Quality estimation of the resistance spot welding based on pattern feature of the electrode displacement signal

The electrode displacement signal of the resistance spot welding process is monitored and mapped into a binary matrix. Some welded spots, from different welding current specifications, are classified into five classes according to the prototypes of the pattern matrices. A reliable quality classifier is developed based on Hopfield network when the tensile shear strength of the welded joint is measured as the quality indicator. The cross validation test results show that the method utilizing pattern matrix of the displacement signal to characterize nugget formation process is feasible and it can provide adequate quality information of the welded spot. At the same time, under small sample circumstance, the classifier presents good classification ability and it also can correctly estimate the weld quality in some abnormal welding process according to the pattern feature of the displacement signal.

Performance and Improvement of MCS Selection with Channel Quality Estimation Errors for HSDPA

The throughput performance of modulation and coding schemes （MCS） selection with channel quality estimation errors （CQEE） is analyzed for high-speed downlink packet access （HSDPA）. To reduce the loss of throughput caused by CQEE, the robust MCS selection method and adaptive MCS switching scheme are proposed. In addition, automatic repeat request （ARQ） scheme is used to improve the block error rate （BLER） performance. Simulation results show that the proposed methods decrease the throughput loss resulted from CQEE efficiently and BLER performance gets better with ARQ scheme.

CCI-based link quality estimation mechanism for wireless sensor networks under non-perceived packet loss

This paper proposes a chip correlation indicator （CCI）-based link quality estimation mechanism for wireless sensor networks under non-perceived packet loss. On the basis of analyzing all related factors, it can be concluded that signal-to-noise rate （SNR） is the main factor causing the non-perceived packet loss. In this paper, the relationship model between CCI and non-perceived packet loss rate （NPLR） is established from related models such as SNR versus packet success rate （PSR）, CCI versus SNR and CCI-NPLR. Due to the large fluctuating range of the raw CCI, Kalman filter is introduced to do de-noising of the raw CCI. The cubic model and the least squares method are employed to fit the relationship between CCI and SNR. In the experiments, many groups of comparison have been conducted and the results show that the proposed mechanism can achieve more accurate measurement of the non-perceived packet loss than existing approaches. Moreover, it has the advantage of decreasing extra energy consumption caused by sending large number of probe packets.

Multi-instance learning for software quality estimation in object-oriented systems:a case study

We investigate a problem of object-oriented (OO) software quality estimation from a multi-instance (MI) perspective. In detail,each set of classes that have an inheritance relation,named 'class hierarchy',is regarded as a bag,while each class in the set is regarded as an instance. The learning task in this study is to estimate the label of unseen bags,i.e.,the fault-proneness of untested class hierarchies. A fault-prone class hierarchy contains at least one fault-prone (negative) class,while a non-fault-prone (positive) one has no negative class. Based on the modification records (MRs) of the previous project releases and OO software metrics,the fault-proneness of an untested class hierarchy can be predicted. Several selected MI learning algorithms were evalu-ated on five datasets collected from an industrial software project. Among the MI learning algorithms investigated in the ex-periments,the kernel method using a dedicated MI-kernel was better than the others in accurately and correctly predicting the fault-proneness of the class hierarchies. In addition,when compared to a supervised support vector machine (SVM) algorithm,the MI-kernel method still had a competitive performance with much less cost.

The Estimation Method of Channel Quality

On the basis of the introduction about water saving irrigation that works as a kind of new irrigation pattern,the method of anti-seep quality estimation of the conveying water and distributing channel which acts as an important engineering measure of water saving irrigation will be introduced in te paper.that is,by means of unit length of channel's water utilization coefficient(η 0)to estimate the quality of channel,and the calculative method has been explained by the example of an actual project.It can be referred to irrigational workers.

Estimating Reduced-Reference Video Quality for Quality-Based Streaming Video

Reduced-reference （RR） video-quality estimators send a small signature to the receiver. This signature comprises the original video content as well as the video stream. RR quality estimation provides reliability and involves a small data payload. While significant in theory, RR estimators have only recently been used in practice for quality monitoring and adaptive system con- trol in streaming-video frameworks. In this paper, we classify RR algorithms according to whether they are based on a） model- ing the signal distortion, b） modeling the human visual system, or c） analyzing the video signal source. We review proposed RR techniques for monitoring and controlling quality in streaming video systems.

Surveillance-image-based outdoor air quality monitoring

Air pollution threatens human health,necessitating effective and convenient air quality monitoring.Recently,there has been a growing interest in using camera images for air quality estimation.However,a major challenge has been nighttime detection due to the limited visibility of nighttime images.Here we present a hybrid deep learning model,capitalizing on the temporal continuity of air quality changes for estimating outdoor air quality from surveillance images.Our model,which integrates a convolutional neural network(CNN)and long short-term memory(LSTM),adeptly captures spatial-temporal image features,enabling air quality estimation at any time of day,including PM_(2.5) and PM10 concentrations,as well as the air quality index(AQI).Compared to independent CNN networks that solely extract spatial features,our model demonstrates superior accuracy on self-constructed datasets with R^(2)?0.94 and RMSE=5.11 mg m^(-3) for PM_(2.5),R^(2)=0.92 and RMSE=7.30 mg m^(-3) for PM10,and R^(2)=0.94 and RMSE?5.38 for AQI.Furthermore,our model excels in daytime air quality estimation and enhances nighttime predictions,elevating overall accuracy.Validation across diverse image datasets and comparative analyses underscore the applicability and superiority of our model,reaffirming its applicability and superiority for air quality monitoring.

Intelligent compaction theory of high roller compacted concrete dam

The concept and realization process of intelligent compaction for the construction of high roller compacted concrete dam were presented, as well as the theory of monitoring and intelligent feedback control. Based on the real-time analysis of the compaction index, a multiple regression model of the dam compactness was established and a realime estimation method of compaction quality for the entire work area of roller compacted concrete dam was proposed finally. The adaptive adjustment of the roiling process parameters was achieved, with the speed, the exciting force, the roller pass and the compaction thickness meeting the standards during the whole construction process. As a result, the compaction quality and construction efficiency can be improved. The research provides a new way for the construction quality control of roller compacted concrete dam.

Forest aboveground biomass estimates in a tropical rainforest in Madagascar: new insights from the use of wood specific gravity data

To generate carbon credits under the Reducing Emissions from Deforestation and forest Degradation program（REDD＋）, accurate estimates of forest carbon stocks are needed. Carbon accounting efforts have focused on carbon stocks in aboveground biomass（AGB）.Although wood specific gravity（WSG） is known to be an important variable in AGB estimates, there is currently a lack of data on WSG for Malagasy tree species. This study aimed to determine whether estimates of carbon stocks calculated from literature-based WSG values differed from those based on WSG values measured on wood core samples. Carbon stocks in forest biomass were assessed using two WSG data sets：（i） values measured from 303 wood core samples extracted in the study area,（ii） values derived from international databases. Results suggested that there is difference between the field and literaturebased WSG at the 0.05 level. The latter data set was on average 16 % higher than the former. However, carbon stocks calculated from the two data sets did not differ significantly at the 0.05 level. Such findings could be attributed to the form of the allometric equation used which gives more weight to tree diameter and tree height than to WSG. The choice of dataset should depend on the level of accuracy（Tier II or III） desired by REDD＋. As higher levels of accuracy are rewarded by higher prices, speciesspecific WSG data would be highly desirable.

Prediction of Canola Seed Longevity in the Drying Process

The probit analysis has been an important tool to predict seed longevity during storage and has been applied for seed drying simulation. Sealed aluminum pouches containing approximately 50 g of canola seed at moisture range of 7% to 21% of water content web basis （%） were conditioned in water-bath at 50, 60 and 70℃ to obtain the model to evaluate the reduction of canola seed germination. This model was included in the drying simulation program and the estimated germination was compared to the experimental values of germination during drying to validate the model. Canola seeds at 21% of moisture content and germination of 93% were dried at 51℃ and 61 ℃, and the model represented significantly the drying experiments. The aim of this study was to propose a germination model to evaluate the quality of canola seeds during the drying process and to offer the seed producers an important tool to control the drying process. The experimental data validated the objectives of the proposed drying model, optimizing the process at given conditions, managing the energy consumption, according to the minimum germination or maximum moisture content limitation for seed storage. For 51℃, the drying time for canola seed would be about 6 h to maintain germination above 90% and for 61℃, 4 h of drying time maintained germination up to 89%.

An Optimization Technique for PMF Estimation in Approximate Circuits

As an emerging computing technology,approximate computing enables computing systems to utilize hardware resources efficiently.Recently,approximate arithmetic units have received extensive attention and have been employed as hardware modules to build approximate circuit systems,such as approximate accelerators.In order to make the approximate circuit system meet the application requirements,it is imperative to quickly estimate the error quality caused by the approximate unit,especially in the high-level synthesis of the approximate circuit.However,there are few studies in the literature on how to efficiently evaluate the errors in the approximate circuit system.Hence,this paper focuses on error evaluation techniques for circuit systems consisting of approximate adders and approximate multipliers,which are the key hardware components in fault-tolerant applications.In this paper,the characteristics of probability mass function(PMF)based estimation are analyzed initially,and then an optimization technique for PMF-based estimation is proposed with consideration of these features.Finally,experiments prove that the optimization technology can reduce the time required for PMF-based estimation and improve the estimation quality.

Estimating posterior inference quality of the relational infinite latent feature model for overlapping community detection

Overlapping community detection has become a very hot research topic in recent decades,and a plethora of methods have been proposed.But,a common challenge in many existing overlapping community detection approaches is that the number of communities K must be predefined manually.We propose a flexible nonparametric Bayesian generative model for count-value networks,which can allow K to increase as more and more data are encountered instead of to be fixed in advance.The Indian buffet process was used to model the community assignment matrix Z,and an uncol-lapsed Gibbs sampler has been derived.However,as the community assignment matrix Zis a structured multi-variable parameter,how to summarize the posterior inference results andestimate the inference quality about Z,is still a considerable challenge in the literature.In this paper,a graph convolutional neural network based graph classifier was utilized to help tosummarize the results and to estimate the inference qualityabout Z.We conduct extensive experiments on synthetic data and real data,and find that empirically,the traditional posterior summarization strategy is reliable.