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

    University of Zagreb Researcher Focuses on Robotics (Generating a Dataset for Semantic Segmentation of Vine Trunks in Vineyards Using Semi-Supervised Learning and Object Detection)

    56-57页
    查看更多>>摘要：A new study on robotics is now available. According to news originating from Zagreb, Croatia, by NewsRx correspondents, research stated, “This article describes an experimentally tested approach using semi-supervised learning for generating new datasets for semantic segmentation of vine trunks with very little human-annotated data, resulting in significant savings in time and resources. The creation of such datasets is a crucial step towards the development of autonomous robots for vineyard maintenance.” Funders for this research include Project Titled Heterogeneous Autonomous Robotic System in Viticulture And Mariculture; European Union Through The European Regional Development Fund-the Competitiveness And Cohesion Operational Programme. The news correspondents obtained a quote from the research from University of Zagreb: “In order for a mobile robot platform to perform a vineyard maintenance task, such as suckering, a semantically segmented view of the vine trunks is required. The robot must recognize the shape and position of the vine trunks and adapt its movements and actions accordingly. Starting with vine trunk recognition and ending with semi-supervised training for semantic segmentation, we have shown that the need for human annotation, which is usually a time-consuming and expensive process, can be significantly reduced if a dataset for object (vine trunk) detection is available. In this study, we generated about 35,000 images with semantic segmentation of vine trunks using only 300 images annotated by a human. This method eliminates about 99% of the time that would be required to manually annotate the entire dataset. Based on the evaluated dataset, we compared different semantic segmentation model architectures to determine the most suitable one for applications with mobile robots.”
      原文链接:
    • NETL
    • NSTL
    • Mdpi

    Data on Machine Learning Reported by Researchers at University of Mataram (Distributed Machine Learning using HDFS and Apache Spark for Big Data Challenges)

    57-58页
    查看更多>>摘要：Researchers detail new data in artificial intelligence. According to news originating from the University of Mataram by NewsRx editors, the research stated, “Hadoop and Apache Spark have become popular frameworks for distributed big data processing. This research aims to configure Hadoop and Spark for conducting training and testing on big data using distributed machine learning methods with MLlib, including linear regression and multi-linear regression.” The news reporters obtained a quote from the research from University of Mataram: “Additionally, an external library, LSTM, is used for experimentation. The experiments utilize three desktop devices to represent a series of tests on single and multi-node networks. Three datasets, namely bitcoin (3,613,767 rows), gold-price (5,585 rows), and housing-price (23,613 rows), are employed as case studies. The distributed computation tests are conducted by allocating uniform core processors on all three devices and measuring execution times, as well as RMSE and MAPE values. The results of the single-node tests using MLlib (both linear and multi-linear regression) with variations of core utilization ranging from 2 to 16 cores, show that the overall dataset performs optimally using 12 cores, with an execution time of 532.328 seconds. However, in the LSTM method, core allocation variations do not yield significant results and require longer program execution times.”
      原文链接:
    • NETL
    • NSTL

    University of Leuven (KU Leuven) Researchers Publish New Studies and Findings in the Area of Machine Learning (Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models)

    58-59页
    查看更多>>摘要：Fresh data on artificial intelligence are presented in a new report. According to news reporting originating from Leuven, Belgium, by NewsRx correspondents, research stated, “Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia, and balance. Accurate monitoring of patient involvement in OEP is challenging, as self-reports (diaries) are often unreliable.” Funders for this research include China Scholarship Council; Enhance Project (S60763) Received A Junior Research Project Grant From The Research Foundation Flanders. Our news correspondents obtained a quote from the research from University of Leuven (KU Leuven): “The development of wearable sensors and their use in Human Activity Recognition (HAR) systems has lead to a revolution in healthcare. However, the use of such HAR systems for OEP still shows limited performance. The objective of this study is to build an unobtrusive and accurate system to monitor OEP for older adults. Data was collected from 18 older adults wearing a single waist-mounted Inertial Measurement Unit (IMU). Two datasets were recorded, one in a laboratory setting, and one at the homes of the patients. A hierarchical system is proposed with two stages: 1) using a deep learning model to recognize whether the patients are performing OEP or activities of daily life (ADLs) using a 10-minute sliding window; 2) based on stage 1, using a 6-second sliding window to recognize the OEP sub-classes. Results showed that in stage 1, OEP could be recognized with window-wise f1-scores over 0.95 and Intersection-over-Union (IoU) f1-scores over 0.85 for both datasets. In stage 2, for the home scenario, four activities could be recognized with f1-scores over 0.8: ankle plantarflexors, abdominal muscles, knee bends, and sit-to-stand.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Studies from Yarmouk University in the Area of Machine Learning Published (Modelling Driver Behaviour at Urban Signalised Intersections Using Logistic Regression and Machine Learning)

    59-59页
    查看更多>>摘要：Data detailed on artificial intelligence have been presented. According to news reporting from Yarmouk University by NewsRx journalists, research stated, “This study investigated several factors that may influence driver actions throughout the yellow interval at urban signalised intersections. The selected samples include 2,168 observations.” The news correspondents obtained a quote from the research from Yarmouk University: “Almost 33% of drivers stopped ahead of the stop line, 60% passed the intersection through the yellow interval, and 7% passed after the yellow interval was complete (red light running, RLR violations). Binary logistic regression models showed that the chance of passing went up as vehicle speed went up and down as the gap between the vehicle and the traffic light and green interval went up. The movement type and vehicle position influenced the passing probability, but the vehicle type did not. Moreover, multinomial logistic regression models showed that the legal passing probability declined with the growth in the green time and vehicle distance to the traffic signal. It also increased with the growth in the speed of approaching vehicles. Also, movement type directly affected the chance of legally passing, but vehicle position and type did not.” According to the news reporters, the research concluded: “Furthermore, the driver’s performance during the yellow phase was studied using the k-nearest neighbours algorithm (KNN), support vector machines (SVM), random forest (RF) and AdaBoost machine learning techniques. The driver’s action run prediction was the most accurate, and the run-on-red camera was the least accurate.”
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Findings from Colorado State University Published (Airborne Radar Quality Control with Machine Learning)

    60-60页
    查看更多>>摘要：New research on artificial intelligence is the subject of a new report. According to news reporting originating from Fort Collins, Colorado, by NewsRx correspondents, research stated, “Airborne Doppler radar provides detailed and targeted observations of winds and precipitation in weather systems over remote or difficult-to-access regions that can help to improve scientific understanding and weather forecasts. Quality control (QC) is necessary to remove nonweather echoes from raw radar data for subsequent analysis.” Funders for this research include National Science Foundation; Noaa Research; Office of Naval Research. Our news correspondents obtained a quote from the research from Colorado State University: “The complex decision-making ability of the machine learning random-forest technique is employed to create a generalized QC method for airborne radar data in convective weather systems. A manually QCed dataset was used to train the model containing data from the Electra Doppler Radar (ELDORA) in mature and developing tropical cyclones, a tornadic supercell, and a bow echo. Successful classification of 96% and 93% of weather and nonweather radar gates, respectively, in withheld testing data indicate the generalizability of the method. Dual-Doppler analysis from the genesis phase of Hurricane Ophelia (2005) using data not previously seen by the model produced a comparable wind field to that from manual QC. The framework demonstrates a proof of concept that can be applied to newer airborne Doppler radars. Significance Statement: Airborne Doppler radar is an invaluable tool for making detailed measurements of wind and precipitation in weather systems over remote or difficult to access regions, such as hurricanes over the ocean. Using the collected radar data depends strongly on quality control (QC) procedures to classify weather and nonweather radar echoes and to then remove the latter before subsequent analysis or assimilation into numerical weather prediction models. Prior QC techniques require interactive editing and subjective classification by trained researchers and can demand considerable time for even small amounts of data.”
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Chongqing Medical University Reports Findings in Imaging Technology (Video-Based Indocyanine Green Fluorescence Applied to Robotic Duodenum-Preserving Pancreatic Head Resection)

    61-62页
    查看更多>>摘要：New research on Technology Imaging Technology is the subject of a report. According to news reporting out of Chongqing, People’s Republic of China, by NewsRx editors, research stated, “Duodenum-preserving pancreatic head resection (DPPHR) serves as a surgical intervention for managing benign and low-grade malignant neoplasms located in the head of the pancreas. This surgical approach enables the thorough excision of pancreatic head lesions, reducing the necessity for digestive tract reconstruction and enhancing the patient’s quality of life.” Our news journalists obtained a quote from the research from the First Affiliated Hospital of Chongqing Medical University, “Performing a minimally invasive DPPHR is a complex surgical procedure, particularly when safeguarding the bile duct and the pancreaticoduodenal arterial arch. Robotic surgery is among the latest innovations in minimally invasive surgery and is widely used in many surgical specialties. It offers advantages such as rotatable surgical instruments, muscle tremor filters and up to 10-15 times three dimensional (3D) visual field, and achieves high flexibility and accuracy in surgical operations. Indocyanine green (ICG) fluorescence imaging technology is also applied to provide real-time intraoperative assessment of the biliary system and blood supply, which helps maintain the biliary system’s integrity. We first report the complete procedure of ICG applied to the da Vinci robotic Xi system for preserving the DPPHR. A 48-year-old female patient was diagnosed with pancreatic duct stones, chronic pancreatitis, and pancreatogenic diabetes. Enhanced computed tomography (CT) scans revealed pancreatic head stones, pancreatic atrophy, scattered calcifications, and a dilated pancreatic duct. An attempt at endoscopic retrograde cholangiopancreatography (ERCP) treatment was abandoned during hospitalization due to unsuccessful catheterization. Following informed consent from the patient and her family, a robotic DPPHR was conducted utilizing ICG fluorescence imaging technology. Approximately 60 min before the surgery, 2 mg of ICG was injected via the peripheral vein. The individual was positioned in a reclined posture with the upper part of the bed raised to an angle of 30° and a leftward tilt of 15°. Upon entering the abdominal cavity, existing adhesions were meticulously separated and the gastrocolic ligament was opened to expose the pancreas. The lower part of the pancreas was separated and the superior mesenteric vein (SMV) was identified at the inferior boundary of the pancreatic neck. The pancreas was cut upward and the pancreatic duct was severed using scissors. Dissection of the lateral wall of the portal vein-SMV in the pancreatic head segment was performed. Meticulous dissection was carried out along the pancreatic tissue, retracting the uncinate process of the pancreas in an upward and rightward direction. During the dissection, caution was exercised to protect the anterior and posterior pancreaticoduodenal arterial arch. By using ICG fluorescence imaging, the path of the common bile duct was identified and verified. Caution was exercised to avoid injuring the bile duct. After isolating the CBD, the head and uncinate process of the pancreas was entirely excised. Under the fluorescence imaging mode, the wholeness of the CBD was scrutinized for any potential seepage of the contrast agent. Ultimately, a Roux-en-Y end-to-side pancreaticojejunostomy (duct to mucosa) was executed. The surgery took 265 min and the estimated blood loss was about 150 mL. Without any postoperative complications, the patient was released from the hospital 13 days following the surgery. Postoperative pathology confirmed pancreatic duct stones and chronic pancreatitis. We have successfully performed four cases of robotic DPPHR using this technique, with only one patient experiencing a postoperative complication of pulmonary embolism. All patients were discharged successfully without any further complications. Employing ICG fluorescence imaging in a robotic DPPHR has been demonstrated to be both secure and achievable.”
      原文链接:
    • NETL
    • NSTL

    Research Results from Universiti Malaya Update Understanding of Machine Learning (Identification of significant features and machine learning technique in predicting helpful reviews)

    62-63页
    查看更多>>摘要：Current study results on artificial intelligence have been published. According to news reporting originating from Kuala Lumpur, Malaysia, by NewsRx correspondents, research stated, “Consumers nowadays rely heavily on online reviews in making their purchase decisions.” Funders for this research include Impact Oriented Interdisciplinary Research Grant University of Malaya. Our news editors obtained a quote from the research from Universiti Malaya: “However, they are often overwhelmed by the mass amount of product reviews that are being generated on online platforms. Therefore, it is deemed essential to determine the helpful reviews, as it will significantly reduce the number of reviews that each consumer has to ponder. A review is identified as a helpful review if it has significant information that helps the reader in making a purchase decision. Many reviews posted online are lacking a sufficient amount of information used in the decision-making process. Past research has neglected much useful information that can be utilized in predicting helpful reviews. This research identifies significant information which is represented as features categorized as linguistic, metadata, readability, subjectivity, and polarity that have contributed to predicting helpful online reviews.”
      原文链接:
    • NETL
    • NSTL
    • Peerj Inc

    Data on Machine Learning Discussed by a Researcher at Xiangtan University (Construction and optimization of corrosion map in a broad region of acidic soil via machine learning)

    63-63页
    查看更多>>摘要：New research on artificial intelligence is the subject of a new report. According to news reporting from Xiangtan, People’s Republic of China, by NewsRx journalists, research stated, “Machine learning has been widely applied to exploring the key affecting factors for metal corrosion in some local regions.” The news reporters obtained a quote from the research from Xiangtan University: “However, there is a lack of systemic research and practicable prediction model for the metal corrosion in a broad region. In this paper, the corrosion map of Q235 steel in a broad region of acidic soils of Hunan province of Central China was constructed and optimized via the field experiment and machine learning. Both the experimental and optimized corrosion maps confirmed that the corrosion rate of the steel decreased from the western to the eastern part of the province. The concentrations of pH, F-, Cl-, NO3-, HCO3-, K+ and Mg2+ were the key affecting factors in the broad region of acidic soils of the province. Among them, the contribution rate of the HCO3concentration was higher than that of other factors.” According to the news editors, the research concluded: “The optimization model based on the ordinary least squares could be used for the optimization of the corrosion map of steels a broad region of acidic soils. The optimized corrosion map was a good alternative of the estimation methods for the corrosion rate of steels in soil.”
      原文链接:
    • NETL
    • NSTL

    Investigators from Tsinghua University Zero in on Robotics (A Sarsa Reinforcement Learning Hybrid Ensemble Method for Robotic Battery Power Forecasting)

    64-64页
    查看更多>>摘要：New research on Robotics is the subject of a report. According to news reporting out of Beijing, People’s Republic of China, by NewsRx editors, research stated, “Building a rail transit workshop with efficient data interconnection has become an inevitable trend in the transformation and development of the current rail transit equipment industry. More and more diversified mobile transport robots have become a priority in the process of digital transformation of smart factories.” Financial supporters for this research include Beijing New Star Program of Science and Technology, China, National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from Tsinghua University, “Accurate prediction of robot battery power can guide the control center to adopt scientific and reasonable instructions in advance to ensure efficient and stable operation of the logistics transportation chain. In this study, we propose a hybrid ensemble method of multiple learners based on state-action-reward-state-action (Sarsa) reinforcement learning algorithm. Maximal overlap discrete wavelet transform (MODWT) is used to preprocess the originally measured robot power supply voltage data. This significantly reduces the non-stationarity and volatility of time series data. Gated recurrent unit (GRU), deep belief network (DBN), and long short-term memory (LSTM), are utilized for the prediction modeling of subseries after decomposition. Finally, the Sarsa reinforcement learning ensemble strategy is used to weight the three basic predictors above. The performance of the Sarsa hybrid model is verified on three real mobile robot power data sets.”
      原文链接:
    • NETL
    • NSTL
    • Journal Of Central South Univ

    Study Findings from Southern Methodist University Broaden Understanding of Robotics (Motion Planning for Multiple Heterogeneous Magnetic Robots Under Global Input)

    65-65页
    查看更多>>摘要：Fresh data on Robotics are presented in a new report. According to news originating from Dallas, Texas, by NewsRx correspondents, research stated, “Magnetism provides an untethered actuation mechanism and an alternative way to actuate robots. Using a magnetic field we can control the motion of robots embedded with magnets.” Our news journalists obtained a quote from the research from Southern Methodist University, “This scales down the size of the robots dramatically such that they can be used in applications like drug delivery, sample col-lection, micromanipulation, and noninvasive procedures. Despite all advantages and potentials, magnetic actuation has one major drawback. Due to the similar interaction between the magnetic field and the embedded magnets in multirobot systems, controlling the robots independently is challenging. Using heterogeneous magnetic robots is one way to overcome the independent control challenge. Here, motion planning for multiple magnetic robots that move in parallel directions at different speeds in response to a global input is addressed in the absence of obstacles in a polygonal work space. Through controllability analysis, it will be shown that having n linearly independent heterogeneous responses to the global input, called Modes of Motion here, enables independent position control of n robots in the system. Further, a procedure to have a potentially feasible sequence of motion is presented and intrarobot collision free directions of movement are formulated mathematically. These procedures are then used in the proposed optimization-based motion planning algorithm. Also, an innovative millimeter scale multimode magnetic pivot walker design is introduced and used for benchmarking in the experiments.”
      原文链接:
    • NETL
    • NSTL
    • IEEE