Multiphase time-varying batch process monitoring based on stage moving model migration by Luping Zhao, Zhongren Chen

“…Secondly, to analyze and capture the relationship between the process variables of both the old mode and new mode and the final quality variable, the JY-PLS algorithm is utilized on each time slice within sliding windows for quality prediction. …”
Get full text

Cloud native intelligent operation and maintenance technology by Long XUE, Gang LU, Qi ZHOU, Huiyan ZHANG, Tingjun WAN

“…Relying on the advantages of simple and fast applications,easy deployment of applications,and on-demand scaling of running applications,cloud native technology has been rapidly promoted.However,with the application of cloud native,the system architecture has become more complex and the scale of resources has become larger,and there is an urgent need for more intelligent operation and maintenance.Using intelligent operation and maintenance can better assist cloud-native application development,reduce operation and maintenance costs,and improve service quality.The application scenarios,key points,classic practices and existing problems of intelligent operation and maintenance were analyzed,and a cloud-native intelligent operation and maintenance architecture were proposed,and the main principles of the three scenarios:the trend prediction,data anomaly detection and fault location diagnosing in the core service algorithm platform were introduced in detail,and finally the future of intelligent operation and maintenance were looked forward.…”
Get full text

RL-Based Vibration-Aware Path Planning for Mobile Robots’ Health and Safety by Sathian Pookkuttath, Braulio Felix Gomez, Mohan Rajesh Elara

“…Terrain roughness is classified into four levels using IMU sensor data, achieving average prediction accuracy of 97% with a 1D CNN model. A vibration cost map is created by assigning vibration costs to each predicted class on a 2D occupancy grid, incorporating obstacles, vibration-prone areas, and the robot’s pose for navigation. …”
Get full text

Machine learning approach for identifying and forecasting streamflow droughts in data limited basins of South Korea using threshold levels by Young-Ho Seo, Jang Hyun Sung, Byung-Sik Kim, Junehyeong Park

“…We utilized the XGBoost algorithm, integrating comprehensive meteorological data to enhance the accuracy and reliability of the drought predictions. …”
Get full text

Modélisation pluie-débit en région tropicale humide : application des réseaux de neurones sur quatre stations hydrométriques du Bandama Blanc (Bada, Marabadiassa, Tortiya et Bou) s... by Yao Blaise Koffi

“…To achieve this goal, two Multilayer Perceptrons trained with the backpropagation algorithm of error have been built. The first model was used only in simulation and the second in simulation and prediction. …”
Get full text

Ecological niche modelling using MaxEnt for riparian species in a Mediterranean context by Jean Stephan, Melissa Korban

“…Despite their key environmental role, riparian tree and shrub species gained little attention in ecological niche modeling (ENM), especially in semi-arid environments.This study examines the performance of selected climatic, topographic, and geographic predictors in ENM of obligate and non-obligate riparian tree and shrub species in perennial and intermittent streams in the Mediterranean biome.MaxEnt algorithm was used for ENM. Three models were designed with different sets of predictors with cropped and non-cropped backgrounds around the riparian zone.The models generated different predicted distribution maps by species and compared them with the presence points of the studied species. …”
Get full text

Identification of an HLA-A2-restricted epitope peptide derived from hypoxia-inducible protein 2 (HIG2). by Sachiko Yoshimura, Takuya Tsunoda, Ryuji Osawa, Makiko Harada, Tomohisa Watanabe, Tetsuro Hikichi, Masahiro Katsuda, Motoki Miyazawa, Masaji Tani, Makoto Iwahashi, Kazuyoshi Takeda, Toyomasa Katagiri, Yusuke Nakamura, Hiroki Yamaue

“…Among several candidate peptides predicted by the HLA-binding prediction algorithm, HIG2-9-4 peptide (VLNLYLLGV) was able to effectively induce peptide-specific cytotoxic T lymphocytes (CTLs). …”
Get full text

The design of copper flotation process based on multi-label classification and regression by Haipei Dong, Fuli Wang, Dakuo He, Yan Liu

“…Moreover, further improves the prediction effect through the following methods: (1) Referencing adaboost algorithm, the training set samples with large prediction error in the previous iteration are set with higher weight; (2) To enhance robustness, the label uncertainty coefficient is introduced; (3) To alleviate the over fitting of small sample machine learning, bootstrap aggregating is introduced for each sub label. …”
Get full text

An AIoT-Based Automated Farming Irrigation System for Farmers in Limpopo Province by Relebogile Langa, Michael Nthabiseng Moeti, Thabiso Maubane

“…A machine learning precipitation prediction algorithm optimizes water usage. The paper also describes a system with multiple sensors that detect soil parameters, and automatically irrigate land based on soil moisture by switching the motor on/off. …”
Get full text

Enhancing Flow Direction in Geothermal Fields Using Sentinel-1 Data for Sustainability Water Management by Utama Widya, Anjasmara Ira Mutiara, Handayani Hepi Hapsari, Indriani Rista Fitri

“…This study develops a flow direction prediction model using Sentinel-1 satellite imagery during rainy and dry seasons through the Random Forest machine learning algorithm. …”
Get full text

Weighted frequent gene co-expression network mining to identify genes involved in genome stability. by Jie Zhang, Kewei Lu, Yang Xiang, Muhtadi Islam, Shweta Kotian, Zeina Kais, Cindy Lee, Mansi Arora, Hui-Wen Liu, Jeffrey D Parvin, Kun Huang

“…Gene co-expression network analysis is an effective method for predicting gene functions and disease biomarkers. However, few studies have systematically identified co-expressed genes involved in the molecular origin and development of various types of tumors. …”
Get full text

Identification of DNA N6-methyladenine modifications in the rice genome with a fine-tuned large language model by Yichi Zhang, Hao Chen, Shicheng Xiang, Zhibin Lv

“…These features are then processed by an XGBoost algorithm to generate predictions. To further validate the effectiveness of our fine-tuning strategy, we employ UMAP(Uniform Manifold Approximation and Projection) visualization. …”
Get full text

Method for Acquiring Passenger Standing Positions on Subway Platforms Based on Binocular Vision by Jing Zuo, Yanchong Wang, Runqi Wang

“…Validation of the proposed model using this dataset shows that 91.9% of the predicted standing positions of passengers exhibit an error of less than 41.8 centimeters, with an average prediction error of 18.1 centimeters and an average computation time of 860 milliseconds. …”
Get full text

Reinforced Cost-Sensitive Graph Network for Detecting Fraud Leaders in Telecom Fraud by Peiwen Gao, Zhihua Li, Dibin Zhou, Liang Zhang

“…Finally, weight coefficients are dynamically optimized using the Deep Deterministic Policy Gradient (DDPG) algorithm, and the prediction results of the three base classifiers are combined to produce the final classification outcomes. …”
Get full text

Field Test and Numerical Research of Blast-Induced Liquefaction in Calcareous Sand by Changchun Li, Yumin Chen, Yingkang Yao, Yonggang Gou, Qiongting Wang, Junwei Guo, Xiao Xie

“…The research results can provide a theoretical reference for the prediction of blast-induced liquefaction in saturated calcareous sand foundations.…”
Get full text

Galaxy Spectroscopy without Spectra: Galaxy Properties from Photometric Images with Conditional Diffusion Models by Lars Doorenbos, Eva Sextl, Kevin Heng, Stefano Cavuoti, Massimo Brescia, Olena Torbaniuk, Giuseppe Longo, Raphael Sznitman, Pablo Márquez-Neila

“…Additionally, we can predict the presence of an active galactic nucleus up to an accuracy of 82%. …”
Get full text

An automated hip fracture detection, classification system on pelvic radiographs and comparison with 35 clinicians by Abdurrahim Yilmaz, Kadir Gem, Mucahit Kalebasi, Rahmetullah Varol, Zuhtu Oner Gencoglan, Yegor Samoylenko, Hakan Koray Tosyali, Guvenir Okcu, Huseyin Uvet

“…This study proposes an automated system that uses convolutional neural networks (CNNs) to detect potential fracture areas and predict fracture conditions, aiming to outperform traditional object detection-based systems. …”
Get full text

Identification of 17 novel epigenetic biomarkers associated with anxiety disorders using differential methylation analysis followed by machine learning-based validation by Yoonsung Kwon, Asta Blazyte, Yeonsu Jeon, Yeo Jin Kim, Kyungwhan An, Sungwon Jeon, Hyojung Ryu, Dong-Hyun Shin, Jihye Ahn, Hyojin Um, Younghui Kang, Hyebin Bak, Byoung-Chul Kim, Semin Lee, Hyung-Tae Jung, Eun-Seok Shin, Jong Bhak

“…We further developed a robust diagnostic risk prediction system to classify anxiety disorders from healthy controls using the 17 biomarkers. …”
Get full text

Machine Learning Creates a Simple Endoscopic Classification System that Improves Dysplasia Detection in Barrett’s Oesophagus amongst Non-expert Endoscopists by Vinay Sehgal, Avi Rosenfeld, David G. Graham, Gideon Lipman, Raf Bisschops, Krish Ragunath, Manuel Rodriguez-Justo, Marco Novelli, Matthew R. Banks, Rehan J. Haidry, Laurence B. Lovat

“…These generate a simple algorithm to accurately predict dysplasia. Once taught to non-experts, the algorithm significantly improves their rate of dysplasia detection. …”
Get full text

Cellular senescence defining the disease characteristics of Crohn’s disease by Wenyu Zhang, Xianzong Ma, Xianzong Ma, Wenqing Tian, Yongsheng Teng, Meihua Ji

“…The support vector machine (SVM) algorithm, random forest algorithm and LASSO regression analysis was used to construct a diagnostic model. …”
Get full text