BBC Russian

Preprint ARTICLE | doi:10.20944/preprints202409.1433.v1

Feature Coding and Graph via Transformer: Different Granularities Classification for Aircrafts

Jianghao Rao, Senlin Qin, Zongyan An, Jianlin Zhang, Qiliang Bao, Zhenming Peng

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: fine-grained; aircraft recognition; label divisions; swin-transformer

Online: 20 September 2024 (03:47:37 CEST)

Show abstract| Download PDF| Share

Against the background of the sky, imaging and perception of aircraft are cru- cial. Among these, the location of aircrafts is not a very difficult problem in general, because that deep learning algorithms and object detection models based on convolutional neural network(CNN) are ever-evolving. In order to have a better identification of various aircrafts, or to accurately locate different types of flying targets in the sky, it becomes significant to distinguish and recognize different types of aircrafts. One question is that, distinguishing and recognizing between sub-categories of aircrafts pose great challenges. Although fine-grained recognition focuses on exploring and studying such problems, aircrafts under different sub-categories and granularities lead us to rethink the application of features. We noticed that features in swin-transformer demonstrates the under- standing and processing of images, fully showcasing the encoding and indexing of information. Through this research and proposed approach, we discovered a better understanding of features encoding and use, which are inspired by the feature encoding and computation in swin-transformer. In our paper, our ap- proach has achieved effects on features encoded graphically, manifested from the architecture design and convolutional neural network computation, and outper- forms other famous fine-graiend classification models on this issue. Not only approach we proposed has demonstrated superior performance in fine-grained aicraft classification, but also the mechanisms of the feature encoding under different sample space partitions is revealed for this issue, which provides a re- search for the representation of aircraft fineness characteristics. The relationship between representation orientation of aircraft feature information under various grained divisions, shows that the recognition of different categories according to man-made, such as aircraft, can be achieved by means of the feature represen- tations studied in this paper, for more specific defined classification tasks and various man-made targets partition criteria, which may influences the princi- ple of design for calculation and feature extraction in fine-grained classification models.

Preprint CONCEPT PAPER | doi:10.20944/preprints202409.1388.v1

Automating Portfolio Replication with Stock Market Algorithms

Srinivas Raju Gottimukkala

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: financial; portfolios; S&; P 500; stakeholders; stock

Online: 20 September 2024 (03:35:31 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1563.v1

Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings

David Cabezuelo, Izar Lopez-Ramirez, June Urkizu, Ander Goikoetxea

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: power consumption prediction; machine learning models; predictive analytics; feature analysis; random forest; support vector machine (SVM); deep neuronal networks (DNN)

Online: 20 September 2024 (02:59:58 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1518.v1

Comparison of Large Language Models Versus Traditional Information Extraction Methods for Real World Evidence of Patient Symptomatology in Acute and Post-Acute Sequelae of SARS-CoV-2

Vedansh Thakkar, Greg M. Silverman, Abhinab Kc, Nicholas E. Ingraham, Emma Jones, Samantha King, Christopher J. Tignanelli

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Information Extraction; Natural Language Processing; Large Language Models; Electronic Health Records

Online: 20 September 2024 (02:48:03 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1557.v1

Generative Artificial Intelligence in Corporate America: A Review of Artificial Intelligence Use, Benefits, Challenges, Regulation and Cyber Security Issues

Joseph Ashley-Osuzoka, Lord Nyame, Eunice Marfo-Ahenkorah, Abigail Abrahams, Godswill Ashong, Daniel Aboagye

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: artificial intelligence; generative AI; corporate strategy; research management; business management; threats; business performance; information technology; cyber security and regulation

Online: 19 September 2024 (15:53:08 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1446.v1

Leveraging Large Language Models to Enhance an Intelligent Agent with Multifaceted Capabilities

Sree Ganesh Thottempudi, Sagar Borra

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: large language models; retrieval augmented generation

Online: 19 September 2024 (10:01:58 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1364.v1

Detection of Aspergillus Flavus in Figs by Means of Hyperspectral Images and Deep Learning Algorithms

Cristian Cruz-Carrasco, Josefa Díaz-Álvarez, Francisco Chávez de la O, Abel Sánchez-Venegas, Juan Villegas-Cortez

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Agriculture; Deep Learning; Hyperspectral; imaging Artificial Neural Network; Precision agriculture

Online: 19 September 2024 (08:48:27 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1287.v1

A Game-Theoretic Model of Global AI Development Race: Dynamics of Domination and Technological Catch-up

Richard Murdoch Montgomery

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Technological Race; Game Theory; Monte Carlo Simulation; Technological Domination; Catch-up Dynamics; National Development Strategies; Global Competition; Innovation Policy; Technological Leapfrogging

Online: 18 September 2024 (04:48:13 CEST)

Show abstract| Download PDF| Share

Preprint CONCEPT PAPER | doi:10.20944/preprints202409.1320.v1

Evaluating the Impact of Fed and Domestic Monetary Policies on Long-Term Government Bond Yields

Srinivas Raju Gottimukkala

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Federal Open Market Committee; Financial; Ordinary Least Squared; US Federal Reserve

Online: 18 September 2024 (03:46:06 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1142.v1

Effect of Virtual Reality Technology in Table Tennis Teaching: A Multi-Center Controlled Study

Tingyu Ma, Wenhao Du, Qiufen Zhang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: virtual reality; table tennis; sports education; skill acquisition; learning motivation; training effectiveness

Online: 18 September 2024 (02:26:36 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1334.v1

Trends and Challenges in Data Analytics and Machine Learning Using Call Detail Records in Telecom Systems

James Barrett, Phil Legg, Jim Smith, Tim Barnes, Charles Boyle

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: call detail records; big data; mobile networks; machine learning

Online: 17 September 2024 (13:30:50 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1310.v1

Comparison of CNN-Based Architectures for Detection of Different Object Classe

Nataliya Bilous, Vladyslav Malko, Marcus Frohme, Alina Nechyporenko

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: deep learning; object detection; neural network; YOLO; SSD; EfficientDet

Online: 17 September 2024 (11:08:53 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1283.v1

Smooth Attention: Improving Image Semantic Segmentation

Boris Kriuk, Fedor Kriuk, Karthik Praveen

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Semantic Segmentation; Attention Mechanism; Spatial Relationships; Computer Vision; Deep Learning

Online: 17 September 2024 (06:14:20 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1197.v1

Intelligent Fault Diagnosis using Deep Learning Algorithms: A Comparative Analysis of MLP, CNN, RNN and LSTM

Vijyalakshmi K, Amuthakkannan Rajakannu, Mohsina Kamarudden, Ramachandran KP, Sri Rajkavin A V

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Condition monitoring; Machine Fault Simulator; unbalancing; Multilayer Perceptron (MLP); Convolutionary Neural Network (CNN); Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)

Online: 17 September 2024 (05:13:59 CEST)

Show abstract| Download PDF| Share

Health management in industrial systems is more critical in maintenance management and it plays an important role in productivity, fault diagnosis, safety, efficiency, and economy in manufacturing industries. Early detection of faults in machinery may increase the effectiveness of maintenance actions and will avoid unwanted consequences in process operations and maintenance. Existing fault diagnosis methods have limitations such as insufficient accuracy, slow detection rate, and handling large and complex data sets. In this digital age, Industry 4.0 techniques have been applied across all fields, including the condition monitoring of machines. This research addresses the gaps in traditional fault diagnosis by using deep learning, a modern AI technique effective for diagnosing faults in various machines. Deep learning algorithms Multilayer Perceptron (MLP), Coevolutionary Neural Network (CNN), and Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are tested for fault diagnosis using vibration datasets collected from Spectra Quest Machinery Fault Simulator (SQMFS). In this research work, NI-DAQ (National Instruments- Data Acquisition) system, accelerometer, and LabVIEW software are used to collect vibration signals. Preprocessing of the signals has been done using a sampling strategy, shuffling, standardization, and reshaping data augmentation. The result shows that MLP accuracy in the prediction of fault is 0.9, CNN reached 0.95, and RNN and LSTM with 0.57 and 0.45 respectively. The high performance of CNN is due to its ability to effectively capture spatial patterns in vibration data which is crucial for fault diagnosis in rotating machinery followed by MLP due to its faster convergence during training. However, when scaling the data, MLP outperformed CNN, demonstrating superior adaptability to increased data complexity and volume. Due to the need for larger datasets and temporal patterns in the vibration data, which RNN and LSTM are designed to handle, they resulted in a lower accuracy. This study shows that CNN has given better results than other deep learning algorithms MLP, RNN, and LSTM in fault diagnosis of rotating machinery. Future research could explore the application of these techniques to different types of machinery and fault conditions.

Preprint ARTICLE | doi:10.20944/preprints202409.1208.v1

Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance

Adarsh MS, Jithin VG, Ditto PS

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: llm; hybrid-llm; reward-token

Online: 17 September 2024 (05:12:30 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202407.2370.v2

Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding

Martin Wimpff, Jan Zerfowski, Bin Yang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Motor imagery; Electroencephalography; Deep Learning; Online decoding; Domain adaptation; Calibration-free; Mutual learning

Online: 15 September 2024 (07:32:28 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1095.v1

IRB-YOLO: An efficient Vatica Segmentation Model based on Inverted Residual Block for Drone Camera

Caili Yu, Yanheng Mai, Caijuan Yang, Jiaqi Zheng, Yongxin Liu, Chaoran Yu

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: precision agriculture; instance segmentation; drone; deep learning; computer vision

Online: 14 September 2024 (10:44:43 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1085.v1

Large Language Models in Entrepreneurship: A Survey

Yutong Li, Yuechen Yang, Chaoran Zhao, Chunling Cao

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Large Language Models; Entrepreneurship

Online: 14 September 2024 (10:37:03 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1118.v1

Cervical Cancer Prediction based on Imbalanced Data using Machine Learning Algorithms

Madalina Maria Muraru, Zsuzsa Simó, László Barna Iantovics

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: cervical cancer; cancer; artificial intelligence; sampling methods; unbalanced datasets; 34 classification methods; prediction methods; K-Nearest Neighbours; Logistic Regression; Random 35 Forest

Online: 14 September 2024 (08:33:58 CEST)

Show abstract| Download PDF| Share

Cervical Cancer affects a large part of female population that makes the prediction of this disease based on Machine Learning (ML) by outmost importance. ML algorithms can be integrated in complex intelligent agent-based systems that can offer decision support to the resident medical doctors or even to experienced medical doctors. For instance can be mentioned the situation when an experienced medical doctor diagnose a case but he/she needs expertise support that is related to another medical specialty. Data imbalance is frequent in healthcare data and has a negative influencing effect in making predictions using ML algorithms. Cancer data generally and cervical cancer data particularly are frequently imbalanced. Based on this fact the study of data imbalance impact on diverse state-of-the-art ML prediction algorithms is important. This research subject is also motivated by the fact that in many research are presented experimental evaluations of algorithms without characterization of the data on that they have been applied. Such characterizations could give clear indication to other researchers regarding the applicability of the algorithms on their specific data. Specifically, if the data have the respective characteristics than are expectable the same performance evaluation results like those in the reported research. For the study we chosed a messy real-life Cervical Cancer dataset available in a recognized data repository included a large amount of missing and noisy values. To identify the best imbalanced technique for this medical dataset, it is compared the performance of eleven important resampling methods combined with the following state-of-the-art ML models: K-Nearest Neighbours (with k values of 2 and 3), binary Logistic Regression, and Random Forest, that are frequently applied in prediction types of researches in healthcare. The studied resampling methods includes seven undersampling methods namely Condensed Nearest Neighbour, Tomek Links, Edited Nearest Neighbours, Repeated Edited Nearest Neighbours, All K-Nearest Neighbours, NearMiss, Neighbourhood Cleaning Rule, and Instance Hardness Threshold, and four oversampling methods namely Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling Approach for Imbalanced Learning SMOTE, Support Vector Machine SMOTE and Borderline SMOTE. In the case of the dataset for the confidence interval with 95% confidence level was between 9.23 and 16.22, while the imbalance ratio is 12.73. The obtained results show that resampling methods help the learning models to improve the classification ability of cervical cancer. The applied oversampling techniques generally showed better results than undersampling methods. In the case of Logistic Regression classifier had the highest impact on balanced techniques, while Random Forest had promising performance, even before balancing techniques and KNN2 was generally better than KNN3.

Preprint ARTICLE | doi:10.20944/preprints202409.1096.v1

A Review of IoT-Enabled Smart Energy Hub Systems: Rising, Applications, Challenges, and Future Prospects

Ruchit Parekh, Bishoy Sedhom, Sanjeevikumar Padmanaban, Abdelfattah A. Eladl

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Smart Energy Hub; Internet of Things; Cybersecurity Strategies; Smart Meters; Blockchain

Online: 14 September 2024 (07:40:45 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1089.v1

Innovative Sentiment Analysis and Prediction of Stock Price Using FinBERT, GPT-4, and Logistic Regression: A Data-Driven Approach

Olamilekan Shobayo, Sidikat Adeyemi-longe, Olusogo Popoola, Bayode Ogunleye

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: FinBERT Model; Logistic Regression; FinBERT; Optuna; Timeseries cross validation

Online: 13 September 2024 (16:56:12 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202406.1808.v3

Energy Efficiency Evaluation of Artificial Intelligence Algorithms

Kalin Penev, Alexander Gegov, Olufemi Isiaq, Raheleh Jafari

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: green computing; software energy efficiency; sustainable and responsible artificial intelligence; Free Search; Bremermann's limit

Online: 13 September 2024 (16:55:04 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1098.v1

CS-Eval—A Concise Benchmark for Evaluating the Security Risks of Large Language Models

Yu Zhang, Yongbing Gao, Lidong Yang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Large language models (LLMs); security risks; security benchmark; Multi-Security Hazard Dataset (MSHD)

Online: 13 September 2024 (15:46:19 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1093.v1

Development Of A Real-Time Object Detection Model For The Detection Of Secretly Cultivated Plants

Ali Yılmaz, Yüksel Yurtay, Nilüfer Yurtay

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: YOLO Series Algorithm, DETR Architecture, Vision Transformers (ViT), Object Detection, FPN (Feature Pyramid Network)

Online: 13 September 2024 (14:55:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202402.1566.v2

Weather Forecasting Using Machine Learning Techniques: Rainfall and Temperature Analysis

Adil Hussain, Ayesha Aslam, Sajib Tripura, VIneet Dhanawat, Varun Shinde

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: rainfall prediction, temperature prediction, ensemble classifier, rain prediction, weather prediction

Online: 13 September 2024 (11:43:09 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1042.v1

Lung and Colon Cancer Detection Using Deep AI Model

Nazmul Shahadat, Ritika Lama, Anna Nguyen

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: 1D CNN; Squeeze-and-Excitation networks; RCN; lightweight model; lung and colon cancer detection; lung cancer detection; colon cancer detection; cancer detection; histopathological images; image classification; deep learning

Online: 13 September 2024 (11:07:43 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1005.v1

A Comparative Analysis of Machine Learning and Deep Learning Techniques for Accurate Market Price Forecasting

Olamilekan Shobayo, Sidikat Adeyemi-longe, Olusogo Popoola, Obinna Okoyeigbo

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Hybrid Model; LSTM; Logistic Regression, Recurrent Neural Network, Support Vector Regression, FinBERT)

Online: 12 September 2024 (12:55:18 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0983.v1

Enhancing Supply Chain Efficiency with Time Series Analysis and Deep Learning Techniques

Jun Sun, Shuwen Zhou, Xiaoan Zhan, Jiang Wu

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Time Series Analysis; Machine Learning Models; Deep Learning Forecasting; Supply Chain; LSTM

Online: 12 September 2024 (12:29:33 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0982.v1

Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images

Olamilekan Shobayo, Oluwatosin Tanimola, Olusogo Popoola, Obinna Okoyeigbo

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Breast cancer; Deep Learning; Transformer models

Online: 12 September 2024 (11:34:10 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0920.v1

A Review of the Application of Hyperspectral Imaging Technology in Agricultural Crop Economics

Pengfei Hu, Jinxing Wu, Yanying Wu, Yi Zhang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: hyperspectral; crop economy; non-destructive detection; classification

Online: 12 September 2024 (07:37:15 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0923.v1

Ensemble based Machine Learning Algorithm for Loan Default Risk Prediction

Abisola Akinjole, Olamilekan Shobayo, Jumoke Popoola, Obinna Okoyeigbo, Bayode Ogunleye

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Credit default prediction; deep learning; ensemble learning; machine leaning

Online: 11 September 2024 (16:42:37 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0890.v1

Derivation of Analytical Equations for the Fundamental Period of Framed Structures Using Machine Learning and SHAP Values

Ioannis Karampinis, Konstaninos Morfidis, Lazaros Iliadis

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: fundamental period; masonry infilled framed structures; machine learning; explainability; SHAP; analytical equations

Online: 11 September 2024 (16:23:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0925.v1

Bag of Feature-Based Ensemble Subspace KNN Classifier in Muscle Ultrasound Diagnosis of Diabetic Peripheral Neuropathy

Kadhim Kamal Al-Barazanchi, Ali Hussein Al-Timemy, Zahid Mohamed Kadhim

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: bag of features; ensemble subspace KNN; muscle ultrasound; diabetic peripheral neuropathy; speeded up robust features

Online: 11 September 2024 (16:19:52 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0897.v1

Advanced ENF Region Classification Using UniTS-SinSpec: A Novel Approach Integrating Sinusoidal Activation Function and Spectral Attention

Yujin LI, Tianliang LU, Gaojun ZENG, Kai ZHAO, Shufan PENG

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: electric network frequency; ENF classification; sinusoidal activation function; spectral attention; UniTS-SinSpec model

Online: 11 September 2024 (12:39:30 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0834.v1

BBPE-AE: A Byte Pair Encoding-Based Auto Encoder for Password Guessing

Samane Ghafari, Leila Safari, Mohsen Afsharchi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Password Guessing; Cybersecurity; Password Strength Assessment; Autoencoder Network; Long Short-Term Memory (LSTM) Networks; Byte-level Byte Pair Encoding

Online: 11 September 2024 (10:49:15 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0871.v1

Enhanced Multi-Scale Attention-Driven 3D Human Reconstruction from Single Image

Yong Ren, Mingquan Zhou, Pengbo Zhou, Shibo Wang, Yangyang Liu, Guohua Geng, Kang Li, Xin Cao

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: enhancing multi-scale attention; single image; normal map; human reconstruction

Online: 11 September 2024 (10:34:23 CEST)

Show abstract| Download PDF| Share

Due to the inherent limitations of a single viewpoint, reconstructing 3D human meshes 1 from a single image has long been a challenging task. While deep learning networks enable us to 2 approximate the shape of unseen sides, capturing the texture details of the non-visible side remains 3 difficult with just one image. Traditional methods utilize Generative Adversarial Networks (GANs) 4 to predict the normal maps of the non-visible side, thereby inferring detailed textures and wrinkles 5 on the model’s surface. However, we have identified challenges with existing normal prediction 6 networks when dealing with complex scenes, such as a lack of focus on local features and insufficient 7 modeling of spatial relationships.To address these challenges, we introduce EMAR—Enhanced 8 Multi-scale Attention-driven Single Image 3D Human Reconstruction. This approach incorporates 9 a novel Enhanced Multi-Scale Attention (EMSA) mechanism, which excels at capturing intricate 10 features and global relationships in complex scenes. EMSA surpasses traditional single-scale attention 11 mechanisms by adaptively adjusting the weights between features, enabling the network to more 12 effectively leverage information across various scales.Furthermore, we have improved the feature 13 fusion method to better integrate representations from different scales. This enhanced feature fusion 14 allows the network to more comprehensively understand both fine details and global structures 15 within the image. Finally, we have designed a hybrid loss function tailored to the introduced attention 16 mechanism and feature fusion method, optimizing the network’s training process and enhancing the 17 quality of reconstruction results.Our network demonstrates significant improvements in performance 18 for 3D human model reconstruction. Experimental results show that our method exhibits greater 19 robustness to challenging poses compared to traditional single-scale approaches.

Preprint ARTICLE | doi:10.20944/preprints202409.0841.v1

Research on Large Scene Adaptive Feature Extraction Based on Deep Learning

Yahe Yang, Iris Li, Ningjing Sang, Lipeng Liu, Xirui Tang, Qiyuan Tian

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: computing methodologies; artificial intelligence; computer vision; computer vision tasks; scene understanding

Online: 11 September 2024 (10:23:23 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0875.v1

Predicting Industrial Property Prices with Explainable Artificial Intelligence

Tris Kee, Winky Ho

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Industrial property prices; Machine learning; Explainable Artificial Intelligence

Online: 11 September 2024 (08:48:15 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0847.v1

TMining: Detecting Fake News with Machine Learning and Explainable AI

Maksym Lupei, Myroslav Shliakhta

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Text Mining; Fake News; Model Explanation; Machine Learning

Online: 11 September 2024 (07:32:27 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0760.v1

Designing a Holistic Student Evaluation Model for E-Learning Using a Multi-Task Attention-Based Deep Learning Approach

Deborah Olaniyan, Julius Olaniyan, Ibidun C Obagbuwa, Esiefarienrhe B Micheal, Olorunfemi P Bernard

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: e-learning; student; performance; multi-task; deep learning; attention mechanism

Online: 10 September 2024 (15:06:03 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0787.v1

Towards an In-depth Evaluation of the Performance, Suitability and Plausibility of Few-Shot Meta Transfer Learning on An Unknown Out-of-Distribution Cyber-attack Detection

Tosin Ige, Christopher Kiekintveld, Aritran Piplai, Amy Wagler, Olukunle Kolade, Bolanle Matti

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Few-Shot Learning; Meta Learning; Transfer Learning; Machine Learning; Deep Learning; Zero-Day; Malware; out-of-distribution attack; cyberattacks

Online: 10 September 2024 (14:20:33 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0698.v1

Enhancing Cardiovascular Risk Prediction: Development of an Advanced Xgboost Model with Hospital-Level Random Effects

Tim Dong, Iyabosola Busola Oronti, Shubhra Sinha, Alberto Freitas, Bing Zhai, Jeremy Chan, Daniel P Fudulu, Massimo Caputo, Gianni D. Angelini

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: machine learning; AI; random effects; cardiovascular medicine; risk prediction; expectation-maximization; xgboost

Online: 10 September 2024 (12:39:32 CEST)

Show abstract| Download PDF| Share

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, are limited. Objectives: The aim of this work is to develop a binary outcome mixed effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aims to assess its performance and compare it to fixed effects Xgboost and traditional logistic regression models. Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 Jan 2012 and 31 Mar 2019 were included. The dataset was split into two cohorts: Training/Validation (n = 157196; 2012-2016) and Holdout (n = 69891; 2017-2019). The outcome variable was 30 days mortality with hospitals considered as clustering variable. The logistic regression, mixed effects logistic regression, Xgboost and binary outcome mixed effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach. Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of mixed effects models. Unstandardized Xgboost BME demonstrated marked improvements in predictor power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glm) and generalized linear mixed-effects models (glmer) models followed similar results, with Xgboost models excelling also at greater sample sizes. Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their applicability in clinical settings where sample size is small such as rare conditions.

Preprint ARTICLE | doi:10.20944/preprints202409.0778.v1

A Driving Model in the Realistic 3D Game Trackmania Using Deep Reinforcement Learning

Jean-Baptiste Authier-Carcelen, Rubina Zadourian

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Autonomous Driving; Computer Vision; Reinforcement Learning; Transfer Learning

Online: 10 September 2024 (09:38:18 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202406.0242.v2

Dual-input Dual-stream Network with Two-fold Margin Loss for Improved Brain Tumor Detection on MRI Images

Mumtaz Ali Kaloi, Riaz Ali, Nazim Hussain Hajano, Abdul Sattar Sattar Chan, Irfan Ali Babbar, Asif Ali

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Dual-input; Dual-stream; Two-fold Margin Loss; Brain Tumor Detection; MRI Images

Online: 10 September 2024 (09:04:02 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0744.v1

Audio Deep Fake Detection with Sonic Sleuth Model

Anfal Sultan Alshehri, Danah Almalki, Somayah Abdullah Albaradei

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Deepfake Detection; Machine Learning; Deep Learning; Deepfake Audio; Audio Forensics; Deepfake

Online: 10 September 2024 (09:00:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0703.v1

Segment Anything in OCT: SAM 2 for Volumetric Segmentation of Retinal Biomarkers

Mikhail Kulyabin, Aleksei Zhdanov, Andrey Pershin, Gleb Sokolov, Anastasia Nikiforova, Mikhail Ronkin, Vasilii I Borisov, Andreas Maier

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: OCT; segmentation; SAM; MedSAM; AMD; DME; Retina

Online: 9 September 2024 (15:16:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0630.v1

Local Structure Information Learning for Small Dataset Fine-Grained Visual Classification Based on Spatial Frequency Domain Fusion

Yongfei Guo, Bo Li, Wenyue Zhang, Weilong Dong

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Local structure information(LSI); spatial frequency domain features(SFD); fine-grained visual classification (FGVC); small dataset fine-grained visual classification (SDFGVC)

Online: 9 September 2024 (12:19:19 CEST)

Show abstract| Download PDF| Share

Preprint COMMUNICATION | doi:10.20944/preprints202409.0682.v1

Advancing Face Recognition for Low-Resolution with Multi-Linear Side Information-Based Discriminant Analysis

Bellili Sana, Ouamane Abdelmalik, Chouchane Ammar, Bourennane Salah

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Face recognitio; Low-resolution; MSIDA; CelebA database

Online: 9 September 2024 (12:03:45 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0667.v1

Predictive Analytics for Thyroid Cancer Recurrence: A Machine Learning Approach

Elizabeth Clark, Samantha Price, Theresa Lucena, Bailey Haberlein, Abdullah Wahbeh, Raed Seetan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Differentiated Thyroid Cancer; SMOTE; Machine Learning; Predictive Analytics; Random Forest Classifier

Online: 9 September 2024 (11:49:43 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0550.v1

AI’s Role in Fortifying Cyber Defenses: A 2024 Perspective on Machine and Deep Learning Applications

Md. Badiuzzaman Biplob, Mahmuda Samia Konika, Kazi Mohammad Moinul Ahsan, Tasnia Zannat, Arif Ahmed

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: artificial intelligence; AI security; cyber security; modern security; machine learning; deep learning; cyber-attack

Online: 9 September 2024 (11:37:20 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0645.v1

Using Machine Learning and Deep Learning to Strengthen Bangladesh’s Financial Infrastructure for Banking Cybersecurity

Md. Badiuzzaman Biplob, Tonmoy Bhuiyan, Al Mohaimin Farabi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: financial-sector; breaches; bangladesh; cyberattacks; deep-learning; machine-learning; fraud; cybersecurity; digital-banking; malware; banking-data; Realtime-analysis; financial-inclusion; digitalization

Online: 9 September 2024 (11:24:39 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0633.v1

Artificial Intelligence Assisted Detection and Localization of Spinal Metastases

Edgars Edelmers, Artūrs Ņikuļins, Klinta Luīze Sprūdža, Patrīcija Stapulone, Niks Saimons Pūce, Elizabete Skrebele, Everita Elīna Siņicina, Viktorija Cīrule, Ance Kazuša, Katrina Boločko

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: artificial intelligence; spinal metastases; vertebras segmentation; computer tomography; medical imaging; instance segmentation; radiomics

Online: 9 September 2024 (09:21:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0616.v1

Optimizing Multi-time Series Forecasting for Enhanced Cloud Resource Utilization Based on Machine Learning

Mateusz Smendowski, Piotr Nawrocki

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Cloud computing; Cloud resource usage optimization; Machine learning; Time series forecasting optimization; Cloud FinOps

Online: 9 September 2024 (08:43:26 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0611.v1

Derangetropy in Probability Distributions and Information Dynamics

Masoud Ataei, Xiaogang Wang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Information Dynamics; Probability Distributions; Functional Measures; Entropy; Combinatorial Analysis; Differential Equations; Information Theory; Equilibrium Analysis

Online: 9 September 2024 (08:43:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0605.v1

Soil Health Management Using Artificial Intelligence for Smart Agriculture Systems

V. T. Shalini, Rahul Neware, Tanvi Kumari, Mukesh Kumar

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Soil Health; Deep Learning; Machine Learning; Unmanned Aerial Vehicle; ANN

Online: 9 September 2024 (08:43:13 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0580.v1

Smart Viniculture: Applying AI for Improved Winemaking and Risk Management

Inmaculada Izquierdo-Bueno, Javier Moraga, Jesús M. Cantoral, Maria Carbú, Carlos Garrido, Victoria E. González-Rodríguez

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Precision Viticulture; Disease Prediction Models; Drone Technology; Automated Harvesting; Water and Nutrient Management; Sustainable Winemaking; Smart Agriculture; Pest Control; Data-Driven Decision Making

Online: 9 September 2024 (08:05:53 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0495.v1

Privacy-Preserving Federated Learning-Based Intrusion Detection Technique for Cyber-Physical System

Syeda Aunanya Mahmud, Nazmul Islam, Zahidul Islam, Ziaur Rahman, Sk. Tanzir Mehedi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Federated Learning (FL); Intrusion Detection System (IDS); Internet of Things (IoT); cyber threats; privacy-preserving; FedAvg

Online: 9 September 2024 (04:42:07 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0509.v1

An In-Depth Investigation into the Performance of State-of-the-Art Zero-Shot, Single-Shot, and Few-Shot Learning Approaches on an Out-of-Distribution Zero-Day Malware Attack Detection

Tosin Ige, Christopher Kiekintveld, Aritran Piplai, Amy Wagler, Olukunle Kolade, Bolanle Hafiz Matti

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Few-Shot Learning; One-Shot Learning; Zero-Shot Learning; Machine Learning; Deep Learning; Zero-Day; Malware

Online: 6 September 2024 (09:40:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0485.v1

Hybrid Machine Learning for Stunting Prevalence: A Novel Comprehensive Approach to Classification, Prediction, and Clustering Optimization in Aceh, Indonesia

Novia Hasdyna, Rozzi Kesuma Dinata, Rahmi Rahmi, T. Irfan Fajri

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: stunting; machine learning; support vector machines; linear regression; k-medoids; clustering optimization; weight product; Aceh

Online: 6 September 2024 (09:33:32 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0490.v1

Ensuring Educational Ecosystem Resilience: Safeguarding the Learning Landscape through IEEE Methodologies

Md. Badiuzzaman Biplob, Al Faysal, Mili Akther

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: educational ecosystem; resilience; learning landscape; cybersecurity; digital platforms; network security; device management; cyber threats; vulnerabilities

Online: 6 September 2024 (09:32:21 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0457.v1

Beyond Network Switching: FPGA-based Switch Architecture for Fast and Accurate Ensemble Learning

Jiuxi Meng, Zhiqiang Que, Ce Guo, Wayne Luk

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: ensemble learning; FPGA-based switch; random projection; k-nearest neighbour; cloud computing

Online: 5 September 2024 (12:11:34 CEST)

Show abstract| Download PDF| Share

Recent advancements in Artificial Intelligence (AI) and generative models have significantly accelerated the evolution of internet services. In data centers, where data is often distributed across multiple machines, leveraging these machines to expedite the training of machine learning applications is common. However, this approach incurs substantial communication overhead. To mitigate this, data compression techniques such as quantization, sparsification, and dimension reduction are gaining attention, especially with iterative training algorithms that frequently exchange gradients. With the advancement of FPGA technology, FPGA-based bump-in-the-wire network interface controllers (smartNICs) have demonstrated notable benefits for data centers, matching ASIC switches in port-to-port latency and capacity. However, FPGA-based switches often have spare hardware resources beyond their switching functions, which are typically wasted. we propose a novel architecture that integrates FPGA-based switches with ensemble learning methods, utilizing these spare resources on FPGA-based network switches. This architecture employs random projection as a compression method to accelerate machine learning tasks while maintaining high accuracy. Our system accelerates the training process for Multilayer Perceptron (MLP) models with a speedup of 2.1-6.7 times across four high-dimensional datasets. In addition, it leverages the Hamming distance metric for k-Nearest Neighbors (kNN) classification, combining random projection with Hamming encoding, to offload large-scale classification tasks from downstream servers. This achieves a worst-case speedup of 2.3-8.7 times and a memory reduction of 3.9-27.7 times compared to CPU-based kNN classifiers using cosine distance. Our architecture addresses the challenges of high-dimensional data processing and exemplifies the potential of AI-driven solutions in accelerating and optimizing internet services. Moreover, the programmability of FPGAs allows the system to adopt various compression methods, extending its applicability. Offloading tasks to FPGAs can significantly reduce query response times, showcasing a crucial step towards achieving greater levels of autonomic computing and the rapid evolution of internet systems.

Preprint REVIEW | doi:10.20944/preprints202409.0400.v1

From Data Breaches to Defense Strategies: A Study of Cybersecurity Information Systems Latest Trends and Future Paradigms

Md. Badiuzzaman Biplob, Kazi Mohammad Moinul Ahsan, Al Mohaimin Farabi, Mahmuda Samia Konika, Arif Ahmed

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: internet; cyber security; cyber attack; artificial intelligence; machine learning; cyber information security; threats

Online: 5 September 2024 (10:55:08 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0438.v1

The Impact of Cybersecurity on the Advancement of IoT: Challenges, Opportunities and Future Directions

Md. Badiuzzaman Biplob, Arif Ahmed, Tasnia Zannat, Mahmuda Samia Konika, Kazi Mohammad Moinul Ahsan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: internet of things; cyber security; transformative; revolutionizing; vulnerabilities

Online: 5 September 2024 (10:41:02 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0407.v1

Leveraging Blockchain Technology for Cyber Security: A Comprehensive Review

Md. Badiuzzaman Biplob, Tasnia Zannat, Arif Ahmed, Mahmuda Samia Konika, Kazi Mohammad Moinul Ahsan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: blockchain; decentralization; immutability; transparency; systematic; survey; cryptocurrency; security

Online: 5 September 2024 (05:04:30 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0303.v1

DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer

Mohamed Touati, Rabeb Touati, Laurent Nana, Faouzi Benzarti, Sadok Ben Yahia

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: AI; diabetic retinopathy; deep learning; DRCCT; classification; transformer

Online: 4 September 2024 (18:03:35 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0372.v1

An Explainable AI-based Modified YOLOv8 Model for Efficient Fire Detection

Md. Waliul Hasan, Shahria Shanto, Jannatun Nayeema, Rashik Rahman, Tanjina Helaly, Ziaur Rahman, Sk. Tanzir Mehedi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: fire detection; modified YOLOv8; deep learning; computer vision; explainable artificial intelligence; EigenCAM

Online: 4 September 2024 (12:56:31 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0353.v1

Digital Cloud Defense: Fortifying Your Data Against Cyber Threats

Md. Badiuzzaman Biplob, Jannatul Ferdous Ramisha, Mili Akther, Al Mohaimin Farabi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: data security; digital privacy; cloud security; information protection; encryption; data breaches; digital identity theft; data privacy regulations; network security; data encryption standards

Online: 4 September 2024 (11:24:00 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0350.v1

Adapting to the Evolution of Cyber Threats: Insights for 2024 and Beyond

Md. Badiuzzaman Biplob, Mili Akther, Al Mohaimin Farabi, Jannatul Ferdous Ramisha

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: AI-powered threat detection; cybersecurity frameworks; behavioral biometrics; risk mitigation; cyber resilience; artificial intelligence; machine learning

Online: 4 September 2024 (09:30:50 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0322.v1

Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis

Francisco Oliveira, Daniel Queirós da Silva, Vítor Filipe, Tatiana M. Pinho, Mário Cunha, José Boaventura Cunha, Filipe N. Santos

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: deep learning; precision agriculture; pruning; robotic systems; YOLO

Online: 4 September 2024 (08:10:37 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0326.v1

The Application of Deep Learning to Accurately Identify the Dimensions of Spinal Canal and Intervertebral Foramen as Evaluated by the IoU Index

Chih-Ying Wu, Wei-Chang Yeh, Shiaw-Meng Chang, Che-Wei Hsu, Zi-Jie Lin

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: artificial intelligence; deep learning; magnetic resonance image; vertebral foramen; intervertebral canal

Online: 4 September 2024 (07:42:08 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0253.v1

Explainable Pre-Trained Language Models for Sentiment Analysis in Low-Resourced Languages

Ronny Mabokela, Mpho Primus, Turgay Celik

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Explainable AI; sentiment analysis; African languages; Africa-Centric models; pre-trained models; transformer models

Online: 3 September 2024 (18:02:13 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0242.v1

Empowering Bangladesh's Financial Infrastructure, Machine Learning, and Deep Learning Perspectives on Banking Cybersecurity

Md. Badiuzzaman Biplob

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: bangladesh; financial infrastructure; machine learning; deep learning; cybersecurity; banking; digitalization; national financial inclusion strategy; robust cybersecurity

Online: 3 September 2024 (17:57:30 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0224.v1

A Small-Scale Object Detection Algorithm in Intelligent Transportation Scenarios

Junzi Song, Chunyan Han, Chenni Wu

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: intelligent transportation; small object detection; YOLOv4 tiny; feature pyramid; information entropy

Online: 3 September 2024 (14:28:05 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0154.v1

Biomarkers of ‘Late Onset Alzheimer’s Disease ‘, Diagnosis and Role of ’Deep Learning’

Manash Sarma, Subarna Chatterjee

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Alzheimer’ s disease; Biomarker; Deep learning; Convolution neural network (CNN)

Online: 3 September 2024 (10:35:43 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0195.v1

Generative Artificial Intelligence Trend on Video Generation

Lord Nyame, Staphord Bengesi

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Generative Artificial Intelligence; Video Cloning; Variation Autoencoders

Online: 3 September 2024 (07:35:22 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2233.v1

Machine Learning Approach for Arabic Handwritten Recognition

A.M. Mutawa, Mohammad Allaho, Monirah Al-Hajeri

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Machine learning; handwritten recognition systems; Arabic handwriting; BiLSTM; ResNet; natural language processing

Online: 3 September 2024 (05:10:05 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2231.v1

Alzheimer Stage Diagnosis from Genomic and Clinical Data Modalities Using ‘Artificial Neural Network’

Manash Sarma, Subarna Chatterjee

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: disease stage diagnosis; blood gene expression; data imbalance; multiclassification; F1 score; AD risk gene; SHAP; LIME

Online: 3 September 2024 (05:01:42 CEST)

Show abstract| Download PDF| Share

INTRODUCTION: This study focusses on diagnosis of stages of AD (Alzheimer’s disease) including MCI (Mild Cognitive Impairment) from two data modalities - gene expression and clinical data of ADNI (Alzheimer’s Disease Neuroimaging Initiative ) participants using multiclassification. The gene expression dataset is highly imbalanced and of HDLSS (high-dimensional and low-sample-size) characteristics. This is the only study where multiclassification based AD stage diagnosis is done to identify multiple stages of Alzheimer. We are able to achieve the best multiclassification result in both the modalities and identify new genetic biomarkers. METHODS: Combination of XGBoost and SFBS (“Sequential Floating Backward Selection”) methods is used to select features. We are able to select the most effective 95 gene probsets out of 49,386. For clinical study data, 8 most effective biomarkers could be selected using SFBS. For both genomic and clinical data, DL (‘Deep Learning’) classifier is used to identify stages - CN (Cognitive Normal), MCI (Mild Cognitive Impairment), AD (Alzheimer’s Disease / Dementia). Because of high data imbalance in genomic data, border line oversampling is used for model training and original data for validation. RESULT & DISCUSSION: With clinical data, we achieved ‘ROC AUC’ scores 0.97, 0.95, 0.94 for CN, MCI, Dementia stage respectively . We achieve ‘ROC AUC’ scores 0.75, 0.74, 0.70 for CN, MCI, Dementia stage respectively and 0.67 for both micro average F1 scores and micro weighted F1 score. This is the best result so far for AD stage diagnosis from gene expression profile data through multiclassification with ADNI data. Results reflect that our multiclassification model can efficiently handle the imbalanced data of HDLSS nature to identify samples of minority class. MAPK14, ZNF835, MID1, HLA-DQA1, TEP1 are some of the new genes found to be associated with AD risk. DRAXIN, HSPA12B, USP47 etc. are found to be AD preventive or suppressor.

Preprint ARTICLE | doi:10.20944/preprints202409.0130.v1

Multi-timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks

Favour Edose Ibude, Abayomi Otebolaku, Jude Ameh, Augustine Ikpehai

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Smart buildings; Energy consumption; Hybrid deep learning; Energy predictions; Building energy management systems

Online: 2 September 2024 (16:59:53 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0021.v1

Exploring Metaheuristic Optimized Machine Learning for Software Defect Detection on Natural Language and Classical Datasets

Aleksandar Petrovic, Luka Jovanovic, Nebojsa Bacanin, Milos Antonijevic, Nikola Savanovic, Miodrag Zivkovic, Marina Milovanovic, Vuk Gajic

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Natural language processing; Software error detection; Metaheuristic; Optimization; XGBoost; AdaBoost; Convolutional neural networks; explainable artificial intelligence

Online: 2 September 2024 (13:33:25 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0001.v1

Predictive Modelling of Customer Response to Marketing Campaigns

Mohammed El-Hajj, Miglena Pavlova

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Customer Relationship Management; Customer response prediction; Decision Tree model; F1-score; ROI optimization; Predictive modeling

Online: 2 September 2024 (12:03:31 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0070.v1

Microwave Digital Twin Prototype for the Shoulder Injury Detection

Sahar Borzooei, Pierre-Henri Tournier, Victorita Dolean, Claire Migliaccio

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Machine learning; Numerical modeling; Microwave sensing system; Tendon injury; SVM classification; Microwave Digital Twin Prototype

Online: 2 September 2024 (10:57:56 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.0013.v1

Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence

Ahrum Son, Jongham Park, Woojin Kim, Yoonki Yoon, Sangwoon Lee, Yongho Park, Hyunsoo Kim

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Computational Biology; Protein Engineering; Artificial Intelligence; Molecular Design; De Novo Protein Design; Therapeutic Proteins; Synthetic Biology

Online: 2 September 2024 (09:12:26 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0016.v1

Multiple Postures and Behaviors Recognition Method for Horse Based on Se-SlowFast Network

Yanhong Liu, Jinxing Li, Fang Zhou, Xuan Chen, Wenxin Zheng, Tao Bai, Leifeng Guo, Xinwen Chen

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: horse; artificial intelligence; behaviors recognition; improved SlowFast network; animal welfare

Online: 2 September 2024 (09:02:04 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0037.v1

Redefining Data-Centric Design: A New Approach with a Domain Model and Core Data Ontology for Computational Systems

William Johnson, James Davis, Tara Kelly

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Data-centric design; distributed data ecosystems; data security; semantic interoperability; ontology development

Online: 2 September 2024 (08:53:49 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202401.1672.v2

Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction

Jiaxi Yang, Jiaquan Shen, Shitong Wang, Yuhang Chen, Qian Zhang, Sitao Luan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: pedestrian detection; aerial image; attention mechanism; multi-scale prediction; convolutional neural network; new benchmark dataset

Online: 30 August 2024 (19:20:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2273.v1

Self-adaptive Differential Evolution for Multi-objective Optimization with Local Search and Indicator-based Selection

Datong Xie

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: multi-objective optimization; self-adaptive differential evolution; orthogonal design; indicator-based selection; local search; k-nearest neighbor

Online: 30 August 2024 (15:54:27 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2225.v1

Knowledge Graph-Based Question Answering via Enhanced Contrastive Learning

Madison Smith, Woods Ali, Tyler Johnson

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: natural language processing; question answering; knowledge graphs; contrastive learning

Online: 30 August 2024 (10:36:00 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2226.v1

Pricing Rainbow Options Using PINNs

Ayesha Ahmad, adnan khan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Qiuantitive finance; option pricing; rainbow options; PINNs; neural networks

Online: 30 August 2024 (10:35:55 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2152.v1

Adaptive Control of Retrieval-Augmented Generation for LLMs Through Reflective Tags

Chengyuan Yang, Satoshi Fujita

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Retrieval-Augmented Generation; Large Language Models; Chain of Thought; reflective tag

Online: 30 August 2024 (03:45:59 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2137.v1

UI-Hawk: Unleashing the Screen Stream Understanding for GUI Agents

Jiwen Zhang, Yaqi Yu, Minghui Liao, Wentao Li, Jihao Wu, Zhongyu Wei

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: GUI Agents; Screen Stream Understanding

Online: 30 August 2024 (03:42:19 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2157.v1

A New Paradigm for Scientific Query Answering

Jacob Martinez, Woods Ali, Madison Taylor

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: information retrieval; neural ranking models,; natural language processing; data-driven decision making

Online: 29 August 2024 (11:33:08 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2125.v1

Federated Learning in Dynamic and Heterogeneous Environments: Advantages, Performances, and Privacy Problems

Fabio Liberti, Davide Berardi, Barbara Martini

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Privacy; Federated Machine Learning; Edge Computing; Ubiquitous Intelligence

Online: 29 August 2024 (09:18:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2109.v1

Advanced Stock Price Prediction with xLSTM-Based Models: Improving Long-Term Forecasting

Xiaojing Fan, Chunliang Tao, Jianyu Zhao

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Neural Networks; Stock Price Prediction; Long Short-Term Memory (LSTM); Extended Long Short-Term Memory (xLSTM); Time Series Forecasting

Online: 29 August 2024 (08:32:14 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2032.v1

Enhancing Multilingual Table-to-Text Generation with QA Blueprints: Overcoming Challenges in Low-Resource Languages

Arpita Soni

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: African; English; Natural Language Processing; Question-Answer

Online: 29 August 2024 (03:05:04 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202408.2063.v1

Artificial Intelligence-Aided Digital Twin Design: A Systematic Review

Nan Hao, Yuangang Li, Kecheng Liu, Songtao Liu, Yingzhou Lu, Bohao Xu, Chenhao Li, Jintai Chen, Ling Yue, Tianfan Fu, Xiyang Hu, Xiao Wang, Yue Zhao

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: digital twin; machine learning; generative AI; synthetic data generation

Online: 28 August 2024 (13:05:26 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.2010.v1

Bio-AD: A Transfer Learning Approach for Diagnosis of Alzheimer’s Diseases in MRI Scans

Mian Muhammad Sadiq Fareed, Gulnaz Ahmed, Shahid Zikria, Saad Ahmed Jamal

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep Learning; Image Classification; Supervised Learning; ; Transfer Learning; Imbalanced data set; MRI data set; Computer-Aided Diagnosis; SMOTE; Class Activation

Online: 28 August 2024 (10:41:59 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202407.1573.v2

Navigating Artificial General Intelligence (AGI): Societal Implications, Ethical Considerations, and Governance Strategies

Dileesh Chandra Bikkasani

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: artificial general intelligence (AGI); AGI ethics; AGI governance; security; societal impact

Online: 28 August 2024 (09:41:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.1909.v1

A Comparative Study of Metaheuristic Feature Selection Algorithms for Respiratory Disease Classification

Damla Gürkan Kuntalp, Nermin Özcan, Okan Düzyel, Yasin Kababulut, Mehmet Kuntalp

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: metaheuristic; feature selection; respiratory disease classification

Online: 27 August 2024 (16:36:44 CEST)

Show abstract| Download PDF| Supplementary Files| Share

Preprint ARTICLE | doi:10.20944/preprints202408.1933.v1

A New Educational Reality: Active Methodologies Empowered by Generative AI

Thiago Maciel Ferreira

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Inteligência Artificial Generativa; Metodologias Ativas; Personalização do Ensino; Aprendizagem Eficaz; Integração Pedagógica

Online: 27 August 2024 (11:52:35 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.1860.v1

AI-Driven Self-Healing Cloud Systems: Enhancing Reliability and Reducing Downtime through Event-Driven Automation

Rajeev Arora, Anoop Kumar, Arpita Soni, Aniruddh Tiwari

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Artificial Intelligence; Cloud System; Engine; OpenStack

Online: 27 August 2024 (11:43:55 CEST)

Show abstract| Download PDF| Share

Computer Science and Mathematics