期刊,Robotics & Machine Learning Daily News 2024年卷Mar.8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

Studies Conducted at University Tenaga Nasional on Intelligent Systems Recently Published (Review of iris segmentation and recognition using deep learning to im prove biometric application)

74-75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 in telligent systems. According to news originating from Selangor, Malaysia, by New sRx editors, the research stated, "Biometric recognition is essential for identi fying people in security, surveillance, and mobile device authentication. Iris r ecognition (IR) biometrics is exact because it uses unique iris patterns to iden tify individuals." The news journalists obtained a quote from the research from University Tenaga N asional: "Iris segmentation, which isolates the iris from the rest of the ocular image, determines iris identification accuracy. The main problem is concerned w ith selecting the best deep learning (DL) algorithm to classify and estimate bio metric iris biometric iris. This study proposed a comprehensive review of DL-bas ed methods to improve biometric iris segmentation and recognition. It also evalu ates reliability, specificity, memory, and F-score. It was reviewed with iris image analysis, edge detection, and classifica tion literature. DL improves iris segmentation and identification in biometric a uthentication, especially when combined with additional biometric modalities lik e fingerprint fusion. Besides, that DL in iris detection requires large training datasets and is challenging to use with noisy or low-quality photos."

原文链接:

NETL
NSTL

Department of Mechanical Engineering Reports Findings in Machine Learning (Plain-Woven Areca Sheath Fiber-Reinforced Epoxy Composites: The Influence of the Fibe r Fraction on Physical and Mechanical Features and Responses of the Tribo System and ...)

75-76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 Karnataka, India, by N ewsRx editors, research stated, "Recent studies focus on enhancing the mechanica l features of natural fiber composites to replace synthetic fibers that are high ly useful in the building, automotive, and packing industries. The novelty of th e work is that the woven areca sheath fiber (ASF) with different fiber fraction epoxy composites has been fabricated and tested for its tribological responses o n three-body abrasion wear testing machines along with its mechanical features." Financial support for this research came from Deanship of Scientific Research, K ing Khalid University. Our news journalists obtained a quote from the research from the Department of M echanical Engineering, "The impact of the fiber fraction on various features is examined. The study also revolves around the development and validation of a mac hine learning predictive model using the random forest (RF) algorithm, aimed at forecasting two critical performance parameters: the specific wear rate (SWR) an d the coefficient of friction (COF). The void fraction is observed to vary betwe en 0.261 and 3.8% as the fiber fraction is incremented. The hardne ss of the mat rises progressively from 40.23 to 84.26 HRB. A fair ascent in the tensile strength and its modulus is also observed. Even though a short descent i n flexural strength and its modulus is seen for 0 to 12 wt % compo site specimens, they incrementally raised to the finest values of 52.84 and 2860 MPa, respectively, pertinent to the 48 wt % fiber-loaded specimen . A progressive rise in the ILSS and impact strength is perceptible. The wear be havior of the specimens is reported. The worn surface morphology is studied to u nderstand the interface of the ASF with the epoxy matrix. The RF model exhibited outstanding predictive prowess, as evidenced by high-squared values coupled with low mean-square error and mean absolute error metrics."

原文链接:

NETL
NSTL

Research in the Area of Androids Reported from Hong Kong University of Science a nd Technology (Human-Inspired Video Imitation Learning on Humanoid Model)

76-77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 androids. According to news reporting originating from Hong Kong University of S cience and Technology by NewsRx correspondents, research stated, "Generating goo d and human-like locomotion or other legged motions for bipedal robots has alway s been challenging." Our news journalists obtained a quote from the research from Hong Kong Universit y of Science and Technology: "One of the emerging solutions to this challenge is to use imitation learning. The sources for imitation are mostly state-only demo nstrations, so using state-of-the-art Generative Adversarial Imitation Learning (GAIL) with Imitation from Observation (IfO) ability will be an ideal framework to use in solving this problem. However, it is often difficult to allow new or c omplicated movements as the common sources for these frameworks are either expen sive to set up or hard to produce satisfactory results without computationally e xpensive preprocessing, due to accuracy problems."

原文链接:

NETL
NSTL

New Artificial Intelligence Study Findings Have Been Reported by Researchers at British University of Egypt (A Comprehensive Survey of Artificial Intelligence-b ased Techniques for Performance Enhancement of Solid Oxide Fuel Cells: Test Case s ...)

77-78页

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 reporting originating in Cairo, Egy pt, by NewsRx journalists, research stated, "Since installing solid oxide fuel c ells (SOFCs)-based systems suffers from high expenses, accurate and reliable mod eling is heavily demanded to detect any design issue prior to the system establi shment. However, such mathematical models comprise certain unknowns that should be properly estimated to effectively describe the actual operation of SOFCs." Financial support for this research came from British University in Egypt (BUE). The news reporters obtained a quote from the research from the British Universit y of Egypt, "Accordingly, due to their recent promising achievements, a tremendo us number of metaheuristic optimizers (MHOs) have been utilized to handle this t ask. Hence, this effort targets providing a novel thorough review of the most re cent MHOs applied to define the ungiven parameters of SOFCs stacks. Specifically, among over 300 attempts, only 175 articles are reported, where thirty up-to-da te MHOs from the last five years are comprehensively illustrated. Particularly, the discussed MHOs are classified according to their behavior into; evolutionary -based, physics-based, swarm-based, and nature-based algorithms. Each is touched with a brief of their inspiration, features, merits, and demerits, along with t heir results in SOFC parameters determination. Furthermore, an overall platform is constructed where the reader can easily investigate each algorithm individual ly in terms of its governing factors, besides, the simulation circumstances rela ted to the studied SOFC test cases. Over and above, numerical simulations are al so introduced for commercial SOFCs' stacks to evaluate the proposed MHOs-based m ethodology. Moreover, the mathematical formulation of various assessment criteri a is systematically presented."

原文链接:

NETL
NSTL

Study Results from Faculty of Mathematical Sciences Provide New Insights into Su pport Vector Machines (Noisy label relabeling by nonparallel support vector mach ine)

78-78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 . According to news reporting originating from Rasht, Iran, by NewsRx corresponden ts, research stated, "In machine learning, models are derived from labeled train ing data where labels signify classes and features define sample attributes. How ever, noise from data collection can impair the algorithm's performance." Our news correspondents obtained a quote from the research from Faculty of Mathe matical Sciences: "Blanco, Japon, and Puerto proposed mixed-integer programming (MIP) models within support vector machines (SVM) to handle label noise in train ing datasets. Nonetheless, it is imperative to underscore that their models demo nstrate an observable escalation in the number of variables as sample size incre ases. The nonparallel support vector machine (NPSVM) is a bi-nary classification method that merges the strengths of both SVM and twin SVM. It accomplishes this by determining two nonparallel hyperplanes by solving two optimization problems . Each hyperplane is strategically po-sitioned to be closer to one of the classe s while maximizing its distance from the other class. In this paper, to take adv antage of NPSVM's fea-tures, NPSVM-based relabeling (RENPSVM) MIP models are dev eloped to deal with the label noises in the dataset. The proposed model adjusts observation labels and seeks optimal solutions while minimizing compu-tational c osts by selectively focusing on class-relevant observations within an e-intensiv e tube." According to the news reporters, the research concluded: "Instances exhibiting s imilarities to the other class are excluded from this e-intensive tube. Experime nts on 10 UCI datasets show that the proposed NPSVM-based MIP models outperform their counter-parts in accuracy and learning time on the majority of datasets."

原文链接:

NETL
NSTL

New Machine Learning Findings from College of Engineering Trivandrum Discussed ( Potential Use of Transesterified Vegetable Oil Blends As Base Stocks for Metalwo rking Fluids and Cutting Forces Prediction Using Machine Learning Tool)

79-80页

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 Machine Learning is now available. According to news reporting originating in Kerala, India, by NewsRx journalists, research stated, "The majority of lubricants used around the world are mineral oil-based, which causes environmental and health risks. The industry is under pressure to develop eco-friendly and biodegradable lubricants due to p oor degradability and the depletion of mineral oil resources." Financial support for this research came from Kerala State Council for Science, Technology, and Environment [KSCSTE], Kera la, India. The news reporters obtained a quote from the research from the College of Engine ering Trivandrum, "Vegetable oils (VO) are being considered as an alternative so urce of lubricants due to their biodegradability, renewability, low toxicity, an d good lubricating characteristics. The VO also suffers few drawbacks such as li mited oxidation stability and poor low-temperature performance. Blending, chemic al modification, and additives can improve the oil's lubricating properties. The objective of the study is to formulate bio-lubricants from vegetable oils such as rice bran oil (RBO), jatropha oil (JO), and a blend of RBO and JO. Transester ification was performed on the vegetable oils, and all samples were assessed for tribological characteristics, oxidative stability, corrosion, and emulsion stab ility using ASTM and international standards. A lathe machine with a tool dynamo meter was used to test the performance of the formulated cutting fluid. Cutting forces were assessed and compared to those of a commercial cutting fluid. Machin e learning algorithms were also used to forecast cutting forces, which were then compared to experimental values. The 1:1 ratio of transesterified RBO and JO ha s shown a better coefficient of friction and superior oxidative stability. Also, the 40% emulsifier in the oil has shown good stability."

原文链接:

NETL
NSTL

Researchers from Henan Normal University Provide Details of New Studies and Find ings in the Area of Intelligent Systems (A Lightweight and Personalized Edge Fed erated Learning Model)

80-80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 - Intelligent Systems are discussed in a new report. According to news originati ng from Xinxiang, People's Republic of China, by NewsRx correspondents, research stated, "As a new distributed machine learning paradigm, federated learning has gained increasing attention in the industry and research community. However, fe derated learning is challenging to implement on edge devices with limited resour ces and heterogeneous data." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Henan Normal Univer sity, "This study aims to realize a lightweight and personalized model through p runing and masking with insufficient resources and heterogeneous data. Particula rly, the server first downloads the subnetwork to the client according to the ma sk, and client prunes the subnetwork with the alternating direction method of mu ltipliers (ADMM), so as to remove the unimportant parameters and reduce the cost of training and communication. At the same time, mask is used to mark the pruni ng condition of the model. Then, the unpruned parts and masks of local models ar e transmitted to the server for aggregation. The experimental results showed tha t the accuracy of the proposed model was improved by 9.36%, and the communication cost was reduced by 1.45 times compared with state-of-the-art mod els."

原文链接:

NETL
NSTL

University of Eastern Finland Reports Findings in Machine Learning (Machine lear ning prediction of future amyloid beta positivity in amyloid-negative individual s)

81-81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 originating in Kuopio, Finlan d,by NewsRx journalists,research stated,"The pathophysiology of Alzheimer's d isease (AD) involves -amyloid (A) accumulation. Early identification of individ uals with abnormal-amyloid levels is crucial, but A quantification with positro n emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expens ive." The news reporters obtained a quote from the research from the University of Eas tern Finland, "We propose a machine learning framework using standard non-invasi ve (MRI, demographics, APOE, neuropsychology) measures to predict future A -posi tivity in A -negative individuals. We separately study A -positivity defined by PET and CSF. Cross-validated AUC for 4-year A conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A definitions. Although not trained for the clinical status-change prediction, the CSF-based model excelled in predict ing future mild cognitive impairment (MCI)/dementia conversion in cognitively no rmal/MCI individuals (AUCs, respectively, 0.76 and 0.89 with a separate dataset).Standard measures have potential in detecting future A -positivity and assessi ng conversion risk, even in cognitively normal individuals."

原文链接:

NETL
NSTL

New Findings on Machine Learning Described by Investigators at University of Bol ogna (Hybrid Models for Knowledge Tracing: a Systematic Literature Review)

81-82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 from Bologna, Italy, by NewsR x journalists, research stated, "Knowledge tracing is a well-known problem in AI for education, consisting of monitoring how the knowledge state of students cha nges during the learning process and accurately predicting their performance in future exercises. In recent years, many advances have been made thanks to variou s machine learning and deep learning techniques." The news correspondents obtained a quote from the research from the University o f Bologna, "Despite their satisfactory performances, they have some pitfalls, e. g., modeling one skill at a time, ignoring the relationships between different s kills, or inconsistency for the predictions, i.e., sudden spikes and falls acros s time steps. For this reason, hybrid machine-learning techniques have also been explored. With this systematic literature review, we aim to illustrate the stat e of the art in this field. Specifically, we want to identify the potential and the frontiers in integrating prior knowledge sources in the traditional machine learning pipeline as a supplement to the normally considered data. We applied a qualitative analysis to distill a taxonomy with the following three dimensions: knowledge source, knowledge representation, and knowledge integration."

原文链接:

NETL
NSTL

Research from Northeast Institute of Geography and Agroecology Yields New Data o n Machine Learning (Remote estimates of suspended particulate matter in global l akes using machine learning models)

82-83页

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 artificial intelligence is now available. According to news originating from Jilin, People's Republic o f China, by NewsRx correspondents, research stated, "Suspended particulate matte r (SPM) in lakes exerts strong impact on light propagation, aquatic ecosystem pr oductivity, which co-varies with nutrients, heavy metal and micro-pollutant in w aters. In lakes, SPM exerts strong absorption and backscattering, ultimately aff ects water leaving signals that can be detected by satellite sensors." The news correspondents obtained a quote from the research from Northeast Instit ute of Geography and Agroecology: "Simple regression models based on specific ba nd or hand ratios have been widely used for SPM estimate in the past with modera te accuracy. There are still rooms for model accuracy improvements, and machine learning models may solve the non-linear relationships between spectral variable and SPM in waters. We assembled more than 16,400 in situ measured SPM in lakes from six continents (excluding the Antarctica continent), of which 9640 samples were matched with Landsat overpasses within ±7 days. Seven machine learning algo rithms and two simple regression methods (linear and partial least squares model s) were used to estimate SPM in lakes and the performance were compared. To over come the problem of imbalance datasets in regression, a Synthetic Minority Over- Sampling technique for regression with Gaussian Noise (SMOGN) was adopted in thi s study. Through comparison, we found that gradient boosting decision tree (GBDT ), random forest (RF), and extreme gradient boosting (XGBoost) models demonstrat ed good spatiotemporal transferability with SMOGN processed dataset, and has pot ential to map SPM at different year with good quality of Landsat land surface re flectance images. In all the tested modeling approaches, the GBDT model has accu rate calibration (n = 6428, R2 = 0.95, MAPE = 29.8 %) from SPM colle cted in 2235 lakes across the world, and the validation (n = 3214, R2 = 0.84, MA PE = 38.8%) also exhibited stable performance. Further, the good pe rformances were also exhibited by RF model with calibration (R2 = 0.93) and vali dation (R2 = 0.86, MAPE = 24.2%) datasets."

原文链接:

NETL
NSTL