首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Anderson University Researchers Report on Findings in Machine Learning (TXAI-ADV : Trustworthy XAI for Defending AI Models against Adversarial Attacks in Realist ic CIoT)

    60-60页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in artificial intelligence. According to news reporting from Anderson, South Caroli na, by NewsRx journalists, research stated, "Adversarial attacks are more preval ent in Consumer Internet of Things (CIoT) devices (i.e., smart home devices, cam eras, actuators, sensors, and micro-controllers) because of their growing integr ation into daily activities, which brings attention to their possible shortcomin gs and usefulness." The news correspondents obtained a quote from the research from Anderson Univers ity: "Keeping protection in the CIoT and countering emerging risks require const ant updates and monitoring of these devices. Machine learning (ML), in combinati on with Explainable Artificial Intelligence (XAI), has become an essential compo nent of the CIoT ecosystem due to its rapid advancement and impressive results a cross several application domains for attack detection, prevention, mitigation, and providing explanations of such decisions. These attacks exploit and steal se nsitive data, disrupt the devices' functionality, or gain unauthorized access to connected networks. This research generates a novel dataset by injecting advers arial attacks into the CICIoT2023 dataset. It presents an adversarial attack det ection approach named TXAI-ADV that utilizes deep learning (Mutli-Layer Perceptr on (MLP) and Deep Neural Network (DNN)) and machine learning classifiers (K-Near est Neighbor (KNN), Support Vector Classifier (SVC), Gaussian Naive Bayes (GNB), ensemble voting, and Meta Classifier) to detect attacks and avert such situatio ns rapidly in a CIoT. This study utilized Shapley Additive Explanations (SHAP) t echniques, an XAI technique, to analyze the average impact of each class feature on the proposed models and select optimal features for the adversarial attacks dataset."
      原文链接:
    • NETL
    • NSTL

    Study Data from Huaqiao University Provide New Insights into Machine Learning (S ampling-Based Machine Learning Models for Intrusion Detection in Imbalanced Data set)

    61-61页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news reporting originating from X iamen, People's Republic of China, by NewsRx correspondents, research stated, "C ybersecurity is one of the important considerations when adopting IoT devices in smart applications." Our news reporters obtained a quote from the research from Huaqiao University: " Even though a huge volume of data is available, data related to attacks are gene rally in a significantly smaller proportion. Although machine learning models ha ve been successfully applied for detecting security attacks on smart application s, their performance is affected by the problem of such data imbalance. In this case, the prediction model is preferable to the majority class, while the perfor mance for predicting the minority class is poor. To address such problems, we ap ply two oversampling techniques and two undersampling techniques to balance the data in different categories. To verify their performance, five machine learning models, namely the decision tree, multi-layer perception, random forest, XGBoos t, and CatBoost, are used in the experiments based on the grid search with 10-fo ld cross-validation for parameter tuning. The results show that both the oversam pling and undersampling techniques can improve the performance of the prediction models used."
      原文链接:
    • NETL
    • NSTL

    Peking University Reports Findings in Machine Learning (Chiral Stacking Identifi cation of Two-Dimensional Triclinic Crystals Enabled by Machine Learning)

    62-63页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Beijing, Peopl e's Republic of China, by NewsRx journalists, research stated, "Chiral materials possess broken inversion and mirror symmetry and show great potential in the ap plication of next-generation optic, electronic, and spintronic devices. Two-dime nsional (2D) chiral crystals have planar chirality, which is nonsuperimposable o n their 2D enantiomers by any rotation about the axis perpendicular to the subst rate."
      原文链接:
    • NETL
    • NSTL

    Researcher at Miguel Hernandez University of Elche Describes Research in Robotic s (A Comparison of Myoelectric Control Modes for an Assistive Robotic Virtual Pl atform)

    62-62页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ro botics. According to news originating from Elche, Spain, by NewsRx editors, the research stated, "In this paper, we propose a daily living situation where objec ts in a kitchen can be grasped and stored in specific containers using a virtual robot arm operated by different myoelectric control modes." The news correspondents obtained a quote from the research from Miguel Hernandez University of Elche: "The main goal of this study is to prove the feasibility o f providing virtual environments controlled through surface electromyography tha t can be used for the future training of people using prosthetics or with upper limb motor impairments. We propose that simple control algorithms can be a more natural and robust way to interact with prostheses and assistive robotics in gen eral than complex multipurpose machine learning approaches."
      原文链接:
    • NETL
    • NSTL

    Gachon University Gil Medical Center Researcher Yields New Findings on Robotics (Motion Accuracy of Pneumatic Stepper Motor-Driven Robotic System Developed for MRI-Guided High-Intensity Focused Ultrasound Treatment of Prostate Disease)

    63-64页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on robotics is now availab le. According to news reporting out of Incheon, South Korea, by NewsRx editors, research stated, "The latest advancement in high-intensity focused ultrasound (H IFU) treatment technology integrates magnetic resonance imaging (MRI) guidance f or precise treatment of prostate disease." The news journalists obtained a quote from the research from Gachon University G il Medical Center: "As conventional electromagnetic motors are not applicable fo r utilization within MRI scanners, we have developed a prototype robotic system driven by pneumatic stepper motors to control the movement of the HIFU transduce r within an intrarectal probe during MRI-guided HIFU treatment procedures. These pneumatic stepper motors were constructed entirely from MRI-compatible plastic materials. Assessment of the robotic system's MRI compatibility was conducted ut ilizing a 3.0T MRI scanner, revealing no discernible MRI image distortion with a minor decrease in the signal-to-noise ratio (2.8%) during the moto r operation. The robotic system enabled the transducer to move inside the probe with two degrees of freedom, allowing both linear and rotational motion. The pos itional accuracy of the transducer movement was assessed, yielding ±0.20 and ±0. 22 mm accuracies in the forward and backward linear movements, respectively, and ±0.79° and ±0.74° accuracies in the clockwise and counterclockwise rotational m otions, respectively."
      原文链接:
    • NETL
    • NSTL

    Studies Conducted at Technological University of Pereira on Machine Learning Rec ently Published (Methodology for Inventory Management in Neighborhood Stores Usi ng Machine Learning and Integer Linear Programming)

    64-65页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on artificial intelligen ce have been presented. According to news originating from Technological Univers ity of Pereira by NewsRx correspondents, research stated, "Nowadays, inventory m anagement poses a challenge given the constant demands related to temporality, g eographic location, price variability, and budget availability, among others. In neighborhood shops, this process is manually done based on experience (the data generated are ignored), which is sometimes not enough to respond to changes." The news editors obtained a quote from the research from Technological Universit y of Pereira: "This shows the need to develop new strategies and tools that use data analysis techniques. Our methodology predicts the weekly demand for 14 comm on products in neighborhood stores, which is later refined based on investment c apital. The method is validated using a database built with synthetic informatio n extracted from statistical sampling. For the prediction model, three supervise d learning models are used: support vector machines (SVM), AutoRegressive models (Arx), and Gaussian processes (GP). This work proposes a restricted linear mode l given an inversion and the predicted quantity of products; the aim is to refin e the prediction while maximizing the shopkeeper's profit. Finally, the problem is solved by applying an integer linear programming paradigm. Tests regarding th e prediction and inventory adjustment stages are conducted, showing that the met hodology can predict the temporal dynamics of the data by inferring the statisti cal moments of the distributions used. It is shown that it is possible to obtain a maximum profit with a lower investment."
      原文链接:
    • NETL
    • NSTL

    Nanjing University Reports Findings in Lung Cancer (Accurate categorization and rapid pathological diagnosis correction with Micro-Raman technique in human lung adenocarcinoma infiltration level)

    65-66页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Lung Cancer is the subject of a report. According to news originating from Nanjing, People' s Republic of China, by NewsRx correspondents, research stated, "In the context of surgical interventions for lung adenocarcinoma (LADC), precise determination of the extent of LADC infiltration plays a pivotal role in shaping the surgeon's strategic approach to the procedure. The prevailing diagnostic standard involve s the expeditious intraoperative pathological diagnosis of areas infiltrated by LADC." Our news journalists obtained a quote from the research from Nanjing University, "Nevertheless, current methodologies rely on the visual interpretation of tissu e images by proficient pathologists, introducing an error margin of up to 15.6% . In this study, we investigated the utilization of Micro-Raman technique on iso lated specimens of human LADC with the objective of formulating and validating a workflow for the pathological diagnosis of LADC featuring diverse degrees of in filtration. Our strategy encompasses a thorough pathological characterization of LADC, spanning different tissue types and levels of infiltration. Through the i ntegration of Raman spectroscopy with advanced deep learning models for simultan eous diagnosis, this approach offers a swift, precise, and clinically relevant m eans of analysis. The diagnostic performance of the convolutional neural network (CNN) model, coupled with the microscopic Raman technique, was found to be exce ptional and consistent, surpassing the traditional support vector machine (SVM) model. The CNN model exhibited an area under the curve (AUC) value of 96.1% for effectively distinguishing normal tissue from LADC and an impressive 99.0% for discerning varying degrees of infiltration in LADCs. To comprehensively asse ss its clinical utility, Raman datasets from patients with intraoperative rapid pathologic diagnostic errors were utilized as test subjects and input into the e stablished CNN model. The results underscored the substantial corrective capacit y of the Micro-Raman technique, revealing a misdiagnosis correction rate exceedi ng 96% in all cases. Ultimately, our discoveries highlight the Mic ro-Raman technique's potential to augment the intraoperative diagnostic precisio n of LADC with varying levels of infiltration. And compared to the traditional S VM model, the CNN model has better generalization ability in diagnosing differen t infiltration levels."
      原文链接:
    • NETL
    • NSTL

    IRCCS Regina Elena National Cancer Institute Reports Findings in Prostatectomy [Novel composite BPH3 trifecta for robotic assisted simple prostatectomy (RASP) v ersus BPH6: A multicenter outcomes comparison]

    66-67页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Surgery - Prostatectom y is the subject of a report. According to news reporting originating from Rome, Italy, by NewsRx correspondents, research stated, "To assess disobstructive pro ficiency of BPH3 trifecta in RASP according to different techniques. Baseline pr ostate volume (PV), uroflowmetry parameters and Validated questionnaires: IIEF, Incontinence severity index score (ISI), International prostatic symptoms score (IPSS), MSHQ, Quality of recovery (QOR), were recorded preoperatively and 12 mon ths postoperatively." Our news editors obtained a quote from the research from IRCCS Regina Elena Nati onal Cancer Institute, "RASP was conducted using both the urethra-sparing (Madig an) technique and a non-urethral-sparing transvesical (Freyer) approach. Two gro ups were evaluated for achievement rates in terms of BPH-3 and BPH-6. BPH-3 was defined by a combination of: a reduction of 30% in IPSS compared t o baseline, ISI score 4, and absence of complications beyond Clavien grade 1. Ab out 158 patients underwent RASP, with 93 undergoing the Madigan procedure and 65 the Freyer approach. Patients in the Madigan group were younger, with lower PV, baseline IPSS score, overactive symptoms (ISI score), but higher MSHQ and IIEF score, when compared to the Freyer population (all <0.02). At 12-month follow-up, patients who underwent the Madigan procedure reported sh orter bladder irrigation time and time to catheter removal (both <0.001). As expected, Madigan patients also demonstrated superior postoperative IIEF and MSHQ scores (all <0.001). Postoperative complicat ion incidence was higher in the Madigan cohort, mainly due to UTI (<0.001). Although there were no differences in postoperative IPSS and Q-max betw een groups, the Madigan cohort presented with higher post void residue (<0.001). BPH6 achievement was higher in the Madigan cohort (48% vs 28%) (<0.001), while no difference was obser ved in BPH3 achievement rate."
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, "Systems And Methods For Smart Remediatio n For Transactions", for Approval (USPTO 20240152924)

    67-69页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-From Washington, D.C., NewsRx journali sts report that a patent application by the inventors Drapeau, Ryan (Seattle, WA , US); Rai, Arash (Seattle, WA, US), filed on November 4, 2022, was made availab le online on May 9, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: "Acceleration of e-commerce transactions has also increased the amount of online credit card fraud. Fraudsters have become more and more so phisticated in finding ways to exploit, for example, weaknesses of a payment pro cessing system, to avoid an online charge from being blocked as fraudulent. "The above information disclosed in this Background section is only for enhancem ent of understanding of the background of the present disclosure, and therefore, it may contain information that does not form prior art."
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Attachments for handling and tracking fabricated custom object s (USPTO 11975463)

    69-72页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent by the inventors Butz, Arthur George (Durham, NC, US), Kalinichenko, Alexey (Cary, NC, US), Lukacs, Gabor (Ra leigh, NC, US), Mojdeh, Mehdi (Fremont, CA, US), Shaw, Jack (Durham, NC, US), So ltero Borrego, Enrique (Ciudad Juarez, MX), filed on December 10, 2020, was publ ished online on May 7, 2024, according to news reporting originating from Alexan dria, Virginia, by NewsRx correspondents. Patent number 11975463 is assigned to AlignTechnology Inc. (San Jose, California , United States). The following quote was obtained by the news editors from the background informa tion supplied by the inventors: "For some applications, shells are formed around molds to achieve a negative of the mold. The shells are then removed from the m olds to be further used for various applications. One example application in whi ch a shell is formed around a mold and then later used is corrective dentistry o r orthodontic treatment. In such an application, the mold is of a dental arch fo r a patient and the shell is an aligner to be used for aligning one or more teet h of the patient.
      原文链接:
    • NETL
    • NSTL