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

    Recent Findings in Machine Learning Described by Researchers from Shanghai University (Low-overhead Xor Multi-puf Against Machine Learning Attacks)

    48-49页
    查看更多>>摘要：Investigators discuss new findings in Machine Learning. According to news reporting from Shanghai, People's Republic of China, by NewsRx journalists, research stated, "Physical unclonable functions (PUF) have been a hot research topic in hardware security in recent years. Still, most of the research has not focused on the design of balancing its resistance to machine learning attacks with resources." The news correspondents obtained a quote from the research from Shanghai University, "Therefore, in this paper, a new low-overhead XOR Multi-PUF design is proposed, which achieves the response of outputting different modes of PUFs with configurable bits to change the number of delays and inverters inside the circuit, completing the PUF design with less hardware overhead. It also introduces an input challenge obfuscation mechanism to improve its resistance to machine learning attacks. In this paper, the proposed PUF circuit design is verified on FPGA boards and good performance metrics are obtained." According to the news reporters, the research concluded: "The design has more challenge-response pairs (CRPs) and less hardware overhead than existing PUF low-overhead designs, improving resistance to machine learning attacks."
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Data on Intelligent Systems Reported by Researchers at Chinese Academy of Sciences (Spcs: a Spatial Pyramid Convolutional Shuffle Module for Yolo To Detect Occluded Object)

    49-49页
    查看更多>>摘要：A new study on Machine Learning - Intelligent Systems is now available. According to news reporting out of Shenyang, People's Republic of China, by NewsRx editors, research stated, "In crowded scenes, one of the most important issues is that heavily overlapped objects are hardly distinguished from each other since most of their pixels are shared and the visible pixels of the occluded objects, which are used to represent their features, are limited. In this paper, a spatial pyramid convolutional shuffle (SPCS) module is proposed to extract refined information from the limited visible pixels of the occluded objects and generate distinguishable representations for the heavily overlapped objects." Our news journalists obtained a quote from the research from the Chinese Academy of Sciences, "We adopt four convolutional kernels with different sizes and dilation rates at each location in the pyramid features and adjacently recombine their fused outputs spatially using a pixel shuffle module. In this way, four distinguishable instance predictions corresponding different convolutional kernels can be produced for each location in the pyramid feature. In addition, multiple convolutional operations with different kernel sizes and dilation rates at the same location can generate refined information for the corresponding regions, which is helpful to extract features for the occluded objects from their limited visible pixels. Extensive experimental results demonstrate that SPCS module can effectively boost the performance in crowded human detection."
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Studies from Informatics Institute for Postgraduate Studies Provide New Data on Support Vector Machines (Using Speech Signal for Emotion Recognition Using Hybrid Features with SVM Classifier)

    50-50页
    查看更多>>摘要：Research findings on support vector machines are discussed in a new report. According to news originating from the Informatics Institute for Postgraduate Studies by NewsRx correspondents, research stated, "Emotion recognition is a hot topic that has received a lot of attention and study,owing to its significance in a variety of fields, including applications needing human-computer interaction (HCI)." Our news reporters obtained a quote from the research from Informatics Institute for Postgraduate Studies: "Extracting features related to the emotional state of speech remains one of the important research challenges. This study investigated the approach of the core idea behind feature extraction is the residual signal of the prediction procedure is the difference between the original and the prediction .hence the visibility of using sets of extracting features from speech single when the statistical of local features were used to achieve high detection accuracy for seven emotions. The proposed approach is based on the fact that local features can provide efficient representations suitable for pattern recognition. Publicly available speech datasets like the Berlin dataset are tested using a support vector machine (SVM) classifier. The hybrid features were trained separately. The results indicated that some features were terrible."
      原文链接:
    • NETL
    • NSTL

    New Robotics Findings Has Been Reported by Investigators at School of Mechanical Engineering (Positioning Error Calibration of Six-axis Robot Based On Sub-identification Space)

    50-51页
    查看更多>>摘要：Data detailed on Robotics have been presented. According to news originating from Tianjin, People's Republic of China, by NewsRx correspondents, research stated, "A novel subspace-based positioning error calibration method is proposed for six-axis industrial robots. This method divides the entire workspace of the robot into two sub-identification spaces to achieve error dimensionality reduction."Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from the School of Mechanical Engineering, "A spherical S-shaped trajectory with multi-axis linkage is proposed by using a double ball bar (DBB). The error measurement mode combining three-axis and six-axis linkage is adopted to effectively simplify the error identification process and improve the calibration accuracy. In order to evaluate the influence of various errors on the positioning error of the robot end-effector, based on the robot kinematics calibration model, the sensitivity analysis of each axis error is carried out by uniaxial and multi-axis linkage. Compared with the last three axes, the error of the first three axes has a greater impact on the positioning error of the robot end-effector. The installation error of the DBB is eliminated by fitting three orthogonal plane circular trajectories."
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Ural Federal University Researcher Details Research in Machine Learning (Bulk Power Systems Emergency Control Based on Machine Learning Algorithms and Phasor Measurement Units Data: A State-of-the-Art Review)

    51-52页
    查看更多>>摘要：Investigators publish new report on artificial intelligence. According to news reporting originating from Ural Federal University by NewsRx correspondents, research stated, "Modern electrical power systems are characterized by a high rate of transient processes, the use of digital monitoring and control systems, and the accumulation of a large amount of technological information. The active integration of renewable energy sources contributes to reducing the inertia of power systems and changing the nature of transient processes." Financial supporters for this research include Russian Science Foundation. The news editors obtained a quote from the research from Ural Federal University: "As a result, the effectiveness of emergency control systems decreases. Traditional emergency control systems operate based on the numerical analysis of power system dynamic models. This allows for finding the optimal set of preventive commands (solutions) in the form of disconnections of generating units, consumers, transmission lines, and other primary grid equipment. Thus, the steady-state or transient stability of a power system is provided. After the active integration of renewable sources into power systems, traditional emergency control algorithms became ineffective due to the time delay in finding the optimal set of control actions. Currently, machine learning algorithms are being developed that provide high performance and adaptability. This paper contains a meta-analysis of modern emergency control algorithms for power systems based on machine learning and synchronized phasor measurement data. It describes algorithms for determining disturbances in the power system, selecting control actions to maintain transient and steady-state stability, stability in voltage level, and limiting frequency. This study examines 53 studies piled on the development of a methodology for analyzing the stability of power systems based on ML algorithms."
      原文链接:
    • NETL
    • NSTL
    • Mdpi

    University Hospital Reports Findings in Adverse Drug Reactions (Robot-assisted early mobilization for intensive care unit patients: Feasibility and first-time clinical use)

    52-53页
    查看更多>>摘要：New research on Drugs and Therapies - Adverse Drug Reactions is the subject of a report. According to news originating from Munich, Germany, by NewsRx correspondents, research stated, "Early mobilization is only carried out to a limited extent in the intensive care unit. To address this issue, the robotic assistance system VEMOTION® was developed to facilitate (early) mobilization measures more easily." Our news journalists obtained a quote from the research from University Hospital, "This paper describes the first integration of robotic assistance systems in acute clinical intensive care units. Feasibility test of robotic assistance in early mobilization of intensive care patients in routine clinical practice. Two intensive are units guided by anesthesiology at a German university hospital. Patients who underwent elective surgery with postoperative treatment in the intensive care unit and had an estimated ventilation time over 48 h. Participants underwent robot-assisted mobilization, scheduled for twenty-minute sessions twice a day, ten times or one week, conducted by nursing staff under actual operational conditions on the units. No randomization or blinding took place. We assessed data regarding feasible cutoff points (in brackets): the possibility of enrollment (× 50 %), duration (pre- and post-setup (× 25 min), therapy duration (x = 20 min), and intervention-related parameters (number of mobilizing professionals (× 2), intensity of training, events that led to adverse events, errors or discontinuation). Mobilizing professionals rated each mobilization regarding their physical stress (× 3) and feasibility (× 4) on a 7 Point Likert Scale. An estimated sample size of at least twenty patients was calculated. We analyzed the data descriptively. Within 6 months, we screened thirty-two patients for enrollment. 23 patients were included in the study and 16 underwent mobilization using robotic assistance, 7 dropped out (enrollment eligibility = 69 %). On average, 1.9 nurses were involved per therapy unit. Participants received 5.6 robot-assisted mobilizations in mean. Pre- and post-setup had a mean duration of 18 min, therapy a mean of 21 min. The robot-assisted mobilization was started after a median of 18 h after admission to the intensive care unit. We documented two adverse events (pain), twelve errors in handling, and seven unexpected events that led to interruptions or discontinuation. No serious adverse events occurred. The mobilizing nurses rated their physical stress as low (mean 2.0 ± 1.3) and the intervention as feasible (mean 5.3 ± 1.6). Robot-assisted mobilization was feasible, but specific safety measures should be implemented to prevent errors. Robotic-assisted mobilization requires process adjustments and consideration of unit staffing levels, as the intervention does not save staff resources or time.
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Study Findings Have Been Reported by Researchers at Lehigh University (Improving Urban Water Demand Forecast Using Conformal Prediction-based Hybrid Machine Learning Models)

    54-54页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting out of Bethlehem, Pennsylvania, by NewsRx editors, research stated, "This paper presents a probabilistic forecasting method that predicts the future water consumption patterns, taking into account the inherent uncertainty in the system. The proposed method leverages statistical techniques to estimate the probability distribution of future water demand scenarios." Financial support for this research came from Lehigh Uni-versity's faculty research startup package. Our news journalists obtained a quote from the research from Lehigh University, "The findings of this study will provide decision-makers with a range of possible alternatives that facilitate better planning and management of water resources. We developed a conformal prediction-based hybrid demand forecast model, which combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) while comparing it with other machine learning models for probabilistic hourly water demand forecasting. Additionally, we address crucial considerations when implementing a probabilistic forecasting system, including selecting appropriate data and choosing model parameters. The performance of the proposed model is validated for probabilistic water demand forecasting in real-world settings. Results indicate noteworthy improvement in deterministic and probabilistic predictions by 10 % and 26.7 %, respectively. The findings underscore the potential benefits of this approach for improved decision-making and resource management."
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    New Findings from Rochester Institute for Technology in the Area of Robotics Reported (Multi-scale Progressive Fusion-based Depth Image Completion and Enhancement for Industrial Collaborative Robot Applications)

    55-55页
    查看更多>>摘要：Fresh data on Robotics are presented in a new report. According to news reporting originating in Rochester, New York, by NewsRx journalists, research stated, "The depth image obtained by consumer-level depth cameras generally has low resolution and missing regions due to the limitations of the depth camera hardware and the method of depth image generation. Despite the fact that many studies have been done on RGB image completion and super-resolution, a key issue with depth images is that there will be evident jagged boundaries and a significant loss of geometric information." Financial support for this research came from German Research Foundation (DFG). The news reporters obtained a quote from the research from Rochester Institute for Technology, "To address these issues, we introduce a multi-scale progressive fusion network for depth image completion and super-resolution in this paper, which has an asymptotic structure for integrating hierarchical features in different domains. We employ two separate branches to learn the features of a multi-scale image given a depth image and its corresponding RGB image. The extracted features are then fused into different level features of these two branches using a step-by-step strategy to recreate the final depth image. To confine distinct borders and geometric features, a multi-dimension loss is also designed. Extensive depth completion and super-resolution studies reveal that our proposed method outperforms state-of-the-art methods both qualitatively and quantitatively. The proposed methods are also applied to two human-robot interaction applications, including a remote-controlled robot based on an unmanned ground vehicle (UGV), AR-based toolpath planning, and automatic toolpath extraction."
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Boston Consulting Group Reports Findings in Machine Learning (Clinical trials are becoming more complex: a machine learning analysis of data from over 16,000 trials)

    56-56页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from London, United Kingdom, by NewsRx correspondents, research stated, "The past decade has seen substantial innovation in clinical trials, including new trial formats, endpoints, and others. Also there have been regulatory changes, increasing competitive pressures and other external factors which impact clinical trials." Financial support for this research came from Boston Consulting Group. Our news editors obtained a quote from the research from Boston Consulting Group, "In parallel, trial timelines have increased and success rates remain stubbornly low. This has led many observers to question whether clinical trials have become overly complex and if this complexity is always needed. Here we present a large-scale analysis of protocols and other data from over 16,000 trials. Using a machine learning algorithm, we automatically assessed key features of these trials, such as number of endpoints, number of inclusion-exclusion criteria and others. Using a regression analysis we combined these features into a new metric, the Trial Complexity Score, which correlates with overall clinical trial duration. Looking at this score across different clinical phases and therapeutic areas we see substantial increases over time, suggesting that clinical trials are indeed becoming more complex."
      原文链接:
    • NETL
    • NSTL

    Blekinge Institute of Technology Reports Findings in Dementia (Prediction of dementia based on older adults' sleep disturbances using machine learning)

    57-57页
    查看更多>>摘要：New research on Neurodegenerative Diseases and Conditions - Dementia is the subject of a report. According to news reporting originating from Blekinge, Sweden, by NewsRx correspondents, research stated, "The most common degenerative condition in older adults is dementia, which can be predicted using a number of indicators and whose progression can be slowed down. One of the indicators of an increased risk of dementia is sleep disturbances." Our news editors obtained a quote from the research from the Blekinge Institute of Technology, "This study aims to examine if machine learning can predict dementia and which sleep disturbance factors impact dementia. This study uses five machine learning algorithms (gradient boosting, logistic regression, gaussian naive Bayes, random forest and support vector machine) and data on the older population (60+) in Sweden from the Swedish National Study on Ageing and Care - Blekinge (n=4175). Each algorithm uses 10-fold stratified cross-validation to obtain the results, which consist of the Brier score for checking accuracy and the feature importance for examining the factors which impact dementia. The algorithms use 16 features which are on personal and sleep disturbance factors. Logistic regression found an association between dementia and sleep disturbances. However, it is slight for the features in the study. Gradient boosting was the most accurate algorithm with 92.9% accuracy, 0.926 f1-score, 0.974 ROC AUC and 0.056 Brier score. The significant factors were different in each machine learning algorithm. If the person sleeps more than two hours during the day, their sex, education level, age, waking up during the night and if the person snores are the variables that most consistently have the highest feature importance in all algorithms. There is an association between sleep disturbances and dementia, which machine learning algorithms can predict."
      原文链接:
    • NETL
    • NSTL