Search Subject Areas | Preprints.org

Preprint ARTICLE | doi:10.20944/preprints202404.0343.v1

Predicting UK Housing Price using Machine Learning Algorithms

Gbadebo Adedotun Ogundeji, Dilkushi de Alwis Pitts, Yeran Sun, Mubeen Ghafoor

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: House pricing; Catboost; Gradient Boosting; Bagging; Random Forest; Extra Tree; KNN; ANN; UK paid housing price

Online: 4 April 2024 (12:58:30 CEST)

Show abstract| Download PDF| Share

The development of reliable predictive algorithm for house price as the housing market is a stand-out among the most involved regarding valuing the price and continues to fluctuate, is constantly a need for socio-economic advancement and welfare of citizen. In this paper, we develop machine learning algorithms for forecasting UK housing Price, and find an optimal algorithm that forecasts housing price accurately on the premises of the presence of many features or covariates. After applying correlation analysis to remove correlated variables in order to avoid multicollinearity, thereby increasing the statistical power, a novel method of using regression analysis to first of all understand and select statistically significant features for the various regions in England based on North South divide is adopted. These features are then used in the machine learning algorithm to further increase the statistical power of the algorithm, increase the level of accuracy for each of them and ultimately increase the predictive values for the algorithms. The model construction involves 3 stages: 1- correlation analysis to identify and remove correlated variables thereby avoiding multicollinearity and increasing the statistical power of the linear regression, 2 - using linear regression to determine variables that are statistically significant and 3 - building the machine learning algorithms based on the variables that are statistically significant from the linear regression. A comprehensive dataset of UK Paid housing Price from 2010 to 2019 was linked to a number of other datasets to generate a total 21 variables or features used for the models. Catboost, Gradient Boosting, Bagging, Random Forest, Extra Tree all achieved the excellent models performance result in all the regions considered. The comparison of the seven models showed that Extra Tree algorithm consistently achieved the best performance in term of level of accuracy in all the regions. K-Nearest Neighbours (KNN) is the only algorithm with less than 50% level of accuracy. Noticeably, the regions considered had varying or differing insignificant variables, implying that although many variables are common (statistically significant) to all the regions, there are regional differences and impact when modelling or predicting housing prices. This study validates the practicability of developing a machine learning methodology for the prediction of housing price. This research offers a reference for future house price prediction based on machine learning.

Preprint ARTICLE | doi:10.20944/preprints202404.0372.v1

Optimising Sensor Controlled Systems With Minimal Intervention: A Fuzzy Relational Calculus Approach

Zlatko Vassilev Zahariev

Subject: Computer Science And Mathematics, Logic Keywords: Sensor-Controlled Systems; Fuzzy Linear Systems of Equations; Inverse Problem

Online: 4 April 2024 (12:36:42 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0375.v1

A Temporal Difference and Cross-variate Fusion Network for Multivariate Time Series Classification

Weihong Cai, Zinan Ji, Qihong Feng

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Multivariate Time Series Classification; Human Motion Recognition; Human Activity Recognition; Medical Signal Classification; Two-stream Model; Depthwise Separable Convolution; Differential LSTM network

Online: 4 April 2024 (12:13:54 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0359.v1

A 'Turing Test' for Self-Awareness

Cameron Witkowski

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Self-Awareness; Self-Consciousness; Turing; LLM; Meaning; Understanding

Online: 4 April 2024 (08:51:13 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0356.v1

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

Nian He, Dengfeng Liu, Zhichen Zhang, Zhiquan Lin, Tiesong Zhao, Yiwen Xu

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Smart City; Smart Electric Energy Management; Electric Load Monitoring; Load Recognition Algorithm; Computer Vision

Online: 4 April 2024 (08:13:36 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0353.v1

Fractal Dimension of Generalized Rényian Entropy With Potential Fractal Dimension Applications to Smart Cities

Ismail A Mageed, Ashiq Hussain Bhat

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Fractal dimension; Generalized Ré; nyian Entropy; Koch snowflake; Sierpiniski Gasket; Information; communications Technology (ICT)

Online: 4 April 2024 (08:06:11 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0334.v1

Chef Dalle: Transforming Cooking with Multimodal AI

Brendan Hannon, Yulia Kumar, J. Jenny Li, Patricia Morreale

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Human-Computer Interaction; Personalized Cooking Experience; Dietary Management; Recipe Recommendations; Artificial Intelligence; ChatGPT

Online: 4 April 2024 (06:06:55 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0253.v1

Disturbance Propagation Model of Luggage Drifting Motion Based on Nonlinear Pressure in Typical Passenger Corridors of Transportation Hubs

Bingyu Wei, Rongyong Zhao, Cuiling Li, Miyuan Li, Yulong Ma, Eric S. W. Wong

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Luggage-laden passenger; passenger-luggage flow; disturbance propagation dynamics; luggage drifting disturbance

Online: 3 April 2024 (16:37:35 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0287.v1

Unfolding the Third Approximation of The Time‐Dependent Controller’s Designed Parameter (TDCDP) of Fokker Planck Kolmogorov (FPK) Probability Density Function(PDF)

Dr Ismail A Mageed

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Control theory; time-dependent controller’ s designed parameter(TDCDP)

Online: 3 April 2024 (14:14:47 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0238.v1

Sectrabank Model to Mitigate Computer Fraud in Electronic Operations through Banking Applications on Android Devices

Jhon Melendez, Jomark Noriega, Jose Tiznado, Paulo Calderon, Yordy Benites, Luis Rivera, Jose Herrera, Jorge Mayhuasca

Subject: Computer Science And Mathematics, Security Systems Keywords: fake app; SIM swapping; cybercrime; computer fraud; security; authentication

Online: 3 April 2024 (13:13:18 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202404.0241.v1

Psychophysics of Social Cyber-Physical System Acceptance

Maya Dimitrova, Neda Chehlarova, Anastas Madzharov, Aleksandar Krastev, Ivan Chavdarov

Subject: Computer Science And Mathematics, Robotics Keywords: cyber-physical systems; robot acceptance; psychophysics; psychological reactance; categorical perception; uncanny valley effect; probability distribution; accessibility

Online: 3 April 2024 (12:07:49 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0125.v2

Cracking Factorization- Cryptography Challenges

Asset Durmagambetov, Aslan Durmagambetov

Subject: Computer Science And Mathematics, Security Systems Keywords: Decryption; factorization problem; gradient descent algorithm; new method for solving; transition from algebraic methods to approaches based on functional analysis

Online: 3 April 2024 (11:20:37 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0250.v1

Human Activity Recognition in a Free-Living Environment Using an Ear-Worn Motion Sensor

Lukas Boborzi, Julian Decker, Razieh Rezaei, Roman Schniepp, Max Wuehr

Subject: Computer Science And Mathematics, Signal Processing Keywords: human activity recognition; inertial sensor; ear; in-ear sensing; vital sign monitoring; wearables; machine learning; deep learning

Online: 3 April 2024 (11:06:45 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0254.v1

Leveraging Sentiment Lexicon in Sentiment Detection

Alex Johnson, Emily Davis, Wyne Nasir, Michael Brown

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Sentiment Detection; Lexicon; Enhanced SentiStrength

Online: 3 April 2024 (11:06:37 CEST)

Show abstract| Download PDF| Share

In the rapidly evolving field of sentiment analysis, the introduction of Transformer-based architectures, particularly the BERT model, has markedly improved accuracy levels, setting new standards in the analysis of textual sentiment. These advancements have been instrumental in enhancing the model's ability to grasp the nuances and complexities inherent in human language, thereby providing deeper insights into the sentiment expressed in various texts. However, the impressive performance of such deep learning models comes at the cost of increased computational demands and a lack of transparency in their decision-making processes. These challenges have reignited interest in rule-based sentiment analysis methods, which utilize sentiment lexicons for a more straightforward and computationally economical approach to determining text sentiment. Despite being overshadowed by the rise of machine learning models in recent years, these lexicon-based methods possess distinct advantages, including ease of interpretation and lower resource requirements, making them particularly appealing for certain applications. This paper seeks to re-evaluate the relevance and effectiveness of two prominent lexicon-based sentiment analysis methods, SO-CAL and SentiStrength, which have been specifically adapted for the language, in light of the advancements represented by Transformer-based models like SentBERT. Through a comprehensive comparative analysis, we examine the performance of these methodologies in contrast to SentBERT across an extensive collection of 16 text corpora, spanning a variety of genres and contexts. Our findings reveal a nuanced landscape of performance, where SentBERT's advanced capabilities typically afford it a significant advantage in accurately capturing sentiment. Nevertheless, in a surprising turn, the SO-CAL method exhibits exceptional performance on a substantial portion of the datasets, underscoring the continuing value and potential of lexicon-based approaches in sentiment analysis. This study not only highlights the strengths and weaknesses of both deep learning and lexicon-based methods but also opens the door for future hybrid approaches that could leverage the best of both worlds to achieve even greater accuracy and efficiency in sentiment analysis tasks.

Preprint ARTICLE | doi:10.20944/preprints202404.0268.v1

Covers of Finitely Generated Acts over Monoids

Xiaoqin Zhang, Tingting Zhao

Subject: Computer Science And Mathematics, Algebra And Number Theory Keywords: cover; coproduct; finitely generated; $\mathcal{X}$-precover

Online: 3 April 2024 (08:28:04 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0143.v1

ROS2 Communication Security Vulnerability Detection Based on Formal Method

Shuo Yang, Jian Guo, Xue Rui

Subject: Computer Science And Mathematics, Computer Networks And Communications Keywords: Robotic System; ROS2; Communication mechanisms; Security and Safety Analysis; formal method

Online: 2 April 2024 (16:12:24 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202302.0051.v64

Duality Principles and Numerical Procedures for a Large Class of Non-convex Models in the Calculus of Variations

Fabio Silva Botelho

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: duality theory; non-convex analysis; numerical method for a non-smooth model

Online: 2 April 2024 (15:41:15 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0219.v1

Understanding Superlinear Speedup in Current HPC Architectures

Flavio Cesar Cunha Galeazzo, R. Gregor Weiß, Sergey Lesnik, Henrik Rusche, Andreas Ruopp

Subject: Computer Science And Mathematics, Computer Science Keywords: OpenFOAM; CFD; HPC; superlinear speedup

Online: 2 April 2024 (15:14:39 CEST)

Show abstract| Download PDF| Share

The performance of OpenFOAM in strong scaling tests on HPC systems with AMD EPYC processors exhibits a pronounced superlinear speedup. Simple test cases show superlinear speedups of over 300%, which significantly impacts the efficient use of computing resources. With the last generation of HPC architectures, a superlinear speedup of about 10% to 20% was well expected and accepted by CFD users. The measured superlinear speedup is much more pronounced and withstands the communication overhead to even larger scales. A detailed performance analysis of OpenFOAM follows, employing various High-Performance Computing (HPC) architectures, including AMD, ARM and Intel systems. The performance metric FVOPS (Finite VOlumes solved Per Second) is introduced to compare the performance of Computational Fluid Dynamics (CFD) applications when varying the grid size, as occurs in a strong scaling test. The achievable FVOPS depends on various factors, including the simulation type, boundary conditions, and especially the grid size of a use case. Analysing FVOPS on a single node level with varying grid size shows a significant difference in performance and cache utilization, which explains the large superlinear speedups seen in the strong scaling tests. Furthermore, FVOPS can be used as a simple benchmark to determine the optimal number of grid elements per rank to simulate a given use case at peak efficiency on a given platform, resulting in time, energy, and cost savings. The FVOPS metric also facilitates the direct comparison between different HPC architectures. The tests using AMD, ARM, and Intel processors show a peak in performance when employing around 10,000 grid elements per core. The presence of a large L3 cache on AMD processors is particularly advantageous, as indicated by L3 cache miss rates observed on AMD EPYC processors. Our results suggest that future HPC architectures with larger caches and higher memory bandwidth would benefit the CFD community.

Preprint ARTICLE | doi:10.20944/preprints202404.0194.v1

Forecasting the Power Generation Mix in Italy Based on Grey Markov Models

Guglielmo D’Amico, Alex Karagrigoriou, Veronica Vigna

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Markov Chain; Grey Model; Energy Mix; Electricity

Online: 2 April 2024 (13:06:32 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0182.v1

Hybrid Genetic Algorithm and Tabu Search for Solving Preventive Maintenance Scheduling Problem for Cogeneration Plants

Khaled Alhamad, Yousif Alkhezi

Subject: Computer Science And Mathematics, Discrete Mathematics And Combinatorics Keywords: preventive maintenance; scheduling; optimization; genetic algorithm; tabu search; metaheuristic

Online: 2 April 2024 (12:56:52 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0074.v1

PTSD Case Detection with Boosting

Vu Nguyen, Minh Phan, Tiantian Wang, Payam Norouzzadeh, Eli Snir, Salih Tutun, Brett McKinney, Bahareh Rahmani

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Linear Support Vector Machine; K-mean Clustering; PTSD; EEG

Online: 2 April 2024 (12:45:01 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202310.0773.v17

Resolving the Collatz Conjecture: A Rigorous Proof through Inverse Discrete Dynamical Systems and Algebraic Inverse Trees

Eduardo Diedrich

Subject: Computer Science And Mathematics, Mathematics Keywords: discrete dynamical systems; inverse modeling; topological equivalence; topological transport; algebraic trees; collatz conjecture; homeomorphic invariance

Online: 2 April 2024 (11:53:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0125.v1

Decryption of Factorization - Cryptography Challenges

Asset Durmagambetov, Aslan Durmagambetov

Subject: Computer Science And Mathematics, Security Systems Keywords: Decryption; factorization problem; gradient descent algorithm; new method for solving; transition from algebraic methods to approaches based on functional analysis

Online: 2 April 2024 (10:34:13 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0154.v1

Towards Improving YARN performance for Frugal Heterogeneous SBC-based Edge Clusters

Basit Qureshi

Subject: Computer Science And Mathematics, Computer Science Keywords: Single Board Computers; Frugal edge computing; Hadoop; YARN; heterogeneous

Online: 2 April 2024 (09:14:06 CEST)

Show abstract| Download PDF| Share

In the dynamic landscape of sustainable computing, use of edge devices is paramount for reducing the need for large-scale centralized data centers. By processing data locally, edge devices minimize the energy-intensive computing in data centers, improving the overall performance, cost-effectiveness whereas reducing the environmental impact. Edge devices may constitute edge clusters composed of resource frugal Single Board Computers (SBC) such as Raspberry Pi etc. The small form-factor and energy efficiency of these computers makes them ideal for processing large data on the edge. Despite their potential, traditional Hadoop configurations struggle to optimize performance in heterogeneous SBC clusters due to disparities in computing resources. Consequently, we propose modifications to the Yet Another Resource Negotiator (YARN) scheduling mechanism to address these challenges. Our proposed changes include the introduction of a Frugality Index and an adaptiveConfig policy. The Frugality Index categorizes SBC nodes based on their capabilities, enabling intelligent resource allocation. The adaptiveConfig policy dynamically adjusts resource allocation in response to workload and cluster conditions, enhancing system efficiency. Additionally, we introduce a fetch_threshold for reduce tasks to improve task prioritization based on locality and data processing efficiency. We evaluate our approach using a 13-node SBC cluster and conduct experiments with CPU-intensive and IO-intensive Hadoop benchmarks. The results demonstrate significant performance improvements compared to native YARN settings, with execution times 4.7 times faster than the worst_native and 1.9 times faster than the best_native scenarios. Furthermore, the proposed adaptiveConfig policy implementing the frugality index and a fetch_threshold outperforms the native YARN by 5.86 times and 1.79 times in Terasort and wordcount executions respectively. Our findings underscore the effectiveness of our approach in managing the heterogeneous nature of SBC clusters and optimizing performance across various hardware configurations. The adaptive policies prove well-suited to the frugal SBC-cluster context, yielding enhanced outcomes and paving the way for sustainable big data processing initiatives.

Preprint ARTICLE | doi:10.20944/preprints202404.0126.v1

A Fluid Dynamic Approach To Model And Optimize Energy Flows In Networked Systems

Massimo de Falco, Luigi Rarità, Alfredo Vaccaro

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: energy flows; optimization; simulation

Online: 2 April 2024 (08:27:43 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0141.v1

Navigating Uncertainty in High-Frequency Trading: A DIKWP Model Approach to Compliance and Strategy under the Financial Regulation

Kunguang Wu, Yucong Duan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: DIKWP model; uncertainty analysis; concept space; cognitive space; semantic space

Online: 2 April 2024 (07:21:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0146.v1

Bayesian Inference for Multiple Datasets

Renata Retkute, William Thurston, Christopher A. Gilligan

Subject: Computer Science And Mathematics, Probability And Statistics Keywords: parameter estimation; adaptive multiple importance sampling; effective sample size; wind direction; pest invasion

Online: 2 April 2024 (07:17:01 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0123.v1

Secure Key Exchange in Tropical Cryptography: Leveraging Efficiency with Advanced Block Matrix Protocols

Mariana Durcheva, Kiril Danilchenko

Subject: Computer Science And Mathematics, Security Systems Keywords: Key Exchange Protocol; Tropical Semiring; Block Matrices; Polynomial of matrices; Linde-de la Puente matrices

Online: 2 April 2024 (03:08:21 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0080.v1

Second Moment/Order Approximations by Kernel Smoothers with Application to Volatility Estimation

León Beleña Lamor, Ernesto Curbelo Benitez, Luca Martino, Valero Laparra Perez-Muelas

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Quantile regression; kernel smoothers; times series; heteroscedasticity; nearest neighbours

Online: 2 April 2024 (02:31:54 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0081.v1

Error Model of the Measurement Chain Containing the Discrete Wavelet Transform Algorithm

Marian Kampik, Jerzy Roj, Łukasz Dróżdż

Subject: Computer Science And Mathematics, Signal Processing Keywords: measurement chain error model; uncertainty estimation; discrete wavelet transform

Online: 2 April 2024 (02:27:20 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201908.0037.v12

Note for the P versus NP Problem

Frank Vega

Subject: Computer Science And Mathematics, Computer Science Keywords: Complexity classes; boolean formula; graph; completeness; polynomial time

Online: 1 April 2024 (17:14:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0037.v1

Research on Unmanned Vehicle Path Planning Based on Improved A and DWA Fusion Algorithm

Ruoming Wang, Ming Ling, Li Xu, Jiaping Shao

Subject: Computer Science And Mathematics, Robotics Keywords: Path planning; A* algorithm; Improved Dynamic Window Approach (DWA); Collision risk function; Search direction

Online: 1 April 2024 (17:05:16 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202404.0055.v1

Optimizing Lead Compounds: The Role of Artificial Intelligence in Drug Discovery

Sarfaraz K. Niazi, Zamara Mariam, Matthias Magoola

Subject: Computer Science And Mathematics, Mathematical And Computational Biology Keywords: Lead optimization; drug discovery; artificial intelligence; machine learning; deep neural networks; cheminformatics; chemical modifications; drug development

Online: 1 April 2024 (13:35:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0059.v1

Enhancing Emotion Detection with Sentiment Analysis Insights

Ethan Parker, Wyne Nasir, Olivia Benson

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: sentiment analysis; transfer learning; natural language processing

Online: 1 April 2024 (13:27:15 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0067.v1

Deep Reinforcement Learning for Optimizing Restricted Access Window in IEEE 802.11ah MAC Layer

Xiaojun Jiang, Shimin Gong, Chengyi Deng, Lanhua Li, Bo Gu

Subject: Computer Science And Mathematics, Computer Networks And Communications Keywords: IEEE 802.11ah; restricted access window (RAW); deep reinforcement learning (DRL)

Online: 1 April 2024 (12:21:24 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0038.v1

Weakly Supervised Semantic Segmentation of Point Cloud Scenes using Boundary-based Feature Aggregation

Yongwei Miao, Guoxiang Ren, Xudong Zhang, Haijian Liu, Fuchang Liu

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Point cloud; Semantic segmentation; Weakly supervised learning; Boundary feature aggregation; Data augmentation

Online: 1 April 2024 (11:12:43 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0009.v1

An Efficient Placement Approach of Visual Sensors Under Observation Redundancy and Communication Connectivity Constraints

Yves FAGA, Frantz TOSSA, Wahabou ABDOU, Julien DUBOIS

Subject: Computer Science And Mathematics, Other Keywords: Visual sensor networks; VSN deployment; multi-objective optimization; target coverage

Online: 1 April 2024 (10:59:16 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0006.v1

Machine Learning for Evaluating Hospital Mobility: An Italian Case Study

Vito Santamato, Caterina Tricase, Nicola Faccilongo, Massimo Iacoviello, Jenny Pange, Agostino Marengo

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Hospital Mobility; Machine Learning; Healthcare Quality Assessment

Online: 1 April 2024 (10:07:07 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0008.v1

An Automatic Near-Duplicate Video Data Cleaning Method Based on a Consistent Feature Hash Ring

Yi Qin, Ou Ye, Yan Fu

Subject: Computer Science And Mathematics, Analysis Keywords: Video cleaning; consistent feature hash ring; feature distance means; mountain peak function; multi-head attention mechanism; near-duplicate videos

Online: 1 April 2024 (09:49:59 CEST)

Show abstract| Download PDF| Share

In recent decades, with the ever-growing scale of video data, near-duplicate videos continue to emerge. Data quality issue caused by near-duplicate videos is becoming more and more prominent, which has affected the application of normal videos. Although current studies on near-duplicate video detection can be helpful to uncover data quality issues for videos, they still lack a process of automatic merging for the video data represented by high-dimensional features, which are difficult to automatically clean the near-duplicate videos to improve data quality for video datasets. At present, there are few studies on near-duplicate video data cleaning. The existing studies have the sensitive problems of video data orderliness and clustering initial center under a condition that prior distribution is unknown, which seriously affect the accuracy of near-duplicate video data cleaning. To address the above issues, an automatic near-duplicate video data cleaning method based on a consistent feature hash ring is proposed in this paper. First, a residual network with convolutional block attention modules, a long short-term memory deep network, and an attention model are integrated to construct an RCLA deep network with the multi-headed attention mechanism to extract spatiotemporal features of video data. Then, a consistent feature hash ring is constructed, which can effectively alleviate the sensitivity of video data orderliness while providing a condition of near-duplicate video merging. To reduce the sensitivity of the initial cluster centers to results of near-duplicate video cleansing, an optimized feature distance-means clustering algorithm is constructed by utilizing a mountain peak function on a consistent feature hash ring, which can implement automatic cleaning of near-duplicate video data. Finally, experiments are conducted based on a commonly used dataset named CC_WEB_VIDEO and a coal mining video dataset. Compared with some existing works, simulation results demonstrate that the performance of the proposed method.

Preprint ARTICLE | doi:10.20944/preprints202403.1833.v1

ResECA-Unet: Enhancement of GI Tract Segmentation Using an Improved U-Net Framework

SM Nuruzzaman Nobel, Omar Faruque Sifat, MD Rajibul Islam, MD Shohel Sayeed, Md Amiruzzaman

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: U-Net; Deep learning; Transfer learning; ECA-Net; Computer vision; GI tract; Segmentation; Radiation therapy

Online: 29 March 2024 (13:51:41 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202310.0773.v16

Resolving the Collatz Conjecture: A Rigorous Proof through Inverse Discrete Dynamical Systems and Algebraic Inverse Trees

Eduardo Diedrich

Subject: Computer Science And Mathematics, Mathematics Keywords: discrete dynamical systems; inverse modeling; topological equivalence; topological transport; algebraic trees; collatz conjecture; homeomorphic invariance

Online: 29 March 2024 (11:23:27 CET)

Show abstract| Download PDF| Share

Preprint DATA DESCRIPTOR | doi:10.20944/preprints202403.1848.v1

Improving Code Smell Detection Using Deep Stacked Autoencoder

Kadem K. Rehef, Ahmed S. Abbas

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: machine learning; deep learning; stack auto encoder; code smell detection; auto encoder.

Online: 29 March 2024 (10:41:57 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1831.v1

A Dynamic Programming Approach to Collision Avoidance of Autonomous Ships

Raphael Zaccone

Subject: Computer Science And Mathematics, Data Structures, Algorithms And Complexity Keywords: Dynamic Programming; Autonomous Ship; Path Planning; Collision Avoidance; Optimization.

Online: 29 March 2024 (10:08:51 CET)

Show abstract| Download PDF| Share

Preprint TECHNICAL NOTE | doi:10.20944/preprints202403.1807.v1

Generalized Definition of the Derivative

Mehmet Pakdemirli

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Limit Definition; Derivative; Error Analysis; Scaling Transformations; Translational Transformations

Online: 29 March 2024 (09:56:14 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1802.v1

Aging Renewal Point Processes and Exchangeability of Event Times

Fabio Vanni, David Lambert

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: renewal processes; exchangeability; statistical aging; survival analysis; high frequency exchange rates

Online: 29 March 2024 (07:41:00 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1747.v1

Crossing Point Estimation in Human/Robot Navigation - Statistical Linearization versus Sigma-Point-Transformation

Rainer Heinrich Palm, Achim J. Lilienthal

Subject: Computer Science And Mathematics, Robotics Keywords: Human-Robot interaction; Gaussian noise; sigma-point transformation; Unscented Kalman Filter

Online: 28 March 2024 (15:26:29 CET)

Show abstract| Download PDF| Supplementary Files| Share

Preprint REVIEW | doi:10.20944/preprints202403.1758.v1

A Comprehensive Survey on Investigation of Machine Learning-Powered Augmented Reality Applications in Education

Haseeb Ali Khan, Sonain Jamil, Md. Jalil Piran, Oh-Jin Kwon, Jong Weon Lee

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Augmented Reality (AR); Machine Learning (ML); Support Vector Machine (SVM); Convolutional Neural Network (CNN); Education

Online: 28 March 2024 (13:37:47 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1771.v1

Balancing Speed and Precision: Lightweight and Accurate Depth Estimation for Light Field Image

Ryutaro Miya, Tatsuya Kawaguchi, Takushi Saito

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: light field; depth estimation; knowledge distillation; lightweight

Online: 28 March 2024 (12:54:44 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1718.v1

Prime Factorization and Diophantine Quintic Equations Insights, Challenges, and New Directions

Budee U Zaman

Subject: Computer Science And Mathematics, Algebra And Number Theory Keywords: algebraic methods,quintic problem,Diophantine equation ,prime number

Online: 28 March 2024 (09:35:31 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1719.v1

Structure and Constraints for a Knowledge Architecture

Riccardo Gatti

Subject: Computer Science And Mathematics, Logic Keywords: Knowledge, information, axiomatic system, informatics, computer science

Online: 28 March 2024 (09:29:26 CET)

Show abstract| Download PDF| Supplementary Files| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1708.v1

Network Medicine-Based Approach Reveals Cyclosporine and Selinexor Drug Combination as an Effective Therapy against SARS-COV-2

AKM Azad

Subject: Computer Science And Mathematics, Mathematical And Computational Biology Keywords: Cyclosporine; Selinexor; Drug Combination; Network Medicine; SARS-COV-2; Functional Enrichment; Drug Target

Online: 28 March 2024 (08:38:26 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202402.0657.v2

A Neural-Network-Based Watermarking Method Approximating JPEG Quantization

Shingo Yamauchi, Masaki Kawamura

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Watermarking method; Neural network; Activation function; JPEG compression

Online: 28 March 2024 (08:30:32 CET)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202403.1695.v1

Smart-Sensing Chairs for Sitting Posture Detection, Classification and Monitoring: A Comprehensive Review

David Odesola, Janusz Kulon, Shiny Verghese, Adam Partlow, Colin Gibson

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: smart sensing chair; musculoskeletal disorders; sitting posture classification

Online: 28 March 2024 (08:29:10 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1724.v1

Cost Effectiveness Analysis of Optimal Rabies Control Strategies

Demsis Dejene Hailemichael, Geremew Kenassa Edessa, Purnachandra Rao Koya

Subject: Computer Science And Mathematics, Mathematical And Computational Biology Keywords: Rabies; sensitivity analysis; Objective Functional; cost-effectiveness; ICER

Online: 28 March 2024 (06:56:39 CET)

Show abstract| Download PDF| Share

A mathematical model that incorporates human attacks on dogs is presented to explore the dynamics of rabies transmission. The model divided the infection rate into two categories: dog-to-dog transmission rates during the prodromal phase (βdP) and the furious phase (βdF). It has been determined that the model is well-posed and that all of the solutions are positive, as well as the feasibility and positivity of the model's solutions. Both the basic reproduction number (R0) and the effective reproductive number (Re) are computed, and it is demonstrated that the model has a unique disease-free equilibrium that is globally asymptotically stable whenever Re < 1. To identify the model's most sensitive parameters and the ones that intervention efforts should focus on, sensitivity analysis of the effective reproduction number is carried out. We can construct an optimal control system using the state equations, the adjoint equations, and the optimality condition that determines the controls by applying Pontryagin's Maximum/Minimum principle. To help decision-makers in allocating funds for rabies interventions, cost-effectiveness analyses are conducted. To determine the degree to which the intervention strategies are advantageous and cost-effective, this study performs a cost-effective analysis of one or all possible combinations of the optimal rabies control strategies (pre-exposed and post-exposed vaccination for both dog and human populations) for the four different transmission settings. After arranging the techniques to increase effectiveness (total infections prevented), a cost-effective analysis using the Incremental Cost Effectiveness Ratio (ICER) was conducted. The result supports the function that the four intervention options are performing to either completely eradicate or significantly reduce rabies disease among the populations. The dynamical behavior of the system is studied through simulations using the ode45 numerical technique from MATLAB.

Preprint ARTICLE | doi:10.20944/preprints202403.1726.v1

Jordan-Type Inequalities and Stratification

Miloš Mićović, Branko Malešević

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: Jordan’ s inequality; stratified families of functions; a minimax approximant; upper and lower bounds of the sinc function; approximations of the sinc function

Online: 28 March 2024 (05:03:41 CET)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202403.1610.v1

Transforming African Healthcare with AI: Paving the Way for Improved Health Outcomes

ANGYIBA ANDIGEMA, NGNOTOUOM NGNOKAM Tania Cyrielle, MAFO KAMGA Lethicia Danaëlle, EWANE Ekwelle

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: African Healthcare; Artificial Intelligence; Health Outcomes; Resource Constraints; Collaboration; Innovation

Online: 27 March 2024 (16:07:28 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1680.v1

Existence and Nonexistence of Positive Solutions for Semilinear Elliptic Equations Involving Hardy-Sobolev Critical Exponents

Lin-Lin Wang, Yong-Hong Fan

Subject: Computer Science And Mathematics, Mathematics Keywords: semilinear elliptic equation; Hardy-Sobolev critical exponents; Mountain Pass Lemma; (PS)c condition

Online: 27 March 2024 (15:07:38 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1670.v1

PatchFusion: Patch-based Nonrigid Tracking and Reconstruction of Deformable Objects using a Single RGB-D Sensor

Mingyuan Zhao, Xuexin Yu, Long Xu

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: nonrigid tracking; deformable objects; RGB-D sensor; deformation optimization

Online: 27 March 2024 (14:11:39 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1687.v1

Existences Results for Some Nonsingular $p$-Kirchhoff Problems with $\psi$-Hilfer Fractional Derivative

Hadeel Z. Alzumi, Wafa Shammakh, Abdeljabbar Ghanmi

Subject: Computer Science And Mathematics, Mathematics Keywords: Fractional calculus; Variational methods; $\psi$-Hilfer operators, Existence of solution.

Online: 27 March 2024 (13:38:19 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1684.v1

How Does ChatGPT Perform on the Italian National Residency Program Admission Test?

Gianmaria Barone, Filippo Confalonieri, Alessandro Gaeta, Vanessa Ferraro, Paolo Vinciguerra, Alessandra Di Maria

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: ChatGPT; Chat Generative Pre-trained Transformer; GPT-3.5; GPT-4; artificial intelligence (AI); chatbot; natural language processing (NLP); medical education; Italian National Residency Program Admission Test; Scuole di Specializzazione in Medicina (SSM)

Online: 27 March 2024 (13:20:49 CET)

Show abstract| Download PDF| Share

Background: Open AI developed ChatGPT, a language model based on the GPT architecture, designed for text-based communication. Trained on diverse internet texts, ChatGPT generates contextually appropriate responses using machine learning. It understands input through analysis and context interpretation, generating coherent and contextually relevant responses. Interaction is possible through messaging platforms. Materials and Methods: In November 2023, we utilized ChatGPT 3.5, the default version at that time, to answer questions from the Italian National Residency Program Admission Tests (SSMs) of 2021, 2022, and 2023. The questions cover clinical, diagnostic, analytical, therapeutic, and epidemiological scenarios, sometimes accompanied by images. The study compared ChatGPT's answers to the official corrections on the Italian Ministry of University and Research (MUR) website. The scoring method used for evaluation was 1 point for correct answers, 0 points for unanswered questions, and -0.25 points for incorrect answers, reflecting the SSM test scoring system. Results: In summary, ChatGPT was tested with a total of 420 questions, 140 for each test. It achieved an overall accuracy of 80.48%, providing correct answers for 338 questions and incorrect answers for 82 questions. When faced with questions containing both text and images, it answered 55% correctly and 45% incorrectly. The model's performance varied over time, with an 82.14% accuracy rate in 2021 and 2022 (115 correct out of 140) and a 77.14% accuracy rate in 2023 (108 correct out of 140). Applying thisscoring method to the SSM test, ChatGPT would have scored 105 points in 2021 and 2022, and 100 points in 2023. Conclusions: ChatGPT has exhibited above-average performance in the last three SSM tests, highlighting its robust capability to interpret clinical scenarios and offer precise diagnostic and therapeutic guidance. Despite this, some limitations persist, notably the software's inability to interpret non-textual information.

Preprint REVIEW | doi:10.20944/preprints202403.1679.v1

Transforming Healthcare in Africa: The Role of Artificial Intelligence in Combatting Infectious Diseases, Neglected Tropical Diseases, and Antimicrobial Resistance

ANGYIBA ANDIGEMA, NGNOTOUOM NGNOKAM Tania Cyrielle, NDJIE Daniel Laetitia, EWANE Ekwelle

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Healthcare; Infectious Disease; Surveillance; Neglected Tropical Diseases (NTDs); Antimicrobial Resistance.

Online: 27 March 2024 (11:58:01 CET)

Show abstract| Download PDF| Share

This review article focuses on the role of Artificial Intelligence (AI) in transforming healthcare in Africa, specifically in combatting infectious diseases, neglected tropical diseases (NTDs), and antimicrobial resistance. We provide a comprehensive overview of the significance of AI in the healthcare industry, highlighting its urgency and importance in addressing these specific health challenges in Africa. We begin by discussing the role of AI in infectious disease surveillance and outbreak detection. We explore how AI technology can be employed for real-time tracking and prediction of outbreaks, providing examples of successful AI applications in infectious disease surveillance within the African context.Next, we examine the potential of AI-enabled diagnosis and treatment for faster and more accurate diagnoses of infectious diseases and NTDs. We highlight specific examples of AI applications in diagnosing and treating these diseases in Africa, showcasing the potential of AI to improve clinical outcomes and save lives.Furthermore, we focus on how AI-driven drug discovery and development can expedite the search for new treatments for infectious diseases and combat antimicrobial resistance. We present examples of AI applications in drug discovery within the African context, illustrating the potential for AI to revolutionize the development of effective therapeutics.In addition, we delve into how AI-powered public health interventions can enhance the design and implementation of targeted interventions. We explore how AI can optimize resource allocation and facilitate data-driven decision-making processes, providing examples of AI applications in public health in Africa.Finally, we address the challenges and limitations of implementing AI in combatting infectious diseases, NTDs, and antimicrobial resistance in Africa. We discuss potential barriers and ethical concerns surrounding AI applications in healthcare, aiming to encourage informed and responsible utilization of AI technologies.Overall, this review emphasizes the importance and potential of AI in combatting infectious diseases, NTDs, and antimicrobial resistance in Africa. It positions AI as a catalyst for revolutionizing healthcare in the region, leading to more effective disease surveillance, diagnosis, treatment, drug discovery, and public health interventions.

Preprint ARTICLE | doi:10.20944/preprints202403.1677.v1

Hybridized Encoder Decoder based LSTM and GRU Architectures for Stocks and Cryptocurrency Prediction

Joy Dip Das, Ruppa K. Thulasiram, Aerambamoorthy Thavaneswaran

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Autoencoder, LSTM, GRU, hybridization, AE-LSTM, AE-GRU, Stocks, Stock Index, Cryptocurrency

Online: 27 March 2024 (11:55:20 CET)

Show abstract| Download PDF| Share

Preprint CONCEPT PAPER | doi:10.20944/preprints202307.0560.v20

Meaningfully Averaging Unbounded Functions

Bharath Krishnan

Subject: Computer Science And Mathematics, Analysis Keywords: expected value; hausdorff measure; (Exact) dimension function; function space; prevalent and shy sets; entropy; choice function

Online: 27 March 2024 (09:10:36 CET)

Show abstract| Download PDF| Share

In this paper we want meanignfully average an "infinite collection of objects covering an infinite expanse of space". For any n∈ ℕ, set A⊆ℝⁿ and set B⊆ℝ where (A,P) is a Polish space, we illustrate this quote with an everywhere, surjective function f∶A→B. The problem is no meaningful expected value of f (e.g., w.r.t the Lebesgue or Hausodorff measure) on Borel sets has a finite value, since the graph of f in any n-dim. interval which covers a subset of A×B has countably infinite points. (The Hausdorff measure of countably infinite points is +∞, where the expected value of f is undefined due to division by infinity.) To fix this, we need the most generalized and "meaningful" expected value; however, consider the following issue. Suppose for n∈ ℕ, set A⊆ℝⁿ and function f∶A→ℝⁿ. If set A is Borel; B* is the set of all Borel measurable function in ℝᴬ for all A⊆ℝⁿ, and B** is the set of all f∈B* with a finite-valued expected value—w.r.t the Hausdorff measure—then B** is a shy subset of B*. Hence a "positive measure" of Borel measurable functions needs to have a finite expected value to increase the chance that everywhere, surjective f:A→B has a finite expectation. To fix this issues, we wish to find a unique and "natural" extension of the expected value—w.r.t the Hausdorff measure—on bounded functions to unbounded/bounded f, which takes finite values only, so B** is a non-shy subset of B*. Note, we haven't found evidence suggesting mathematicians have thought of this problem; however, it's assumed, in general, there's no meaningful way of averaging functions which cover an infinite expanse of space. Note, we haven’t found evidence suggesting mathematicians thought of this problem; however, it’s assumed, in general, there’s no meaningful way of averaging functions which cover an infinite expanse of space. Regardless, we’ll choose a sequence of bounded functions using a "choice function". Note, we find the "choice function" using a question with criteria in §2.4. Also, in §3 and §4, we attempt to answer this question that should "choose" a sequence of bounded functions that a) meaningfully averages everywhere, surjective functions and b) obtains a finite average from a "positive measure" of Borel measurable functions.

Preprint ARTICLE | doi:10.20944/preprints202403.1629.v1

CCA-Transformer: Cascaded Cross-Attention Based Transformer for Facial Analysis in Multi-modal Data

Jun-Hwa Kim, Namho Kim, Minsoo Hong, Cheesun Won

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: face analysis; expression; valence-arousal; action unit

Online: 27 March 2024 (06:11:04 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1635.v1

On Feature Selection Techniques for Detecting DoS Attacks with a Multi-class Classifier

Iuri A. Mundstock, Yuri Santo, Thiago L. T. da Silveira, Roger Immich, André Riker, Bruno L. Dalmazo

Subject: Computer Science And Mathematics, Computer Networks And Communications Keywords: Network Security; Feature Selection; Denial of Service Attacks; Systematic Review; Smart City; Anomaly Detection

Online: 27 March 2024 (00:16:15 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1611.v1

A Formal Model for Reliable Data Acquisition and Control in Legacy Critical Infrastructures

Jose Miguel Blanco, Jose M. Del Alamo, Juan C. Dueñas, Felix Cuadrado

Subject: Computer Science And Mathematics, Information Systems Keywords: Critical Infrastructure; Water Distribution Network; Formal Model; Digital Transformation; Data Management; Data Security; Data Acquisition

Online: 26 March 2024 (14:35:30 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1514.v1

Application Weighted Physics-Informed Neural Networks to High-Pressure Gas Flows Simulation in Pipelines

Sultan Alpar, Rinat Faizulin, Fatima Tokmukhamedova, Yevgeniya Daineko

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: physics-informed neural networks; artificial neural networks; CFD; gas flow; Euler equation

Online: 26 March 2024 (13:08:27 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1548.v1

Optimizing Attribute Reduction in Multi-granularity Data through a Hybrid Supervised-Unsupervised Model

Zeyuan Fan, Jianjun Chen, Hongyang Cui, Jingjing Song, Taihua Xu

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: rough sets; attribute reduction; multi-granularity; information gain

Online: 26 March 2024 (13:05:00 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1560.v1

A Blockchain-Based Fish Supply Chain Framework for Maintaining Fish Quality and Authenticity

Shereen Ismail, Muhammad Nouman, Hassan Reza, Fartash Vasefi, Hossein Kashani Zadeh

Subject: Computer Science And Mathematics, Security Systems Keywords: fish supply chain; blockchain; ethereum; smart contract; artificial intelligence; internet of things; traceability; fish quality; authenticity; QAT technology

Online: 26 March 2024 (13:03:18 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1598.v1

The Elba Curves

Elkhan B Beylarov, Ilyas R Hasanov

Subject: Computer Science And Mathematics, Mathematics Keywords: Fermat's last theorem; circle; ellipse; triangle; n-degree curves; equations

Online: 26 March 2024 (12:27:57 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1535.v1

The General Solution to a Classical Matrix Equation AXB=C over the Dual Split Quaternion Algebra

Kai-Wen Si, Qing-Wen Wang

Subject: Computer Science And Mathematics, Mathematics Keywords: dual split quaternion; real representation; matrix equation; general solution

Online: 26 March 2024 (11:51:23 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202310.0773.v15

Resolving the Collatz Conjecture: A Rigorous Proof through Inverse Discrete Dynamical Systems and Algebraic Inverse Trees

Eduardo Diedrich

Subject: Computer Science And Mathematics, Mathematics Keywords: discrete dynamical systems; inverse modeling; topological equivalence; topological transport; algebraic trees; collatz conjecture; homeomorphic invariance

Online: 26 March 2024 (11:50:16 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1520.v1

Using Optical Sensor Applied to Rapid Soil Test Kit for NH4+ and NO3- in Soil

Chawaroj Jaisin, Suphathida Aumtong, Charkit Chotamonsak

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: soil; optical sensor; NH4+; NO3-

Online: 26 March 2024 (11:48:09 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1569.v1

Highly-Sensitive Measure of Complexity Captures Boolean Networks Regimes and Temporal Order More Optimally

Manuel de J. Luevano, Alejandro Puga

Subject: Computer Science And Mathematics, Computer Science Keywords: Random boolean ; networks; ; entropy; ; algorithmic ; complexity; compressibility

Online: 26 March 2024 (10:07:13 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1568.v1

Optimizing Classroom Resource Allocation Using a Modified Salp Swarm Algorithm

Aya Fujii, Hiroshi Tanaka, Yoko Suzuki, Kenji Sato, Ayumi Yamamoto

Subject: Computer Science And Mathematics, Data Structures, Algorithms And Complexity Keywords: classroom resource allocation; modified salp swarm algorithm; optimization; cloud computing

Online: 26 March 2024 (09:45:00 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1554.v1

Computation of The Mann-Whitney Effect under Parametric Survival Copula Models

Kosuke Nakazono, Yu-Cheng Lin, Gen-Yih Liao, Ryuji Uozumi, Takeshi Emura

Subject: Computer Science And Mathematics, Probability And Statistics Keywords: censoring; copula; Hand’s paradox; potential outcome; Mann-Whitney effect; stress-strength model; two-sample comparison; survival analysis; survival function; treatment effect

Online: 26 March 2024 (09:41:01 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1551.v1

Exploring the Impact of Deep Learning Activities in the Mathematics Classroom on Students’ Academic Performance: A Comprehensive Study

Enoch Suglo

Subject: Computer Science And Mathematics, Mathematics Keywords: Deep learning; academic performance; mathematics

Online: 26 March 2024 (08:23:38 CET)

Show abstract| Download PDF| Share

Preprint CONCEPT PAPER | doi:10.20944/preprints202307.0560.v19

Meaningfully Averaging Unbounded Functions

Bharath Krishnan

Subject: Computer Science And Mathematics, Analysis Keywords: expected value; hausdorff measure; (Exact) dimension function; function space; prevalent and shy sets; entropy; choice function

Online: 26 March 2024 (08:22:18 CET)

Show abstract| Download PDF| Share

In this paper we want meanignfully average an "infinite collection of objects covering an infinite expanse of space". We illustrate this quote with an explicit n-dimensional function, where the graph of the function is dense in ℝ^(n+1). The problem is non meaningful expected value of the function (e.g., w.r.t the Lebesgue or Hausodorff measure) has a finite value. In fact "almost no" Borel measurable functions have a finite and meaningful value. In rigorous terms, suppose for n∈ ℕ, set A⊆ℝⁿ and function f∶A→ℝⁿ. If set A is Borel; B* is the set of all Borel measurable function in ℝᴬ for all A⊆ℝⁿ, and B** is the set of all f∈B* with a finite expected value—w.r.t the Hausdorff measure—then B** is a shy subset of B*. To fix these issues, we wish to find a unique and "natural" extension of the expected value—w.r.t the Hausdorff measure—on bounded functions to unbounded/bounded f, which takes finite values only, so B** is a non-shy subset of B*. Note we haven't found evidence suggesting mathematicians have thought of this problem; however, it's assumed, in general, there's no meaningful way of averaging functions which cover an infinite expanse of space. Regardless, we'll attempt to solve the problem by defining a choice function—this shall choose a unique set of equivalent sequences of sets (Fₖ***) , where the set-theoretic limit of Fₖ*** is the graph of f; the measure Hʰ is the ℎ-Hausdorff measure, such for each k∈ℕ, 0 < Hʰ(Fₖ***) < +∞; and (fₖ*) is a sequence of functions where {(x₁,...,xₙ,fₖ*(x₁,...,xₙ))∶x∈ dom(Fₖ***)}=Fₖ***. Thus, if (Fₖ***) converges to A at a rate linear or super-linear to the rate non-equivelant sequences of sets converge, and the extended expected value of or E**[f,Fₖ***] in the eq. below: ∀(ε>0)∃(N∈ℕ)∀(k∈N)(k≥N⇒1/Hʰ(dom(Fₖ***))∫dom(Fₖ*** )fₖ* dHʰ - E**[f,Fₖ***]<ε ) exists, then E**[f,Fₖ***] is a unique and "natural" extension of the original expected value on bounded f, so B**—the set of all f∈B* with a finite E**[f,Fₖ***]—is a non-shy set in B*. Note we guessed the choice function using computer programming we redefine linear and super-linear convergence in terms of partitions of

Preprint ARTICLE | doi:10.20944/preprints202403.1490.v1

SVM Dynamic Selection of Voting Rule for Cooperative Spectrum Sensing in CUAVNs

Chongyu Yu, Jin Shen, Jun Wu, Ruiyi Zheng, Mingkun Su, Lei Qiao, Jipeng Gan, and Weiwei Cao

Subject: Computer Science And Mathematics, Signal Processing Keywords: Unmanned aerial vehicle; cooperative spectrum sensing; voting rule; support vector machine; dynamic selection

Online: 26 March 2024 (08:18:22 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1497.v1

Ethnic Representation Matters: Investigating Bias in Facial Age Prediction Models

Nenad Panić, Marina Marjanović, Timea Bezdan

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Facial recognition; Age prediction; Convolutional Neural Network (CNN); Ethnicity bias

Online: 26 March 2024 (08:15:07 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1550.v1

Cultural Heritage and Virtual Reality: A Setup for Balzi Rossi Museum

Saverio Iacono, Matteo Scaramuzzino, Luca Martini, Chiara Panelli, Daniele Zolezzi, Massimo Perotti, Antonella Traverso, Gianni Vercelli

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Virtual reality; Cultural Heritage; 3D Reconstruction

Online: 26 March 2024 (07:27:47 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1533.v1

Escaping Stagnation through Improved Orca Predator Algorithm with Deep Reinforcement Learning for Feature Selection

Rodrigo Olivares, Camilo Ravelo, Ricardo Soto, Broderick Crawford

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: biomimetic orca predator algorithm; deep reinforcement learning; feature selection

Online: 26 March 2024 (07:27:45 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1544.v1

Problem of Heliostat Field Efficiency Calculation Based on Innovative Monte Carlo Simulation

Tengda Xu, Junliang Wu, Tengwei Yang, Jiajia Qin

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: heliostat field; Monte Carlo simulation; light tracing; optimal design

Online: 26 March 2024 (06:31:18 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1498.v1

The Clique Width of Two Classes of Series-Parallel Digraphs

Ruzayn Quaddoura

Subject: Computer Science And Mathematics, Discrete Mathematics And Combinatorics Keywords: Series parallel digraphs; Clique-width; Complexity

Online: 26 March 2024 (03:16:55 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1310.v1

An Improved Deadlock Detection and Resolution Algorithm for Distributed Computing Systems

Tarek Helmy

Subject: Computer Science And Mathematics, Computer Science Keywords: Distributed Computing Systems; Deadlock Detection

Online: 26 March 2024 (03:12:27 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1316.v1

Weighing the Pros and Cons of Newton’s Sum in Quadratic Root Function Computations Analysis

Peter Chew

Subject: Computer Science And Mathematics, Mathematics Keywords: Newton's Sum; Quadratic; ; Root; Function; Computations ;

Online: 26 March 2024 (02:48:26 CET)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202403.1467.v1

Blockchain and Distributed Systems: Basic Concepts and Implications

Mauricio Witter, Antonio Rodrigo De Vit

Subject: Computer Science And Mathematics, Computer Networks And Communications Keywords: Blockchain; Peer-to-Peer; RPC; Overlay Network

Online: 26 March 2024 (01:26:07 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1489.v1

Exploiting Signal Propagation Delays to match Task Memory Requirements in Reservoir Computing

Stefan Iacob, Joni Dambre

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: distance-based delays; inter-neuron delays; echo state networks; recurrent neural networks; reservoir computing; memory capacity

Online: 25 March 2024 (15:04:44 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1484.v1

Integrated Neuro-Symbolic Analysis Pipeline for Cerebral Aneurysm Rupture Diagnosis

Max Xiao

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Neuro-symbolic; Deep learning; Data fusion; 3D segmentation; Intracranial Aneurysms; MRA; Model Pipeline

Online: 25 March 2024 (12:50:51 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1479.v1

Applied Category Theory in the Wolfram Language using Categorica I: Diagrams, Functors and Fibrations

Jonathan Gorard

Subject: Computer Science And Mathematics, Computational Mathematics Keywords: Applied category theory; monoidal categories; Mathematica

Online: 25 March 2024 (11:40:52 CET)

Show abstract| Download PDF| Share

This article serves as a preliminary introduction to the design of a new, open-source applied and computational category theory framework, named Categorica, built on top of the Wolfram Language. Categorica allows one to configure and manipulate abstract quivers, categories, groupoids, diagrams, functors and natural transformations, and to perform a vast array of automated abstract algebraic computations using (arbitrary combinations of) the above structures; to manipulate and abstractly reason about arbitrary universal properties, including products, coproducts, pullbacks, pushouts, limits and colimits; and to manipulate, visualize and compute with strict (symmetric) monoidal categories, including full support for automated string diagram rewriting and diagrammatic theorem-proving. In so doing, Categorica combines the capabilities of an abstract computer algebra framework (thus allowing one to compute directly with epimorphisms, monomorphisms, retractions, sections, spans, cospans, fibrations, etc.) with those of a powerful automated theorem-proving system (thus allowing one to convert universal properties and other abstract constructions into (higher-order) equational logic statements that can be reasoned about and proved using standard automated theorem-proving methods, as well as to prove category-theoretic statements directly using purely diagrammatic methods). Internally, Categorica relies upon state-of-the-art graph and hypergraph rewriting algorithms for its automated reasoning capabilities, and is able to convert seamlessly between diagrammatic/combinatorial reasoning on labeled graph representations and symbolic/abstract reasoning on underlying algebraic representations of all category-theoretic concepts. In this first of two articles introducing the design of the framework, we shall focus principally upon its handling of quivers, categories, diagrams, groupoids, functors and natural transformations, including demonstrations of both its algebraic manipulation and theorem-proving capabilities in each case.

Preprint ARTICLE | doi:10.20944/preprints202302.0051.v63

Duality Principles and Numerical Procedures for a Large Class of Non-convex Models in the Calculus of Variations

Fabio Silva Botelho

Subject: Computer Science And Mathematics, Applied Mathematics Keywords: duality theory; non-convex analysis; numerical method for a non-smooth model

Online: 25 March 2024 (11:21:37 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1461.v1

On δP-approximation Spaces

Faik Mayah, Huda Mohsin

Subject: Computer Science And Mathematics, Mathematics Keywords: Rough sets; Upper and lower approximations; P-open sets; δ P-open sets

Online: 25 March 2024 (11:15:54 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1433.v1

A Simple Machine Learning-Based Quantitative Structure-Activity Relationship Model for Predicting pIC50 Inhibition Values of FLT3 Tyrosine Kinase

Jackson J. Alcázar, Ignacio Sánchez, Cristian Merino, Bruno Monasterio, Gaspar Sajuria, Diego Miranda, Felipe Díaz, Paola R. Campodónico

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: FLT3 Inhibitors; Ligand-based Drug Design; Computer-Aided Drug Design; QSAR Modeling; AML Treatment

Online: 25 March 2024 (08:47:40 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1432.v1

Empowering Community Clinical Triage through Innovative Data-Driven Machine Learning

Binu M. Suresh, Nitsa J. Herzog

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: clinical triaging; machine learning; community health care triaging; prediction; classification; artificial intelligence

Online: 25 March 2024 (08:47:31 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202401.0227.v21

Collatz Conjecture

Asset Durmagambetov, Aniyar Durmagambetova

Subject: Computer Science And Mathematics, Analysis Keywords: binary representation; Collatz conjecture

Online: 25 March 2024 (08:12:10 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1386.v1

A Nonlinear ODE Model for a Consumeristic Society

Marino Badiale, Isabella Cravero

Subject: Computer Science And Mathematics, Mathematics Keywords: Human and nature dynamics; ODE systems for society dynamics; Ecological- Economic Modeling

Online: 22 March 2024 (14:44:07 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1364.v1

Enhancing Sentiment Analysis with Term Sentiment Entropy: Capturing Nuanced Sentiment in Text Classification

Suttipong Klongdee, Jatsada Singthongchai

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: sentiment analysis; term weighting; text classification; TF-IDF; TFRF; natural language processing

Online: 22 March 2024 (14:35:34 CET)

Show abstract| Download PDF| Share

Preprint COMMUNICATION | doi:10.20944/preprints202403.1354.v1

Analyzing the Energy Consumption of Smart Home and Price Prediction

Milka Kutseva

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: internet of things; smart home; machine learning; consumption prediction

Online: 22 March 2024 (11:21:11 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202403.1349.v1

Parkinson's Disease Recognition using Decorrelated Convolutional Neural Networks: Addressing Imbalance and Scanner Bias in rs-fMRI Data

Pranita Patil, W. Randolph Ford

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Class bias; DcCNN; decorrelation; deep learning; FE-DcCNN; invariant features; Parkinson’s disease; rs-fMRI image; scanner bias

Online: 22 March 2024 (09:21:12 CET)

Show abstract| Download PDF| Share

Parkinson’s Disease (PD) is a neurodegenerative and progressive disease that impacts the nerve cells in the brain and varies from person to person. The exact cause of PD is still unknown, and the diagnosis of PD does not include a specific objective test with certainty. Although deep learning has made great progress in medical neuroimaging analysis, these methods are very susceptible to biases present in neuroimaging datasets. An innovative decorrelated deep learning technique is introduced to mitigate class bias and scanner bias while simultaneously focusing on finding distinguishing characteristics in resting-state functional MRI (rs-fMRI) data, which assist in recognizing the PD with good accuracy. The decorrelation function reduces the non-linear correlation between features and bias in order to learn bias-invariant features. The Parkinson’s Progression Markers Initiative (PPMI) dataset, referred to as a single scanner imbalanced dataset in this study used to validate our method. The imbalanced dataset problem affects the performance of the deep learning framework by overfitting to the majority class. To resolve this problem, we propose a new Decorrelated Convolutional Neural Networks (DcCNN) framework by applying decorrelation-based optimization to Convolutional Neural Networks(CNN). An analysis of evaluation metrics comparisons shows that integrating the decorrelation function boosts the performance of PD recognition by removing class bias. Specifically, our DcCNN model performs significantly better than existing traditional approaches to tackle the imbalance problem. Finally, the same framework can be extended to create scanner invariant features without significantly impacting the performance of a model. The obtained dataset is a multi-scanner dataset which leads to scanner bias due to the differences in acquisition protocols and scanners. The multi-scanner dataset is a combination of two datasets, namely PPMI and FTLDNI - frontotemporal lobar degeneration neuroimaging initiative (NIFD) dataset. The results of t-distributed stochastic neighbor embedding (t-SNE) and scanner classification accuracy of our proposed Feature Extraction-DcCNN (FE-DcCNN) model validated the effective removal of scanner bias. Our method achieves an average accuracy of 77.80% on a multi-scanner dataset for differentiating PD from healthy control, which is superior to the DcCNN model trained on a single scanner imbalanced dataset.

Preprint ARTICLE | doi:10.20944/preprints202403.1357.v1

Towards A Distributed Digital Twin Framework for Predictive Maintenance in Manufacturing Systems

Ibrahim Abdullahi, Stefano Longo, Mohammad Samie

Subject: Computer Science And Mathematics, Computer Science Keywords: Digital Twins; Predictive Maintenance; Wind Turbines; Fog Computing; Machine Learning; Internet of Things

Online: 22 March 2024 (09:21:10 CET)

Show abstract| Download PDF| Share

Computer Science and Mathematics