期刊,Robotics & Machine Learning Daily News 2024年卷Feb.22期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Researchers from Hunan University Report Recent Findings in Ma- chine Learning (Machine-learning-based Detection for Quantum Hacking Attacks On Continuous-variable Quantum-key-distribution Systems)

96-97页

查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting from Changsha, People's Republic of China, by NewsRx journalists, research stated, "Continuous- variable quantum key distribution (CVQKD) is a mature technology that can theoretically provide an unconditional security guarantee. However, a practical CVQKD system may be vulnerable to various quantum hacking attacks due to imperfect devices and insufficient assumptions." Financial supporters for this research include National Natural Science Foundation of China (NSFC), Natural Science Foundation of Hunan Province, Hunan Provincial Education Department. The news correspondents obtained a quote from the research from Hunan University, "In this paper, we propose a universal defense strategy called a machine-learning-based attack detection scheme (MADS). Leveraging the combined advantages of density-based spatial clustering of applications with noise (DB- SCAN) and multiclass support vector machines (MCSVMs), MADS demonstrates remarkable effectiveness in detecting quantum hacking attacks. Specifically, we first establish a set of attack-related features to extract feature vectors. These vectors are then utilized as input data for DBSCAN to identify and remove any noise or outliers. Finally, the trained MCSVMs are employed to classify and predict the processed data. The predicted results can immediately determine whether or not to generate a final secret key."

原文链接:

NETL
NSTL

New Artificial Intelligence Data Have Been Reported by Researchers at Babasaheb Bhimrao Ambedkar University (Exploring the Scope of Explainable Artificial Intelligence In Link Prediction Problem-an Experimental Study)

97-98页

查看更多>>摘要：Researchers detail new data in Artificial Intelligence. According to news originating from Lucknow, India, by NewsRx correspondents, research stated, "The realm of SN has witnessed remarkable developments, capturing the attention of researchers who seek to process and analyze user data in order to extract meaningful insights for future predictions and recommendations. Among the challenging problems in SN analysis is LP, which leverages available data and network knowledge, including node characteristics and connecting edges, to forecast potential associations in the near future." Our news journalists obtained a quote from the research from Babasaheb Bhimrao Ambedkar Uni- versity, "LP is used in data mining, commercial and e-commerce recommendation systems, and expert systems. This research presents a thorough LP taxonomy, including Similarity Metrics and Learning-based approaches, and their recent expansion in numerous network environments. This article also discusses XAI, a method that helps people understand and trust ML systems. LP taxonomy based on XAI is also proposed. The research also examines LIME, a popular XAI approach that illuminates ML and DL models. LIME provides model-independent local explanations for regression and classification tasks on structured and unstructured data. The study includes an extensive experimental evaluation of incorporating XAI with LP, which shows the XAI approach's ability to solve LP problems and interpret predictions."

原文链接:

NETL
NSTL
Springer Nature

Universite Paris Cite Reports Findings in Antibiotics (Machine learn- ing to predict antimicrobial resistance: future applications in clinical practice?)

98-99页

查看更多>>摘要：New research on Drugs and Therapies - Antibiotics is the subject of a report. According to news reporting originating from Paris, France, by NewsRx correspondents, research stated, "Machine learning (ML) is increasingly being used to predict antimicrobial resistance (AMR). This review aims to provide physicians with an overview of the literature on ML as a means of AMR prediction." Our news editors obtained a quote from the research from Universite Paris Cite, "References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, ACM Digital Library, and IEEE Xplore Digital Library up to December 2023. Thirty-six studies were included in this review. Thirty-two studies (32/36, 89%) were based on hospital data and four (4/36, 11%) on outpatient data. The vast majority of them were conducted in high-resource settings (33/36, 92%). Twenty-four (24/36, 67%) studies developed systems to predict drug resistance in infected patients, eight (n=8/36, 22%) tested the performances of ML-assisted antibiotic prescription, two (n=2/36, 6%) assessed ML per- formances in predicting colonization with carbapenem-resistant bacteria and, finally, two assessed national and international AMR trends. The most common inputs were demographic characteristics (25/36, 70%), previous antibiotic susceptibility testing (19/36, 53%) and prior antibiotic exposure (15/36, 42%). Thirty- three (92%) studies targeted prediction of Gram-negative bacteria (GNB) resistance as an output (92%). The studies included showed moderate to high performances, with AUROC ranging from 0.56 to 0.93. ML can potentially provide valuable assistance in AMR prediction."

原文链接:

NETL
NSTL

Data on Machine Learning Reported by Researchers at Dongbei University of Finance & Economics (How To Achieve the High- quality Development of Srdi Enterprises? Evidence From Machine Learning)

99-100页

查看更多>>摘要：Current study results on Machine Learning have been published. According to news originating from Liaoning, People's Republic of China, by NewsRx correspondents, research stated, "Ex- ploring how SRDI enterprises achieve high-quality development constitutes a pivotal task for small and medium-sized enterprises (SMEs) and niche leaders. While prior research primarily concentrated on the in- fluence of innovative policies on SRDI enterprises, it has disregarded the intrinsic propelling forces intrinsic to these enterprises." Financial support for this research came from National Office for Philosophy and Social Sciences. Our news journalists obtained a quote from the research from the Dongbei University of Finance & Economics, "To bridge this research gap, our study leverages a machine learning model that incorporates 19 feature variables spanning four dimensions-'specialization, refinement, distinctiveness, and innovation'- to anticipate high-quality development in enterprises. Drawing on a sample of 667 A-share SRDI-listed enterprises from 2012 to 2022, and after subjecting the data to preprocessing, the study employs the mean of five machine learning models to predict high-quality development in enterprises. Moreover, we discern pivotal feature variables and dimensions. Notably, outcomes underscore the paramount significance of market share in achieving high-quality progress within SRDI enterprises, with refinement emerging as the foremost feature dimension among the four."

原文链接:

NETL
NSTL
Wiley

Report Summarizes Machine Learning Study Findings from Univer- sity of Quebec Montreal (Assessing and Comparing Fixed-target Forecasts of Arctic Sea Ice: Glide Charts for Feature-engineered Linear Regression and Machine Learning Models)

100-101页

查看更多>>摘要：A new study on Machine Learning is now available. According to news originating from Montreal, Canada, by NewsRx correspondents, research stated, "We use 'glide charts'(plots of sequences of root mean squared forecast errors as the target date is approached) to evaluate and compare fixed- target forecasts of Arctic sea ice. We first use them to evaluate the simple feature-engineered linear regression (FELR) forecasts of Diebold and Gobel (2022), and to compare FELR forecasts to naive pure- trend benchmark forecasts." Our news journalists obtained a quote from the research from the University of Quebec Montreal, "Then we introduce a much more sophisticated feature-engineered machine learning (FEML) model, and we use glide charts to evaluate FEML forecasts and compare them to a FELR benchmark. Our substantive results include the frequent appearance of predictability thresholds, which differ across months, meaning that accuracy initially fails to improve as the target date is approached but then increases progressively once a threshold lead time is crossed."

原文链接:

NETL
NSTL
Elsevier

Researchers at Tsinghua University Target Artificial Intelligence (CPT: Colorful Prompt Tuning for pre-trained vision-language mod- els)

101-101页

查看更多>>摘要：New study results on artificial intelligence have been published. According to news re- porting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "Vision-Language Pre-training (VLP) models have shown promising capabilities in grounding natural language in image data, facilitating a broad range of cross-modal tasks." Financial supporters for this research include National Natural Science Foundation of China. The news journalists obtained a quote from the research from Tsinghua University: "However, we note that there exists a significant gap between the objective forms of model pre-training and fine-tuning, resulting in a need for large amounts of labeled data to stimulate the visual grounding capability of VLP models for downstream tasks. To address the challenge, we present Color-based Prompt Tuning (CPT), a novel paradigm for tuning VLP models, which reformulates visual grounding into a fill-in-the-blank problem with color-based co-referential markers in image and text, maximally mitigating the gap. In this way, CPT enables strong few-shot and even zero-shot visual grounding capabilities of VLP models. Comprehensive experimental results show that CPT achieves state-of-the-art performance on zero/few- shot visual grounding (e.g., 75.1 zero-shot accuracy in RefCOCO evaluation), outperforming fine-tuned and other prompt-tuned models by a large margin. Moreover, CPT can also be easily extended to achieve promising zero/few-shot performance on other vision-language tasks, such as visual relation detection, visual commonsense reasoning and visual question answering."

原文链接:

NETL
NSTL

Fudan University Reports Findings in Gliomas (MRI-based Machine Learning Radiomics Can Predict CSF1R Expression Level and Prog- nosis in High-grade Gliomas)

102-102页

查看更多>>摘要：New research on Oncology - Gliomas is the subject of a report. According to news reporting from Shanghai, People's Republic of China, by NewsRx journalists, research stated, "The purpose of this study is to predict the mRNA expression of CSF1R in HGG non-invasively using MRI (magnetic resonance imaging) omics technology and to evaluate the correlation between the established radiomics model and prognosis. We investigated the predictive value of CSF1R in the Cancer Genome Atlas (TCGA) and The Cancer Imaging Archive (TCIA) database." The news correspondents obtained a quote from the research from Fudan University, "The Support vector machine (SVM) and the Logistic regression (LR) algorithms were used to create a radiomics_score (Rad_score), respectively. The effectiveness and performance of the radiomics model was assessed in the training (n = 89) and tenfold cross-validation sets. We further analyzed the correlation between Rad_score and macrophage-related genes using Spearman correlation analysis. A radiomics nomogram combining the clinical factors and Rad_score was constructed to validate the radiomic signatures for individualized survival estimation and risk stratification. The results showed that CSF1R expression was markedly elevated in HGG tissues, which was related to worse prognosis. CSF1R expression was closely related to the abundance of infiltrating immune cells, such as macrophages. We identified nine features for establishing a radiomics model. The radiomics model predicting CSF1R achieved high AUC in training (0.768 in SVM and 0.792 in LR) and tenfold cross-validation sets (0.706 in SVM and 0.717 in LR). Rad_score was highly associated with tumor-related macrophage genes. A radiomics nomogram combining the Rad_score and clinical factors was constructed and revealed satisfactory performance. MRI-based Rad_score is a novel way to predict CSF1R expression and prognosis in high-grade glioma patients."

原文链接:

NETL
NSTL

Findings from University of Miskolc in Nanoparticles Reported (Ma- chine Learning-assisted Characterization of Electroless Deposited Ni-p Particles On Nano/micro Sic Particles)

103-104页

查看更多>>摘要：2024 FEB 22 (NewsRx) – By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A new study on Nanotechnology - Nanoparticles is now available. According to news reporting from Miskolc, Hungary, by NewsRx journalists, research stated, "In this experiment, Ni-P nanoparticles were deposited (ED) on SiC micro- and nanoparticles with different parameters. Our goal was to suc- cessfully prepare metal deposits and develop an effective method for comparing and evaluating the various procedures." Funders for this research include New National Excellence Program of the Ministry for Innovation, National Research, Development and Innovation Fund, Ministry of Innovation and Technology from the National Research, Development and Innovation Fund, National Research, Development & Innovation Office (NRDIO) - Hungary, Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, European Union (EU). The news correspondents obtained a quote from the research from the University of Miskolc, "During the experimental work, a three-step electroless Ni-P coating process was applied with different concentrations. The coated SiC particles were examined by scanning electron microscopy (SEM). The mass-specific surface area (SSA) of the coated SiC was measured by the Brunauer-Emmett-Teller (BET) method, while the volumetric-specific surface area (VSSA) was also calculated. The adhesion between the metal and the ceramic particle was analyzed by X-ray photoelectron spectroscopy (XPS)."

原文链接:

NETL
NSTL
Elsevier

Research Study Findings from University of Management and Tech- nology Update Understanding of Robotics (Computing dominant metric dimensions of certain connected networks)

103-103页

查看更多>>摘要：Research findings on robotics are discussed in a new report. According to news reporting originating from Lahore, Pakistan, by NewsRx correspondents, research stated, "In the studies of the connected networks, metric dimension being a distance-based parameter got much more attention of the researches due to its wide range of applications in different areas of chemistry and computer science." The news journalists obtained a quote from the research from University of Management and Tech- nology: "At present its various types such as local metric dimension, mixed metric dimension, solid metric dimension, and dominant metric dimension have been used to solve the problems related to drug discov- eries, embedding of biological sequence data, classification of chemical compounds, linear optimization, robot navigation, differentiating the interconnected networks, detecting network motifs, image processing, source localization and sensor networking. Dominant resolving sets are better than resolving sets because they carry the property of domination. In this paper, we obtain the dominant metric dimension of wheel, gear and anti-web wheel network in the form of integral numbers. We observe that the aforesaid networks have bounded dominant metric dimension as the order of the network increases."

原文链接:

NETL
NSTL
Elsevier

Studies from Northwest A&F University in the Area of Field Robotics Reported (Performance Evaluation of Newly Released Cameras for Fruit Detection and Localization In Complex Kiwifruit Orchard Environments)

104-105页

查看更多>>摘要：New research on Robotics - Field Robotics is the subject of a report. According to news reporting from Shaanxi, People's Republic of China, by NewsRx journalists, research stated, "Consumer RGB-D and binocular stereo cameras were applied to fruit detection and localization. However, few studies are documented on performance comparison of newly released cameras under same scene in complex orchard." Financial supporters for this research include National Natural Science Foundation of China (NSFC), Key Research and Development Program of Shaanxi, China, National Foreign Expert Project, Ministry of Science and Technology, China. The news correspondents obtained a quote from the research from Northwest A&F University, "This study evaluates performance of consumer RGB-D and binocular stereo cameras based on YOLOv5x for kiwifruit detection and localization and selection of optimal one with better application in complex orchard environment. Firstly, Azure Kinect, RealSense D435, and ZED 2i cameras were employed to capture images of kiwifruit canopies. Subsequently, YOLOv5x was applied to train and detect kiwifruits and calyxes in the images. Meanwhile, an overlap-partitioning detection strategy was applied on kiwifruit and calyx detection. Additionally, spatial coordinate transformation was performed by integrating camera's extrinsic parameters and depth map generated by each camera. Finally, three-dimensional coordinates of calyxes were calculated and compared with ground truth, followed by localization accuracy of calyxes were analyzed. YOLOv5x obtained mean average precision of 93.2%, 91.3%, and 95.8% for three cameras on kiwifruit and calyx detection, respectively. Overlap-partitioning detection strategy improved the calyx detection and significantly increased average precision by 13.00%, 16.30%, and 7.70%, respectively. The mean absolute deviation of calyx coordinates on Y-axis is relatively high for ZED 2i at 8.44 mm in comparison of 6.67 mm for Azure Kinect, while RealSense D435 achieved minimum of 10.42 mm on X-axis and 18.33 mm on Z-axis. Average spatial localization speed of calyxes in one image was 0.164 s, 0.037 s, and 0.062 s for Azure Kinect, RealSense D435, and ZED 2i, respectively."

原文链接:

NETL
NSTL
Wiley