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 from San Jose, California, by NewsRx journalists, research stated, "Insomnia causes serious adverse health ef fects and is estimated to affect 10-30% of the worldwide populatio n. This study leverages personalized fine-tuned machine learning algorithms to d etect insomnia risk based on questionnaire and longitudinal objective sleep data collected by a smart bed platform." The news correspondents obtained a quote from the research, "Users of the Sleep Number smart bed were invited to participate in an IRB approved study which requ ired them to respond to four questionnaires (which included the Insomnia Severit y Index; ISI) administered 6 weeks apart from each other in the period from Nove mber 2021 to March 2022. For 1,489 participants who completed at least 3 questio nnaires, objective data (which includes sleep/wake and cardio-respiratory metric s) collected by the platform were queried for analysis. An incremental, passive- aggressive machine learning model was used to detect insomnia risk which was def ined by the ISI exceeding a given threshold. Three ISI thresholds (8, 10, and 15 ) were considered. The incremental model is advantageous because it allows perso nalized finetuning by adding individual training data to a generic model. The g eneric model, without personalizing, resulted in an area under the receiving-ope rating curve (AUC) of about 0.5 for each ISI threshold. The personalized fine-tu ning with the data of just five sleep sessions from the individual for whom the model is being personalized resulted in AUCs exceeding 0.8 for all ISI threshold s. Interestingly, no further AUC enhancements resulted by adding personalized da ta exceeding ten sessions."
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 from Kaohsiung City, Taiwan, by NewsRx journalists, research stated, "A detection and classification machine- learning model to inspect Thin Film Transistor Liquid Crystal Display (TFT-LCD) Mura is proposed in this study." Our news journalists obtained a quote from the research from National Kaohsiung University of Science and Technology: "To improve the capability of the machine- learning model to inspect panels' low-contrast grayscale images, piecewise gamma correction and a Selective Search algorithm are applied to detect and optimize the feature regions based on the Semiconductor Equipment and Materials Internati onal Mura (SEMU) specifications. In this process, matching the segment proportio ns to gamma values of piecewise gamma is a task that involves derivative-free op timization which is trained by adaptive particle swarm optimization. The detecti on accuracy rate (DAR) is approximately 93.75%. An enhanced convolu tional neural network model is then applied to classify the Mura type through us ing the Taguchi experimental design method that identifies the optimal combinati on of the convolution kernel and the maximum pooling kernel sizes."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Fresh data on artificial intelligence are present ed in a new report. According to news reporting originating from Nanjing, People 's Republic of China, by NewsRx correspondents, research stated, "Metamodeling i s a promising technique for alleviating the computational burden of building ene rgy simulation." Financial supporters for this research include National Natural Science Foundati on of China; Jiangsu Province Natural Science Foundation; Ministry of Education of The People's Republic of China Humanities And Social Sciences Youth Foundatio n. The news journalists obtained a quote from the research from Nanjing Tech Univer sity: "Although various machine learning (ML) algorithms have been applied, the interactive effects of multiple factors on ML algorithm performance remain uncle ar. In this study, six popular ML algorithms, including ridge regression, random forest, extreme gradient boosting (XGBoost), support vector regression (SVR), k-nearest neighbor (KNN) regression and multi-layer perceptron (MLP), were analyz ed for a benchmark metamodeling problem in building energy simulation under the impacts of four factors: input dimension, sample size, degree of input-output se nsitivity and hyperparameter optimization (HPO) technique. The results indicated that XGBoost had high model precision and strong robustness, while KNN and SVR performed poorly on the two metrics. Increasing the sample size could mitigate t he impact of the other three factors on model precision, especially for MLP."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Research findings on Robotics are discussed in a new report. According to news originating from Xi'an, People's Republic of China, by NewsRx correspondents, research stated, "Aimed at the challenges of wide-an gle mobile robot visual perception for diverse field applications, we present th e spherical robot visual system that uses a 360 degrees field of view (FOV) for realizing real-time object detection. The spherical robot image acquisition syst em model is developed with optimal parameters, including camera spacing, camera axis angle, and the distance of the target image plane." Funders for this research include National Natural Science Foundation of China ( NSFC), Shanxi Provincial Key Research Project, Xinjiang Funded by Autonomous Reg ion Major Science and Technology Special Project, Shaanxi Provincial Key RD Prog ram, Fundamental Research Funds for the Central Universities. Our news journalists obtained a quote from the research from Xi'an Jiaotong Univ ersity, "Two 180 $ <. > {\circ}$ -wide panoramic FOVs, front and rear view, are formed using four on-board cameras. Th e speed of the SURF algorithm is increased for feature extraction and matching. For seamless fusion of the images, an improved fade-in and fade-out algorithm is used, which not only improves the seam quality but also improves object detecti on performance. The speed of the dynamic image stitching is significantly enhanc ed by using a cache-based sequential image fusion method. On top of the acquired panoramic wide FOVs, the YOLO algorithm is used for real-time object detection. "
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-Adenocarcin oma is the subject of a report. According to news reporting from Winnipeg, Canad a, by NewsRx journalists, research stated, "The main difficulty of minimally inv asive Ivor Lewis (IL) procedure for adenocarcinoma of the esophagogastric juncti on (AEGJ) is the intrathoracic esophagogastric anastomosis (IEA). We aimed to as sess the safety and feasibility of the IL procedure with the da Vinci surgical s ystem for treatment of AEGJ with semi-mechanical intrathoracic IEA." The news correspondents obtained a quote from the research from the University o f Manitoba, "The cohort included 72 patients with AEGJ who received treatment at the Department of Minimally Invasive Esophagus Surgery of the Tianjin Medical U niversity Cancer Institute and Hospital from August 2020 to March 2023. Of these 72 patients, 17 received neoadjuvant chemo-immunotherapy. The robot-assisted mi nimally invasive IL procedure was performed using a linear stapler for overlap s ide-to-side intrathoracic anastomosis and the stapler defect was closed with dou ble full-layer continuous sutures by robotic handsewn (semi-mechanical) IEA. Of the 72 AEGJ patients, 2 were converted to exploration, 7 were converted to lapa rotomy and thoracotomy for circular-stapled intrathoracic anastomosis, and 6 wer e converted to thoracotomy for circular-stapled anastomosis, which included 2 ca ses of extensive pleural adhesion and 4 cases of overlap anastomosis failure, wh ereas 57 underwent the robot-assisted minimally invasive IL procedure with semi- mechanical IEA. Among the 9 patients converted to laparotomy, the laparotomy rat e was closely related to the Siewert classification (P <0.0 05) and preoperative use of neoadjuvant therapy (P <0.05). Among the 57 patients who underwent the robot-assisted minimally invasive IL pro cedure with semi-mechanical IEA, there were 2 cases of anastomotic leakages (2/5 7, 3.5%), no case of anastomotic stricture, 5 cases of postoperativ e pneumonia (5/57, 8.77%), 2 cases of intensive care unit admission (2/57, 3.5%), and 1 case of readmission within 30 days (1/57, 1.75 %). None of the patients died within 30 days after surgery. The rob ot-assisted minimally invasive IL procedure with semi-mechanical IEA is both saf e and feasible for AEGJ."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on artificial intelligence have been published. According to news originating from Rostov on Don, Russia, b y NewsRx correspondents, research stated, "The determination of mechanical prope rties for different building materials is a highly relevant and practical field of application for machine learning (ML) techniques within the construction sect or." Funders for this research include Russian Science Foundation. Our news correspondents obtained a quote from the research from Don State Techni cal University: "When working with vibrocentrifuged concrete products and struct ures, it is crucial to consider factors related to the impact of aggressive envi ronments. Artificial intelligence methods can enhance the prediction of vibrocen trifuged concrete properties through the use of specialized machine learning alg orithms for materials' strength determination. The aim of this article is to est ablish and evaluate machine learning algorithms, specifically Linear Regression (LR), Support Vector Regression (SVR), Random Forest (RF), CatBoost (CB), for th e prediction of compressive strength in vibrocentrifuged concrete under diverse aggressive operational conditions. This is achieved by utilizing a comprehensive database of experimental values obtained in laboratory settings. The following metrics were used to analyze the accuracy of the constructed regression models: Mean Absolute Error (* * MAE* * ), Mean Squared Error (* * MSE* * ), Root-Mean-S quare Error (* * RMSE* * ), Mean Absolute Percentage Error (* * MAPE* * ) and co efficient of determination (* * R* * 2). The average * * MAPE* * in the range from 2% (RF, CB) to 7% (LR, SVR) allowed us to draw conclusions about the possibility of using ‘smart' algorithms in the development of compositions and quality control of vibrocentri fuged concrete, which ultimately entails the improvement and acceleration of the construction and building materials manufacture."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning-Intelligent Systems. According to news reporting out of Fes, Morocco, by NewsRx editors, research stated, "Recent advances in imaging technologies h ave led to a significant increase in the adoption of stereoscopic images. Howeve r, despite this proliferation, in-depth research into the complex analysis of th e visual content of these stereoscopic images is still relatively rare." Financial support for this research came from King Saud University. Our news journalists obtained a quote from the research from Sidi Mohamed Ben Ab dellah University, "The advent of stereoscopic imaging has brought a new dimensi on to visual content. These images offer a higher level of visual detail, making them increasingly common in a variety of fields, including medicine and industr ial applications. However, exploiting the full potential of stereoscopic images requires a deeper understanding. By exploiting the capabilities of octonion mome nts and the power of artificial intelligence, we aim to break new ground by intr oducing a novel method for classifying stereoscopic images. The proposed method is divided into two key stages: The first stage involves data preprocessing, dur ing which we strive to construct a balanced database divided into three distinct categories. In addition, we extract the stable Octonion Krawtchouk moments (SOK M) for each image, leading to a database of moment images with dimensions of 128 x 128 x 1. In the second step, we train a convolutional neural network (CNN) mo del using this database, with the aim of discriminating between different catego ries. Standard measures such as precision, accuracy, recall, F1 score, and ROC c urves are used to assess the effectiveness of our method."
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 out of Beijing, People's Repu blic of China, by NewsRx editors, research stated, "Traditional methods for deve loping new materials are no longer sufficient to meet the needs of the human ene rgy transition. Machine learning (ML) artificial intelligence (AI) and advanceme nts have caused materials scientists to realize that using AI/ML to accelerate t he development of new materials for batteries is a powerful potential tool." Funders for this research include National Natural Science Foundation of China, Ministry of Science and Technology of the People's Republic of China. Our news journalists obtained a quote from the research from Tsinghua University, "Although the use of certain fixed properties of materials as descriptors to a ct as a bridge between the two separate disciplines of AI and materials chemistr y has been widely investigated, many of the descriptors lack universality and ac curacy due to a lack of understanding of the mechanisms by which AI/ML operates. Therefore, understanding the underlying operational mechanisms and learning log ic of AI/ML has become mandatory for materials scientists to develop more accura te descriptors. To address those challenges, this paper reviews previous work on AI, machine learning and materials descriptors and introduces the basic logic o f AI and machine learning to help materials developers understand their operatio nal mechanisms."
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 originating from the Mechanical Engineering Department by NewsRx editors, the research stated, "Among four joints of human foot in the ank le area, the tibiotalar and subtalar joints play the most important role in maki ng it possible for the foot to perform rotational movements such that kinematic behavior of foot is almost completely affected by orientation of their rotation axes." The news correspondents obtained a quote from the research from Mechanical Engin eering Department: "Deviation of the axis of rotation from the normal position c an impair the function of the ankle and even the lower extremity. In this study, a new non-invasive method has been proposed, through which, using a gyroscopic mechanism, the orientation of the rotation axes of the tibiotalar and subtalar j oints can be determined. This method is based on indirect data acquisition from the kinematic behavior of the foot. Using the calculated matrices and through th e optimization method, the orientation and position of the rotation axes were re spectively calculated at relatively high precision. These results were also asse ssed in practice by building an ankle mechanical model and a robotic gyroscopic mechanism which is used as a robotic rehabilitation device for ankle rehabilitat ion."
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 originating from the Vishwakarma In stitute of Information Technology by NewsRx correspondents, research stated, "Ma chine learning algorithms have quickly risen to the top of several fields' decis ion-making processes in recent years." Our news correspondents obtained a quote from the research from Vishwakarma Inst itute of Information Technology: "However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choice s. In this work, we examine bias in machine learning in great detail and offer s trategies for promoting fair and moral algorithm design. The paper then emphasis es the value of fairnessaware machine learning algorithms, which aim to lessen b ias by including fairness constraints into the training and evaluation procedure s. Reweighting, adversarial training, and resampling are a few strategies that c ould be used to overcome prejudice. Machine learning systems that better serve s ociety and respect ethical ideals can be developed by promoting justice, transpa rency, and inclusivity." According to the news reporters, the research concluded: "This paper lays the gr oundwork for researchers, practitioners, and policymakers to forward the cause o f ethical and fair machine learning through concerted effort."
NETL
NSTL