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

    Medical University of Graz Reports Findings in Dysphagia (Clinical evaluation of a machine learning-based dysphagia risk prediction tool)

    21-21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 Digestive System Disea ses and Conditions - Dysphagia is the subject of a report. According to news rep orting originating in Graz, Austria, by NewsRx journalists, research stated, "Th e rise of digitization promotes the development of screening and decision suppor t tools. We sought to validate the results from a machine learning based dysphag ia risk prediction tool with clinical evaluation." Financial support for this research came from Medical University of Graz. The news reporters obtained a quote from the research from the Medical Universit y of Graz, "149 inpatients in the ENT department were evaluated in real time by the risk prediction tool, as well as clinically over a 3-week period. Patients w ere classified by both as patients at risk/no risk. The AUROC, reflecting the di scrimination capability of the algorithm, was 0.97. The accuracy achieved 92.6% given an excellent specificity as well as sensitivity of 98% and 8 2.4% resp. Higher age, as well as male sex and the diagnosis of or opharyngeal malignancies were found more often in patients at risk of dysphagia. The proposed dysphagia risk prediction tool proved to have an outstanding perfo rmance in discriminating risk from no risk patients in a prospective clinical se tting."
      原文链接:
    • NETL
    • NSTL

    Researchers' Work from Chongqing University of Posts and Telecommunications Focu ses on Artificial Intelligence (Gws: Rotation Object Detection In Aerial Remote Sensing Images Based On Gauss-wasserstein Scattering)

    22-22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 Ar tificial Intelligence. According to news reporting originating from Chongqing, P eople's Republic of China, by NewsRx correspondents, research stated, "The major ity of existing rotating target detectors inherit the horizontal detection parad igm and design the rotational regression loss based on the inductive paradigm. B ut the loss design limitation of the inductive paradigm makes these detectors ha rdly detect effectively tiny targets with high accuracy, particularly for large- aspect-ratio objects." Our news editors obtained a quote from the research from the Chongqing Universit y of Posts and Telecommunications, "Therefore, in view of the fact that horizont al detection is a special scenario of rotating target detection and based on the relationship between rotational and horizontal detection, we shift from an indu ctive to a deductive paradigm of design to develop a new regression loss functio n named Gauss-Wasserstein scattering (GWS). First, the rotating bounding box is transformed into a two-dimensional Gaussian distribution, and then the regressio n losses between Gaussian distributions are calculated as theWasserstein scatter ; By analyzing the gradient of centroid regression, centroid regression is shown to be able to adjust gradients dynamically based on object characteristics, and small targets requiring high accuracy detection rely on this mechanism, and mor e importantly, it is further demonstrated that GWS is scale-invariant while poss essing an explicit regression logic."
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Chongqing Medical University Reports Findings in Hi lar Cholangiocarcinoma (Robotic Right Hepatectomy with En Bloc Caudatectomy for Bismuth IIIa Hilar Cholangiocarcinoma: A Video Demonstration of Left-Liver-First ...)

    23-24页
    查看更多>>摘要：esearch on Oncology - Hilar Chola ngiocarcinoma is the subject of a report. According to news reporting out of Cho ngqing, People's Republic of China, by NewsRx editors, research stated, "Minimal ly invasive resection for perihilar cholangiocarcinoma is a complicated and tech nically demanding surgical procedure. Radical surgical resection is regarded as the best treatment for hepatic hilar cholangiocarcinoma." Our news journalists obtained a quote from the research from the First Affiliate d Hospital of Chongqing Medical University, "Right hepatectomy with caudate lobe resection is necessary as the treatment for bismuth IIIa hilar cholangiocarcino ma. The left-liver-first anterior radical modular orthotopic right hemihepatecto my (LARMORH), which can simplify surgical steps and decrease procedural difficul ty, may be a better choice for Bismuth IIIa hilar cholangiocarcinoma. However, t here are no reports of this approach using robotic technique for this operation. We will provide a detailed introduction to this method through this video. A 45 -year-old female patient was diagnosed with a hilar cholangiocarcinoma. Followin g a 7-day percutaneous biliary drainage of the left intrahepatic bile duct and o btaining informed consent, we performed a robotic radical resection of the HCCA using the LARMORH approach. The patient was positioned supine with the entire be d elevated 20° and tilted 15° to the left. Trocars were placed in position (Fig. 1). After entering the abdominal cavity, it was explored for tumor metastasis. The surgery adopted a left approach, initially exploring the left hepatic artery and vein to further assess resectability. After confirming resectability, the r ight hepatic artery and gastroduodenal artery (GDA) were dissected. The common b ile duct was dissected and transected at its distal end, ensuring R0 surgical ma rgins. Lymph nodes were cleared from the foot side to the head side, confirming the metastasis to the lymph node group 13a, so we further cleared the group 16 a nd 9 lymph nodes. Subsequently, we approached the resection of the right half an d the entire caudate lobe with the reverse thinking of left hepatic resection mo de, preserving only the left branch of the portal vein and left hepatic artery, and dissecting the liver tissue along the resection plane of the left liver. Aft er transection of the left hepatic duct, the activity space of the left liver wa s larger and the caudate lobe could be better exposed. The Spiegel lobe was lift ed to the right in a ‘turn the page' fashion for in situ resection of the entire caudate lobe and the right half of the liver. Finally, a bilioenteric anastomos is was performed using the Roux-en-Y method. Robotic right hepatectomy with caud ate lobectomy was successfully performed in 450 min, with an estimated blood los s of 200 ml. The histological grading was determined as T1aN1M0 (stage IIIB) on the basis of postoperative pathological biopsy results. The patient achieved a s atisfactory postoperative recovery and was discharged on the 14th postoperative day without any major complications. Following the operation, the patient receiv ed capecitabine chemotherapy according to the Chinese Society of Clinical Oncolo gy (CSCO) criteria. Since September 2022, our team has completed three radical r esections for Bismuth IIIa HCCA using this technique. All patients achieved a sa tisfactory postoperative recovery without any further complications. Robotic lef t-liver-first anterior radical modular orthotopic right hemihepatectomy for Bism uth IIIa HCCA is both safe and feasible."
      原文链接:
    • NETL
    • NSTL

    New Support Vector Machines Study Findings Recently Were Reported by Researchers at Hangzhou Dianzi University (An Intelligent Broaching Tool Design Method Base d On Cbr and Support Vector Machine)

    24-25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 Support Vector Machine s is the subject of a report. According to news reporting originating in Hangzho u, People's Republic of China, by NewsRx journalists, research stated, "Due to t he numerous design parameters and complex relationships inherent in cutting tool s, their design process relies heavily on expert design experience, which greatl y hinders the design and production efficiency of cutting tool manufacturing ent erprises. based reasoning (CBR) and rule-based reasoning (RBR) methods have been widely used in the field of mechanical product design, both of which have impro ved product design efficiency to a certain extent, but still cannot meet the act ual design and production needs, lacking research on the intelligent design proc ess of complex cutting tools." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Key R&D projects in Zhejiang Province.
      原文链接:
    • NETL
    • NSTL

    University of Milan Reports Findings in Hernias [First report of robotic retromuscular incisional hernia repair with Hugo Ras™ surgical syste m]

    25-26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 Gastroenterology - Her nias is the subject of a report. According to news originating from Milan, Italy , by NewsRx correspondents, research stated, "Treatment of incisional hernia is a rapidly evolving field of surgery, with actual trends being oriented toward re tromuscular/ preperitoneal mesh placement. The diffusion of robotic surgery is co nstantly growing in different surgical specialties and is gaining widespread acc eptance for abdominal wall reconstruction." Our news journalists obtained a quote from the research from the University of M ilan, "Recently, novel robotic platforms have entered into the market. In this s tudy, we present the first transabdominal retromuscular incisional hernia repair performed with the new Hugo RAS™system (Medtronic, Minneapolis, MN, USA). The surgical team had previous robotic experience and completed an official 2-day se ssion running incisional hernia repair on human cadaver lab. Operating room sett ing and trocar layout were planned. The patient presented a 4 x 4 cm midline inc isional hernia and was scheduled for transabdominal retromuscular incisional her nia repair at our Institution. A description of the operative room setup, roboti c arm configuration and docking/tilt angles is provided. Docking time, operative time, and console time were 15, 95, and 75 min, respectively. All the surgical steps were completed without critical surgical errors or high-priority alarms. N either intraoperative complications nor conversion to open surgery was recorded. Postoperative course was uneventful and the patient was discharged on postopera tive day 2."
      原文链接:
    • NETL
    • NSTL

    First Hospital of Jilin University Reports Findings in Hemiplegia (Effect of tas k-oriented training assisted by force feedback hand rehabilitation robot on fing er grasping function in stroke patients with hemiplegia: a randomised controlled ...)

    26-27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 Nervous System Disease s and Conditions - Hemiplegia is the subject of a report. According to news repo rting originating in Changchun, People's Republic of China, by NewsRx journalist s, research stated, "Over 80% of patients with stroke experience f inger grasping dysfunction, affecting independence in activities of daily living and quality of life. In routine training, task-oriented training is usually use d for functional hand training, which may improve finger grasping performance af ter stroke, while augmented therapy may lead to a better treatment outcome." The news reporters obtained a quote from the research from the First Hospital of Jilin University, "As a new technology-supported training, the hand rehabilitat ion robot provides opportunities to improve the therapeutic effect by increasing the training intensity. However, most hand rehabilitation robots commonly appli ed in clinics are based on a passive training mode and lack the sensory feedback function of fingers, which is not conducive to patients completing more accurat e grasping movements. A force feedback hand rehabilitation robot can compensate for these defects. However, its clinical efficacy in patients with stroke remain s unknown. This study aimed to investigate the effectiveness and added value of a force feedback hand rehabilitation robot combined with task-oriented training in stroke patients with hemiplegia. In this single-blinded randomised controlled trial, 44 stroke patients with hemiplegia were randomly divided into experiment al (n = 22) and control (n = 22) groups. Both groups received 40 min/day of conv entional upper limb rehabilitation training. The experimental group received 20 min/day of task-oriented training assisted by a force feedback rehabilitation ro bot, and the control group received 20 min/day of task-oriented training assiste d by therapists. Training was provided for 4 weeks, 5 times/week. The Fugl-Meyer motor function assessment of the hand part (FMA-Hand), Action Research Arm Test (ARAT),grip strength, Modified Ashworth scale (MAS), range of motion (ROM), Br unnstrom recovery stages of the hand (BRS-H), and Barthel index (BI) were used t o evaluate the effect of two groups before and after treatment. Intra-group comp arison: In both groups, the FMA-Hand, ARAT, grip strength, AROM, BRS-H, and BI s cores after 4 weeks of treatment were significantly higher than those before tre atment (p <0.05), whereas there was no significant differe nce in finger flexor MAS scores before and after treatment (p > 0.05). Inter-group comparison: After 4 weeks of treatment, the experimental gro up's FMA-Hand total score, ARAT, grip strength, and AROM were significantly bett er than those of the control group (p <0.05). However, the re were no statistically significant differences in the scores of each sub-item of the FMA-Hand after Bonferroni correction (p > 0.007). In addition, there were no statistically significant differences in MAS, BRS-H, and BI scores (p > 0.05). Hand performance improved in patients with stroke after 4 weeks of task-oriented training."
      原文链接:
    • NETL
    • NSTL

    New Findings from Yale University in Artificial Intelligence Provides New Insigh ts (Artificial Intelligence and Illusions of Understanding In Scientific Researc h)

    27-28页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Research findings on Artificial Intelligence are discussed in a new report. According to news reporting originating from New Have n, Connecticut, by NewsRx correspondents, research stated, "Scientists are enthu siastically imagining ways in which artificial intelligence (AI) tools might imp rove research. Why are AI tools so attractive and what are the risks of implemen ting them across the research pipeline? Here we develop a taxonomy of scientists ' visions for AI, observing that their appeal comes from promises to improve pro ductivity and objectivity by overcoming human shortcomings."
      原文链接:
    • NETL
    • NSTL

    Investigators at Tsinghua University Report Findings in Machine Learning (Physic ally Interpretable Wavelet-guided Networks With Dynamic Frequency Decomposition for Machine Intelligence Fault Prediction)

    28-29页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating from Beijing, P eople's Republic of China, by NewsRx correspondents, research stated, "Machine i ntelligence fault prediction (MIFP) is crucial for ensuring complex systems' saf e and reliable operation. While deep learning has become the mainstream tool for MIFP due to its excellent learning abilities, its interpretability is limited, and it struggles to learn frequencies, making it challenging to understand the p hysical knowledge of signals at the frequency level." Financial support for this research came from Beijing Municipal Natural Science Foundation-Rail Transit Joint Research Program.
      原文链接:
    • NETL
    • NSTL

    South China University of Technology Reports Findings in Robotics (Extended resi dual learning with one-shot imitation learning for robotic assembly in semi-stru ctured environment)

    29-30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 Robotics is the subjec t of a report. According to news originating from Guangzhou, People's Republic o f China, by NewsRx correspondents, research stated, "Robotic assembly tasks requ ire precise manipulation and coordination, often necessitating advanced learning techniques to achieve efficient and effective performance. While residual reinf orcement learning with a base policy has shown promise in this domain, existing base policy approaches often rely on hand-designed full-state features and polic ies or extensive demonstrations, limiting their applicability in semi-structured environments." Our news journalists obtained a quote from the research from the South China Uni versity of Technology, "In this study, we propose an innovative Object-Embodimen t-Centric Imitation and Residual Reinforcement Learning (OEC-IRRL) approach that leverages an object-embodiment-centric (OEC) task representation to integrate v ision models with imitation and residual learning. By utilizing a single demonst ration and minimizing interactions with the environment, our method aims to enha nce learning efficiency and effectiveness. The proposed method involves three ke y steps: creating an object-embodiment-centric task representation, employing im itation learning for a base policy using via-point movement primitives for gener alization to different settings, and utilizing residual RL for uncertainty-aware policy refinement during the assembly phase. Through a series of comprehensive experiments, we investigate the impact of the OEC task representation on base an d residual policy learning and demonstrate the effectiveness of the method in se mi-structured environments. Our results indicate that the approach, requiring on ly a single demonstration and less than 1.2 h of interaction, improves success r ates by 46% and reduces assembly time by 25%."
      原文链接:
    • NETL
    • NSTL

    Shibaura Institute of Technology Researchers Update Current Data on Robotics (At tention-Based Grasp Detection With Monocular Depth Estimation)

    30-31页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on robotics are presented i n a new report. According to news reporting from Tokyo, Japan, by NewsRx journal ists, research stated, "Grasp detection plays a pivotal role in robotic manipula tion, allowing robots to interact with and manipulate objects in their surroundi ngs. Traditionally, this has relied on three-dimensional (3D) point cloud data a cquired from specialized depth cameras." Funders for this research include Jsps Kakenhi. Our news journalists obtained a quote from the research from Shibaura Institute of Technology: "However, the limited availability of such sensors in real-world scenarios poses a significant challenge. In many practical applications, robots operate in diverse environments where obtaining high-quality 3D point cloud data may be impractical or impossible. This paper introduces an innovative approach to grasp generation using color images, thereby eliminating the need for dedicat ed depth sensors. Our method capitalizes on advanced deep learning techniques fo r depth estimation directly from color images. Instead of relying on conventiona l depth sensors, our approach computes predicted point clouds based on estimated depth images derived directly from Red-Green-Blue (RGB) input data. To our know ledge, this is the first study to explore the use of predicted depth data for gr asp detection, moving away from the traditional dependence on depth sensors. The novelty of this work is the development of a fusion module that seamlessly inte grates features extracted from RGB images with those inferred from the predicted point clouds. Additionally, we adapt a voting mechanism from our previous work (VoteGrasp) to enhance robustness to occlusion and generate collision-free grasp s. Experimental evaluations conducted on standard datasets validate the effectiv eness of our approach, demonstrating its superior performance in generating gras p configurations compared to existing methods."
      原文链接:
    • NETL
    • NSTL