期刊,Robotics & Machine Learning Daily News 2024年卷Jun.19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

New Machine Learning Findings from Friedrich-Schiller-University Jena Described (Enhancing Glass Property Predictions Through Ab Initio-derived Descriptors)

96-97页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting originating from Jena , Germany, by NewsRx correspondents, research stated, "The performance of ab ini tio descriptors derived from density functional theory simulations is systematic ally investigated in comparison to traditional compositional descriptors for the ability to predict glass properties utilizing machine learning algorithms. Two datasets are used for this purpose: an extensive, publicly available database in volving a wide range of oxide glasses, and a small in-house dataset covering a b roader collection of inorganic glasses from metallic to non-metallic materials." Financial supporters for this research include Federal Ministry of Education & Research (BMBF), Federal Ministry of Education & Research (BMBF), Carl Zeiss Foundation, German Research Foundation (DFG). Our news editors obtained a quote from the research from Friedrich-Schiller-Univ ersity Jena, "For the larger dataset, it was demonstrated that ab initio descrip tors offer a substantial reduction in input dimensionality while retaining nearl y equivalent predictive performance when compared to the compositional descripto rs. The combination of ab initio and compositional descriptors showed an improve ment in prediction accuracy. For the smaller dataset, the ab initio-derived desc riptors performed significantly better than the compositional descriptors, provi ding a valuable tool to improve glass property prediction in settings where the availability of data is limited. Furthermore, ab initio-derived descriptors are not only computationally inexpensive and allow extrapolation beyond the training composition space but also facilitate model interpretation. Simple yet effectiv e descriptors: ab initio-derived descriptors improve the performance of machine learning models for predicting glass properties in small datasets. They provide dimensionality reduction and enable predictions beyond the initial compositional space of the training set."

原文链接:

NETL
NSTL

Researchers at Texas A&M University Release New Data on Machine Lea rning (Traditional Machine Learning Methods In Predicting the Physics of Subcrit ical Systems In Source-equilibrium)

97-98页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news reporting originating from College Station, Texas, by NewsRx correspondents, research stated, "Reactivity measurement method s, that are formulas relating integral physics quantity to system observable, we re mostly derived from Point Reactor Kinetics (PRK). PRK presupposes fundamental mode that is driven solely by fissions; however, in Subcritical Assemblies (SCA s), an independent source is present to maintain flux." Financial support for this research came from Department of Science and Technolo gy (DOST) - Science Education Institute of the Republic of the Philippines.

原文链接:

NETL
NSTL

Recent Research from Department of Electronics and Telecommunication Engineering Highlight Findings in Machine Learning (Ultrahigh Frequency Path Loss Predictio n Based On K-nearest Neighbors)

98-99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 from Maharashtra, India, by NewsRx journalists, research stated, "Path loss prediction (PLP) is an importan t feature of wireless communications because it allows a receiver to anticipate the signal strength that will be received from a transmitter at a given distance . The PLP is done by using machine learning models that take into account numero us aspects such as the frequency of the signal, the surroundings, and the type o f antenna." The news correspondents obtained a quote from the research from the Department o f Electronics and Telecommunication Engineering, "Various machine learning metho ds are used to anticipate path loss propagation but it is difficult to predict p ath loss in unknown propagation conditions. In existing models rely on incomplet e or outdated data, which can affect the accuracy and reliability of predictions and they do not take into account the effects of environmental factors, such as terrain, foliage, and weather conditions, on path loss. Furthermore, existing m odels are not robust enough to handle the real-world variability and uncertainty , leading to significant errors in predictions. To tackle this issue, a novel ul trahigh frequency (UHF) PLP based on K-nearest neighbors (KNNs) is developed for predicting and optimizing the path loss for UHF. In this proposed model, a KNN- based PLP has been used to predict the path loss in the UHF. This technique is u sed for high-accuracy PLP through KNN forecast route loss by determining the K-n earest data points to a particular test point based on a distance metric. Moreov er, the existing models were not able to optimize path loss due to complex and l arge-scale machine learning models. Therefore, the stochastic gradient descent t echnique has been used to minimize the objective function, which is often a meas ure of the difference between the model's predictions and the actual output that will fine-tune the parameters of the KNN model, by measuring the similarity bet ween data points."

原文链接:

NETL
NSTL

Researchers at Department of Civil Engineering Report New Data on Artificial Int elligence (Optimizing Aerobic Granular Sludge Process Performance: Unveiling the Power of Coupling Experimental Factorial Design Methodology With Artificial ... )

99-100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 out of Toronto, Canada, by Ne wsRx editors, research stated, "This research explored innovative approaches, in tegrating artificial intelligence (AI) and design of experiments, to enhance the performance of the aerobic granular sludge (AGS) process in wastewater treatmen t. A hybrid model coupling artificial neural networks and random forests (ANN-RF ) with response surface methodology (RSM) via central composite design (CCD) and Box-Behnken design (BBD) was developed to improve the optimization process." Financial support for this research came from Natural Sciences and Engineering R esearch Council of Canada (NSERC) Alliance International Grants.

原文链接:

NETL
NSTL

Reports from Hanoi University of Science and Technology Advance Knowledge in Mac hine Learning (Self-adaptive Algorithms for Quasiconvex Programming and Applicat ions To Machine Learning)

100-100页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Machine Learning have be en published. According to news reporting out of Hanoi, Vietnam, by NewsRx edito rs, research stated, "For solving a broad class of nonconvex programming problem s on an unbounded constraint set, we provide a self-adaptive step-size strategy that does not include line-search techniques and establishes the convergence of a generic approach under mild assumptions. Specifically, the objective function may not satisfy the convexity condition." Funders for this research include Tryyng Dstrok;yi hyc Bch Khoa H Nyi, Hanoi Uni versity of Science and Technology (HUST). Our news journalists obtained a quote from the research from the Hanoi Universit y of Science and Technology, "Unlike descent line-search algorithms, it does not need a known Lipschitz constant to figure out how big the first step should be. The crucial feature of this process is the steady reduction of the step size un til a certain condition is fulfilled. In particular, it can provide a new gradie nt projection approach to optimization problems with an unbounded constrained se t."

原文链接:

NETL
NSTL

Medical University of Silesia in Katowice Reports Findings in Drug Delivery Syst ems (Sharper vision, steady hands: can robots improve subretinal drug delivery? Systematic review)

101-101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 Drugs and Therapies - Drug Delivery Systems is the subject of a report. According to news reporting ou t of Zabrze, Poland, by NewsRx editors, research stated, "Subretinal injection ( SI) is a novel drug delivery method, directly to retina for treatment of various eye disease. However, manual injection requires surgical experience and precisi on due to physiological factors." Our news journalists obtained a quote from the research from the Medical Univers ity of Silesia in Katowice, "Robots offer solution to this issue, by reducing ha nd tremor and increased accuracy. This systematic review analyzes current status on robot-assisted SI compared to conventional techniques. Systematic search acr oss 5 databases was conducted to identify studies comparing manual and robot-ass isted SI procedures. Extracted data included robotic systems, complications, and success rates. Four studies, including one human trial, two ex vivo porcine eye studies, and one artificial eye model study were included in the synthesis. The findings show early advantages of robot-assisted SI. Compared to traditional in terventions, robot procedures result in reduced tremor, what potentially lowers the risk of complications, including retinal tears and reflux. The first in-huma n randomized trial showed encouraging results, with no significant differences i n surgical times or complications between robot-assisted and manual SI. However, major limitation of robot-assisted procedures is longer procedure time. Robot-a ssisted SI holds promise by offering increased precision and stability, reducing human error and potentially improving clinical outcomes. Challenges include cos t, availability, and learning curve. Overall, early stage of robot-assisted SI s uggests advantages in precision, complication reduction, and potentially improve d drug delivery."

原文链接:

NETL
NSTL

Ghent University Reports Findings in Machine Learning (Machine learning modeling to predict causes of infectious abortions and perinatal mortalities in cattle)

102-102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 Machine Learning is th e subject of a report. According to news reporting out of Merelbeke, Belgium, by NewsRx editors, research stated, "A plethora of infectious and non-infectious c auses of bovine abortions and perinatal mortalities (APM) have been reported in literature. However, due to financial limitations or a potential zoonotic impact , many laboratories only offer a standard analytical panel, limited to a preesta blished number of pathogens." Our news journalists obtained a quote from the research from Ghent University, " To improve the cost-efficiency of laboratory diagnostics, it could be beneficial to design a targeted analytical approach for APM cases, based on maternal and e nvironmental characteristics associated with the prevalence of specific abortifa cient pathogens. The objective of this retrospective observational study was to implement a machine learning pipeline (MLP) to predict maternal and environmenta l factors associated with infectious APM. Our MLP based on a greedy ensemble app roach incorporated a standard tuning grid of four models, applied on a dataset o f 1590 APM cases with a positive diagnosis that was achieved by analyzing an ext ensive set of abortifacient pathogens. Production type (dairy/beef), gestation l ength, and season were successfully predicted by the greedy ensemble, with a mod est prediction capacity which ranged between 63 and 73 %. Besides t he predictive accuracy of individual variables, our MLP hierarchically identifie d predictor importance causes of associated environmental/maternal characteristi cs of APM. For instance, in APM cases that happened in beef cows, season at APM (spring/summer) was the most important predictor with a relative importance of 2 4 %. Furthermore, at the last trimester of gestation Trueperella py ogenes and Neospora caninum were the most important predictors of APM with a rel ative importance of 22 and 17 %, respectively. Interestingly, herd size came out as the most relevant predictor for APM in multiparous dams, with a relative importance of 12 %."

原文链接:

NETL
NSTL

Research on Artificial Intelligence Detailed by Researchers at Ben- Gurion Univer sity of the Negev (Semi-supervised active learning using convolutional auto- enc oder and contrastive learning)

103-103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 artificial intelligenc e is the subject of a new report. According to news reporting from Be'er Sheva, Israel, by NewsRx journalists, research stated, "Active learning is a field of m achine learning that seeks to find the most efficient labels to annotate with a given budget, particularly in cases where obtaining labeled data is expensive or infeasible. This is becoming increasingly important with the growing success of learning-based methods, which often require large amounts of labeled data." The news reporters obtained a quote from the research from Ben-Gurion University of the Negev: "Computer vision is one area where active learning has shown prom ise in tasks such as image classification, semantic segmentation, and object det ection. In this research, we propose a pool-based semi-supervised active learnin g method for image classification that takes advantage of both labeled and unlab eled data. Many active learning approaches do not utilize unlabeled data, but we believe that incorporating these data can improve performance. To address this issue, our method involves several steps. First, we cluster the latent space of a pre-trained convolutional autoencoder. Then, we use a proposed clustering cont rastive loss to strengthen the latent space's clustering while using a small amo unt of labeled data. Finally, we query the samples with the highest uncertainty to annotate with an oracle. We repeat this process until the end of the given bu dget."

原文链接:

NETL
NSTL

Researchers at Presidency University Have Reported New Data on Machine Learning (Pirap: a Study On Optimized Multi-language Classification and Text Categorizati on Using Supervised Hybrid Machine Learning Approaches)

103-104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 Ma chine Learning. According to news reporting originating in Bengaluru, India, by NewsRx journalists, research stated, "Nowadays, all the records in various langu ages are accessible with their advanced structures. For simple recovery of these digitized records, these reports should be ordered into a class as indicated by their content." The news reporters obtained a quote from the research from Presidency University , "Text Categorization is an area of Text Mining which helps to overcome this ch allenge. Text Classification is a demonstration of allotting classes to records. This paper investigates Text Classification works done in foreign Languages, re gional languages and a list of books' content. Messages available in different l anguages force the difficulties of NLP approaches. This study shows that supervi sed ML algorithms such as Logistic regression, Naive Bayes classifier, k-Nearest -Neighbor classifier, Decision Tree and SVMs performed better for Text Classific ation tasks. The automated document classification technique is useful in our da y-to-day life to find out the type of language and different department books ba sed on their text content. We have been using different foreign and regional lan guages here to classify such as Tamil, Telugu, Kannada, Bengali, English, Spanis h, French, Russian and German. Here, we utilize one versus all SVMs for multi-ch aracterization with 3-crease Cross Validation in all cases and see that SVMs out perform different classifiers."

原文链接:

NETL
NSTL

New Findings from University of Maryland in the Area of Machine Learning Describ ed (Machine intelligence accelerated design of conductive MXene aerogels with pr ogrammable properties)

104-105页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in artificial intelligence. According to news reporting originating from the Univer sity of Maryland by NewsRx correspondents, research stated, "Designing ultraligh t conductive aerogels with tailored electrical and mechanical properties is crit ical for various applications." Our news journalists obtained a quote from the research from University of Maryl and: "Conventional approaches rely on iterative, time-consuming experiments acro ss a vast parameter space. Herein, an integrated workflow is developed to combin e collaborative robotics with machine learning to accelerate the design of condu ctive aerogels with programmable properties. An automated pipetting robot is ope rated to prepare 264 mixtures of Ti3C2Tx MXene, cellulose, gelatin, and glutaral dehyde at different ratios/loadings. After freeze-drying, the aerogels' structur al integrity is evaluated to train a support vector machine classifier. Through 8 active learning cycles with data augmentation, 162 unique conductive aerogels are fabricated/characterized via robotics-automated platforms, enabling the cons truction of an artificial neural network prediction model. The prediction model conducts two-way design tasks: (1) predicting the aerogels' physicochemical prop erties from fabrication parameters and (2) automating the inverse design of aero gels for specific property requirements."

原文链接:

NETL
NSTL