To see the other types of publications on this topic, follow the link: LSVM.
Journal articles on the topic 'LSVM'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'LSVM.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Chu, Wenbo, Donge Zhao, Baowei Liu, Bin Zhang, and Zhiguo Gui. "Research on Target Deviation Measurement of Projectile Based on Shadow Imaging Method in Laser Screen Velocity Measuring System." Sensors 20, no. 2 (January 19, 2020): 554. http://dx.doi.org/10.3390/s20020554.
Full textAbstract:
In the laser screen velocity measuring (LSVM) system, there is a deviation in the consistency of the optoelectronic response between the start light screen and the stop light screen. When the projectile passes through the light screen, the projectile’s over-target position, at which the timing pulse of the LSVM system is triggered, deviates from the actual position of the light screen (i.e., the target deviation). Therefore, it brings errors to the measurement of the projectile’s velocity, which has become a bottleneck, affecting the construction of a higher precision optoelectronic velocity measuring system. To solve this problem, this paper proposes a method based on high-speed shadow imaging to measure the projectile’s target deviation, ΔS, when the LSVM system triggers the timing pulse. The infrared pulse laser is collimated by the combination of the aspherical lens to form a parallel laser source that is used as the light source of the system. When the projectile passes through the light screen, the projectile’s over-target signal is processed by the specially designed trigger circuit. It uses the rising and falling edges of this signal to trigger the camera and pulsed laser source, respectively, to ensure that the projectile’s over-target image is adequately exposed. By capturing the images of the light screen of the LSVM system and the over-target projectile separately, this method of image edge detection was used to calculate the target deviation, and this value was used to correct the target distance of the LSVM to improve the accuracy of the measurement of the projectile’s velocity.
2
Mirbagheri, Babak, and Abbas Alimohammadi. "Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling." ISPRS International Journal of Geo-Information 7, no. 9 (August 24, 2018): 347. http://dx.doi.org/10.3390/ijgi7090347.
Full textAbstract:
The use of local information for the classification and modelling of spatial variables has increased with the application of statistical and machine learning algorithms, such as support vector machines (SVMs). This study presents a new local SVM (LSVM) model that was developed to model the probability of urban development and simulate urban growth in a subregion in the southwestern suburb of the Tehran metropolitan area, Iran, for the periods of 1992–1996 and 1996–2002. Based on the focal training sample, the model was calibrated using the cross-validation method, and the optimal bandwidth was determined. The results were compared with those of a nonlinear global SVM (GSVM) model that was calibrated based on the ten-fold cross-validation method. This study then evaluated an integrated SVM model (LGSVM) obtained based on a weighted combination of the local and global urban development probabilities. A comparison of the probability maps showed a higher accuracy for the LGSVM than for either the LSVM or GSVM model. To assess the performance of the LSVM, GSVM and LGSVM models in the simulation of urban growth, probability maps were employed as the transition rules for urban cellular automata. The results show that a trade-off between local and global SVM models can enhance the performance of urban growth modelling.
3
Šimenc, Laura, Urška Kuhar, Urška Jamnikar-Ciglenečki, and Ivan Toplak. "First Complete Genome of Lake Sinai Virus Lineage 3 and Genetic Diversity of Lake Sinai Virus Strains From Honey Bees and Bumble Bees." Journal of Economic Entomology 113, no. 3 (March 24, 2020): 1055–61. http://dx.doi.org/10.1093/jee/toaa049.
Full textAbstract:
Abstract The complete genome of Lake Sinai virus 3 (LSV3) was sequenced by the Ion Torrent next-generation sequencing (NGS) technology from an archive sample of honey bees collected in 2010. This strain M92/2010 is the first complete genome sequence of LSV lineage 3. From October 2016 to December 2017, 56 honey bee samples from 32 different locations and 41 bumble bee samples from five different locations were collected. These samples were tested using a specific reverse transcriptase-polymerase chain reaction (RT-PCR) method; 75.92% of honey bee samples and 17.07% of bumble bee samples were LSV-positive with the RT-PCR method. Phylogenetic comparison of 557-base pair-long RNA-dependent RNA polymerase (RdRp) genome region of selected 23 positive samples of honey bees and three positive bumble bee samples identified three different LSV lineages: LSV1, LSV2, and LSV3. The LSV3 lineage was confirmed for the first time in Slovenia in 2010, and the same strain was later detected in several locations within the country. The LSV strains detected in bumble bees are from 98.6 to 99.4% identical to LSV strains detected among honey bees in the same territory.
4
KHASNOBISH, ANWESHA, ARINDAM JATI, GARIMA SINGH, AMIT KONAR, and D. N. TIBAREWALA. "OBJECT-SHAPE RECOGNITION BY TACTILE IMAGE ANALYSIS USING SUPPORT VECTOR MACHINE." International Journal of Pattern Recognition and Artificial Intelligence 28, no. 04 (June 2014): 1450011. http://dx.doi.org/10.1142/s0218001414500116.
Full textAbstract:
The sense of touch is important to human to understand shape, texture, and hardness of the objects. An object under grip, i.e. object exploration by enclosure, provides a unique pressure distribution on the different regions of palm depending on its shape. This paper utilizes the above experience for recognition of object shapes by tactile image analysis. The high pressure regions (HPRs) are segmented and analyzed for object shape recognition rather than analyzing the entire image. Tactile images are acquired by capacitive tactile sensor while grasping a particular object. Geometrical features are extracted from the chain codes obtained by polygon approximation of the contours of the segmented HPRs. Two-level classification scheme using linear support vector machine (LSVM) is employed to classify the input feature vector in respective object shape classes with an average classification accuracy of 93.46% and computational time of 1.19 s for 12 different object shape classes. Our proposed two-level LSVM reduces the misclassification rates, thus efficiently recognizes various object shapes from the tactile images.
5
Su, Tingting, Shaomin Mu, Aiju Shi, Zhihao Cao, and Mengping Dong. "A CNN-LSVM MODEL FOR IMBALANCED IMAGES IDENTIFICATION OF WHEAT LEAF." Neural Network World 29, no. 5 (2019): 345–61. http://dx.doi.org/10.14311/nnw.2019.29.021.
Full text
6
Pan, Fei, Baoying Wang, Xin Hu, and William Perrizo. "Comprehensive vertical sample-based KNN/LSVM classification for gene expression analysis." Journal of Biomedical Informatics 37, no. 4 (August 2004): 240–48. http://dx.doi.org/10.1016/j.jbi.2004.07.003.
Full text
7
Manciu, Marian, Mario Cardenas, Kevin E. Bennet, Avudaiappan Maran, Michael J. Yaszemski, Theresa A. Maldonado, Diana Magiricu, and Felicia S. Manciu. "Assessment of Renal Osteodystrophy via Computational Analysis of Label-free Raman Detection of Multiple Biomarkers." Diagnostics 10, no. 2 (January 31, 2020): 79. http://dx.doi.org/10.3390/diagnostics10020079.
Full textAbstract:
Accurate clinical evaluation of renal osteodystrophy (ROD) is currently accomplished using invasive in vivo transiliac bone biopsy, followed by in vitro histomorphometry. In this study, we demonstrate that an alternative method for ROD assessment is through a fast, label-free Raman recording of multiple biomarkers combined with computational analysis for predicting the minimally required number of spectra for sample classification at defined accuracies. Four clinically relevant biomarkers: the mineral-to-matrix ratio, the carbonate-to-matrix ratio, phenylalanine, and calcium contents were experimentally determined and simultaneously considered as input to a linear discriminant analysis (LDA). Additionally, sample evaluation was performed with a linear support vector machine (LSVM) algorithm, with a 300 variable input. The computed probabilities based on a single spectrum were only marginally different (~80% from LDA and ~87% from LSVM), both providing an unacceptable classification power for a correct sample assignment. However, the Type I and Type II assignment errors confirm that a relatively small number of independent spectra (7 spectra for Type I and 5 spectra for Type II) is necessary for a p < 0.05 error probability. This low number of spectra supports the practicality of future in vivo Raman translation for a fast and accurate ROD detection in clinical settings.
8
Wei, Yanlin, Xiaofeng Li, Xin Pan, and Lei Li. "Nondestructive Classification of Soybean Seed Varieties by Hyperspectral Imaging and Ensemble Machine Learning Algorithms." Sensors 20, no. 23 (December 7, 2020): 6980. http://dx.doi.org/10.3390/s20236980.
Full textAbstract:
During the processing and planting of soybeans, it is greatly significant that a reliable, rapid, and accurate technique is used to detect soybean varieties. Traditional chemical analysis methods of soybean variety sampling (e.g., mass spectrometry and high-performance liquid chromatography) are destructive and time-consuming. In this paper, a robust and accurate method for nondestructive soybean classification is developed through hyperspectral imaging and ensemble machine learning algorithms. Image acquisition, preprocessing, and feature selection are used to obtain different types of soybean hyperspectral features. Based on these features, one of ensemble classifiers-random subspace linear discriminant (RSLD) algorithm is used to classify soybean seeds. Compared with the linear discrimination (LD) and linear support vector machine (LSVM) methods, the results show that the RSLD algorithm in this paper is more stable and reliable. In classifying soybeans in 10, 15, 20, and 25 categories, the RSLD method achieves the highest classification accuracy. When 155 features are used to classify 15 types of soybeans, the classification accuracy of the RSLD method reaches 99.2%, while the classification accuracies of the LD and LSVM methods are only 98.6% and 69.7%, respectively. Therefore, the ensemble classification algorithm RSLD can maintain high classification accuracy when different types and different classification features are used.
9
Sun, Guodong, Yuan Gao, Kai Lin, and Ye Hu. "Fine-Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning." Shock and Vibration 2019 (November 20, 2019): 1–13. http://dx.doi.org/10.1155/2019/1531079.
Full textAbstract:
To accurately diagnose fine-grained fault of rolling bearing, this paper proposed a new fault diagnosis method combining multisynchrosqueezing transform (MSST) and sparse feature coding based on dictionary learning (SFC-DL). Firstly, the high-resolution time-frequency images of raw vibration signals, including different kinds of fine-grained faults of rolling bearing, were constructed by MSST. Then, the basis dictionary was trained through nonnegative matrix factorization with sparseness constraints (NMFSC), and the trained basis dictionary was employed to extract features from time-frequency matrixes by using nonnegative linear equations. Finally, a linear support vector machine (LSVM) was trained with features of training samples, and the trained LSVM was employed to diagnosis the fault classification of test samples. Compared with state-of-the-art fault diagnosis methods, the proposed method, which was tested on the bearing dataset from Case Western Reserve University (CWRU), achieved the fine-grained classification of 10 mixed fault states. Meanwhile, the proposed method was applied on the dataset from the Machinery Failure Prevention Technology (MFPT) Society and realized the classification of 3 fault states under different working conditions. These results indicate that the proposed method has great robustness and could better meet the needs of practical engineering.
10
Cornman, Robert S. "Relative abundance and molecular evolution of Lake Sinai Virus (Sinaivirus) clades." PeerJ 7 (March 21, 2019): e6305. http://dx.doi.org/10.7717/peerj.6305.
Full textAbstract:
Lake Sinai Viruses (Sinaivirus) are commonly detected in honey bees (Apis mellifera) but no disease phenotypes or fitness consequences have yet been demonstrated. This viral group is genetically diverse, lacks obvious geographic structure, and multiple lineages can co-infect individual bees. While phylogenetic analyses have been performed, the molecular evolution of LSV has not been studied extensively. Here, I use LSV isolates from GenBank as well as contigs assembled from honey bee Sequence Read Archive (SRA) accessions to better understand the evolutionary history of these viruses. For each ORF, substitution rate variation, codon usage, and tests of positive selection were evaluated. Outlier regions of high or low diversity were sought with sliding window analysis and the role of recombination in creating LSV diversity was explored. Phylogenetic analysis consistently identified two large clusters of sequences that correspond to the current LSV1 and LSV2 nomenclature, however lineages sister to LSV1 were the most frequently detected in honey bee SRA accessions. Different expression levels among ORFs suggested the occurrence of subgenomic transcripts. ORF1 and RNA-dependent RNA polymerase had higher evolutionary rates than the capsid and ORF4. A hypervariable region of the ORF1 protein-coding sequence was identified that had reduced selective constraint, but a site-based model of positive selection was not significantly more likely than a neutral model for any ORF. The only significant recombination signals detected between LSV1 and LSV2 initiated within this hypervariable region, but assumptions of the test (single-frame coding and independence of substitution rate by site) were violated. LSV codon usage differed strikingly from that of honey bees and other common honey-bee viruses, suggesting LSV is not strongly co-evolved with that host. LSV codon usage was significantly correlated with that of Varroa destructor, however, despite the relatively weak codon bias exhibited by the latter. While codon usage between the LSV1 and LSV2 clusters was similar for three ORFs, ORF4 codon usage was uncorrelated between these clades, implying rapid divergence of codon use for this ORF only. Phylogenetic placement and relative abundance of LSV isolates reconstructed from SRA accessions suggest that detection biases may be over-representing LSV1 and LSV2 in public databases relative to their sister lineages.
11
Nour, Majid, and Kemal Polat. "Automatic Classification of Hypertension Types Based on Personal Features by Machine Learning Algorithms." Mathematical Problems in Engineering 2020 (January 20, 2020): 1–13. http://dx.doi.org/10.1155/2020/2742781.
Full textAbstract:
Hypertension (high blood pressure) is an important disease seen among the public, and early detection of hypertension is significant for early treatment. Hypertension is depicted as systolic blood pressure higher than 140 mmHg or diastolic blood pressure higher than 90 mmHg. In this paper, in order to detect the hypertension types based on the personal information and features, four machine learning (ML) methods including C4.5 decision tree classifier (DTC), random forest, linear discriminant analysis (LDA), and linear support vector machine (LSVM) have been used and then compared with each other. In the literature, we have first carried out the classification of hypertension types using classification algorithms based on personal data. To further explain the variability of the classifier type, four different classifier algorithms were selected for solving this problem. In the hypertension dataset, there are eight features including sex, age, height (cm), weight (kg), systolic blood pressure (mmHg), diastolic blood pressure (mmHg), heart rate (bpm), and BMI (kg/m2) to explain the hypertension status and then there are four classes comprising the normal (healthy), prehypertension, stage-1 hypertension, and stage-2 hypertension. In the classification of the hypertension dataset, the obtained classification accuracies are 99.5%, 99.5%, 96.3%, and 92.7% using the C4.5 decision tree classifier, random forest, LDA, and LSVM. The obtained results have shown that ML methods could be confidently used in the automatic determination of the hypertension types.
12
Głowacz, Adam. "Recognition of acoustic signals of induction motor using FFT, SMOFS-10 and LSVM." Ekspolatacja i Niezawodnosc - Maintenance and Reliability 17, no. 4 (September 16, 2015): 569–74. http://dx.doi.org/10.17531/ein.2015.4.12.
Full text
13
Do, Thanh‐Nghi, and François Poulet. "Latent‐lSVM classification of very high‐dimensional and large‐scale multi‐class datasets." Concurrency and Computation: Practice and Experience 31, no. 2 (June 30, 2017): e4224. http://dx.doi.org/10.1002/cpe.4224.
Full text
14
Renesto, Diego M. "Supplement levels and functional oils to replace virginiamycin for young bulls during early dry season on grasslands and finishing phase in feedlot systems." Spanish Journal of Agricultural Research 19, no. 3 (September 2021): e0609-e0609. http://dx.doi.org/10.5424/sjar/2021193-15795.
Full textAbstract:
Aim of study: To assess the effects of replacing virginiamycin (VM) by functional oils (FO) from castor beans and cashew nut on beef cattle system during the early dry season (Experiment I) and during the finishing phase were evaluated the historical effect, keeping the treatments and methods intact (Experiment II). Area of study: These experiments were conducted at the Forage Crops and Grasslands section of São Paulo State University, “Julio de Mesquita Filho” (Unesp–Jaboticabal, São Paulo, Brazil). Material and methods: Two supplementation levels combined with two additives (four treatments in total) were evaluated: LSVM, low supplementation (0.3% body weight [BW]) with VM; LSFO, low supplementation (0.3% BW) with FO, HSVM, high supplementation (0.6% BW) with VM, and HSFO, high supplementation (0.6% BW) with FO. In both experiments, the experimental design was completely randomized with a 2 × 2 factorial arrangement (supplementation levels × additives). Main results: In Exp. I, the additive effect of VM provided greater average daily gain (ADG, p=0.02), higher supplementation level resulted in higher ADG (p=0.04) and the greatest crude protein apparent digestibility (p=0.002). However, no effects were observed between supplementation levels, additives, and interactions (p≥0.11) on voluntary intake and ruminal parameters. In Exp. II, LSVM treatment resulted in lower dry matter intake (p=0.04). Animals maintained on LSFO during the early dry season exhibited lower carcass yield (p=0.004). Research highlights: FO can be used to replace VM in beef cattle diet during the finishing phase in the feedlot without altering animal performance.
15
Glowacz, Adam. "Recognition of Acoustic Signals of Loaded Synchronous Motor Using FFT, MSAF-5 and LSVM." Archives of Acoustics 40, no. 2 (June 1, 2015): 197–203. http://dx.doi.org/10.1515/aoa-2015-0022.
Full textAbstract:
AbstractThis article discusses a system of recognition of acoustic signals of loaded synchronous motor. This software can recognize various types of incipient failures by means of analysis of the acoustic signals. Proposed approach uses the acoustic signals generated by loaded synchronous motor. A plan of study of the acoustic signals of loaded synchronous motor is proposed. Studies include following states: healthy loaded synchronous motor, loaded synchronous motor with shorted stator coil, loaded synchronous motor with shorted stator coil and broken coil, loaded synchronous motor with shorted stator coil and two broken coils. The methods such as FFT, method of selection of amplitudes of frequencies (MSAF-5), Linear Support Vector Machine were used to identify specific state of the motor. The proposed approach can keep high recognition rate and reduce the maintenance cost of synchronous motors.
16
Iwanowicz, Deborah D., Judy Y. Wu-Smart, Tugce Olgun, Autumn H. Smart, Clint R. V. Otto, Dawn Lopez, Jay D. Evans, and Robert Cornman. "An updated genetic marker for detection of Lake Sinai Virus and metagenetic applications." PeerJ 8 (July 17, 2020): e9424. http://dx.doi.org/10.7717/peerj.9424.
Full textAbstract:
Background Lake Sinai Viruses (LSV) are common RNA viruses of honey bees (Apis mellifera) that frequently reach high abundance but are not linked to overt disease. LSVs are genetically heterogeneous and collectively widespread, but despite frequent detection in surveys, the ecological and geographic factors structuring their distribution in A. mellifera are not understood. Even less is known about their distribution in other species. Better understanding of LSV prevalence and ecology have been hampered by high sequence diversity within the LSV clade. Methods Here we report a new polymerase chain reaction (PCR) assay that is compatible with currently known lineages with minimal primer degeneracy, producing an expected 365 bp amplicon suitable for end-point PCR and metagenetic sequencing. Using the Illumina MiSeq platform, we performed pilot metagenetic assessments of three sample sets, each representing a distinct variable that might structure LSV diversity (geography, tissue, and species). Results The first sample set in our pilot assessment compared cDNA pools from managed A. mellifera hives in California (n = 8) and Maryland (n = 6) that had previously been evaluated for LSV2, confirming that the primers co-amplify divergent lineages in real-world samples. The second sample set included cDNA pools derived from different tissues (thorax vs. abdomen, n = 24 paired samples), collected from managed A. mellifera hives in North Dakota. End-point detection of LSV frequently differed between the two tissue types; LSV metagenetic composition was similar in one pair of sequenced samples but divergent in a second pair. Overall, LSV1 and intermediate lineages were common in these samples whereas variants clustering with LSV2 were rare. The third sample set included cDNA from individual pollinator specimens collected from diverse landscapes in the vicinity of Lincoln, Nebraska. We detected LSV in the bee Halictus ligatus (four of 63 specimens tested, 6.3%) at a similar rate as A. mellifera (nine of 115 specimens, 7.8%), but only one H. ligatus sequencing library yielded sufficient data for compositional analysis. Sequenced samples often contained multiple divergent LSV lineages, including individual specimens. While these studies were exploratory rather than statistically powerful tests of hypotheses, they illustrate the utility of high-throughput sequencing for understanding LSV transmission within and among species.
17
Rafiammal, S. S., D. N. Jamal, and S. K. Mohideen. "Reconfigurable Hardware Design for Automatic Epilepsy Seizure Detection using EEG Signals." Engineering, Technology & Applied Science Research 10, no. 3 (June 7, 2020): 5803–7. http://dx.doi.org/10.48084/etasr.3419.
Full textAbstract:
Reconfigurable circuit designs for automatic seizure detection devices are essential to prevent epilepsy affected people from severe injuries and other health-related problems. In this proposed design, an automatic seizure detection algorithm based on the Linear binary Support Vector Machine learning algorithm (LSVM) is developed and implemented in a Field-Programmable Gate Array (FPGA). The experimental results showed that the mean detection accuracy is 86% and sensitivity is 97%. The resource utilization of the implemented design is less when compared to existing hardware implementations. The power consumption of the proposed design is 76mW at 100MHz. The experimental results assure that a physician can make use of this proposed design in detecting seizure events.
18
Zaim Shahrel, Mohamed, Sofianita Mutalib, and Shuzlina Abdul-Rahman. "PriceCop – Price Monitor and Prediction Using Linear Regression and LSVM-ABC Methods for E-commerce Platform." International Journal of Information Engineering and Electronic Business 13, no. 1 (February 8, 2021): 1–14. http://dx.doi.org/10.5815/ijieeb.2021.01.01.
Full text
19
Farayola, Adedayo M., Ali N. Hasan, and Ahmed Ali. "Optimization of PV Systems Using Data Mining and Regression Learner MPPT Techniques." Indonesian Journal of Electrical Engineering and Computer Science 10, no. 3 (June 1, 2018): 1080. http://dx.doi.org/10.11591/ijeecs.v10.i3.pp1080-1089.
Full textAbstract:
<span>Supervised machine learning techniques such as artificial neural network (ANN) and ANFIS are powerful tools used to track the maximum power point (MPPT) in photovoltaic systems. However, these offline MPPT techniques still require large and accurate training data sets for successful tracking. This paper presents an innovative use of rational quadratic gaussian process regression (RQGPR) technique to generate the large and very accurate training data required for MPPT task. To confirm the effectiveness of the RQGPR technique, the combination of ANN and RQGPR as ANN-RQGPR technique results were compared with the conventional ANN technique results, and that of combined ANN and linear support vector machine regression as ANN-LSVM technique results under different weather conditions. Results show that ANN-RQGPR technique produced the overall best result and with an improved performance. </span>
20
Glowacz, Adam, Witold Glowacz, Jarosław Kozik, Krzysztof Piech, Miroslav Gutten, Wahyu Caesarendra, Hui Liu, Frantisek Brumercik, Muhammad Irfan, and Z. Faizal Khan. "Detection of Deterioration of Three-phase Induction Motor using Vibration Signals." Measurement Science Review 19, no. 6 (December 1, 2019): 241–49. http://dx.doi.org/10.2478/msr-2019-0031.
Full textAbstract:
Abstract Nowadays detection of deterioration of electrical motors is an important topic of research. Vibration signals often carry diagnostic information of a motor. The authors proposed a setup for the analysis of vibration signals of three-phase induction motors. In this paper rotor fault diagnostic techniques of a three-phase induction motor (TPIM) were presented. The presented techniques used vibration signals and signal processing methods. The authors analyzed the recognition rate of vibration signal readings for 3 states of the TPIM: healthy TPIM, TPIM with 1 broken bar, and TPIM with 2 broken bars. In this paper the authors described a method of the feature extraction of vibration signals Method of Selection of Amplitudes of Frequencies – MSAF-12. Feature vectors were obtained using FFT, MSAF-12, and mean of vector sum. Three methods of classification were used: Nearest Neighbor (NN), Linear Discriminant Analysis (LDA), and Linear Support Vector Machine (LSVM). The obtained results of analyzed classifiers were in the range of 97.61 % – 100 %.
21
Usha N., Sriraam N., Kavya N., Bharathi Hiremath, Anupama K. Pujar, Prabha Ravi, Aditi Jain, Venkatraman B., and Menaka M. "Effect of GLCM Texture Features on the Medio-Lateral Oblique (MLO) View of Digital Mammograms for Breast Cancer Detection." International Journal of Biomedical and Clinical Engineering 9, no. 2 (July 2020): 25–44. http://dx.doi.org/10.4018/ijbce.2020070103.
Full textAbstract:
Breast cancer is one among the most common cancers in women. The early detection of breast cancer reduces the risk of death. Mammograms are an efficient breast imaging technique for breast cancer screening. Computer aided diagnosis (CAD) systems reduce manual errors and helps radiologists to analyze the mammogram images. The mammogram images are typically in two views, cranial-caudal (CC) and medio lateral oblique (MLO) views. MLO contains pectoral muscles (chest muscles) at the upper right or left corner of the image. In this study, it was removed by using a semi-automated method. All the normal and abnormal images were filtered and enhanced to improve the quality. GLCM (Gray Level Co-occurrence Matrix) texture features were extracted and analyzed by changing the number of features in a feature set. Linear Support Vector Machine (LSVM) was used as classifier. The classification accuracy was improved as the number of features in GLCM feature set increases. Simulation results show an overall classification accuracy of 96.7% with 19 GLCM features using SVM classifiers.
22
Xing, Jie, Xiu Hua Chen, Wen Hui Ma, Rui Li, Jian Jun Yang, and Jie Yu. "Anode-Supported LSGM Films Prepared by Slurry Spin Coating." Advanced Materials Research 898 (February 2014): 123–27. http://dx.doi.org/10.4028/www.scientific.net/amr.898.123.
Full textAbstract:
La0.9Sr0.1Ga0.8Mg0.2O2.85 (LSGM) electrolyte films were successfully prepared by slurry spin coating method on porous La0.7Sr0.3Cr0.5Mn0.5O2.75 (LSCM) anode substrates. Ethyl celluloses content, coating cycles for slurry spin coating on the fabrication LSGM electrolyte films were investigated. The compatibility between LSGM and LSCM powders, microstructures and electricity conductivity of fabricated LSGM films were examined using XRD, SEM and electrochemical workstation. The film with good apparent morphology and electrical conductivity were obtained when the operating parameters were setted as the content of ethyl cellulose 10wt%, and the coating cycles 5.
23
Li, Jianwu, Haizhou Wei, and Wangli Hao. "Weight-Selected Attribute Bagging for Credit Scoring." Mathematical Problems in Engineering 2013 (2013): 1–13. http://dx.doi.org/10.1155/2013/379690.
Full textAbstract:
Assessment of credit risk is of great importance in financial risk management. In this paper, we propose an improved attribute bagging method, weight-selected attribute bagging (WSAB), to evaluate credit risk. Weights of attributes are first computed using attribute evaluation method such as linear support vector machine (LSVM) and principal component analysis (PCA). Subsets of attributes are then constructed according to weights of attributes. For each of attribute subsets, the larger the weights of the attributes the larger the probabilities by which they are selected into the attribute subset. Next, training samples and test samples are projected onto each attribute subset, respectively. A scoring model is then constructed based on each set of newly produced training samples. Finally, all scoring models are used to vote for test instances. An individual model that only uses selected attributes will be more accurate because of elimination of some of redundant and uninformative attributes. Besides, the way of selecting attributes by probability can also guarantee the diversity of scoring models. Experimental results based on two credit benchmark databases show that the proposed method, WSAB, is outstanding in both prediction accuracy and stability, as compared to analogous methods.
24
Yu, Jie, Wen Hui Ma, Hang Sheng Lin, Hong Yan Sun, Xiu Hua Chen, and Bin Yang. "Fabrication of LSGM Thin Film Electrolyte on LSCM Anode by RF Magnetron Sputtering for IT-SOFC." Materials Science Forum 675-677 (February 2011): 81–84. http://dx.doi.org/10.4028/www.scientific.net/msf.675-677.81.
Full textAbstract:
La0.9Sr0.1Ga0.8Mg0.2O3-δ (LSGM) thin film electrolytes were fabricated on La0.7Sr0.3Cr0.5Mn0.5O3-δ (LSCM) porous anodes by radio-frequency (RF) magnetron sputtering. The formation and microstructure of LSGM thin films were characterized by X-ray diffraction(XRD) and scanning electron microscopy (SEM). The effects of different sputtering conditions, such as Ar gas pressure, substrate temperature and sputtering power, on the performance of LSGM electrolyte film were estimated. Dense LSGM thin film electrolytes with thickness of about 2μm, which are compatible with LSCM-based anodes and without crack, have been successfully fabricated on LSCM-based anode supports by RF magnetron sputtering when sputtering power density is 5.2W·cm-2, Ar gas pressure is 5Pa and substrate temperature is 300°C. It is found that high sputtering power density and high Ar gas pressure, as well as high substrate temperature, are beneficial to deposition of dense electrolyte thin film, close bonding of electrolyte thin film with anode substrate, and formation of large three phase boundaries between anode and electrolyte.
25
Yu, Jie, Jie Xing, Xiu Hua Chen, Wen Hui Ma, Rui Li, and Jian Jun Yang. "Substrate Temperature and La0.9Sr0.1Ga0.8Mg0.2O3-δ Electrolyte Film Growth by Radio Frequency Magnetron Sputtering." Materials Science Forum 833 (November 2015): 127–33. http://dx.doi.org/10.4028/www.scientific.net/msf.833.127.
Full textAbstract:
La0.9Sr0.1Ga0.8Mg0.2O3-δ (LSGM) electrolyte thin films were fabricated on La0.7Sr0.3Cr0.5Mn0.5O2.75 (LSCM) porous anode substrates by Radio Frequency (RF) magnetron sputtering method. The compatibility between LSGM and LSCM was examined. Microstructures of LSGM thin films fabricated were observed by scanning electron microscope (SEM). The effect of substrate temperature on LSGM thin films was clarified by X-ray Diffraction (XRD). Deposition rate increases firstly at the range of 50°C~150°C, and then decreases at the range of 150°C ~300°C. After annealing, perovskite structure with the same growth orientation forms at different substrate temperature. Crystallite size decreases at first, to the minimum point at 150°C, then increases as substrate temperature rises.
26
Muriira, Lawrence, Zhiwei Zhao, and Geyong Min. "Exploiting Linear Support Vector Machine for Correlation-Based High Dimensional Data Classification in Wireless Sensor Networks." Sensors 18, no. 9 (August 28, 2018): 2840. http://dx.doi.org/10.3390/s18092840.
Full textAbstract:
Linear Support Vector Machine (LSVM) has proven to be an effective approach for link classification in sensor networks. In this paper, we present a data-driven framework for reliable link classification that models Kernelized Linear Support Vector Machine (KLSVM) to produce stable and consistent results. KLSVM is a linear classifying technique that learns the “best” parameter settings. We investigated its application to model and capture two phenomena: High dimensional multi-category classification and Spatiotemporal data correlation in wireless sensor network (WSN). In addition, the technique also detects anomalies within the network. With the optimized selection of the linear kernel hyperparameters, the technique models high-dimensional data classification and the examined packet traces exhibit correlations between link features. Link features with Packet Reception Rate (PRR) greater than 50% show a high degree of negative correlation while the other sensor node observations show a moderate degree of positive correlation. The model gives a good visual intuition of the network behavior. The efficiency of the supervised learning technique is studied over real dataset obtained from a WSN testbed. To achieve that, we examined packet traces from the 802.15.4 network. The technique has a good performance on link quality estimation accuracy and a precise anomaly detection of sensor nodes within the network.
27
Thakur, Rashmi K., and Manojkumar V. Deshpande. "Kernel Optimized-Support Vector Machine and MapReduce Framework for Sentiment Classification of Train Reviews." International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 27, no. 06 (December 2019): 1025–50. http://dx.doi.org/10.1142/s0218488519500454.
Full textAbstract:
Sentiment analysis is one of the popular techniques gaining attention in recent times. Nowadays, people gain information on reviews of users regarding public transportation, movies, hotel reservation, etc., by utilizing the resources available, as they meet their needs. Hence, sentiment classification is an essential process employed to determine the positive and negative responses. This paper presents an approach for sentiment classification of train reviews using MapReduce model with the proposed Kernel Optimized-Support Vector Machine (KO-SVM) classifier. The MapReduce framework handles big data using a mapper, which performs feature extraction and reducer that classifies the review based on KO-SVM classification. The feature extraction process utilizes features that are classification-specific and SentiWordNet-based. KO-SVM adopts SVM for the classification, where the exponential kernel is replaced by an optimized kernel, finding the weights using a novel optimizer, Self-adaptive Lion Algorithm (SLA). In a comparative analysis, the performance of KO-SVM classifier is compared with SentiWordNet, NB, NN, and LSVM, using the evaluation metrics, specificity, sensitivity, and accuracy, with train review and movie review database. The proposed KO-SVM classifier could attain maximum sensitivity of 93.46% and 91.249% specificity of 74.485% and 70.018%; and accuracy of 84.341% and 79.611% respectively, for train review and movie review databases.
28
Aghnaiya, Alghannai, Yaser Dalveren, and Ali Kara. "On the Performance of Variational Mode Decomposition-Based Radio Frequency Fingerprinting of Bluetooth Devices." Sensors 20, no. 6 (March 19, 2020): 1704. http://dx.doi.org/10.3390/s20061704.
Full textAbstract:
Radio frequency fingerprinting (RFF) is one of the communication network’s security techniques based on the identification of the unique features of RF transient signals. However, extracting these features could be burdensome, due to the nonstationary nature of transient signals. This may then adversely affect the accuracy of the identification of devices. Recently, it has been shown that the use of variational mode decomposition (VMD) in extracting features from Bluetooth (BT) transient signals offers an efficient way to improve the classification accuracy. To do this, VMD has been used to decompose transient signals into a series of band-limited modes, and higher order statistical (HOS) features are extracted from reconstructed transient signals. In this study, the performance bounds of VMD in RFF implementation are scrutinized. Firstly, HOS features are extracted from the band-limited modes, and then from the reconstructed transient signals directly. Performance comparison due to both HOS feature sets is presented. Moreover, the lower SNR bound within which the VMD can achieve acceptable accuracy in the classification of BT devices is determined. The approach has been tested experimentally with BT devices by employing a Linear Support Vector Machine (LSVM) classifier. According to the classification results, a higher classification performance is achieved (~4% higher) at lower SNR levels (−5–5 dB) when HOS features are extracted from band-limited modes in the implementation of VMD in RFF of BT devices.
29
Czabanski, Robert, Krzysztof Horoba, Janusz Wrobel, Adam Matonia, Radek Martinek, Tomasz Kupka, Michal Jezewski, Radana Kahankova, Janusz Jezewski, and Jacek Leski. "Detection of Atrial Fibrillation Episodes in Long-Term Heart Rhythm Signals Using a Support Vector Machine." Sensors 20, no. 3 (January 30, 2020): 765. http://dx.doi.org/10.3390/s20030765.
Full textAbstract:
Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%.
30
Garcia-Garcia, Francisco J., Yunqing Tang, Francisco J. Gotor, and María J. Sayagués. "Development by Mechanochemistry of La0.8Sr0.2Ga0.8Mg0.2O2.8 Electrolyte for SOFCs." Materials 13, no. 6 (March 18, 2020): 1366. http://dx.doi.org/10.3390/ma13061366.
Full textAbstract:
In this work, a mechanochemical process using high-energy milling conditions was employed to synthesize La0.8Sr0.2Ga0.8Mg0.2O3-δ (LSGM) powders from the corresponding stoichiometric amounts of La2O3, SrO, Ga2O3, and MgO in a short time. After 60 min of milling, the desired final product was obtained without the need for any subsequent annealing treatment. A half solid oxide fuel cell (SOFC) was then developed using LSGM as an electrolyte and La0.8Sr0.2MnO3 (LSM) as an electrode, both obtained by mechanochemistry. The characterization by X-ray diffraction of as-prepared powders showed that LSGM and LSM present a perovskite structure and pseudo-cubic symmetry. The thermal and chemical stability between the electrolyte (LSGM) and the electrode (LSM) were analyzed by dynamic X-ray diffraction as a function of temperature. The electrolyte (LSGM) is thermally stable up to 800 and from 900 °C, where the secondary phases of LaSrGa3O7 and LaSrGaO4 appear. The best sintering temperature for the electrolyte is 1400 °C, since at this temperature, LaSrGaO4 disappears and the percentage of LaSrGa3O7 is minimized. The electrolyte is chemically compatible with the electrode up to 800 °C. The powder sample of the electrolyte (LSGM) at 1400 °C observed by HRTEM indicates that the cubic symmetry Pm-3m is preserved. The SOFC was constructed using the brush-painting technique; the electrode–electrolyte interface characterized by SEM presented good adhesion at 800 °C. The electrical properties of the electrolyte and the half-cell were analyzed by complex impedance spectroscopy. It was found that LSGM is a good candidate to be used as an electrolyte in SOFC, with an Ea value of 0.9 eV, and the LSM sample is a good candidate to be used as cathode.
31
Yang, Jian Jun, Wen Hui Ma, Jie Yu, Xiu Hua Chen, Jie Xing, and Rui Li. "Preparation of La0.9SR0.1Ga0.8Mg0.2O3-δ Electrolyte Films Deposited by RF Magnetic Sputtering." Advanced Materials Research 634-638 (January 2013): 2550–54. http://dx.doi.org/10.4028/www.scientific.net/amr.634-638.2550.
Full textAbstract:
La0.9Sr0.1Ga0.8Mg0.2O3-d (LSGM) electrolyte materials were synthesized using solid state reactions. The LSGM material film was deposited by radiofrequency magnetic sputtering on La0.7Sr0.3Cr0.5Mn0.5O3-d (LSCM) substrates. The analysis results show the films did not form but formed some “mountains” when deposited for 4 h. While the depositing time extended to 12 h, a dense and uniform film with perovskite phase was obtained, and the element amounts of the film were closed to those of the LSGM materials.
32
Du, Yanhai. "Interactions and Compatibilities of LSGM Electrolyte and LSCM Anode." ECS Proceedings Volumes 2005-07, no. 1 (January 2005): 1127–36. http://dx.doi.org/10.1149/200507.1127pv.
Full text
33
Malik, Yoga Trianzar, Atiek Rostika Noviyanti, and Dani Gustaman Syarif. "Lowered Sintering Temperature on Synthesis of La9.33Si6O26 (LSO) – La0.8Sr0.2Ga0.8Mg0.2O2.55 (LSGM) Electrolyte Composite and the Electrical Performance on La0.7Ca0.3MnO3 (LCM) Cathode." Jurnal Kimia Sains dan Aplikasi 21, no. 4 (October 1, 2018): 205–10. http://dx.doi.org/10.14710/jksa.21.4.205-210.
Full textAbstract:
Solid oxide fuel cell (SOFC) is the device that can convert chemical energy into electricity with highest efficiency among other fuel cell. La9.33Si6O26 (LSO) is the potential electrolyte at intermediate operation temperature SOFC. Low ionic conductivity of lanthanum silicate-based electrolyte will lead into bad electrical performance on lanthanum manganite-based anode. In this study, LSO was combine with La0.8Sr0.2Ga0.8Mg0.2O2.55 (LSGM) electrolyte by using conventional solid state reaction to enhance the electrical performance of LSO on LCM cathode. However, pre-requisite high sintering temperature on preparation of LSO-LSGM composite will lead into phase transition phase of LSGM that may affect in decreasing the electrical performance. This study resulted that lowered sintering temperature from its ideal temperature still give an improved electrical performance of LCM/LSO-LSGM/LCM symmetrical cell. The ASR value is 0.14 Ω.cm2 which much lower than its analogous symmetrical cell, LSM/LSO/LSM that was reported before.
34
DOTELLI, G., C. MARI, R. RUFFO, R. PELOSATO, and I. SORA. "Electrical behaviour of LSGM–LSM composite cathode materials." Solid State Ionics 177, no. 19-25 (October 15, 2006): 1991–96. http://dx.doi.org/10.1016/j.ssi.2006.05.033.
Full text
35
Bai, Shuang. "Scene Categorization Through Using Objects Represented by Deep Features." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 09 (February 2017): 1755013. http://dx.doi.org/10.1142/s0218001417550138.
Full textAbstract:
Objects in scenes are thought to be important for scene recognition. In this paper, we propose to utilize scene-specific objects represented by deep features for scene categorization. Our approach combines benefits of deep learning and Latent Support Vector Machine (LSVM) to train a set of scene-specific object models for each scene category. Specifically, we first use deep Convolutional Neural Networks (CNNs) pre-trained on the large-scale object-centric image database ImageNet to learn rich object features and a large number of general object concepts. Then, the pre-trained CNNs is adopted to extract features from images in the target dataset, and initialize the learning of scene-specific object models for each scene category. After initialization, the scene-specific object models are obtained by alternating between searching over the most representative and discriminative regions of images in the target dataset and training linear SVM classifiers based on obtained region features. As a result, for each scene category a set of object models that are representative and discriminative can be acquired. We use them to perform scene categorization. In addition, to utilize global structure information of scenes, we use another CNNs pre-trained on the large-scale scene-centric database Places to capture structure information of scene images. By combining objects and structure information for scene categorization, we show superior performances to state-of-the-art approaches on three public datasets, i.e. MIT-indoor, UIUC-sports and SUN. Experiment results demonstrated the effectiveness of the proposed method.
36
Lei, Xinxiang, Wei Chen, and Binh Thai Pham. "Performance Evaluation of GIS-Based Artificial Intelligence Approaches for Landslide Susceptibility Modeling and Spatial Patterns Analysis." ISPRS International Journal of Geo-Information 9, no. 7 (July 17, 2020): 443. http://dx.doi.org/10.3390/ijgi9070443.
Full textAbstract:
The main purpose of this study was to apply the novel bivariate weights-of-evidence-based SysFor (SF) for landslide susceptibility mapping, and two machine learning techniques, namely the naïve Bayes (NB) and Radial basis function networks (RBFNetwork), as benchmark models. Firstly, by using aerial photos and geological field surveys, the 263 landslide locations in the study area were obtained. Next, the identified landslides were randomly classified according to the ratio of 70/30 to construct training data and validation models, respectively. Secondly, based on the landslide inventory map, combined with the geological and geomorphological characteristics of the study area, 14 affecting factors of the landslide were determined. The predictive ability of the selected factors was evaluated using the LSVM model. Using the WoE model, the relationship between landslides and affecting factors was analyzed by positive and negative correlation methods. The above three hybrid models were then used to map landslide susceptibility. Thirdly, the ROC curve and various statistical data (SE, 95% CI and MAE) were used to verify and compare the predictive power of the model. Compared with the other two models, the Sysfor model had a larger area under the curve (AUC) of 0.876 (training dataset) and 0.783 (validation dataset). Finally, by quantitatively comparing the susceptibility values of each pixel, the differences in spatial morphology of landslide susceptibility maps were compared, and the model was found to have limitations and effectiveness. The landslide susceptibility maps obtained by the three models are reasonable, and the landslide susceptibility maps generated by the SysFor model have the highest comprehensive performance. The results obtained in this paper can help local governments in land use planning, disaster reduction and environmental protection.
37
Gao, P. P., Y. P. Li, G. H. Huang, and Y. Y. Su. "An integrated Bayesian least-squares-support-vector-machine factorial-analysis (B-LSVM-FA) method for inferring inflow from the Amu Darya to the Aral Sea under ensemble prediction." Journal of Hydrology 594 (March 2021): 125909. http://dx.doi.org/10.1016/j.jhydrol.2020.125909.
Full text
38
Ricci, S., and A. Caggiati. "Echoanatomical Patterns of the Long Saphenous Vein in Patients with Primary Varices and in Healthy Subjects." Phlebology: The Journal of Venous Disease 14, no. 2 (June 1999): 54–58. http://dx.doi.org/10.1177/026835559901400204.
Full textAbstract:
Objective: To evaluate the pathway of reflux in incompetent long saphenous veins (LSVs), paying particular attention to the role of longitudinal saphenous tributaries in the thigh (accessory saphenous veins, ASVs). Design: Prospective study in a group of patients with primary varices. Comparison with the anatomical patterns in a group of normal subjects. Setting: Private phlebology practice. Patients: Sixty-seven patients with primary varices (100 limbs) and 66 subjects without varices and with competent saphenous veins (120 limbs). Methods: Duplex ultrasound evaluation of the saphenous system in the thigh of patients and healthy subjects. The ‘eye’ ultrasonographic sign was used as the marker to distinguish the LSV from the longitudinal tributary veins of the thigh. Results: In 57% of limbs in patients with varices, reflux followed the saphenous vein, while in 43% the reflux spilled outside the LSV into an ASV (h or S types). When reflux followed the saphenous vein, no large calibre ASVs could be observed. In 30% of limbs in control subjects a parallel tributary vein with a similar calibre was found joining the LSV. Conclusion: Clinically visible varices in the thigh rarely comprise the LSV itself, but are usually dilated ASVs, the reflux stream passing from the proximal LSV into a more superficial ASV. The distal LSV running parallel beneath is often competent. In subjects with healthy LSVs, a large competent tributary vein is already present in the thigh in 30% of cases. This suggests that superficial deviation of reflux flow into an ASV in patients with varices may not arise from haemodynamically acquired changes, but could have a congenital origin. This could even be a predisposing factor in the development of varices.
39
Armstrong, Tad J., and Anil V. Virkar. "Performance of Solid Oxide Fuel Cells with LSGM-LSM Composite Cathodes." Journal of The Electrochemical Society 149, no. 12 (2002): A1565. http://dx.doi.org/10.1149/1.1517282.
Full text
40
Deepika, Nalabala, and Mundukur Nirupamabhat. "An Optimized Machine Learning Model for Stock Trend Anticipation." Ingénierie des systèmes d information 25, no. 6 (December 31, 2020): 783–92. http://dx.doi.org/10.18280/isi.250608.
Full textAbstract:
Security market is an economical-volatile in nature as it is driven by not only based on historical prices various unpredictable external factors like financial news, changes in socio-political issues and natural calamities happened in real world; hence its forecasting is a challenging task for traders. To gain profits and to overcome any crisis in financial market, it is essential to have a very accurate calculation of future trends by for the investors. The trend prediction results can be used as recommendations for investors as to whether they should buy or sell. Feature selection, dimensionality reduction and optimization techniques can be integrated with emerging advanced machine learning models, to get improvised prediction in terms of quality, performance, security and for effective assessment external factors role in stock market nonlinear signals. In this empirical research work, a set of hybrid models were built and their predictive abilities were compared to find consistent model. This work implies the base model, boosted model and deep learning model along with optimization techniques. From the experimental result, the optimized deep learning model, ABC-LSTM was turned out superior to all other considered financial models LSSVM, Gradient Boost, LSTM, ABC-LSSVM, ABC-Gradient Boost by showing best Mean Absolute Percentage Error (MAPE) value, which was low.
41
Iqbal, Naeem, Rashid Ahmad, Faisal Jamil, and Do-Hyeun Kim. "Hybrid features prediction model of movie quality using Multi-machine learning techniques for effective business resource planning." Journal of Intelligent & Fuzzy Systems 40, no. 5 (April 22, 2021): 9361–82. http://dx.doi.org/10.3233/jifs-201844.
Full textAbstract:
Quality prediction plays an essential role in the business outcome of the product. Due to the business interest of the concept, it has extensively been studied in the last few years. Advancement in machine learning (ML) techniques and with the advent of robust and sophisticated ML algorithms, it is required to analyze the factors influencing the success of the movies. This paper presents a hybrid features prediction model based on pre-released and social media data features using multiple ML techniques to predict the quality of the pre-released movies for effective business resource planning. This study aims to integrate pre-released and social media data features to form a hybrid features-based movie quality prediction (MQP) model. The proposed model comprises of two different experimental models; (i) predict movies quality using the original set of features and (ii) develop a subset of features based on principle component analysis technique to predict movies success class. This work employ and implement different ML-based classification models, such as Decision Tree (DT), Support Vector Machines with the linear and quadratic kernel (L-SVM and Q-SVM), Logistic Regression (LR), Bagged Tree (BT) and Boosted Tree (BOT), to predict the quality of the movies. Different performance measures are utilized to evaluate the performance of the proposed ML-based classification models, such as Accuracy (AC), Precision (PR), Recall (RE), and F-Measure (FM). The experimental results reveal that BT and BOT classifiers performed accurately and produced high accuracy compared to other classifiers, such as DT, LR, LSVM, and Q-SVM. The BT and BOT classifiers achieved an accuracy of 90.1% and 89.7%, which shows an efficiency of the proposed MQP model compared to other state-of-art- techniques. The proposed work is also compared with existing prediction models, and experimental results indicate that the proposed MQP model performed slightly better compared to other models. The experimental results will help the movies industry to formulate business resources effectively, such as investment, number of screens, and release date planning, etc.
42
Albergel, Clément, Yongjun Zheng, Bertrand Bonan, Emanuel Dutra, Nemesio Rodríguez-Fernández, Simon Munier, Clara Draper, et al. "Data assimilation for continuous global assessment of severe conditions over terrestrial surfaces." Hydrology and Earth System Sciences 24, no. 9 (September 2, 2020): 4291–316. http://dx.doi.org/10.5194/hess-24-4291-2020.
Full textAbstract:
Abstract. LDAS-Monde is a global offline land data assimilation system (LDAS) that jointly assimilates satellite-derived observations of surface soil moisture (SSM) and leaf area index (LAI) into the ISBA (Interaction between Soil Biosphere and Atmosphere) land surface model (LSM). This study demonstrates that LDAS-Monde is able to detect, monitor and forecast the impact of extreme weather on land surface states. Firstly, LDAS-Monde is run globally at 0.25∘ spatial resolution over 2010–2018. It is forced by the state-of-the-art ERA5 reanalysis (LDAS_ERA5) from the European Centre for Medium Range Weather Forecasts (ECMWF). The behaviour of the assimilation system is evaluated by comparing the analysis with the assimilated observations. Then the land surface variables (LSVs) are validated with independent satellite datasets of evapotranspiration, gross primary production, sun-induced fluorescence and snow cover. Furthermore, in situ measurements of SSM, evapotranspiration and river discharge are employed for the validation. Secondly, the global analysis is used to (i) detect regions exposed to extreme weather such as droughts and heatwave events and (ii) address specific monitoring and forecasting requirements of LSVs for those regions. This is performed by computing anomalies of the land surface states. They display strong negative values for LAI and SSM in 2018 for two regions: north-western Europe and the Murray–Darling basin in south-eastern Australia. For those regions, LDAS-Monde is forced with the ECMWF Integrated Forecasting System (IFS) high-resolution operational analysis (LDAS_HRES, 0.10∘ spatial resolution) over 2017–2018. Monitoring capacities are studied by comparing open-loop and analysis experiments, again against the assimilated observations. Forecasting abilities are assessed by initializing 4 and 8 d LDAS_HRES forecasts of the LSVs with the LDAS_HRES assimilation run compared to the open-loop experiment. The positive impact of initialization from an analysis in forecast mode is particularly visible for LAI that evolves at a slower pace than SSM and is more sensitive to initial conditions than to atmospheric forcing, even at an 8 d lead time. This highlights the impact of initial conditions on LSV forecasts and the value of jointly analysing soil moisture and vegetation states.
43
Zeng, Qilin, Jiaxin Liu, and Weiming Xiong. "Research on Antennas Alignment of Dynamic Point-to-Point Communication." Mathematical Problems in Engineering 2018 (November 11, 2018): 1–5. http://dx.doi.org/10.1155/2018/8697647.
Full textAbstract:
In the dynamic point-to-point communication, to track and aim at antenna fast and accurately is the guarantee of high quality communication signal. In order to solve the problem of antenna alignment, we used the least square method (LSM) to fit the optimal level signal value (LSV) point which is based on coordinate coarse tracking alignment and matrix scanning strategy to find the LSV in this paper. Antenna is driven by two-dimensional turntable (azimuth and elevation angle (AE)): the two-dimensional turntable is decomposed into two independent one-dimensional turntables, and the LSV in AE direction are obtained by scanning, respectively. The optimal LSV point of two-dimensional turntable can be find by combing optimal LSV point of two independent one-dimensional turntables. The method has the advantages of high precision and easy implementation and can meet the requirement of fast and accurately alignment in dynamic point-to-point communication antenna engineering.
44
Hollingsworth, S. J., C. B. Tang, and S. G. E. Barker. "The Effects of Heparin on Cultured Explants of Varicose Long Saphenous Vein." Phlebology: The Journal of Venous Disease 16, no. 2 (June 2001): 60–67. http://dx.doi.org/10.1177/026835550101600203.
Full textAbstract:
Objective: To examine the effects of heparin on smooth muscle cells (SMCs) in explants of varicose, long saphenous vein (LSV). Procedures: Explants of varicose LSV were cultured for 7 days either alone, or with heparin at 10, 100 or 1000 IU/ml (Monoparin). At 7 days, cultured explants were analysed for changes in intimal and medial thickness and by immuno-histochemistry. Comparisons were made with explants at initial isolation and with similar, cultured explants of normal LSV. Results: In normal LSV, by day 7, SMC-derived neo-intimal hyperplasia developed ( p<0.01) with an increase in intimal thickness ( p<0.02) and a decrease in medial thickness ( p<0.001). Heparin at 10 and 100 IU/ml further enhanced this neo-intima formation ( p<0.001). In contrast, at 1000 IU/ml, heparin inhibited neo-intima formation. In varicose explants, the pattern of intimal and medial changes was different. At isolation, varicose LSVs had substantially thicker intimal layers ( p<0.001). When cultured alone, a thicker media developed ( p<0.001) but there was little change in intimal thickness. Heparin at all concentrations had no effect on the thicker medial development seen in controls but did, however, reduce intimal thickness ( p<0.005). Conclusions: The response to heparin in explants of varicose LSV is different from that of normal LSV, which is biphasic and complex.
45
Yoon, Heechul, Taewook Kim, Sungtae Park, Nigel Mark Sammes, and Jong-Shik Chung. "Stable LSM/LSTM bi-layer interconnect for flat-tubular solid oxide fuel cells." International Journal of Hydrogen Energy 43, no. 1 (January 2018): 363–72. http://dx.doi.org/10.1016/j.ijhydene.2017.11.024.
Full text
46
Chen, Xiu Hua, Wen Hui Ma, and Jie Yu. "Research on LSCMCo-CDC Composites as Improved Anode Material for IT-SOFC." Advanced Materials Research 79-82 (August 2009): 123–26. http://dx.doi.org/10.4028/www.scientific.net/amr.79-82.123.
Full textAbstract:
La1-xSrxCr1-yMnyO3-δ(LSCM) has unique advantages over the traditional anodes for it’s stability and high catalytic activity being an anode of solid oxide fuel cell(SOFC). Doped cerium material and Co element are used to improve the conductivity both in oxidative and reductive conditions. La0.7Sr0.3Cr0.5Mn0.5-xCoxO3-δ-Ce0.8Ca0.2O2(LSCMCo-CDC) composite anode materials are synthesized in one-step by glycine nitrate process(GNP). X-ray diffraction patterns(XRD), scanning electron microscopy(SEM) and energy dispersive X-ray spectroscopy(EDS) are used to characterize the powders. The conductivity of LSCMCo-CDC increases with increasing the quantity of Co when the temperature is above 750°C, and the maximum values are 10.5 Scm-1 and 0.7 Scm-1 of LSCMCo0.15-CDC at 800°C in air and H2 atmosphere, respectively. It’s conductivity in intermediate temperature have been promoted obviously comparing to that of LSCM-CDC and LSCMCo. Good chemical compatibility between LSCMCo-CDC and La0.9Sr0.1Ga0.8Mg0.2O3-δ(LSGM) is confirmed by XRD results.
47
Zabel, F., and W. Mauser. "2-way coupling the hydrological land surface model PROMET with the regional climate model MM5." Hydrology and Earth System Sciences 17, no. 5 (May 2, 2013): 1705–14. http://dx.doi.org/10.5194/hess-17-1705-2013.
Full textAbstract:
Abstract. Most land surface hydrological models (LSHMs) consider land surface processes (e.g. soil–plant–atmosphere interactions, lateral water flows, snow and ice) in a spatially detailed manner. The atmosphere is considered as exogenous driver, neglecting feedbacks between the land surface and the atmosphere. On the other hand, regional climate models (RCMs) generally simulate land surface processes through coarse descriptions and spatial scales but include land–atmosphere interactions. What is the impact of the differently applied model physics and spatial resolution of LSHMs on the performance of RCMs? What feedback effects are induced by different land surface models? This study analyses the impact of replacing the land surface module (LSM) within an RCM with a high resolution LSHM. A 2-way coupling approach was applied using the LSHM PROMET (1 × 1 km2) and the atmospheric part of the RCM MM5 (45 × 45 km2). The scaling interface SCALMET is used for down- and upscaling the linear and non-linear fluxes between the model scales. The change in the atmospheric response by MM5 using the LSHM is analysed, and its quality is compared to observations of temperature and precipitation for a 4 yr period from 1996 to 1999 for the Upper Danube catchment. By substituting the Noah-LSM with PROMET, simulated non-bias-corrected near-surface air temperature improves for annual, monthly and daily courses when compared to measurements from 277 meteorological weather stations within the Upper Danube catchment. The mean annual bias was improved from −0.85 to −0.13 K. In particular, the improved afternoon heating from May to September is caused by increased sensible heat flux and decreased latent heat flux as well as more incoming solar radiation in the fully coupled PROMET/MM5 in comparison to the NOAH/MM5 simulation. Triggered by the LSM replacement, precipitation overall is reduced; however simulated precipitation amounts are still of high uncertainty, both spatially and temporally. The distribution of precipitation follows the coarse topography representation in MM5, resulting in a spatial shift of maximum precipitation northwards of the Alps. Consequently, simulation of river runoff inherits precipitation biases from MM5. However, by comparing the water balance, the bias of annual average runoff was improved from 21.2% (NOAH/MM5) to 4.4% (PROMET/MM5) when compared to measurements at the outlet gauge of the Upper Danube watershed in Achleiten.
48
Guellil, Imane, Ahsan Adeel, Faical Azouaou, Sara Chennoufi, Hanene Maafi, and Thinhinane Hamitouche. "Detecting hate speech against politicians in Arabic community on social media." International Journal of Web Information Systems 16, no. 3 (July 31, 2020): 295–313. http://dx.doi.org/10.1108/ijwis-08-2019-0036.
Full textAbstract:
Purpose This paper aims to propose an approach for hate speech detection against politicians in Arabic community on social media (e.g. Youtube). In the literature, similar works have been presented for other languages such as English. However, to the best of the authors’ knowledge, not much work has been conducted in the Arabic language. Design/methodology/approach This approach uses both classical algorithms of classification and deep learning algorithms. For the classical algorithms, the authors use Gaussian NB (GNB), Logistic Regression (LR), Random Forest (RF), SGD Classifier (SGD) and Linear SVC (LSVC). For the deep learning classification, four different algorithms (convolutional neural network (CNN), multilayer perceptron (MLP), long- or short-term memory (LSTM) and bi-directional long- or short-term memory (Bi-LSTM) are applied. For extracting features, the authors use both Word2vec and FastText with their two implementations, namely, Skip Gram (SG) and Continuous Bag of Word (CBOW). Findings Simulation results demonstrate the best performance of LSVC, BiLSTM and MLP achieving an accuracy up to 91%, when it is associated to SG model. The results are also shown that the classification that has been done on balanced corpus are more accurate than those done on unbalanced corpus. Originality/value The principal originality of this paper is to construct a new hate speech corpus (Arabic_fr_en) which was annotated by three different annotators. This corpus contains the three languages used by Arabic people being Arabic, French and English. For Arabic, the corpus contains both script Arabic and Arabizi (i.e. Arabic words written with Latin letters). Another originality is to rely on both shallow and deep leaning classification by using different model for extraction features such as Word2vec and FastText with their two implementation SG and CBOW.
49
Mucia, Anthony, Bertrand Bonan, Yongjun Zheng, Clément Albergel, and Jean-Christophe Calvet. "From Monitoring to Forecasting Land Surface Conditions Using a Land Data Assimilation System: Application over the Contiguous United States." Remote Sensing 12, no. 12 (June 24, 2020): 2020. http://dx.doi.org/10.3390/rs12122020.
Full textAbstract:
LDAS-Monde is a global land data assimilation system (LDAS) developed by Centre National de Recherches Météorologiques (CNRM) to monitor land surface variables (LSV) at various scales, from regional to global. With LDAS-Monde, it is possible to jointly assimilate satellite-derived observations of surface soil moisture (SSM) and leaf area index (LAI) into the interactions between soil biosphere and atmosphere (ISBA) land surface model (LSM) in order to analyze the soil moisture profile together with vegetation biomass. In this study, we investigate LDAS-Monde’s ability to predict LSV states up to two weeks in the future using atmospheric forecasts. In particular, the impact of the initialization, and the evolution of the forecasted variables in the LSM are addressed. LDAS-Monde is an offline system normally driven by atmospheric reanalysis, but in this study is forced by atmospheric forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF) for the 2017–2018 period over the contiguous United States (CONUS) at a 0.2° × 0.2° spatial resolution. These LSV forecasts are initialized either by the model alone (LDAS-Monde open-loop, without assimilation) or by the analysis (assimilation of SSM and LAI). These two forecasts are then evaluated using satellite-derived observations of SSM and LAI, evapotranspiration (ET) estimates, as well as in situ measurements of soil moisture from the U.S. Climate Reference Network (USCRN). Results indicate that for the three evaluation variables (SSM, LAI, and ET), LDAS-Monde provides reasonably accurate and consistent predictions two weeks in advance. Additionally, the initial conditions after assimilation are shown to make a positive impact with respect to LAI and ET. This impact persists in time for these two vegetation-related variables. Many model variables, such as SSM, root zone soil moisture (RZSM), LAI, ET, and drainage, remain relatively consistent as the forecast lead time increases, while runoff is highly variable.
50
Zabel, F., and W. Mauser. "Analysis of feedback effects and atmosphere responses when 2-way coupling a hydrological land surface model with a regional climate model – a case study for the Upper-Danube catchment." Hydrology and Earth System Sciences Discussions 9, no. 6 (June 13, 2012): 7543–70. http://dx.doi.org/10.5194/hessd-9-7543-2012.
Full textAbstract:
Abstract. Most land surface hydrological models (LSHMs) take land surface processes (e.g. soil-plant-atmosphere interactions, lateral water flows, snow and ice) into detailed spatial account. On the other hand, they usually consider the atmosphere as exogenous driver only, thereby neglecting feedbacks between the land surface and the atmosphere. Regional climate models (RCMs), on the other hand, generally describe land surface processes much coarser but naturally include land-atmosphere interactions. What is the impact on RCMs performance of the differently applied model physics and spatial resolution of LSHMs? In order to investigate this question, this study analyses the impact of replacing the land surface model (LSM) within a RCM by a LSHM. Therefore, a 2-way coupling approach was applied for a full integration of the LSHM PROMET (1×1 km2) and the atmospheric part of the RCM MM5 (45×45 km2). The scaling interface SCALMET is used for down- and upscaling the linear and non-linear fluxes between the model scales. The response of the MM5 atmosphere to the replacement is investigated and validated for temperature and precipitation for a 4 yr period from 1996 to 1999 for the Upper-Danube catchment. By substituting the NOAH-LSM with PROMET, simulated non-bias-corrected near surface air temperature significantly improves for annual, monthly and daily courses, when compared to measurements from 277 meteorological weather stations within the Upper-Danube catchment. The mean annual bias was improved from −0.85 K to −0.13 K. In particular, the improved afternoon heating from May to September is caused by increased sensible heat flux and decreased latent heat flux as well as more incoming solar radiation in the fully coupled PROMET/MM5 in comparison to the NOAH/MM5 simulation. Triggered by the LSM replacement, precipitation overall is reduced, however simulated precipitation amounts are still of high uncertainty, both spatially and temporally. The distribution of precipitation follows the coarse topography representation in MM5, resulting in a spatial shift of maximum precipitation northwards the Alps. Consequently, simulation of river runoff inherits precipitation biases from MM5. However, by comparing the water balance, the bias of annual average runoff was improved from 21.2% (NOAH/MM5) to 4.4% (PROMET/MM5) when compared to measurements at the outlet gauge of the Upper-Danube watershed in Achleiten.