Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)最新文献

{"title":"A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis","authors":"Sadia Islam Tonni,&nbsp;Md. Alif Sheakh,&nbsp;Mst. Sazia Tahosin,&nbsp;Md. Zahid Hasan,&nbsp;Taslima Ferdaus Shuva,&nbsp;Touhid Bhuiyan,&nbsp;Muhammad Ali Abdullah Almoyad,&nbsp;Nabil Anan Orka,&nbsp;Md. Tanvir Rahman,&nbsp;Risala Tasin Khan,&nbsp;M. Shamim Kaiser,&nbsp;Mohammad Ali Moni","doi":"10.1002/aisy.202400495","DOIUrl":"https://doi.org/10.1002/aisy.202400495","url":null,"abstract":"<p>Brain tumors are among the most severe health challenges, necessitating early and precise diagnosis for effective treatment planning. This study introduces an optimized hybrid transfer learning (TL) framework for brain tumor classification using magnetic resonance imaging images. The proposed system integrates advanced preprocessing techniques, an ensemble of pretrained deep learning models, and explainable artificial intelligence (XAI) methods to achieve high accuracy and reliability. The methodology enhances image quality through noise reduction and contrast enhancement, facilitating robust feature extraction. The ensemble model combines VGG16 and ResNet152V2 architectures, achieving a classification accuracy of 99.47% on a challenging four-class dataset. Additionally, gradient-weighted class activation mapping and SHapley Additive exPlanations (SHAP)-based XAI techniques provide visual and quantitative insights into model predictions, improving interpretability and clinical trust. This comprehensive framework demonstrates the potential of hybrid TL and XAI in advancing diagnostic accuracy and supporting clinical decision-making for brain tumor detection. The results underscore its applicability in clinical settings, particularly in resource-constrained environments.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400495","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network","authors":"Yu Cai,&nbsp;Yefeng Yang,&nbsp;Tao Huang,&nbsp;Boyang Li","doi":"10.1002/aisy.202400427","DOIUrl":"https://doi.org/10.1002/aisy.202400427","url":null,"abstract":"<p>This article introduces a novel robust reinforcement learning (RL) control scheme for a quadrotor unmanned aerial vehicle (QUAV) under external disturbances and model uncertainties. First, the translational and rotational motions of the QUAV are decoupled and trained separately to mitigate the computational complexity of the controller design and training process. Then, the proximal policy optimization algorithm with a dual-critic structure is proposed to address the overestimation issue and accelerate the convergence speed of RL controllers. Furthermore, a novel reward function and a robust compensator employing a switch value function are proposed to address model uncertainties and external disturbances. At last, simulation results and comparisons demonstrate the effectiveness and robustness of the proposed RL control framework.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400427","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robot-Assisted Measurement of the Critical Micelle Concentration","authors":"Vincenzo Scamarcio,&nbsp;Gadi Slor,&nbsp;Josie Hughes,&nbsp;Francesco Stellacci","doi":"10.1002/aisy.202400386","DOIUrl":"https://doi.org/10.1002/aisy.202400386","url":null,"abstract":"<p>The critical micelle concentration (CMC) is the key characterization of surfactants. To date, no method can yield sequential CMC measurements in an automated fashion. This work introduces SIMO (smart integrator for manual operations), a novel robotic platform for automating the determination of CMC for surfactants. It highlights the precision and reproducibility of SIMO, with an 80% reduction in standard deviation compared to a manual method. The article discusses the robotic protocol and data postprocessing, highlighting the challenges behind integrating automation and robotics in laboratories. SIMO's reliability is tested against a challenging experiment, that of determining the effect of various cations on the CMC of polymeric surfactants. The work presented showcases the potential of robotics in scientific experimentation, promising enhanced accuracy and efficiency.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400386","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-Driving Lab for Solid-Phase Extraction Process Optimization and Application to Nucleic Acid Purification","authors":"Sebastian Putz,&nbsp;Jonathan Döttling,&nbsp;Tim Ballweg,&nbsp;Andre Tschöpe,&nbsp;Vitaly Biniyaminov,&nbsp;Matthias Franzreb","doi":"10.1002/aisy.202570005","DOIUrl":"https://doi.org/10.1002/aisy.202570005","url":null,"abstract":"<p><b>Self-Driving Labs</b>\u0000 </p><p>The cover image symbolizes the synergy of robotics, data, and biotechnology in this research. A robotic hand balances a sphere surrounded by DNA and binary code, reflecting the optimization of DNA purification through our self-driving laboratory (SDL). Integrating robotics, machine learning, and automation, the SDL accelerates bioprocess development, enabling sustainable, efficient, and scalable solutions for complex biotechnological challenges. More details can be found in article number 2400564 by Sebastian Putz, Matthias Franzreb, and co-workers.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Star-Nose-Inspired Bionic Soft Robot for Nonvisual Spatial Detection and Reconstruction","authors":"Qiwei Shan,&nbsp;Yunqi Cao,&nbsp;Haozhen Chi,&nbsp;Shuyu Fan,&nbsp;Ziying Zhu,&nbsp;Dibo Hou","doi":"10.1002/aisy.202570001","DOIUrl":"https://doi.org/10.1002/aisy.202570001","url":null,"abstract":"<p><b>Star-Nose-Inspired Bionic Soft Robot</b>\u0000 </p><p>This image portrays a bionic soft robot inspired by the star-nosed mole, equipped with a PDMS-PET cylindrical tactile sensor array based on bilayer single-electrode triboelectric nanogenerators, mimicking the appendage surrounded by Eimer’s organs and the muscle tissue of the mole’s nose. It detects object distance and shapes effectively, achieving non-visual three-dimensional spatial detection and reconstruction. More details can be found in article number 2400601 by Yunqi Cao, Dibo Hou, and co-workers.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low Computational Cost for Multiple Waypoints Trajectory Planning: A Time-Optimal-Based Approach","authors":"Da-hui Lin-Yang,&nbsp;Francisco Pastor,&nbsp;Alfonso J. García-Cerezo","doi":"10.1002/aisy.202570002","DOIUrl":"https://doi.org/10.1002/aisy.202570002","url":null,"abstract":"<p><b>Multiple Waypoints Trajectory Planning</b>\u0000 </p><p>In article number 2400363, Da-hui Lin-Yang, Francisco Pastor, and Alfonso J. García-Cerezo present a time-optimal trajectory planner for drones, computing minimal-time multi-waypoint trajectories. The cover highlights drones navigating pre-planned paths with precision, visualized through colorful arcs. The experiments were conducted in a motion capture system, ensuring accurate trajectory tracking and validation in controlled environments. This work advances rapid and efficient motion planning.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Intelligent Systems: Shaping the Future of Robotics and AI","authors":"","doi":"10.1002/aisy.202401109","DOIUrl":"https://doi.org/10.1002/aisy.202401109","url":null,"abstract":"&lt;p&gt;As we reflect on 2024, we are proud to celebrate the continued success of &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt;, now in its 7th volume. Over the past year, &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; has again cemented its position as a premier platform for groundbreaking research in robotics, artificial intelligence, machine learning, and neuromorphic engineering.&lt;/p&gt;&lt;p&gt;The journal's reputation for quality and impact is stronger than ever thanks to the dedication of our &lt;b&gt;board members&lt;/b&gt;, &lt;b&gt;authors&lt;/b&gt;, &lt;b&gt;reviewers&lt;/b&gt;, and &lt;b&gt;readers&lt;/b&gt;, &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; has achieved some remarkable milestones. The 2023 impact factor of the journal, released in June by Clarivate Analytics, was 6.8, which places &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; among Q1 journals in all of its JCR categories: Robotics (7/46), Computer Science – Artificial Intelligence (30/197), and Automation &amp; Control (9/84). Highly cited papers have contributed the most to these successful results. The highest-cited articles published in 2021 and 2022 are included in &lt;b&gt;Table&lt;/b&gt; 1.&lt;/p&gt;&lt;p&gt;While bibliometric indicators remain valuable, Wiley, as a signatory of the &lt;b&gt;Declaration on Research Assessment (DORA)&lt;/b&gt;, emphasizes responsible and diverse research evaluation. We now incorporate &lt;b&gt;additional metrics&lt;/b&gt; to provide a holistic view of research impact. &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; remains committed to connecting &lt;b&gt;authors&lt;/b&gt;, &lt;b&gt;readers&lt;/b&gt;, and the &lt;b&gt;broader scientific community&lt;/b&gt;. Over the past year, our articles have gained notable attention, as can been in &lt;b&gt;Table&lt;/b&gt; 2.&lt;/p&gt;&lt;p&gt;\u0000 &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; promotes an inclusive open communication platform for connecting readers, authors, reviewers, editors, and board members with the content and tools they need, which has led &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; to be an excellent home for articles with publication based on scientific novelty and interest. The open access publication model undoubtedly increases the visibility of the published articles. More details about open access advantages can be found here. Moreover, your open access article publication charge (APC) may be covered by your institution, you can check the eligibility for funding here, visit the Ensure Funder Compliance and Funder Agreements for more information.&lt;/p&gt;&lt;p&gt;Our promotional activities to enhance the visibility of the journal and its papers continued in 2024. Articles published in &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; are regularly picked up by the editors of our partner news platform, Advanced Science News, and highlighted on their website and X account. Additionally, highlights of the journal shared via our own X account have received noticeable attention from the community. The most out-standing papers published in &lt;i&gt;Advanced Intelligent Systems&lt;/i&gt; are identified by the journal's editors and collected in the Wiley Online Library. In addition to the regular issue, a video featuring a selection of the be","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202401109","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Precision Drop-on-Demand Printing of Charged Droplets on Nonplanar Surfaces with Machine Learning","authors":"Shaheer Mohiuddin Khalil,&nbsp;Shahzaib Ali,&nbsp;Vu Dat Nguyen,&nbsp;Dae-Hyun Cho,&nbsp;Doyoung Byun","doi":"10.1002/aisy.202570004","DOIUrl":"https://doi.org/10.1002/aisy.202570004","url":null,"abstract":"<p><b>High-Precision Drop-on-Demand Printing</b>\u0000 </p><p>In article number 2400621, Dae-Hyun Cho, Doyoung Byun, and co-workers introduce a high-precision printing technique that uses charged droplets to pattern complex, nonplanar surfaces with the help of machine learning. The method suits flexible electronics and display technologies, enabling precise material deposition on curved and 3D substrates. This approach promises new possibilities in advanced manufacturing and next-generation device fabrication.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570004","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SuperResNET: Model-Free Single-Molecule Network Analysis Software Achieves Molecular Resolution of Nup96","authors":"Yahongyang Lydia Li,&nbsp;Ismail M. Khater,&nbsp;Christian Hallgrimson,&nbsp;Ben Cardoen,&nbsp;Timothy H. Wong,&nbsp;Ghassan Hamarneh,&nbsp;Ivan R. Nabi","doi":"10.1002/aisy.202400521","DOIUrl":"https://doi.org/10.1002/aisy.202400521","url":null,"abstract":"<p>SuperResNET is an integrated machine learning-based analysis software for visualizing and quantifying 3D point cloud data acquired by single-molecule localization microscopy (SMLM). SuperResNET computational modules include correction for multiple blinking of single fluorophores, denoising, segmentation (clustering), feature extraction used for cluster group identification, modularity analysis, blob retrieval, and visualization in 2D and 3D. Here, a graphical user interface version of SuperResNET was applied to publicly available direct stochastic optical reconstruction microscopy (dSTORM) data of nucleoporin Nup96 and Nup107 labeled nuclear pores that present a highly organized octagon structure of eight corners. SuperResNET effectively segments nuclear pores and Nup96 corners based on differential proximity threshold analysis from 2D and 3D SMLM datasets. SuperResNET quantitatively analyzes features from segmented nuclear pores, including complete structures with eightfold symmetry, and from segmented corners. SuperResNET modularity analysis of segmented corners from 2D SMLM distinguishes two modules at 10.7 ± 0.1 nm distance, corresponding to two individual Nup96 molecules. SuperResNET is therefore a model-free tool that can reconstruct network architecture and molecular distribution of subcellular structures without the bias of a specified prior model, attaining molecular resolution from dSTORM data. SuperResNET provides flexibility to report on structural diversity in situ within the cell, providing opportunities for biological discovery.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400521","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network","authors":"Jingon Jang,&nbsp;Yoonseok Song,&nbsp;Sungjun Park","doi":"10.1002/aisy.202400710","DOIUrl":"https://doi.org/10.1002/aisy.202400710","url":null,"abstract":"<p>Analog conductance switching characteristics of memristor devices have been studied to be utilized for constituent elements of synaptic weight matrix in neural networks, related to system design of hardware-level parallel neuromorphic computing architecture for the artificial intelligence application. In this manner, it is important to systematically investigate the specific requirements of memristor characteristics associated with the capability to emulate plenty of synaptic weight elements linked between constituent layers in neural networks. Here, the learning capabilities of analog conductance state of memristor device for the perceptron of unstructured complex dataset in multilayer neural network are analyzed in terms of the number of analog state, nonlinearity, and conductance error. It is found that the requirable number of analog state is analyzed in about ≈50 states and conductance deviation of each analog state is until ≈5% of original value with nonlinearity of ≈0.142 according to constant programming pulse scheme. With the memristor characteristics enough to mimic synaptic weight to be learnt and infer the Fashion-mnist dataset, the classification accuracy is satisfied as ≈84.36% with the loss of ≈16.8% to original level. Owing to this investigation, applicability of novel memristor device could be conveniently examined for the utilization as synaptic weight in multilayer neural networks.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400710","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}