A hierarchical enhanced data-driven battery pack capacity estimation framework for real-world operating conditions with fewer labeled data

Battery pack capacity estimation under real-world operating conditions is important for battery performance optimization and health management,contributing to the reliability and longevity of batterypowered systems.However,complex operating conditions,coupling cell-to-cell inconsistency,and limited labeled data pose great challenges to accurate and robust battery pack capacity estimation.To address these issues,this paper proposes a hierarchical data-driven framework aimed at enhancing the training of machine learning models with fewer labeled data.Unlike traditional data-driven methods that lack interpretability,the hierarchical data-driven framework unveils the“mechanism”of the black box inside the data-driven framework by splitting the final estimation target into cell-level and pack-level intermediate targets.A generalized feature matrix is devised without requiring all cell voltages,significantly reducing the computational cost and memory resources.The generated intermediate target labels and the corresponding features are hierarchically employed to enhance the training of two machine learning models,effectively alleviating the difficulty of learning the relationship from all features due to fewer labeled data and addressing the dilemma of requiring extensive labeled data for accurate estimation.Using only 10%of degradation data,the proposed framework outperforms the state-of-the-art battery pack capacity estimation methods,achieving mean absolute percentage errors of 0.608%,0.601%,and 1.128%for three battery packs whose degradation load profiles represent real-world operating conditions.Its high accuracy,adaptability,and robustness indicate the potential in different application scenarios,which is promising for reducing laborious and expensive aging experiments at the pack level and facilitating the development of battery technology.

Effective implementation and improvement of fast labeled multi-Bernoulli filter

Effective implementation of the fast labeled multi-Bernoulli(FLMB)filter is addressed for target tracking with interval measurements.Firstly,a sequential Monte Carlo(SMC)implementation of the FLMB filter,SMC-FLMB filter,is derived based on generalized likelihood function weighting.Then,a box particle(BP)implementation of the FLMB filter,BP-FLMB filter,is developed,with a computational complexity reduction of the SMC-FLMB filter.Finally,an improved version of the BP-FLMB filter,improved BP-FLMB(IBP-FLMB)filter,is proposed,improving its estimation accuracy and real-time performance under the conditions of low detection probability and high clutter.Simulation results show that the BP-FLMB filter has a great improvement of the real-time performance than the SMC-FLMB filter,with similar tracking performance.Compared with the BP-FLMB filter,the IBP-FLMB filter has better estimation performance and real-time performance under the conditions of low detection probability and high clutter.

Hopf Algebra of Labeled Simple Graphs

A lot of combinatorial objects have a natural bialgebra structure. In this paper, we prove that the vector space spanned by labeled simple graphs is a bialgebra with the conjunction product and the unshuffle coproduct. In fact, it is a Hopf algebra since it is graded connected. The main conclusions are that the vector space spanned by labeled simple graphs arising from the unshuffle coproduct is a Hopf algebra and that there is a Hopf homomorphism from permutations to label simple graphs.

PLDMLT:Multi-Task Learning of Diabetic Retinopathy Using the Pixel-Level Labeled Fundus Images

In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs.In this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification labels.To this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks.Extensive experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation accuracy.In addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.

The Antioxidization Effects of TP-5, Thy(1[Lys23] and Their Spin Labeled Derivatives

TP-5 and Thy(1, synthesized by solid phase synthesis, have the effect to restrain the formation of superoxide anion in xanthine oxidase system in vitro. The formations of lipid peroxide in several organs (such as liver, brain and thymus) of the mice treated with TP-5, TP-5(R, active fragment of Thy(1 and active fragment of Thy(1(R of 10 (g(kg(d-1 for 10 d were decreased. That means these peptides possess the capability of antioxidezation.

基于Labeled LDA主题模型的医学文献自动分类法

提出了一种基于Labeled LDA主题模型的医学文献自动分类法。以10个医学领域的研究文献为案例,通过语料库的设置及参数设置调整模型为最佳,与SVM方法进行对比实验。结果显示,无论是准确率还是召回率,基于Labeled LDA主题模型的自动分类法均比SVM法高出7.00%左右,表明基于Labeled LDA主题模型的医学文献自动分类法具有较好的医学领域文本分类效果。

Total Energy Expenditure of 16 Chinese Young Men Measured by the Doubly Labeled Water Method

Objective Doubly labeled water （DLW） method is the gold standard for measuring total energy expenditure （TEE）. We used this method to measure TEE in Chinese young men. Methods Sixteen healthy young men age 23±1 recruited. TEE was measured by the DLW method, by indirect calorimetry. We also conducted 24-h estimate energy requirements of the subjects. years with body mass index 22.0±1.4 kg/m2 were and basal energy expenditure （BEE） was determined activity, energy balance and factorial approach to Results TEE of subjects by DLW method was 9.45±0.57 M J/day （2258±180 kcal/day）. The 24-h activity was 10.80±0.33 M J/day （2582±136 kcal/day）. The energy requirement, derived from energy balance observations, was 9.93±1.32 M J/day （2373±315 kcal/day）. The BEE of 6.65±0.28 M J/day （1589±67 kcal/day）, calculated by the adjusted Schofield equation, was significantly higher （P〈O.O01） than that measured by indirect calorimetry, 5.99-±0.66 M J/day （1433-±158 kcal/day）. The TEE derived from the factorial approach was 10.31-±0.43 M J/day （2463±104 kcal/day）. Conclusion The TEE of Chinese young men measured by the DLW method was about 10% lower than the current recommended nutrient intake （RNI）, suggesting that the RNI for Chinese men maybe overestimated. Further studies are warranted to determine the value of the estimated energy requirement.

Radioimmunoimaging of colorectal cancer using ^(99m)Tc-labeled monoclonal antibody

AIM To determine whether Hb3 and its fragment F(ab')2 have practical value in radioimmunoimaging of colorectal cancer.METHODS Intact Hb3 was purified by hydroxylapatite chromatography. The fragment F(ab')2 was prepared by cold digestion and purified as intact Hb3. Hb3 and its fragment F(ab')2 were labeled with 99mTc by direct labeling method using SnCl2 as reducing agent. The radioactive doses ranged from 15 to 40 mCi. The imaging was accomplished by single photon emission computered tomograph (SPECT) with imaging time ranging from 2.5 to 48 hours. In this study, 10 patients were selected. Among them, 7 were administered with intact Hb3, and 3 with F(ab')2 fragment. All the patients were diagnosed as having colorectal adenocarcinoma.RESULTS After purification, intact Hb3 and its fragment F(ab')2 were fit for radioimmunoimaging. The percentage of labeling of 99mTc to Hb3 or F(ab')2 was 80.6%-91.5%. Among the 10 patients, 3 of 7 patients administered with intact Hb3 had positive scans, the other 4 had negative scans, and 2 of 3 patients administered with F(ab')2 had positive scans, the other 1 had negative scans.CONCLUSION The results showed that both intact Hb3 and its F(ab')2 have some practical value in radioimmunoimaging of colorectal cancer, and the effects of imaging with F(ab')2 was better than that with intact Hb3.

Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples

The accuracy of laser-induced breakdown spectroscopy(LIBS) quantitative method is greatly dependent on the amount of certified standard samples used for training. However, in practical applications, only limited standard samples with labeled certified concentrations are available. A novel semi-supervised LIBS quantitative analysis method is proposed, based on co-training regression model with selection of effective unlabeled samples. The main idea of the proposed method is to obtain better regression performance by adding effective unlabeled samples in semisupervised learning. First, effective unlabeled samples are selected according to the testing samples by Euclidean metric. Two original regression models based on least squares support vector machine with different parameters are trained by the labeled samples separately, and then the effective unlabeled samples predicted by the two models are used to enlarge the training dataset based on labeling confidence estimation. The final predictions of the proposed method on the testing samples will be determined by weighted combinations of the predictions of two updated regression models. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples were carried out, in which 5 samples with labeled concentrations and 11 unlabeled samples were used to train the regression models and the remaining 7 samples were used for testing. With the numbers of effective unlabeled samples increasing, the root mean square error of the proposed method went down from 1.80% to 0.84% and the relative prediction error was reduced from 9.15% to 4.04%.

THE DIVERGENT PROJECTIONS OF PERIPHERAL PROCESSES OF SUBSTANCE P-CONTAINING SPINAL GANGLIONIC NEURONS——Tri-labeled method of combining fluorescein tracing and immunocytochemistry

The development of fluorescien double labeling method in recent years,has identified the peripheral processes of spinal ganglionic neurons project divergently to the somatic and visceral areas,but the chemical nature of these neurons remains unknown.For this reason,we developed a tri-labeled method of combining fluorescein tracing and immunocytochemistry to clarify this problem.

FURTHER RESULTS ON THE EXISTENCE OF LABELED RESOLVABLE BLOCK DESIGNS

It was proved in this paper that there exists a labeled resolvable block design LRB (4,3; v ) if and only if v ≡0 (mod 4) and v ≥8, with 8 possible exceptions. It was also proved that there exists a nearly Kirkman system NKS (2,4; v ) if and only if v ≡0 (mod 12) and v ≥24, except possibly when v =264 or 372.

EXPERIMENTAL STUDIES OF TARGETING THERAPY OF GASTRIC CANCER WITH ^(131)-I LABELED McAbs

To investigate the radioimmunotherapeutic efficacy, radio-immunoconjugate 131-I-3G9, 811-I-3H11 and 131-I-NMIgG (irre levant antibody) were i.p. injected into nude mice bearing human gastric cancer xenograftes. Each animal received a single doses of 555MBq. Over 14 days the accumulative absorbed doses in tumors were 13.7 Gy for 131-I-3H11 and 12.17 Gy for 131-I-3G9. Both were significantly higher than that for 131-I-NMIgG (3.23 Gy). Thera peutic efficacy appeared most sharply from 2 to 3 weeks after injection. The inhibition ratio of tumor were 86% and 70% for 131-I-3H11 and 131-I-3G9 respectively. Histopathological evidance indicated that in tumor tissues radioactive damage was showed as karyopyknosis, karyorrhexis and necrosis or partial disappearance of tumor cells, while in the other tissues no radioactive damage was observed. WBC counts of all animals did not show significant difference before and after treatment, which indicated that the haemopoietic function of bone marrow was not affected.

Synthesis of Novel Spin Labeled Daunomycin Derivatives

Three spin labeled daunomycin derivatives 2-4 were synthesized and their biological activities were tested against mouse leukemia L1210 and human liver cancer BEL-7402 cells in vitro.

ON THE NUMBER OF INCREASING PATHS IN LABELED CYCLES AND STARS

A labeled graph is an ordered pair （G, L） consisting of a graph G and its labeling L ： V（G） → {1,2 ,n}, where n = ｜V（G）｜. An increasing nonconsecutive path in a labeled graph （G,L） is either a path （u1,u2 uk） （k ≥ 2） in G such that L（u,） ＋ 2 ≤ L（ui＋1） for all i = 1, 2, ..., k- 1 or a path of order 1. The total number of increasing nonconsecutive paths in （G, L） is denoted by d（G, L）. A labeling L is optimal if the labeling L produces the largest d（G, L）. In this paper, a method simpler than that in Zverovich （2004） to obtain the optimal labeling of path is given. The optimal labeling of other special graphs such as cycles and stars is obtained.

Validation of Total Daily Energy Expenditure Calculated with Actiheart against Doubly Labeled Water Method in Costa Rican Schoolchildren

The purpose of this study was to use the measurement of the PAEE taken from Actiheart in order to calculate the TEE in Costa Rican schoolchildren, and at the same time, to determine the effectiveness when it is compared against the TEE obtained by the DLW. A total of sixteen male schoolchildren were measured for their total daily energy expenditure (TEE) with the doubly labeled water (DLW) technique. The TEE obtained by the Actiheart monitor was calculated and validated against the DWL. The TEE was obtained adding the physical activity energy expenditure given by the Actiheart, plus the basal metabolic rate, and the energy cost of growth. The Pearson’s product‐moment correlation coefficient and the paired t‐test sample were measured in order to identify the association of the data and to evidence the differences between both measurements of TEE respectively. The Lin’s concordance correlation coefficient and the Bland-Altman plot evaluated the concordance of both methods. The correlation between the TEE obtained by DLW and the one calculated by Actiheart was r = 0.97, P < 0.001. The paired t-test showed no significant differences between both methods. Lin’s concordance correlation coefficient was Cb = 0.99, classified as almost perfect. The study validated the TEE calculated with Actiheart against the TEE measured by the DLW.

Photochemical Reaction of 9,10-Anthraquinone Labeled Bovine Serum Albumin Conjugate

Bovine serum albumin (BSA) was labeled with 9,10-anthraquinone and the photochemical fluorimetric reactivity of the covalently conjugated 9,10-anthraquinone was remarkably improved. The mechanism for the enhancement in the photochemical reactivity of conjugated 9,10-anthraquinone with BSA was discussed.

Studies on mitochondrial macromolecular syntheses in various organs of aging animals labeled with 3H-precursors as revealed by electron microscopic radioautography

In order to study the aging changes of intramitochondrial macromolecular synthesis in various organs of aging animals during the development and aging, 10 groups of developing and aging mice, each consisting of 3 individuals, total 30, from fetal day 19 to postnatal newborn at day 1, 3, 9, 14 and adult at month 1, 2, 6, 12 to 24 were injected with 3H-thymidine a DNA precurson, another 10 groups consisting of 3 individuals, total 30, were injected with 3H-uridine a RNA precursor, and another 10 groups of 30 individuals were injected with 3H-leucine a protein precursor, total 90 individuals. Then, all the animals were sacrificed 1 hr after the injections and the liver tissues, the lung tissues, the kidney tissues, the testis and ovary tissues, the adrenal tissues were taken out, fixed and processed for electron microscopic radioautography. On electron microscopic radioautograms obtained from each animal, ten photographs in respective groups, numbers of mitochondria per cell profile area, numbers of labeled mitochondria per cell and the mitochondrial labeling index (LI) labeled with 3H-thymidine showing DNA synthesis, LI labeled with 3H-uridine showing RNA synthesis, and LI labeled with 3H-leucine showing protein synthesis, in various organs, were counted and the results in various organs in respective aging groups were compared, respectively. From the results, it was demonstrated that the numbers of mitochondria in hepatocytes as well as in 3 zones of the adrenal cortex, the zona glomerulosa, fasciculata and reticularis of mice at various ages increased from fetal day 19 to postnatal month 1 due to development and aging of animals. On the other hand, the numbers of labeled mitochondria and the labeling indices of intramitochondrial DNA syntheses incorporating 3H-thymidine in hepatocytes and 3 zones of cortical cells increased from fetal day 19 to postnatal month 1 and decreased to month 24. The numbers of labeled mitochondria and the labeling indices of intramitochondrial RNA syntheses incorporating 3H-uridine in hepatocytes and 3 zones of cortical cells increased from fetal day 19 to postnatal month 1 and decreased to month 24. The numbers of labeled mitochondria and the labeling indices of intramitochondrial RNA syntheses incorporating 3H-uridine in hepatocytes and 3 ones of cortical cells increased from fetal day 19 to postnatal month 1 and decreased to month 24. Moreover, some other organs such as the lung and the testis were also review and discussed. From the results, it was shown that the activity of intramitochnodrial DNA synthesis, RNA synthesis, and protein synthesis in hepatocytes, adrenal cortical cells, pulmonary cells and testicular cells in developing and aging mice as well as some other organs increased and decreased due to development and aging.

Quinolinium Structure as Labeled Biomarkers

In this study the compatible chemical and biological investigations of several N-phenylquinolinium derivatives have been carried out in order to find the most perspective quinolinium structures for the nuclear-chemical synthesis of tritium labeled biomarkers.