The potential role of next-generation sequencing in identifying MET amplification and disclosing resistance mechanisms in NSCLC patients with osimertinib resistance by Xiao Xiao, Xiao Xiao, Ren Xu, Ren Xu, Jun Lu, Beibei Xin, Chenyang Wang, Kexin Zhu, Hao Zhang, Xinyu Chen

“…With FISH results as gold standard, enumeration algorithm was applied to establish the optimal model for identifying MET amplification using gene copy number (GCN) data.ResultsThe optimal model for identifying MET amplification was constructed based on the GCN of MET, BRAF, CDK6 and CYP3A4, which achieved a 74.0% overall agreement with FISH and performed well in identifying MET amplification except polysomy with a sensitivity of 85.7% and a specificity of 93.9%. …”
Get full text

Development of a Conditional Generative Adversarial Network Model for Television Spectrum Radio Environment Mapping by Oluwatobi Emmanuel Dare, Kennedy Okokpujie, Emmanuel Adetiba, Olabode Idowu-Bismark, Abdultaofeek Abayomi, Raymond Jules Kala, Emmanuel Owolabi, Udeme Christopher Ukpong

“…A REM construction model with few constraints and optimal performance is needed to better support cognitive radio for dynamic spectrum sharing (DSS) and other benefits of REM. …”
Get full text

Implementing Remote Radiotherapy Planning to Increase Patient Flow at a Johannesburg Academic Hospital, South Africa: Protocol for a Prospective Feasibility Study by Duvern Ramiah, Sonwabile Ngcezu, Oluwatosin Ayeni, Okechinyere Achilonu, Mariam Adeleke, Theo Nair, Joseph Otten, Daniel Mmereki

“…Phase 1 (feasibility) encompasses system commissioning, including beam modeling, computed tomography (CT)-to-electron density calibration, multileaf collimator (MLC) optimization, and dose calculations using the anisotropic analytical algorithm. …”
Get full text

Prediction-Based Tip-Over Prevention for Planetary Exploration Rovers by Siddhant Shete, Raúl Domínguez, Ravisankar Selvaraju, Mariela De Lucas Álvarez, Frank Kirchner

“…The proposed system employs linear accelerations and angular velocities measured by the accelerometer and the gyroscope of the Inertial Measurements Unit (IMU) to monitor the rover’s dynamic behavior and stability while navigating the environment. By leveraging deep learning algorithms, the system evaluates predictions and true measurements in real time to identify potential tip-overs. …”
Get full text

SpaceRL — A reinforcement learning-based knowledge graph driver by Miguel Bermudo, Daniel Ayala, Inma Hernández, David Ruiz, Miguel Toro

“…The generation of such agents is a complex task, even more so for a non-expert user.SpaceRL is meant to overcome these limitations by providing a flexible set of tools designed with a wide variety of customization options, in order to adapt to different users’ needs, while also including a variety of state-of-the-art RL algorithms and several embedding models that can be combined to optimize the agents performance. …”
Get full text

Explainable Recommender Systems Through Reinforcement Learning and Knowledge Distillation on Knowledge Graphs by Alexandra Vultureanu-Albişi, Ionuţ Murareţu, Costin Bădică

“…This study presents a novel framework, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>X</mi><msup><mi>R</mi><mn>2</mn></msup><msup><mi>K</mi><mn>2</mn></msup><mi>G</mi></mrow></semantics></math></inline-formula> (X for explainability, first R for recommender systems, the second R for reinforcement learning, first K for knowledge graph, the second K stands for knowledge distillation, and G for graph-based techniques), with the goal of developing a next-generation recommender system with a focus on careers empowerment. To optimize recommendations while ensuring sustainability and transparency, the proposed method integrates reinforcement learning with graph-based representations of career trajectories. …”
Get full text

Dual-Ascent-Inspired Transformer for Compressed Sensing by Rui Lin, Yue Shen, Yu Chen

“…Notably, DAT achieves comparable PSNR to the ISTA-Net+ baseline within just one epoch, while competing methods require significantly more training time. …”
Get full text

Benefits and Challenges of AI-Based Digital Twin Integration in the Saudi Arabian Construction Industry: A Correspondence Analysis (CA) Approach by Aljawharah A. Alnaser, Haytham Elmousalami

“…However, several challenges hinder the realization of these benefits, including a lack of standardization of integrated DT and AI in construction projects, a lack of understanding of AI’s capabilities, a lack of logistics and the limited availability of IT infrastructure, and the complexity of AI algorithms. These findings underscore the transformative potential of integrating AI-driven DTs to optimize construction performance, improve decision-making, and address real-world complexities. …”
Get full text

Employing Streaming Machine Learning for Modeling Workload Patterns in Multi-Tiered Data Storage Systems by Edson Ramiro Lucas Filho, George Savva, Lun Yang, Kebo Fu, Jianqiang Shen, Herodotos Herodotou

“…Modern multi-tiered data storage systems optimize file access by managing data across a hybrid composition of caches and storage tiers while using policies whose decisions can severely impact the storage system’s performance. …”
Get full text

Harnessing AI and Quantum Computing for Revolutionizing Drug Discovery and Approval Processes: Case Example for Collagen Toxicity by David Melvin Braga, Bharat Rawal

“…By generating computational data, predicting the efficacy of pharmaceuticals, and assessing their safety, AI and quantum computing can accelerate and optimize the process of identifying potential drug candidates. …”
Get full text

Signal Mining and Analysis of Drug-Induced Myelosuppression: A Real-World Study From FAERS by Kaiyue Xia MM, Shupeng Chen MD, Yingjian Zeng MD, Nana Tang MD, Meiling Zhang MD

“…Introduction Drug-induced myelosuppression (DIM) is a serious side effect of several medications, particularly chemotherapy, immunosuppressants, and targeted therapies, which can lead to infections, anemia, and bleeding. While these drugs are effective, their adverse effects can disrupt treatment plans and reduce quality of life. …”
Get full text

Intelligent gear decision method for vehicle automatic transmission system based on data mining by Yong Wang, Jianfeng Zeng, Pengfei Du, Huachao Xu

“…Subsequently, dynamic programming algorithms are employed to optimize intelligent gear decisions. …”
Get full text

Research on Fast SOC Balance Control of Modular Battery Energy Storage System by Jianlin Wang, Shenglong Zhou, Jinlu Mao

“…In recent years, SOC balancing methods based on software algorithms have gained popularity. For instance, intelligent control algorithms are being integrated into battery management systems to optimize control strategies for SOC balancing. …”
Get full text

Instrument Performance Analysis for Methane Point Source Retrieval and Estimation Using Remote Sensing Technique by Yuhan Jiang, Lu Zhang, Xingying Zhang, Xifeng Cao, Haiyang Dou, Lingfeng Zhang, Huanhuan Yan, Yapeng Wang, Yidan Si, Binglong Chen

“…While a spatial resolution degradation within 120 m has little impact on quantification, a high spatial resolution is important for detecting low-emission plumes. …”
Get full text

APPLICATION OF ARTIFICIAL NEURON NETWORK AND FUZZY INFERENCE IN THE HOUSEPLANT WATERING INTELLIGENT SYSTEM by Roman Korostenskyi, Igor Olenych

“…The proposed approach ensures an optimal soil moisture level of 50–60%, suitable for plant growth and development, while also reducing the average monthly water consumption by 25–27%. …”
Get full text

Performance evaluation of inset feed microstrip patch antenna parameters with different substrate materials for 5G wireless applications by Kebbekoppalu Shrinivasa Praveena, M Patil Chandrashekar

“…The proposed method uses a new hybrid GA-PSO algorithm with Dynamic Adaptive Mutation and Inertia Control (DAMIC). …”
Get full text

A machine learning approach to identifying key predictors of Peruvian school principals' job satisfaction by Luis Alberto Holgado-Apaza, Dany Dorian Isuiza-Perez, Nelly Jacqueline Ulloa-Gallardo, Yban Vilchez-Navarro, Ruth Nataly Aragon-Navarrete, Wilian Quispe Layme, Marleny Quispe-Layme, Danger David Castellon-Apaza, Remo Choquejahua-Acero, Jaime Cesar Prieto-Luna

“…The Histogram-Based Gradient Boosting algorithm, optimized with Bayesian techniques and trained with data balanced through Random Oversampling, achieved a balanced accuracy of 0.63 on a test set with real-world class distribution. …”
Get full text

Development and validation of dynamic clinical subphenotypes in acute pancreatitis patients using vital sign trajectories in intensive care units: a multinational cohort study by Zichen Wang, Wen Wang, Jiayue Xu, Qiao He, Che Sun, Shuangyi Xie, Kang Zou, Qing Xia, Xin Sun

“…For hyperinflammatory phenotype, the algorithm-estimated lowest-risk fluid range was 4100–4300 mL on day 1 and 3400–3600 mL on day 2; for phenotype hypoinflammatory phenotype, the optimal ranges were 2800–3800 mL and 1400–2600 mL, respectively. …”
Get full text

Comprehensive analysis on soil nitrogen prediction using near-infrared spectroscopy: Models, methods, and insights for precision agriculture by Xiaoyu Wang, Zhiyou Zhang, Yujiao Li, Jie Li, Qing Yang, Qiqi Liu, Zhijie Gong, Mengling Zhang, Xu Wang, Guanghui Xie

“…Key findings include: (1) Sample sizes for modeling predominantly ranged between 22 and 163 (80.0 %); (2) Fourier transform near-infrared spectrometers were the most widely used NIR spectrometers (43.5 %), followed by a grating near-infrared spectrometer (17.4 %); (3) The most common NIR spectrometer wavelength range was 12,804–588 cm−1 (60.9 %); (4) Smoothing techniques (SG, average, and Whittaker) were the dominant preprocessing methods (44.4 %), while partial least squares (PLS) as the most effective modeling algorithm (69.7 %). …”
Get full text

Soil Organic Carbon Prediction and Mapping in Morocco Using PRISMA Hyperspectral Imagery and Meta-Learner Model by Yassine Bouslihim, Abdelkrim Bouasria, Budiman Minasny, Fabio Castaldi, Andree Mentho Nenkam, Ali El Battay, Abdelghani Chehbouni

“…This study presents a novel meta-learner framework that combines multiple machine learning algorithms and spectra processing algorithms to optimize SOC prediction using the PRISMA hyperspectral satellite imagery in the Doukkala plain of Morocco. …”
Get full text