Nirmala Irudayam Sep 2023

An Analysis Of Obesity In School Children During The Pandemic Covid-19 Using Plithogenic Single Valued Fuzzy Sets, S. P. Priyadharshini, F. Nirmala Irudayam

Neutrosophic Systems with Applications

The objective of this research is to examine the perception that school children with obesity, when excluded from organized academic performance and constrained to their residences during the coronavirus epidemic 2019, will reveal negative consequences in health behaviors. To meet the objective, the concept of Plithogenic Single valued fuzzy sets (PSFS) and their aggregation operators were introduced. Based on the proposed theory, an analysis is presented with the case study to highlight its practicality and preciseness.


Graphical Method For Solving Neutrosophical Nonlinear Programming Models, Maissam Jdid, Florentin Smarandache Sep 2023

Graphical Method For Solving Neutrosophical Nonlinear Programming Models, Maissam Jdid, Florentin Smarandache

Neutrosophic Systems with Applications

An important method for finding the optimal solution for linear and nonlinear models is the graphical method, which is used if the linear or nonlinear mathematical model contains one, two, or three variables. The models that contain only two variables are among the most models for which the optimal solution has been obtained graphically, whether these models are linear or non-linear in references and research that are concerned with the science of operations research, when the data of the issue under study is classical data. In this research, we will present a study through, which we present the graphical method …


Covering Properties Via Neutrosophic B-Open Sets, Sudeep Dey, Gautam Chandra Ray Sep 2023

Covering Properties Via Neutrosophic B-Open Sets, Sudeep Dey, Gautam Chandra Ray

Neutrosophic Systems with Applications

The purpose of this article is to study some covering properties in neutrosophic topological spaces using neutrosophic b-open sets. We define neutrosophic b-open cover, neutrosophic b-compactness, neutrosophic countably b-compactness neutrosophic b-Lindelofness, neutrosophic local b-compactness and study various properties entangled with them. We study some covering properties involving neutrosophic continuous, neutrosophic b-continuous and neutrosophic b*-continuous functions. Lastly, we define neutrosophic base, neutrosophic subbase, neutrosophic second countability via neutrosophic b-open sets and investigate some properties.


Toward Energy Transformation: Intelligent Decision-Making Model Based On Uncertainty Neutrosophic Theory, Mona Mohamed, Nissreen El-Saber Sep 2023

Toward Energy Transformation: Intelligent Decision-Making Model Based On Uncertainty Neutrosophic Theory, Mona Mohamed, Nissreen El-Saber

Neutrosophic Systems with Applications

There has been an increasing tendency for the generation of energy from diverse renewable resources because of the application of contemporary pollution mitigation and justification regulations. Precisely a consequence, choosing the best renewable energy source might be considered a challenging issue given the complexity of the future conditions in any society. Environmental, economic, social, and technical aspects are merely some of the factors that are taken into consideration while evaluating renewable energy sources (RnESs). The suitable RES selection problem, which relies on ambiguous and imprecise data, is also influenced by a variety of circumstances. Hence, this study constructs multi-stages intelligent …


Identity Management Pki System Using Blockchain, Mohamed Abdel Fattah Abdel Baki Awad Sep 2023

Identity Management Pki System Using Blockchain, Mohamed Abdel Fattah Abdel Baki Awad

Theses and Dissertations

Identity management is one of the most important topics in the security field. Public Key Infrastructure (PKI) is the most commonly used approach in legally identity management systems. PKI systems have many centralized services that might affect the availability and trustworthiness of the system. Issues related to certificate verification methods such as Certificate Revocation List (CRL) and Online Certificate Status Protocol (OCSP) can be avoided if blockchain is used. Blockchain is a decentralized trusted system where data can only be appended to a public ledger. Edits are not allowed in blockchain. Blockchain consists of several nodes all of them have …


Covering Properties Via Neutrosophic B-Open Sets, Sudeep Dey, Gautam Chandra Ray Sep 2023

Covering Properties Via Neutrosophic B-Open Sets, Sudeep Dey, Gautam Chandra Ray

Neutrosophic Systems with Applications

The purpose of this article is to study some covering properties in neutrosophic topological spaces using neutrosophic b-open sets. We define neutrosophic b-open cover, neutrosophic b-compactness, neutrosophic countably b-compactness neutrosophic b-Lindelofness, neutrosophic local b-compactness and study various properties entangled with them. We study some covering properties involving neutrosophic continuous, neutrosophic b-continuous and neutrosophic b*-continuous functions. Lastly, we define neutrosophic base, neutrosophic subbase, neutrosophic second countability via neutrosophic b-open sets and investigate some properties.


Toward Energy Transformation: Intelligent Decision-Making Model Based On Uncertainty Neutrosophic Theory, Mona Mohamed, Nissreen El-Saber Sep 2023

Toward Energy Transformation: Intelligent Decision-Making Model Based On Uncertainty Neutrosophic Theory, Mona Mohamed, Nissreen El-Saber

Neutrosophic Systems with Applications

There has been an increasing tendency for the generation of energy from diverse renewable resources because of the application of contemporary pollution mitigation and justification regulations. Precisely a consequence, choosing the best renewable energy source might be considered a challenging issue given the complexity of the future conditions in any society. Environmental, economic, social, and technical aspects are merely some of the factors that are taken into consideration while evaluating renewable energy sources (RnESs). The suitable RES selection problem, which relies on ambiguous and imprecise data, is also influenced by a variety of circumstances. Hence, this study constructs multi-stages intelligent …


Emotion-Aware Music Recommendation, Hieu Tran, Tuan Le, Anh Do, Tram Vu, Steven Bogaerts, Brian T. Howard Sep 2023

Emotion-Aware Music Recommendation, Hieu Tran, Tuan Le, Anh Do, Tram Vu, Steven Bogaerts, Brian T. Howard

Computer Science Faculty publications

It is common to listen to songs that match one's mood. Thus, an AI music recommendation system that is aware of the user's emotions is likely to provide a superior user experience to one that is unaware. In this paper, we present an emotion-aware music recommendation system. Multiple models are discussed and evaluated for affect identification from a live image of the user. We propose two models: DRViT, which applies dynamic routing to vision transformers, and InvNet50, which uses involution. All considered models are trained and evaluated on the AffectNet dataset. Each model outputs the user's estimated valence and arousal …