Proposing a framework for body mass prediction with point clouds: A study applied in typical swine pen environments by Gabriel Pagin, Luciane Silva Martello, Rubens André Tabile, Rafael Vieira de Sousa

“…Using a Python script, the Convex Hull (CH) and Alpha Shape (AS) algorithms were applied to extract dimensional characteristics from the dorsal region of the pigs, including perimeter, surface area (3D), projected surface area (2D), and volume, generating two datasets (CH and AS). Subsequently, machine learning models (Random Tree - RT, Random Forest - RF, Linear Regression - LR, K-Nearest Neighbors - KNN, Support Vector Regression - SVR, and Multilayer Perceptron - MLP) were trained, optimized, and evaluated using k-fold cross-validation, followed by statistical analysis. …”
Get full text

Super-Exponential Approximation of the Riemann–Liouville Fractional Integral via Gegenbauer-Based Fractional Approximation Methods by Kareem T. Elgindy

“…Tunable shifted Gegenbauer (SG) parameters enable flexible optimization across diverse problems, while rigorous error analysis confirms rapid error decay under optimal settings. …”
Get full text

Penjadwalan Cement Mill Berbasis Minimasi Faktor Klinker dalam Proses Pembilasan dan Impor Klinker by Nilda Tri Putri, Indah Kurnia Ramadhani

“…Cement production influenced by the number of demand, raw materials and the number of the available machine. The number of demand increases with a corporate capacity which keeps the company had to set an optimal production schedule. …”
Get full text

Positron emission tomography imaging biomarker and artificial intelligence for the characterization of solitary pulmonary nodule by Ashish Kumar Jha, Ashish Kumar Jha, Umeshkumar Baburao Sherkhane, Umeshkumar Baburao Sherkhane, Nilendu C. Purandare, Nilendu C. Purandare, Leonard Wee, Andre Dekker, Venkatesh Rangarajan, Venkatesh Rangarajan

“…A total of 1,098 features were extracted from PET images using PyRadiomics. To optimize model performance two strategies i.e., (a) feature selection and (b) feature reduction techniques were employed, including hierarchical clustering, RFE in feature selection, and PCA in feature reduction. …”
Get full text

Innovative approach for gauge-based QPE in arid climates: comparing neural networks and traditional methods by Bayan Banimfreg, Ernesto Damiani, Vesta Afzali Gorooh, Duncan Axisa, Luca Delle Monache, Youssef Wehbe

“…Future studies are encouraged to expand the use of machine learning models to unravel the complexities of arid climate hydrology further.…”
Get full text

Detection Storage Time of Mild Bruise’s Loquats Using Hyperspectral Imaging by Zhaoyang Han, Bin Li, Qiu Wang, Akun Yang, Yande Liu

“…Finally, the LS-SVM model based on mixed-spectral is optimized by UVE, SPA, CARS, and GA, respectively; it is found that the UVE-LS-SVM model based on mixed-spectral is the best, and the overall accuracy is 92%. …”
Get full text

Hybrid intelligence systems for reliable automation: advancing knowledge work and autonomous operations with scalable AI architectures by Allan Grosvenor, Anton Zemlyansky, Abdul Wahab, Kyrylo Bohachov, Aras Dogan, Dwyer Deighan

“…Planning: Reinforcement learning, world model-based reinforcement learning, and model predictive control orchestrate adaptive workflows tailored to user requests or live system demands.ResultsThe system’s capabilities are demonstrated in two mission-critical applications: Space Domain Awareness, Satellite Behavior Detection: A graph-based JEPA paired with multi-agent reinforcement learning enables near real-time anomaly detection across 15,000 on-orbit objects, delivering a precision-recall score of 0.98. …”
Get full text

Research on adaptive motion methods of flexible knee joints based on the artificial potential field by LUO Tianhong, LI Chaoyang, MA Xiangyu, FU Qiang, FANG Shangchen

“…ObjectiveConsidering the tracking error of the motion trajectory of the flexible knee joint and the influence of the flexibility on the joint motion, an adaptive impedance control method based on the artificial potential field (APF) was proposed.MethodsThe method took the pneumatic artificial muscle as the power source, and by establishing a kinetic model between the human-machine interaction moment and the knee joint motion angular velocity, the size of the impedance control parameter could be adjusted in real time, so as to realize the following of the motion of the exoskeleton knee joint and the human leg; the control parameter was optimized using the APF concept to enhance the effect of the motion following, and the effectiveness of the algorithm was verified by simulation and test.ResultsThe results show that the proposed APF-based adaptive impedance control method enables the exoskeleton to adaptively track the human motion trajectory and can reduce the error of trajectory tracking, thus improving the suppleness of the flexible knee joint control and enhancing the human-machine synergy of the system.…”
Get full text

Novel transfer learning based bone fracture detection using radiographic images by Aneeza Alam, Ahmad Sami Al-Shamayleh, Nisrean Thalji, Ali Raza, Edgar Anibal Morales Barajas, Ernesto Bautista Thompson, Isabel de la Torre Diez, Imran Ashraf

“…Initially, the spatial features are extracted from bone X-ray images using a transfer model, MobileNet, and then input into a tree-based light gradient boosting machine (LGBM) model for the generation of class probability features. …”
Get full text

Enhancing Real Estate Listings Through Image Classification and Enhancement: A Comparative Study by Eyüp Tolunay Küp, Melih Sözdinler, Ali Hakan Işık, Yalçın Doksanbir, Gökhan Akpınar

“…The extended platform offers information on the role of machine learning models and image enhancement methods in technology for the real estate industry. …”
Get full text

A Novel Ensemble Classifier Selection Method for Software Defect Prediction by Xin Dong, Jie Wang, Yan Liang

“…This method makes full use of the diversity characteristics of base learners, leverages their classification ability, optimizes the selection method for ensemble learning, and enhances the predictive performance of the ensemble model. …”
Get full text

Multi-Stage Adversarial Defense for Online DDoS Attack Detection System in IoT by Yonas Kibret Beshah, Surafel Lemma Abebe, Henock Mulugeta Melaku

“…However, these DDoS attack-detection models are vulnerable to adversarial attacks. Adversarial attacks are small, crafted adversarial perturbations that are designed to fool machine learning model, leading misclassification of input. …”
Get full text

Reduced O3 subsequence labelling: a stepping stone towards optimisation sequence prediction by Yi-Ping You, Yi-Chiao Su

“…There have been many deep learning models proposed to solve problems, such as predicting the optimal heterogeneous mapping or thread-coarsening factor; however, very few have revisited the problem of optimisation phase tuning. …”
Get full text

Research on Obstacle-Avoidance Trajectory Planning for Drill and Anchor Materials Handling by a Mechanical Arm on a Coal Mine Drilling and Anchoring Robot by Siya Sun, Sirui Mao, Xusheng Xue, Chuanwei Wang, Hongwei Ma, Yifeng Guo, Haining Yuan, Hao Su

“…Firstly, the kinematic model of the robotic arm with material was established by improving the D-H parameter method. …”
Get full text

Strategy to improve the confidence level of qualitative screening by high resolution mass spectrometry: A case study of mycotoxins in maize by Yan Gao, Mengyu Feng, Xiuqin Li, Yan Zhang, Jinglei Hu, Kangcong Li, Jianhua Duan, Qinghe Zhang

“…To ensure the sensitivity and applicability of the method, 41 mycotoxin standards were applied for method optimization. A quantitative structure-retention relationships (QSRR) model was developed for retention time prediction and projection using machine learning, providing supplementary evidence for molecule annotation. …”
Get full text

DAC-GCN: A Dual Actor-Critic Graph Convolutional Network with Multi-Hop Aggregation for Enhanced Recommender Systems by Gholamreza Zare, Nima Jafari, Mehdi Hosseinzadeh, Amir Sahafi

Get full text

Standardizing multidrug resistance definitions and visualizations to support surveillance across One Health by Claudia Cobo Angel, Ava Glowney, Emma Lin, Abdolreza Mosaddegh, Kurtis Sobkowich, Zvonimir Poljak, J. Scott Weese, Casey L. Cazer

“…Six databases and grey literature were searched with antimicrobial, resistance, surveillance, and figure or dashboard terms. An active machine learning model was used for the initial screening of references. …”
Get full text

Quantum Circuit Learning for Uncertainty Quantification of RELAP5 Code Analysis of ROSA/LSTF Small Break LOCA Tests by Kinoshita Ikuo

“…To reduce the computational demand in the best estimate plus uncertainty (BEPU) analysis, an accurate and inexpensive machine learning model is expected to be used to replace the high-fidelity RELAP5 code for rapid determination of the uncertainties on the figure of merit of interest. …”
Get full text

Is Deep Learning for Image Recognition Applicable to Stock Market Prediction? by Hyun Sik Sim, Hae In Kim, Jae Joon Ahn

“…For verifying the usefulness of deep learning for image recognition in stock markets, the predictive accuracies of the proposed model were compared to typical artificial neural network (ANN) model and support vector machine (SVM) model. …”
Get full text

FingerUNeSt++: Improving Fingertip Segmentation in Contactless Fingerprint Imaging Using Deep Learning by Laurenz Ruzicka, Bernhard Kohn, Clemens Heitzinger

Get full text