Search | Preprints.org

Preprint ARTICLE | doi:10.20944/preprints201810.0239.v1

A Mobile Positioning Method Based on Deep Learning Techniques

Ling Wu, Chi-Hua Chen, Qishan Zhang

Subject: Computer Science And Mathematics, Computer Science Keywords: deep learning; recurrent neural networks; mobile positioning method; fingerprinting positioning method; received signal strength

Online: 11 October 2018 (13:31:28 CEST)

Show abstract| Download PDF| Supplementary Files| Share

Preprint ARTICLE | doi:10.20944/preprints201809.0088.v1

Deep Learning with Unsupervised Data Labeling for Weeds Detection on UAV Images

M Dian Bah, Adel Hafiane, Raphael Canals

Subject: Computer Science And Mathematics, Computer Science Keywords: weeds detection; deep learning; unmanned aerial vehicle; image processing; precision agriculture; crop lines detection

Online: 5 September 2018 (06:13:06 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201808.0551.v1

An Extreme Learning Machine Approach to Effective Energy Disaggregation

Valerio Mario Salerno, Graziella Rabbeni

Subject: Engineering, Energy And Fuel Technology Keywords: Non-intrusive Load Monitoring; Machine Learning; Deep Modeling; Extreme Learning Machine; Data Driven Approach.

Online: 31 August 2018 (15:44:51 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201805.0463.v1

Is There a Right to Get a Right Diagnosis Whenever Possible? Ethical and Social Issues in Dealing with Undiagnosed Rare Diseases

Sabina Gainotti, Deborah Mascalzoni, Virginie Bros Facer, Carlo Petrini, Giovanna Floridia, Marco Roos, Marco Salvatore, Domenica Taruscio

Subject: Medicine And Pharmacology, Other Keywords: undiagnosed rare diseases; diagnostic odyssey; NGS; deep phenotyping; genomic matchmaking; secondary findings; patient involvement

Online: 31 May 2018 (09:35:32 CEST)

Show abstract| Download PDF| Share

The time required to reach a correct diagnosis is one of the most important problems for rare disease (RD) patients. Diagnostic delay can be intolerably long, to the point that it is usually described as a “diagnostic odyssey” and, sometimes, a diagnosis might never occur. The International Rare Disease Research Consortium proposed, as ultimate goal for 2017-2027, to enable all people with a suspected RD to be diagnosed within one year if the disorder is known, and to enter a globally coordinated diagnostic and research pipeline for the unsolved cases. In-depth analysis of the genotype through next generation sequencing, together with a standardized in-depth phenotype description and sophisticated high-throughput approaches, have been applied as diagnostic tools to increase the chance of a timely and accurate diagnosis. This approach is very fruitful as, according to the Orphanet database, from 2010 to March 2017 more than 600 new RDs have been described and about 3600 genes linked to RDs have been identified. However, combination of -omics and phenotype data and international sharing of this information raise ethical concerns. Values to be assessed include not only patient autonomy but also family implications, beneficence, non-maleficence, justice, solidarity and reciprocity, which must be respected and promoted and, at the same time, balanced among each other. In this work we suggest that, to maximise patients involvement in the search for a diagnosis and identification of new causative genes, undiagnosed patients should have the possibility to: 1) actively participate in the description of their phenotype; 2) choose the level of visibility of their profile in matchmaking databases; 3) express their preferences regarding return of new findings, in particular which level of Variant of Unknown Significance (VUS) significance should be considered relevant to them. The quality of the relation between individual patients and physicians, and between the patient community and the scientific community is critically important for making the best use of available data and combining efforts in the search for matches with similar cases worldwide that will help to solve unsolved cases. The contribution of patients to collecting and coding data comprehensively is critical for efficient use of data downstream of data collection.

Preprint ARTICLE | doi:10.20944/preprints201804.0207.v1

Failure Characteristics Induced by Unloading Disturbance and Corresponding Mechanical Mechanism of the Coal Seam Floor in Deep Mining

Li Jiazhuo, Xie Guangxiang, Wang Lei

Subject: Engineering, Civil Engineering Keywords: deep mining; coal seam floor; unloading disturbance; space–time difference; stress shell; mechanical mechanism

Online: 16 April 2018 (11:29:05 CEST)

Show abstract| Download PDF| Share

Failure characteristics induced by unloading disturbance and the corresponding mechanical mechanism of the coal seam floor are important theoretical bases for water-bursting prevention from the floor of the coal seam and rock burst alarm in deep mining. However, the existing two-dimensional ground-pressure-control theory based on shallow mining cannot sufficiently guide deep-mining practices. In this study, the redistribution of mining-induced stress field in rocks surrounding the longwall face and mechanical behaviors of strata in deep mining are investigated through a combination of numerical simulation, physical simulation, and field measurement. Results demonstrate that mining-induced stress fields in the floor of the longwall face differ in space and time. Vertical stress unloading from top to bottom of the floor and horizontal stress unloading are relatively low. A concentration zone of high horizontal stress exists at stope boundaries. The critical yield load of rock stratum in the floor is determined through thin plate yield theory. Under the combined effect of concentrated high horizontal and vertical resilience stresses, strata in the floor fracture from seam to seam if the load increases to the minimum critical buckling value. Fractured strata slide along the fracture surface, which leads to floor heave. The stope floor shows evident time-delay progressive failure characteristics. The stress shell in the stope floor in deep mining is found to be a sensitive mechanical parameter that produces three-dimensional ground-pressure behavior in the floor. This ground-pressure behavior in the stope floor is controlled by the existence of the corresponding stress shell and effects induced by its space–time evolution. This study provides theoretical basis for the dynamic control of a hazard-inducing environment in engineering and minimizing or altering disaster-occurrence conditions during the construction engineering of the coal seam floor.

Preprint ARTICLE | doi:10.20944/preprints201801.0097.v1

Heterogeneous Deep Model Fusion for Automatic Modulation Classification

Duona Zhang, Wenrui Ding, Baochang Zhang, Chunyu Xie, Chunhui Liu, Jungong Han, Hongguang Li

Subject: Engineering, Electrical And Electronic Engineering Keywords: deep learning; automatic modulation classification; classifier fusion; convolutional neural network; long short-term memory

Online: 11 January 2018 (04:47:00 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201712.0157.v1

A CNN-Based Fusion Method for Feature Extraction from Sentinel Data

Giuseppe Scarpa, Massimiliano Gargiulo, Antonio Mazza, Raffaele Gaetano

Subject: Engineering, Electrical And Electronic Engineering Keywords: Coregistration; pansharpening; multi-sensor fusion; multitemporal images; deep learning; normalized difference vegetation index (NDVI)

Online: 21 December 2017 (17:10:23 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201704.0061.v1

Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images

Mi Zhang, Xiangyun Hu, Like Zhao, Ye Lv, Min Luo, Shiyan Pang

Subject: Engineering, Electrical And Electronic Engineering Keywords: semantic segmentation; deep convolutional neural networks; manifold ranking; single stream optimization; high resolution image

Online: 11 April 2017 (10:27:10 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202410.2564.v1

General Theory of Information: The Bridge to Mindful Machines

Rao Mikkilineni

Subject: Artificial Intelligence And Machine Learning, Computer Science And Mathematics Keywords: Cognition; Computing Models; Deep Learning; Knowledge Structures; Structural Machines; Associative Memory; Event-Driven Transaction History

Online: 31 October 2024 (16:45:41 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202410.2097.v1

Increased Levels of Hsa-miR-199a-3p and Hsa-miR-382-5p in Maternal and Neonatal Blood Plasma in the Case of Placenta Accreta Spectrum

Angelika V. Timofeeva, Ivan S. Fedorov, Anastasia D. Nikonets, Alla M. Tarasova, Ekaterina N. Balashova, Dmitry N. Degtyarev, Gennady T. Sukhikh

Subject: Biology And Life Sciences, Biochemistry And Molecular Biology Keywords: placenta accreta spectrum; RDS; antenatal corticosteroid therapy; miRNA; deep sequencing; PCR; neonatal complication; blood plasma

Online: 28 October 2024 (13:35:19 CET)

Show abstract| Download PDF| Share

Despite the increasing number of placenta accreta spectrum (PAS) cases in recent years, its im-pact on neonatal outcomes and respiratory morbidity has not yet been extensively studied. In this context, it is crucial to understand the underlying mechanisms of neonatal complications. Moreover, no study has yet demonstrated the effectiveness of antenatal corticosteroid therapy (CT) for prevention of the respiratory distress syndrome (RDS) in newborns of mothers with PAS at the molecular level. In this regard, miRNA profiling was performed on 160 blood plasma sam-ples from preterm infants (gestational age 33–36 weeks) and their mothers diagnosed with or without PAS. The samples with PAS were categorized into groups: without antenatal RDS prophylaxis, and with CT admin-istered either 2–7 days, 7–14 days, or more than 14 days before delivery. These groups were compared to a control group without PAS in the absence of antenatal CT. Deep sequencing was conducted using the NEB-Next® Multiplex Small RNA Library Prep Set for Illumina® on the NextSeq 500/550 platform, followed by validation by quantitative real-time PCR. A significant increase in hsa-miR-199a-3p and hsa-miR-382-5p levels was observed in the blood plasma of newborns with PAS (placenta accreta and increta) compared to the control group. In maternal blood, hsa-miR-199a-3p levels were markedly higher than hsa-miR-382-5p. The timing of antenatal CT significantly influenced the levels of hsa-miR-199a-3p and hsa-miR-382-5p in neonatal plasma from mothers with placenta accreta or increta. A clear trend toward normalization was observed when CT was administered within 14 days before delivery, particularly in the seven days before delivery, but not beyond 14 days. Among newborns with PAS, higher levels of hsa-miR-382-5p were significantly associated with increased Neomod scale severity scores of 2, 4, and 5 compared to a score of 0. Additional-ly, a direct correlation was found between hsa-miR-382-5p level in neonatal plasma and hsa-miR-199a-3p level in the same sample (r = 0.49; p = 0.0001), oxygen requirements in the NICU (r = 0.41; p = 0.0016), duration of NICU stay (r = 0.31; p = 0.019), and the severity of the newborn’s condition based on the NEOMOD scale (r = 0.36; p = 0.0051). Logistic regression mod-els based on maternal plasma levels of hsa-miR-199a-3p and hsa-miR-382-5p predicted the need for cardiotonic therapy, invasive mechanical ventilation, or high-frequency oscillatory ventila-tion in newborns during the early neonatal period, with a sensitivity of 95-100%. It was con-cluded that elevated circulating levels of miRNAs, hsa-miR-199a-3p and hsa-miR-382-5p, in ma-ternal and fetal blood are crucial in the development of respiratory and cardiac complications in newborns from pregnancies affected by PAS. These miRNAs regulate surfactant synthesis in al-veolar cells, fetal organogenesis via IGF-1, the formation of proper lung tissue architecture, and vascular tone.

Preprint REVIEW | doi:10.20944/preprints202410.1785.v1

The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection

Momina Liaqat Ali, Zhou Zhang

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: YOLO; single stage detection; object detection; performance evaluation; deep neural network; real-time object detection

Online: 23 October 2024 (07:25:08 CEST)

Show abstract| Download PDF| Share

This paper presents a comprehensive review of the You Only Look Once (YOLO) framework, a transformative one-stage object detection algorithm renowned for its remarkable balance between speed and accuracy. Since its inception, YOLO has evolved significantly, with versions spanning from YOLOv1 to the most recent YOLOv11, each introducing pivotal innovations in feature extraction, bounding box prediction, and optimization techniques. These advancements, particularly in the backbone, neck, and head components, have positioned YOLO as a leading solution for real-time object detection across a variety of domains. In this review, we explore YOLO's diverse applications, including its critical role in medical imaging for COVID-19 detection, breast cancer identification, and tumor localization, where it has significantly enhanced diagnostic efficiency. YOLO's robust performance in autonomous vehicles is also highlighted, as it excels in challenging conditions like fog, rain, and low-light environments, thereby contributing to improved road safety and autonomous driving systems. In the agricultural sector, YOLO has transformed precision farming by enabling early detection of pests, diseases, and crop health issues, promoting more sustainable farming practices. Additionally, we provide an in-depth performance analysis of YOLO models—such as YOLOv9, YOLO-NAS, YOLOv10, and YOLOv11—across multiple benchmark datasets. This analysis compares their suitability for a range of applications, from lightweight embedded systems to high-resolution, complex object detection tasks. The paper also addresses YOLO's challenges, such as occlusion, small object detection, and dataset biases, while discussing recent advancements that aim to mitigate these limitations. Moreover, we examine the ethical implications of YOLO's deployment, particularly in surveillance and monitoring applications, raising concerns about privacy, algorithmic biases, and the potential to perpetuate societal inequities. These ethical considerations are critical in domains like law enforcement, where biased object detection models can have serious repercussions. Through this detailed review of YOLO's technical advancements, applications, performance, and ethical challenges, this paper serves as a valuable resource for researchers, developers, and policymakers looking to understand YOLO’s current capabilities and future directions in the evolving field of object detection.

Preprint ARTICLE | doi:10.20944/preprints202410.1487.v1

Resistance Spot Welding Defect Detection Based on Visual Inspection: Improved Faster R-CNN Model

Weijie Liu, Jie Hu, Jin Qi

Subject: Engineering, Mechanical Engineering Keywords: resistance spot welding; surface defect detection; deep learning model; Faster R-CNN; small object detection

Online: 18 October 2024 (14:06:38 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202410.1263.v1

Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritisation

Martina Cotena PhD, Angela Ayobi, Colin Zuchowski, Jacqueline C. Junn, Brent D. Weinberg, Peter D. Chang, Daniel S. Chow, Jennifer E. Soun, Mar Roca-Sogorb, Yasmina Chaibi, Sarah Quenet

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: aortic dissection; automated detection; deep learning; prioritised worklist; emergency radiology; multi-reader multi-case study

Online: 16 October 2024 (11:38:12 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202410.0696.v1

Artificial Intelligence Based Target for Personalized Interventions of Atherosclerosis from Gut Microbiota Signature

Suravi Majumder, Koushik Sen, Rabimba Karanjai

Subject: Medicine And Pharmacology, Cardiac And Cardiovascular Systems Keywords: Atherosclerosis; probiotics; gut microbiome; cardiovascular disease; Artificial Intelligence (AI); Machine learning (ML); Deep learning (DL)

Online: 9 October 2024 (14:40:51 CEST)

Show abstract| Download PDF| Supplementary Files| Share

Preprint COMMUNICATION | doi:10.20944/preprints202410.0431.v1

Determining the Level of Threat in Maritime Navigation Based on the Detection of Small Floating Objects with Deep Neural Networks

Mirosław Łącki

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: deep neural networks; detection and classification; safety of marine navigation; image processing; object detection techniques

Online: 8 October 2024 (12:00:28 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202410.0100.v1

Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning

Yihui Wu, Xueying Sun, Dongming Jiang, Hao Zhang, Chunpeng Li, Demin Gao

Subject: Biology And Life Sciences, Forestry Keywords: peak point; Water System; DEM; Spatial Analysis; GIS; terrain characteristics; Landform; Error Analysis; Deep Learning

Online: 1 October 2024 (20:06:56 CEST)

Show abstract| Download PDF| Share

In the study of mountainous areas, mountain peaks play a vital role as geomorphic features that have significant influence on hydrological processes, vegetation distribution, and other important topographic characteristics. From the perspectives of geomorphology and hydrology, the river network water system is an interconnected entity that serves as a crucial component in describing regional topography, geomorphology, and hydrological features. The primary objective of this article is to extract water system information and mountain peak data in Chongli District, Hebei Province. To extract mountain peaks, coarse-resolution Digital Elevation Model (DEM) data is utilized to estimate their positions and initiate data sampling based on DEM elevations. Deep learning models are employed to avoid explicit feature extraction and instead implicitly learn from training data. By using weight sharing techniques, the training parameters of the network are reduced, achieving more accurate extraction and recognition of mountain peaks in Chongli District, along with their classification. For the extraction of the water system, the fast regional convolutional neural network algorithm from target detection is introduced to enhance the efficiency and accuracy of extracting water system information through image processing. This algorithm rapidly identifies the type, location, and width of the water systems. Additionally, the AlexNet transfer learning method is applied to locate the river skeleton within the extracted water system area. Morphological methods are then used to extract river morphology and calculate its length and width. Finally, a developed algorithm for water system information extraction detects the presence of water system coverage areas in Chongli District. Through experiments, a total of 2792 mountain peak data points were successfully extracted. In terms of water system information extraction, the Faster R-CNN and CNN-based methods demonstrate high efficiency and low detection rates. This study provides information services and data support for the operation and maintenance of the Chongli Winter Olympics. Furthermore, it serves as a reference for future research conducted by scholars in the Chongli area, offering insights into various fields such as environmental changes, vegetation classification, and geomorphic features.

Preprint ARTICLE | doi:10.20944/preprints202409.2211.v1

Bayesian Neural Network-Based Approach for Probabilistic Prediction of Building Energy Demands

Akash Mahajan, Srijita Das, Wencong Su, Van-Hai Bui

Subject: Engineering, Electrical And Electronic Engineering Keywords: bayesian neural network; deep learning; building systems; energy demand; probabilistic prediction; time series data ;

Online: 29 September 2024 (03:42:44 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.1975.v1

Biomarkers: The Key To Enhancing Dbs Treatment For Psychiatric Conditions

Guillermo Jose Bazarra Castro, Vicente Casitas, Carlos Martinez-Macho, Alejandra Madero Pohlen, Amelia Alvarez-Sala, Enrique Barbero Pablos, José Fernández Alén, Cristina V. Torres

Subject: Neuroscience And Neurology, Medicine And Pharmacology Keywords: Deep Brain Stimulation (DBS); Psychosurgery; Depression; Obsessive-Compulsive Disorder (OCT); Biomarkers; Diffusion tensor imaging (DTI)

Online: 25 September 2024 (12:46:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.1851.v1

From Single Shot to Structure: End-to-End Network based Deflectometry for Specular Free-Form Surface Reconstruction

M.Hadi Sepanj, Saed Moradi, Amir Nazemi, Claire Preston, Anthony M. D. Lee, Paul Fieguth

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Deflectometry, Specular Surface Reconstruction, Deep Neural Networks, Single-Shot Measurement, Data Simulation, Variational Autoencoder (VAE)

Online: 25 September 2024 (11:35:54 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202409.1879.v1

A Review of Crowd Abnormal Behavior Recognition Technology Based on Computer Vision

Rongyong Zhao, Feng Hua, Bingyu Wei, Cuiling Li, Yulong Ma, Eric S. W. Wong, Fengnian Liu

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Computer Vision; Abnormal Behavior Recognition; Crowd Abnormal Behavior; Deep Learning; Neural Network; Self-Attention Mechanism

Online: 24 September 2024 (10:42:42 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0970.v1

Multi-modal Data Fusion and Deep Ensemble Learning for Accurate Crop Yield Prediction

Akshay Dagadu Yewle, Oktay Karakus

Subject: Environmental And Earth Sciences, Remote Sensing Keywords: Crop Yield; Rice Crop; Multi-modal Remote Sensing; Machine Learning; Ensemble Learning; Deep Ensemble Model

Online: 12 September 2024 (15:50:38 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0740.v1

Secured Artificial Intelligence Based Face Anti-spoofing Detection Model via Serverless Architecture and SaaS Based Cloud Platform

Sai Sanjay Kottakota, Anantha Gnaneswar

Subject: Computer Science And Mathematics, Computer Science Keywords: Serverless Architecture; Facial Recognition Security; Spoof Attack Prevention; Cloud Computin; Cybersecurity; Deep Learning; Threat Mitigation

Online: 10 September 2024 (09:00:24 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202409.0702.v1

Deep Learning Approaches for Wildfire Severity Prediction: A Comparative Study of Image Segmentation Networks and Visual Transformers on the EO4WildFires Dataset

Dimitris Sykas, Dimitrios Zografakis, Konstantinos Demestichas

Subject: Environmental And Earth Sciences, Remote Sensing Keywords: forest wildfires; earth observation; remote sensing; machine learning; deep learning; training dataset; multi-sensor data

Online: 9 September 2024 (16:11:36 CEST)

Show abstract| Download PDF| Share

This paper investigates the applicability of deep learning models for predicting the severity of forest wildfires, utilizing an innovative benchmark dataset called EO4WildFires. EO4WildFires integrates multispectral imagery from Sentinel-2, SAR data from Sentinel-1 and meteorological data from NASA Power annotated with EFFIS data for forest fire detection and size estimation. Resulting in a coverage of 45 countries (Figure \ref{Figure1-events}) with a total of 31730 wildfire events from 2018 to 2022. All these various sources of data are archived into data cubes, with the intention of assessing wildfire severity by considering both current and historical forest conditions, utilizing a broad range of data including temperature, precipitation, and soil moisture. The experimental setup has been arranged to test different deep learning architectures’ effectiveness in predicting the size and shape of wildfire burned areas. The study incorporates both Image Segmentation networks and Visual Transformers, employing a consistent experimental design across various models to ensure comparability of results. Adjustments were made to the training data, such as the exclusion of empty labels and very small events, to refine the focus on more significant wildfire events and potentially improve prediction accuracy. The models’ performance was evaluated using metrics like F1 Score, IoU Score, and Average Percentage Difference (aPD). These metrics offer a multi-faceted view of model performance, assessing aspects such as precision, sensitivity, and the accuracy of the burned area estimation. Through extensive testing with Image Segmentation networks and Visual Transformers, the research not only aims at enhancing the accuracy of estimating the burned area but also underscores the significance of quality training data and the comparative effectiveness of traditional segmentation methods over transformer-based models for this specific application. The dataset is published with an Open Access license and is hosted at: \url{10.5281/zenodo.7762564}.

Preprint ARTICLE | doi:10.20944/preprints202408.1616.v1

Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning

Julian Decker, Lukas Boborzi, Roman Schniepp, Klaus Jahn, Max Wuehr

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: gait analysis; inertial sensor; ear; earable; in-ear sensing; vital sign monitoring; wearables; deep learning

Online: 22 August 2024 (06:01:07 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.1432.v1

Application of Artificial Intelligence and Machine Learning in Expert Systems for the Mining Industry: Literature Review of Modern Methods and Technologies

Natalya Mutovina, Margulan Nurtay, Alexey Kalinin, Aleksandr Tomilov, Nadezhda Tomilova

Subject: Computer Science And Mathematics, Computer Science Keywords: Machine Learning; Artificial Intelligence; Mining Industry; deep learning; Internet of Things; Predictive Analysis; reinforcement learning

Online: 20 August 2024 (08:47:10 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.0948.v1

Groundnut (ARACHIS HYPOGAEA L.) Seed Defect Classification Using Ensemble Deep Learning Techniques

Gebeyehu Belay Gebremeskel, Dinkie Gashaye

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: deep ensemble learning feature extraction; Generative Adversarial Network; Histogram of Oriented Gradients; Visual Geometry Group

Online: 13 August 2024 (13:06:34 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202408.0233.v1

High-Efficiency Extraction of Flavonoids from Flos Sophorae Immaturus Using Ultrasound-Assisted Deep Eutectic Solvent: Optimization and Antioxidant Activity

Xinrui Yang, Ziyan Zhang, Yifeng Zhang

Subject: Chemistry And Materials Science, Food Chemistry Keywords: Flos Sophorae Immaturus; deep eutectic solvent; ultrasound-assisted extraction; flavonoid; response surface methodology; antioxidant activity

Online: 5 August 2024 (11:25:31 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202408.0047.v2

Explainable Artificial Intelligence (XAI) for Diagnosing and Treating Tumors of the Female Reproductive Systems: Challenges and Advances

Xin Gao, Haoyu Li, Chunxia You, Lala Zhou, Qinxuan Shi, Zhanglong Yang, Sicong Shao, Yudong Zhang

Subject: Engineering, Electrical And Electronic Engineering Keywords: Artificial intelligence (AI); gynecological oncology; women’ s health; weakly supervised learning; deep learning; diagnosis and treatment

Online: 21 August 2024 (18:21:10 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202407.2102.v2

Intelligent Vehicle Classification System Based on Deep Learning and Multi-Sensor Fusion

Xinjin Li, Yuanzhe Yang, Yixiao Yuan, Yu Ma, Yangchen Huang, Haowei Ni

Subject: Computer Science And Mathematics, Computer Science Keywords: vehicle classification; deep learning; multi-sensor fusion; convolutional neural network; lidar; gradient boosting decision tree

Online: 30 July 2024 (12:30:24 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202407.2024.v1

Hydropower Plant Available Energy Forecasting Using Artificial Neural Network and Particle Swarm Optimization

Suriya Kaewarsa, Vanhkham Kongpaseuth

Subject: Engineering, Electrical And Electronic Engineering Keywords: energy prediction; reservoir inflow forecasting; deep learning; artificial neural network; particle swarm optimization; PSO-ANN

Online: 25 July 2024 (12:58:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202406.1170.v2

Origin-Destination prediction from Road Segment Speed Data using GraphResLSTM Model

Jun Zhang, Guangtong Hu

Subject: Engineering, Transportation Science And Technology Keywords: OD prediction, Deep learning, Complex network, Intelligent Transportation System, Spatiotemporal dependency, Key Road segment selection

Online: 27 June 2024 (08:07:26 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202406.0986.v1

Deep Learning for Early Disease Detection: A CNN Approach to Classify Potato, Tomato, and Pepper Leaf Diseases

Karan Sarawagi, Hardik Dhiman, Ashutosh Pagrotra, Navjot Singh Talwandi

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: convolutional neural network (CNN); data augmentation; plant disease detection; ReLU activation; deep learning; softmax activation

Online: 14 June 2024 (08:22:52 CEST)

Show abstract| Download PDF| Share

Preprint COMMUNICATION | doi:10.20944/preprints202405.0312.v1

Mineral Identification based on Out-Of-Distribution Detection

Xiaohui Ji, Kaiwen Liang, Yang Yang, Mei Yang, Mingyue He, Zhaochong Zhang, Shan Zeng, Yuzhu Wang

Subject: Environmental And Earth Sciences, Geophysics And Geology Keywords: mineral identification; deep learning; out-of-distribution detection; one-class support vector machines (OCSVM); ResNet

Online: 7 May 2024 (02:24:40 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202403.0484.v2

Deep Learning and Machine Learning for Automatic Grapevine Varieties Identification: A Brief Review

Gabriel A. Carneiro, António Cunha, Joaquim Sousa

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep Learning; Computer Vision; Machine Learning; Grape Variety Identification; Artificial Intelligence; Grapevine Classification; Precision Viticulture

Online: 6 May 2024 (08:47:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202405.0047.v1

The “Galenic Question”: A solution Based on Historical Sources and Mathematical Analysis of Texts

Fernando La Greca, Liberato De Caro, Emilio Matricciani

Subject: Arts And Humanities, History Keywords: classical Greek; deep– language variables; Galen of Pergamum; history of medicine; statistical analysis; linguistics

Online: 1 May 2024 (07:20:05 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.1758.v1

Exploring the Practical Applications of Artificial Intelligence, Deep Learning, and Machine Learning in Maxillofacial Surgery: A Comprehensive Analysis of Published Works

Ladislav Czako, Barbora Sufliarsky, Kristian Simko, Marek Soviš, Ivana Vidova, Michaela Lifkova, Tomas Hamar, Branislav Galis

Subject: Medicine And Pharmacology, Clinical Medicine Keywords: artificial intelligence; deep learning; machine learning; maxillofacial surgery; evidence-based practice; head and neck surgery

Online: 26 April 2024 (14:47:11 CEST)

Show abstract| Download PDF| Share

Artificial intelligence (AI), deep learning (DL) or machine learning (ML) is the ability of computer systems, machines and enginery to work devise procedures like humans. These technologies provide opportunities and possibilities to advance diagnostics and in planning also in the field of human medicine and dentistry. The purpose of this literature review was to ascertain the applicability and significance of AI, as well as to highlight its uses in maxillofacial surgery. The primary inclusion criterion for this publication was an original paper written in English focusing on the use of AI, DL or ML in maxillofacial surgery. The sources of information were PubMed, Scopus and Web of Science, and the queries were made on 31st of December 2023. The search strings used were “artificial intelligence maxillofacial surgery”, “machine learning maxillofacial surgery” and “deep learning maxillofacial surgery”. Following the removal of duplicates, all remaining publications that were returned by the searches and were screened by three independent operators to minimize the risk of bias. The analysis of publications from 1992 to 2023 identified certain records, of which 324 were finally selected. These were calculated according to the year of publication with a continuous increase (excluding 2012 and 2013) of R2 = 0.9295. Generally, in orthognathic dentistry and maxillofacial surgery, artificial intelligence and machine learning have gained popularity over the past few decades. When we included the keywords "planning in maxillofacial surgery" and "planning in orthognathic surgery", the set of published papers significantly increased to the number of 7535 publications. The first publication appeared in 1965, with an increasing trend (excluding 2014-2018), with an R2 value of 0.8642. These tools have been found useful for diagnosis, treatment planning in head and neck surgical oncology, cosmetic and aesthetic surgery, and in oral pathology. In orthognathic surgery, they have been utilised for diagnosis, treatment planning, assessment of treatment needs, cephalometric analyses, and orthognathic surgeries, among other applications. The review confirms that the current use of artificial intelligence and machine learning in maxillofacial surgery is focused mainly on the evaluation of digital diagnostic methods especially radiology, treatment plans and postoperative results. However, as these technologies are integrated in maxillofacial surgery and robotic surgery in head and neck region, it is expected that in the future they will be gradually utilized to plan and comprehensively evaluate the success of maxillofacial surgeries.

Preprint ARTICLE | doi:10.20944/preprints202404.1111.v1

Predicting Machine Failures From Multivariate Time Series: An Industrial Case Study

Nicolò Oreste Pinciroli Vago, Francesca Forbicini, Piero Fraternali

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Failure prediction; Machine Learning; Deep Learning; Predictive Maintenance; Compressor; Blood refrigerator; Nitrogen generator; Wrapping machine

Online: 17 April 2024 (11:41:43 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202404.0548.v1

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

Fomekong Fomekong Rachel Merveille, Baozhu Jia, Zhizun Xu

Subject: Engineering, Marine Engineering Keywords: Visual Simultaneous Localization and Mapping (SLAM), Unmanned Underwater Vehicle, Deep learning, Underwater Navigation, Sensor integration

Online: 8 April 2024 (11:36:27 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202404.0383.v1

Object and Event Detection Pipeline for Rink Hockey Games

J. M. Lopes, L. P. Mota, S. M. Mota, José Manuel Torres, Rui S. Moreira, Christophe Soares, Ivo Pereira, Feliz Gouveia, Pedro Sobral

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep Learning; Rink Hockey; Objects and Events Detection; Artificial Intelligence; Computer Vision; YOLOv7; Team Sports

Online: 4 April 2024 (13:32:18 CEST)

Show abstract| Download PDF| Share

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/preprints202403.1793.v1

A Deep Learning Approach for Online State of Health Estimation of Lithium-Ion Batteries Using Partial Constant Current Charging Curves

Mano Schmitz, Julia Kowal

Subject: Engineering, Electrical And Electronic Engineering Keywords: lithium-ion battery; state of health (SOH); deep learning; neural network; charging curve; ageing scenarios

Online: 29 March 2024 (07:28:21 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/preprints202403.1110.v1

CCLR-DL: A Novel Statistics and Deep Learning Hybrid Method for Feature Selection and Forecasting Healthcare Demand

Guillem Hernández Guillamet, Francesc López Seguí, Josep Vidal Alaball, Beatriz López Ibáñez

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep learning; explainability; feature selection; Granger causality; health demand modelling; LSTM; multivariate time-series forecasting

Online: 22 March 2024 (07:31:07 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202402.1634.v1

Enhancing Legal Sentiment Analysis: A CNN-LSTM Document-Level Model

Bolanle Abimbola, Enrique De La Cal Marin, Qing Tan

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Convolutional neural networks; deep neural networks; long short-term memory; sentimental analysis; recurrent neural networks

Online: 28 February 2024 (13:48:43 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202402.0821.v1

Data Augmentation with Generative Adversarial Network for Solar Panel Segmentation from Remote Sensing Images

Justinas Lekavičius, Valentas Gružauskas

Subject: Environmental And Earth Sciences, Remote Sensing Keywords: deep learning; solar panels; semantic segmentation; data augmentation; generative adversarial network; remote sensing; transfer learning

Online: 14 February 2024 (16:32:01 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202401.1604.v1

Application of Deep Learning Algorithm in Optimization Control of Electrostatic Precipitator in Coal-fired Power Plants

Jianjun Zhu, Chao Feng, Zhongyang Zhao, Haoming Yang, Yujie Liu

Subject: Environmental And Earth Sciences, Pollution Keywords: pollution reduction and carbon emissions reduction; deep learning; energy saving; concentration prediction; particle swarm optimization

Online: 23 January 2024 (00:09:05 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202401.0125.v1

Lung-DT: An AI-Powered Digital Twin Framework for Thoracic Health Monitoring and Diagnosis

Roberta Avanzato, Francesco Beritelli, Alfio Lombardo, Carmelo Ricci

Subject: Computer Science And Mathematics, Signal Processing Keywords: Digital twin; IoT sensors; image processing; lung healthcare; smart healthcare; convolutional neural network; deep learning

Online: 3 January 2024 (10:36:37 CET)

Show abstract| Download PDF| Share

The integration of Artificial Intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in the diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish a digital representation of a patient’s respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-Rays into five distinct categories of lung diseases, including "Normal," "Covid," "Lung Opacity," "Pneumonia," and "Tuberculosis". The system’s performance was evaluated on a chest X-Ray dataset, demonstrating an impressive average accuracy of 96.6% across all classes. Further tests (prediction) were conducted on the trained network using a third dataset available in the literature and completely unknown to the network, yielding an average accuracy of 98% across three classes. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-Rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient’s respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights for personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation.

Preprint ARTICLE | doi:10.20944/preprints202312.0317.v1

Demystifying the Deep Learning Building Blocks

Humberto de Jesús Ochoa Domínguez, Vianey Guadalupe Cruz Sánchez, Osslan Osiris Vergara Villegas

Subject: Engineering, Electrical And Electronic Engineering Keywords: Deep learning; artificial neural networks; convolutional neural layer; activation layer; pooling layer; forward propagation; backpropagation.

Online: 6 December 2023 (07:27:12 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202312.0306.v1

Towards Enhancing Automated Defect Detection (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data Through X-ray Intensity Distribution Modeling for Deep Learning Algorithms

Bata Hena, Ziang Wei, Luc Perron, Clemente Ibarra Castanedo, Xavier P. V. Maldague

Subject: Engineering, Industrial And Manufacturing Engineering Keywords: non-destructive testing; synthetic data; deep learning; automated defect recognition (ADR); digital X-ray radiography

Online: 6 December 2023 (04:00:32 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202311.1462.v1

Evaluation and Comparison of SVM, Deep Learning, and Naïve Bayes Performances for Natural Language Processing Text Classification Task

Destiny Ogaga, Abiodun Olalere

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: text classification; natural language processing; multinomial naï; ve bayes; support vector machine; deep learning

Online: 23 November 2023 (05:28:12 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202310.0329.v1

Marine Cultural Target Detection for Underwater Robotics Based on Deep Aggregation Network with Deformation Convolution

Yutuo Yang, Wei Liang, Daoxian Zhou, Yinlong Zhang, Gaofei Xu

Subject: Computer Science And Mathematics, Robotics Keywords: autonomous underwater vehicle (AUV); underwater target detection; deformable convolution; multi-scale deep aggregation; attention mechanism

Online: 6 October 2023 (11:51:19 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.1788.v1

Characteristics and Research Significance of Micro-Nanoparticles in Geothermal Fluids in the Central Area of Shandong Province

Lei Zuo, Peng Zhang, Yaqin Wang, Rui Liu, Guangxi Ma

Subject: Environmental And Earth Sciences, Water Science And Technology Keywords: geothermal fluids; micro-nanoparticles; TEM; NTA; deep hidden geothermal resources; central area of Shandong Province

Online: 27 September 2023 (05:44:12 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202309.1715.v1

Percutaneous Deep Venous Arterialization for Limb Salvage of No Option Patients with Chronic Limb-Threatening Ischemia

Stavros Spiliopoulos, Efstathia Davoutis, Nikolaos-Achilleas Arkoudis, Kaji Sritharan, Symeon Lechareas

Subject: Medicine And Pharmacology, Cardiac And Cardiovascular Systems Keywords: chronic limb-threatening ischemia; peripheral arterial disease; endovascular treatment; tibial vessels; percutaneous deep venous arterialization

Online: 26 September 2023 (04:44:37 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.1675.v1

Dataset and System Design for Orthopedic Walker Fall Detection and Activity Logging Using Motion Classification

Antony Garcia, Maxwell Huang

Subject: Engineering, Electrical And Electronic Engineering Keywords: orthopedic walker; dataset; IoT; fall detection; activity logging; inertial measurement unit; machine learning; deep learning

Online: 25 September 2023 (10:07:40 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.1392.v1

Developing an Advanced Software Requirements Classification Model Using BERT: an Empirical Evaluation Study on Newly Generated Turkish Data

Fatih Yucalar

Subject: Computer Science And Mathematics, Computer Science Keywords: software requirements classification; transformer learning; deep neural networks; machine learning; functional requirements non-functional requirements.

Online: 20 September 2023 (10:46:19 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.1232.v1

A Survey of Deep Learning-Based Lightning Prediction

Xupeng Wang, Keyong Hu, Yongling Wu, Wei Zhou

Subject: Environmental And Earth Sciences, Atmospheric Science And Meteorology Keywords: lightning prediction; deep learning; spatio-temporal features; convolutional neural networks; long short-term memory networks

Online: 19 September 2023 (13:32:06 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.1174.v1

ENN: Hierarchical Image Classification Ensemble Neural Network for Large-Scale Automated Detection of Potential Design Infringement

Chan Jae Lee, Seong Ho Jeong, Young Yoon

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Design Right Infringement; Deep Learning; Ensemble Learning; Image Classification; Object Detection; Large-Scale Detection System

Online: 19 September 2023 (03:03:46 CEST)

Show abstract| Download PDF| Share

This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. Design rights specify the unique aesthetic characteristics of a product. Due to the rapid change of trends, new design rights are continuously generated. This work proposes an Ensemble Neural Network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. At first, we performed image classification and objection detection learning per design right using the existing models with a proven track record of high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiples the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was done an order of magnitude faster than the single model. ENN maintained a high level of accuracy as it scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as the customs at the border that deal with a swarm of products.

Preprint ARTICLE | doi:10.20944/preprints202309.0702.v1

An Efficient Convolution Neural Network Based Novel Framework for Potato Leaf Diseases Classification and Identification

Sawrnali Khatun, Monishanker Halder, Md. Yasir Arafat, Mohammad Nowsin Amin Sheikh, Dr. Md. Nasim Adnan, Sk. Shalauddin Kabir

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Potato Leaf Diseases Detection; Classification; Transfer learning; Convolution Neural Network; Deep learning; Pre-trained Models

Online: 12 September 2023 (02:52:13 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.0642.v1

Combination of Physics-Informed Neural Networks and Single-Relaxation-Time Lattice Boltzmann Method for Solving Inverse Problems in Fluid Mechanics

Zhixiang Liu, Yuanji Chen, Ge Song, Wei Song, Jingxiang Xu

Subject: Computer Science And Mathematics, Mathematics Keywords: physics-informed neural networks; deep neural networks; lattice Boltzmann method; fluid mechanics; inverse problem; PDEs

Online: 11 September 2023 (07:35:30 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202309.0085.v1

The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild

Panagiotis Derekas, Panagiota Spyridonos, Aristidis Likas, Athanasia Zampeta, George Gaitanis, Ioannis Bassukas

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: deep learning; semantic segmentation; U‐Net; actinic keratosis; cutaneous cancerization field; skin lesions; clinical photography

Online: 4 September 2023 (04:23:19 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202307.2161.v1

Enhancing Water Temperature Prediction in Stratified Reservoirs: A Process-Guided Deep Learning Approach

Sungjin Kim, Sewoong Chung

Subject: Environmental And Earth Sciences, Water Science And Technology Keywords: CE-QUAL-W2; Daecheong Reservoir; Long short-term memory; Process guided deep learning; Water temperature

Online: 1 August 2023 (07:16:22 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202307.0847.v1

Quorum Sensing: Unravelling the Intricacies of Microbial Communication for Biofilm Formation, Biogeochemical Cycling, and Biotechnological Applications

Edamkue Israel, Selvarajan Ramganesh, Akebe Luther King Abia, Chioma Blaise Chikere

Subject: Environmental And Earth Sciences, Environmental Science Keywords: quorum sensing; microbial communication; biofilm formation; biogeochemical cycling; biotechnological applications; marine environment; deep‐sea environment

Online: 13 July 2023 (05:26:58 CEST)

Show abstract| Download PDF| Share

Preprint TECHNICAL NOTE | doi:10.20944/preprints202307.0705.v1

Technical Note: Using Computer Vision’s Pixel Segmentation to Detect Beef Cattle Feeding Behavior

Yalong Pi, Egleu Mendes, Luis Tedeschi, Jian Tao, Siddhanth Reddy, Nick Duffield

Subject: Biology And Life Sciences, Animal Science, Veterinary Science And Zoology Keywords: Computer Vision; Pixel Segmentation; Deep Learning; Convolutional Neural Network; Precision Livestock Farming; Feeding Behavior Analysis

Online: 11 July 2023 (11:52:38 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202307.0288.v1

Predicting Idiosyncratic Volatility from Stock Market Trade Records: A Machine Learning Approach

Nasrin Seifi, Hassan S. Shavarani

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Idiosyncratic Volatility Estimation/Prediction; Machine Learning; Deep learning Based Regression; Tree-Based Regression; Artificial Intelligence

Online: 6 July 2023 (02:14:16 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202306.1068.v1

Comparison of Transfer Learning and Established Calibration Transfer Methods for Metal Oxide Semiconductor Gas Sensors

Yannick Robin, Johannes Felix Amann, Tizian Schneider, Andreas Schütze, Christian Bur

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Indoor air quality; metal oxide semiconductor; volatile organic compounds; calibration transfer; deep learning; direct standardization

Online: 15 June 2023 (07:17:20 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202306.0830.v1

Wireless Device with Energy Management for Closed-Loop Deep Brain Stimulation (CLDBS)

Tiago Matheus Nordi, Gabriel Augusto Ginja, Rodrigo Gounella, Erich Talanoni Fonoff, Eduardo Colombari, Melkzedekue M. Alcântara Moreira, Jose A. Afonso, Vitor Monteiro, Joao L. Afonso, João Paulo Carmo

Subject: Engineering, Electrical And Electronic Engineering Keywords: closed-loop deep brain stimulation (CLDBS); neurostimulatio; implantable devices; internet of things (IoT); energy management

Online: 12 June 2023 (11:11:09 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202305.2180.v1

Deep Camera-Radar Fusion with Attention Framework for Autonomous Vehicle Vision in Foggy Weather Conditions

Isaac Oluwadunsin Ogunrinde, Shonda Bernadin

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Sensor fusion; object detection; deep learning; autonomous vehicles; camera-radar; adverse weather; fog; attention module

Online: 31 May 2023 (07:25:27 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202305.1245.v1

The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models

Talya Tümer-Sivri, Nergis Pervan-Akman, Ali Berkol

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep neural networks; Activation functions; Multiclass classification; Time-Series prediction; Reuters data; Energy trade value

Online: 17 May 2023 (11:11:21 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202305.0376.v1

Monkeypox: Re-emerging Infectious Disease and One Health Strategy

Cheryl Ann Ann Alexander, Lidong Wang

Subject: Public Health And Healthcare, Public Health And Health Services Keywords: monkeypox; One Health; Big Data analytics; deep learning; blockchain; cybersecurity; vaccine; sexually transmitted diseases; HIV

Online: 6 May 2023 (04:50:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202305.0007.v1

An Advanced Approach on Enhancing Accommodation Maintenance Via Text-Based Customer Review Analysis

Tharindu Wickramasinghe, Pumudu Fernando

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Machine Learning; Classification; Natural Language Processing; Text-based Customer Review Analysis; Sentiment Analysis; Deep Learning

Online: 1 May 2023 (03:21:05 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202304.1035.v1

A Review on Deriving Maintenance of Accommodations Via Text-based Feedback Analysis

Tharindu Wickramasinghe, Pumudu Fernando

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Machine Learning; Classification; Natural Language Processing; Text-based Customer Review Analysis; Sentiment Analysis; Deep Learning

Online: 27 April 2023 (04:30:17 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202304.0645.v1

Automated Word-level Lip Reading using Convolutional Neural Networks with New Turkish Dataset

Nergis Pervan-Akman, Ali Berkol, Hamit Erdem

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Lip Reading; Multiclass Classification; Turkish Lip Reading Dataset; Deep Learning; Convolutional Neural Networks; Lip Detection

Online: 20 April 2023 (10:07:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202304.0022.v1

Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters - An Experimental Study

Bata Hena, Ziang Wei, Clemente Ibarra Castanedo, Xavier Maldague

Subject: Engineering, Aerospace Engineering Keywords: non-destructive testing; deep learning; automated defect recognition (ADR); semantic segmentation; digital X-ray radiography

Online: 3 April 2023 (10:25:31 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202303.0203.v1

Liver Transplant in Patients With Hepatocarcinoma: Imaging Guidelines and Future Perspectives Using Artificial Intelligence

Mihai Dan Pomohaci, Mugur Cristian Grasu, Radu Lucian Dumitru, Mihai Toma, Ioana Gabriela Lupescu

Subject: Medicine And Pharmacology, Gastroenterology And Hepatology Keywords: Hepatocarcinoma; Cirrhosis; Liver transplantation; Liver transplant; Artificial intelligence; Machine learning; Radiomics; Deep learning; Neural networks

Online: 13 March 2023 (02:13:50 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202302.0236.v1

Reinforcement Learning for the Face Support Pressure of Tunnel Boring Machines

Enrico Soranzo, Carlotta Guardiani, Wei Wu

Subject: Engineering, Civil Engineering Keywords: Tunnelling; Tunnel Boring Machine; Support pressure; Face stability; Reinforcement Learning; Machine Learning; Deep-Q-Network

Online: 14 February 2023 (06:10:35 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202302.0050.v1

A Concise Overview of the Vision-based Human Action Recognition Field

Fernando Camarena, Miguel Gonzalez-Mendoza, Leonardo Chang, Ricardo J Cuevas-Ascencio

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: video-based human action recognition; Action Recognition; Deep Learning Methods; handcrafted Methods; Human Action; Overview

Online: 3 February 2023 (01:17:56 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202206.0230.v1

How the First Year of the COVID-19 Pandemic Impacted Patients’ Care in the Vascular Surgery Divisions of the Southern Regions of the Italian Peninsula

Eugenio Martelli, Giovanni Sotgiu, Laura Saderi, Massimo Federici, Giuseppe Sangiorgi, Matilde Zamboni, Allegra Rosa Martelli, Giancarlo Accarino, Giuseppe Bianco, Francesco Bonanno, Umberto Marcello Bracale, Enrico Cappello, Giovanni Cioffi, Giovanni Colacchio, Adolfo Crinisio, Salvatore De Vivo, Carlo Patrizio Dionisi, Loris Flora, Giovanni Impedovo, Francesco Intrieri, Luca Iorio, Gabriele Maritati, Piero Modugno, Mario Monaco, Giuseppe Natalicchio, Vincenzo Palazzo, Fernando Petrosino, Francesco Pompeo, Raffaele Pulli, Davide Razzano, Maurizio Ruggero Ruggieri, Carlo Ruotolo, Paolo Sangiuolo, Gennaro Vigliotti, Pietro Volpe, Antonella Biello, Pietro Boggia, Michelangelo Boschetti, Enrico Maria Centritto, Flavia Condò, Lucia Cucciolillo, Amodio Salvatore D'Amodio, Mario De Laurentis, Claudio Desantis, Daniela Di Lella, Giovanni Di Nardo, Angelo Disabato, Ilaria Ficarelli, Angelo Gasparre, Antonio Nicola Giordano, Alessandro Luongo, Mafalda Massara, Vincenzo Molinari, Andrea Padricelli, Marco Panagrosso, Anna Petrone, Serena Pisanello, Roberto Prunella, Michele Tedesco, Alberto Maria Settembrini

Subject: Medicine And Pharmacology, Hematology Keywords: COVID-19; carotid stenosis; abdominal aortic aneurysm; chronic limb-threatening ischemia; amputation; deep venous thrombosis

Online: 16 June 2022 (04:40:54 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202206.0166.v1

The Long-Term Efficacy, Prognostic Factors, Safety, and Hospitalization Costs following Denervation and Myotomy of the Affected Muscles and Deep Brain Stimulation in 94 Patients with Spasmodic Torticollis

Zhiqiang Cui, Tong Chen, Jian Wang, Zhiqi Mao, Longsheng Pan, Zhipei Ling, Jianning Zhang, Xuemei Li

Subject: Medicine And Pharmacology, Neuroscience And Neurology Keywords: spasmodic torticollis (ST); deep brain stimulation (DBS); denervation and myotomy (DAM); hospitalization cost; prognostic factors

Online: 13 June 2022 (04:12:34 CEST)

Show abstract| Download PDF| Share

Surgical methods for treating spasmodic torticollis include denervation and myotomy (DAM) of the affected muscles, and deep brain stimulation (DBS). This study reports on the long-term efficacy, prognostic factors, safety, and hospitalization costs following these two procedures. We collected data from 94 patients with spasmodic torticollis, of whom 41 and 53 were treated with DAM and DBS, respectively, from June 2008 to December 2020 at the Chinese People’s Liberation Army General Hospital. We used the Tsui scale and the global outcome score of the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS) to evaluate the preoperative and postoperative clinical condition in all patients. We also determined the cost of hospitalization, prognostic factors, and serious adverse events following the two surgical procedures. The mean follow-up time was 68.83 months (range = 13–116). Both resection surgery and DBS showed good results in terms of Tsui (Z = -5.103, P = 0.000; Z = -6.210, P = 0.000) and TWSTRS scores (t = 8.762, P = 0.000; Z = -6.308, P = 0.000). Compared with the DAM group, the preoperative (47.71, range 24–67.25) and postoperative (18.57, range 0–53) TWSTRS scores in the DBS group were significantly higher (Z = -3.161, P = 0.002). We found no correlation between prognostic factors and the patient age, gender, or disease duration for either surgical procedure. However, prognostic factors were related to the length of the postoperative follow-up period in the DBS surgery group (Z = -2.068, P = 0.039; Z = -3.287, P = 0.001). The mean hospitalization cost in the DBS group was 6.85 times that found in the resection group (Z = -8.284, P = 0.000). The total complication rate was 4.26%. We found, both resection surgery and DBS, showed good results in the patients with spasmodic torticollis. Although DBS had a greater impact on the quality of life and the degree of pain relief, it was more expensive. Prognostic factors were related to the length of the postoperative follow-up period in patients who underwent DBS surgery.

Preprint ARTICLE | doi:10.20944/preprints202204.0279.v1

Exploiting Concepts of Instance Segmentation to Boost Detection in Challenging Environments

Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: object detection; challenging environments; low-light; image enhancement; complex environments; deep neural networks; computer vision

Online: 28 April 2022 (09:42:37 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202202.0301.v1

Deep Learning Segmentation of Satellite Imagery Identifies Aquatic Vegetation Associated with Snail Intermediate Hosts of Schistosomiasis in Senegal, Africa

Zac Yung-Chun Liu, Andrew J. Chamberlin, Krti Tallam, Isabel J. Jones, Lance L. Lamore, John Bauer, Mariano Bresciani, Caitlin M. Wolfe, Renato Casagrandi, Lorenzo Mari, Mariano Gatto, Abdou Ka Diongue, Lamine Toure, Jason Rohr, Gilles Riveau, Nicolas Jouanard, Chelsea L. Wood, Susanne H. Sokolow, Lisa Mandle, Gretchen Daily, Eric F. Lambin, Giulio A. De Leo

Subject: Biology And Life Sciences, Ecology, Evolution, Behavior And Systematics Keywords: deep learning; U-Net; semantic segmentation; schistosomiasis; aquatic vegetation; Neglected Tropical Diseases; Senegal River Basin

Online: 24 February 2022 (07:38:13 CET)

Show abstract| Download PDF| Share

Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identify potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination.

Preprint ARTICLE | doi:10.20944/preprints202112.0192.v1

Using Enhanced Sparrow Search Algorithm-Deep Extreme Learning Machine Model to Forecast End-Point Phosphorus Content of BOF

Lingxiang Quan, Ailian Li, Guimei Cui, Shaofeng Xie

Subject: Engineering, Industrial And Manufacturing Engineering Keywords: End-point phosphorus content; Deep extreme learning machine; Sparrow search algorithm; Trigonometric substitution; Cauchy mutation

Online: 10 December 2021 (15:04:59 CET)

Show abstract| Download PDF| Supplementary Files| Share

Preprint ARTICLE | doi:10.20944/preprints202110.0237.v1

Deep Cross-Project Software Reliability Growth Model using Project Similarity Based Clustering

Kyawt Kyawt San, Hironori Washizaki, Yoshiaki Fukazawa, Kiyoshi Honda, Masahiro Taga, Akira Matsuzaki

Subject: Computer Science And Mathematics, Information Systems Keywords: Software reliability; deep learning; long short-term memory; project similarity and clustering; cross-project prediction

Online: 18 October 2021 (10:33:39 CEST)

Show abstract| Download PDF| Share

Working Paper ARTICLE

Sensor-fusion for Smartphone Location Tracking using Hybrid Multimodal Deep Neural Networks

Xijia Wei, Zhiqiang Wei, Valentin Radu

Subject: Computer Science And Mathematics, Computer Science Keywords: Indoor Localization; Sensor Fusion; Multimodal Deep Neural Network; Multimodal Sensing; WiFi Fingerprinting; Pedestrian Dead Reckoning

Online: 13 October 2021 (12:14:39 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202108.0347.v1

A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction

Tahjid Ashfaque Mostafa, Sara Soltaninejad, Tara L. McIsaac, Irene Cheng

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Parkinson’s Disease; Freeze of Gait; Deep Learning; Ensemble Learning; Wearable Sensor Data, Detection and Predication

Online: 16 August 2021 (16:48:14 CEST)

Show abstract| Download PDF| Share

Working Paper REVIEW

Machine Learning of Spatial Data

Behnam Nikparvar, Jean-Claude Thill

Subject: Social Sciences, Geography, Planning And Development Keywords: spatial machine learning; spatial dependence; spatial heterogeneity; scale; spatial observation matrix; learning algorithm; deep learning

Online: 6 August 2021 (14:18:55 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202108.0060.v1

Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions

Iqbal H. Sarker

Subject: Computer Science And Mathematics, Information Systems Keywords: deep learning; artificial neural network; artificial intelligence; discriminative learning; generative learning; hybrid learning; intelligent systems;

Online: 2 August 2021 (17:33:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202106.0294.v1

Combining Business Model Innovation and Model-based Analysis to Tackle the Deep Uncertainty of Societal Transitions – A Case Study on Industrial Electrification and Power Grid Management

Juliana Zapata Riveros, Matthias Speich, Mirjam West, Silvia Ulli-Beer

Subject: Business, Economics And Management, Accounting And Taxation Keywords: Prosumer concepts; technology change; business strategies; system dynamics; decentralization; photovoltaic; deep uncertainty; low-carbon transitions

Online: 10 June 2021 (13:26:49 CEST)

Show abstract| Download PDF| Supplementary Files| Share

Preprint ARTICLE | doi:10.20944/preprints202103.0165.v1

Combining Business Model Innovation and Model-Based Analysis to Tackle the Deep Uncertainty of Societal Transitions – a Case Study on Industrial Electrification and Power Grid Management

Juliana Zapata Riveros, Matthias Speich, Mirjam West, Silvia Ulli-Beer

Subject: Business, Economics And Management, Accounting And Taxation Keywords: Prosumer concepts; technology change; business strategies; system dynamics; decentralization; photovoltaic; deep uncertainty; low-carbon transitions

Online: 4 March 2021 (14:14:46 CET)

Show abstract| Download PDF| Supplementary Files| Share

Preprint REVIEW | doi:10.20944/preprints202102.0340.v1

Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective

Iqbal H. Sarker

Subject: Computer Science And Mathematics, Security Systems Keywords: Cybersecurity; Deep Learning; Artificial Neural Network; Artificial Intelligence; Cyber-Attacks; Cybersecurity Analytics; Cyber Threat Intelligence

Online: 16 February 2021 (15:31:02 CET)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202102.0108.v1

Machine Learning and Deep Learning for Sentiment Analysis Over Students' Reviews: An Overview Study

Ru Yang

Subject: Computer Science And Mathematics, Algebra And Number Theory Keywords: Sentiment Analysis; Students' feedback; Students' reviews; Natural language processing; Data mining; Deep learning; Machine learning

Online: 3 February 2021 (10:11:54 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202011.0591.v2

Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform

Mohammadreza Kaji, Jamshid Parvizian, Hans Wernher van de Venn

Subject: Engineering, Automotive Engineering Keywords: health indicator; performance degradation assessment; deep learning; vibration monitoring; bearing; remaining useful life; digital twin

Online: 11 December 2020 (11:59:20 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202011.0039.v1

Generative Model for Skeletal Human Movements based on conditional DC-GAN applied to pseudo-images

Wang Xi, Guillaume Devineau, Fabien Moutarde, Jie Yang

Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: generative model; human movement; conditional Deep Convolutional Generative Adversarial Network; GAN; spatio-temporal pseudo-image

Online: 2 November 2020 (12:55:22 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202010.0290.v1

Rapid COVID-19 Diagnosis Using Deep Learning of the Computerized Tomography Scans

Hamed Tabrizchi, Amir Mosavi, Akos Szabo-Gali, Laszlo Nadai

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: COVID-19; image-based diagnosis; artificial intelligence; machine learning; deep learning; computerized tomography; coronavirus disease

Online: 14 October 2020 (09:07:51 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202009.0458.v1

High-Throughput Phenotyping of Soybean Maturity Using Time Series UAV Imagery and Convolutional Neural Networks

Rodrigo Trevisan, Osvaldo Pérez, Nathan Schmitz, Brian Diers, Nicolas Martin

Subject: Biology And Life Sciences, Agricultural Science And Agronomy Keywords: machine learning; deep leaning; physiological maturity; computer vision; plant breeding; Phenology; Glycine max (L.) Merr.

Online: 19 September 2020 (10:08:43 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints202008.0320.v1

Data Science in Unveiling COVID-19 Pathogenesis and Diagnosis: Evolutionary Origin to Drug Repurposing

Jayanta Kumar Das, Giuseppe Tradigo, Pierangelo Veltri, Pietro H Guzzi, Swarup Roy

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Data Science; Machine Learning; Deep Learning; Genomics; COVID-19; Drug Discovery; Image Analysis; Interactomics; Epidemiology

Online: 14 August 2020 (11:01:56 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints202008.0179.v1

Breast Cancer Mass Detection in DCE-MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs In Situ Carcinoma through A Machine-learning Approach

Luana Conte, Benedetta Tafuri, Maurizio Portaluri, Alessandro Galiano, Eleonora Maggiulli, Giorgio De Nunzio

Subject: Medicine And Pharmacology, Oncology And Oncogenics Keywords: Breast Cancer; Radiomics; Machine Learning; Deep Learning; Segmentation; In Situ Breast Cancer; Infiltrative Breast Cancer

Online: 7 August 2020 (09:29:33 CEST)

Show abstract| Download PDF| Share

Preprint REVIEW | doi:10.20944/preprints201908.0166.v1

Deep Learning and Machine Learning in Hydrological Processes, Climate Change and Earth Systems: A Systematic Review

Sina Faizollahzadeh ardabili, Amir Mosavi, Majid Dehghani, Annamária R. Várkonyi-Kóczy

Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: machine learning; deep learning; big data; hydrology; climate change; global warming; hydrological model; earth systems

Online: 15 August 2019 (05:50:48 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201904.0322.v1

Research on Recognition Technology of Aluminum Profile Surface Defects Based on Deep Learning

Ruofeng Wei, Yunbo Bi

Subject: Engineering, Mechanical Engineering Keywords: aluminum profile surface defects; multiscale defect detection network; deep learning; average precision(AP); saliency maps

Online: 29 April 2019 (09:37:07 CEST)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201811.0612.v1

A Deep Temporal Convolutional Neural Network for Regional and Teleseismic Detection

Joshua Dickey, Brett Borghetti, William Junek

Subject: Environmental And Earth Sciences, Geophysics And Geology Keywords: geophysical signal processing; pattern recognition; temporal convolutional neural networks; seismology; deep learning; nuclear treaty monitoring

Online: 29 November 2018 (03:37:48 CET)

Show abstract| Download PDF| Share

Preprint ARTICLE | doi:10.20944/preprints201811.0045.v1

Cyber-Physical Attack Detection and Recovery based on RNN in Automotive Brake Systems

Jongho Shin, Youngmi Baek, Jaeseong Lee, Seonghun Lee

Subject: Engineering, Electrical And Electronic Engineering Keywords: Cyber-Physical Systems; Automotive; Cyber-Physical Attack; Integrity; Sensor Attack Detection; Speed Estimation; Deep learning

Online: 2 November 2018 (10:16:50 CET)

Show abstract| Download PDF| Share

The violation of data integrity in automotive Cyber-Physical Systems (CPS) may lead to dangerous situations for drivers and pedestrians in terms of safety. In particular, cyber-attacks on the sensor could easily degrade data accuracy and consistency over any other attack, we investigate attack detection and identification based on a deep learning technology on wheel speed sensors of automotive CPS. For faster recovery of a physical system with detection of the cyber-attacks, estimation of a specific value is conducted to substitute false data. To the best of our knowledge, there has not been a case of joining sensor attack detection and vehicle speed estimation in existing literatures. In this work, we design a novel method to combine attack detection and identification, vehicle speed estimation of wheel speed sensors to improve the safety of CPS even under the attacks. First, we define states of the sensors based on the cases of attacks that can occur in the sensors. Second, Recurrent Neural Network (RNN) is applied to detect and identify wheel speed sensor attacks. Third, in order to estimate the vehicle speeds accurately, we employ Weighted Average (WA), as one of the fusion algorithms, in order to assign a different weight to each sensor. Since environment uncertainty while driving has an impact on different characteristics of vehicles and cause performance degradation, the recovery mechanism needs the ability adaptive to changing environments. Therefore, we estimate the vehicle speeds after assigning a different weight to each sensor depending on driving situations classified by analyzing driving data. Experiments including training, validation, and test are carried out with actual measurements obtained while driving on the real road. In case of the fault detection and identification, classification accuracy is evaluated. Mean Squared Error (MSE) is calculated to verify that the speed is estimated accurately. The classification accuracy about test additive attack data is 99.4978%. MSE of our proposed speed estimation algorithm is 1.7786. It is about 0.2 lower than MSEs of other algorithms. We demonstrate that our system maintains data integrity well and is safe relatively in comparison with systems which apply other algorithms.

Search Results

1474 articles found