Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images

Targeted multimodal sentiment classification(TMSC)aims to identify the sentiment polarity of a target mentioned in a multimodal post.The majority of current studies on this task focus on mapping the image and the text to a high-dimensional space in order to obtain and fuse implicit representations,ignoring the rich semantic information contained in the images and not taking into account the contribution of the visual modality in the multimodal fusion representation,which can potentially influence the results of TMSC tasks.This paper proposes a general model for Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images(ITMSC)as a way to tackle these issues and improve the accu-racy of multimodal sentiment analysis.Specifically,the ITMSC model can automatically adjust the contribution of images in the fusion representation through the exploitation of semantic descriptions of images and text similarity relations.Further,we propose a target-based attention module to capture the target-text relevance,an image-based attention module to capture the image-text relevance,and a target-image matching module based on the former two modules to properly align the target with the image so that fine-grained semantic information can be extracted.Our experimental results demonstrate that our model achieves comparable performance with several state-of-the-art approaches on two multimodal sentiment datasets.Our findings indicate that incorporating semantic descriptions of images can enhance our understanding of multimodal content and lead to improved sentiment analysis performance.

Research on PCA and KPCA Self-Fusion Based MSTAR SAR Automatic Target Recognition Algorithm

This paper proposes a PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. This algorithm combines the linear feature extracted from principal component analysis （PCA） and nonlinear feature extracted from kernel principal component analysis （KPCA） respectively, and then utilizes the adaptive feature fusion algorithm which is based on the weighted maximum margin criterion （WMMC） to fuse the features in order to achieve better performance. The linear regression classifier is used in the experiments. The experimental results indicate that the proposed self-fusion algorithm achieves higher recognition rate compared with the traditional PCA and KPCA feature fusion algorithms.

Targeted metabolic analysis of nucleotides and identification of biomarkers associated with cancer in cultured cell models

Cancer,like other diseases accompanied by metabolic changes,shows characteristic DNA/RNA modifications and activities of modifying enzymes,resulting in fluctuations in nucleoside levels.In this study,we undertook targeted metabolomic analyses of nucleotides in different cancer cell culture models using a sensitive and reproducible ion-pair HPLC method.The experimental data were analyzed by principal component analysis(PCA)to identify potential biomarkers in cancer cells,and statistical significance was determined by one-way analysis of variance.As a result,a clear differentiation of normal and tumor cells into two clusters was shown,indicating abnormal metabolism of nucleotides in tumor cells.Six variables(AMP,UDP,CTP levels with a significance of Po0.05;ATP,UTP and GMP levels with a significance of Po0.01)were considered as potential biomarkers;the content of AMP,UTP,GMP and ATP was significantly higher in cancer cells.The receiver operating characteristic(ROC)curve analysis allowed us to discriminate normal cells from tumor cells based on area under the curve(AUC).The sequence of their AUC values were:ATP(0.979)4UTP(0.938)4CTP¼GMP(0.896)4AMP(0.812)4UDP(0.792),so we conclude that ATP and UTP are the best potential biomarkers in tumor cells.This study may provide a valuable tool for studying minute alterations of intracellular nucleotide pools induced by anticancer/antiviral drugs,diseases or environmental factors.

Prognostic factors of primary gastrointestinal stromal tumors： a cohort study based on high-volume centers

Objective： We aimed to evaluate the clinicopathologic characteristics, immunohistochemical expression and prognostic factors of patients with primary gastrointestinal stromal tumors（GISTs）.Methods： Data from 2,570 consecutive GIST patients from four medical centers in China（January2001–December 2015） were reviewed. Survival curves were constructed by the Kaplan-Meier method, and Cox regression models were used to identify independent prognostic factors.Results： Of the included patients, 1,375（53.5%） were male, and the patient age range was 18 to 95（median, 58）years. The tumors were mostly found in the stomach（64.5%）, small intestine（25.1%） and colorectal region（5.1%）.At the time of diagnosis, the median tumor size was 4.0（range： 0.1–55.0） cm, and the median mitotic index per 50 high power fields（HPFs） was 3（range： 0–254）. Of the 2,168 resected patients, 2,009（92.7%） received curative resection. According to the modified National Institutes of Health（NIH） classification, 21.9%, 28.9%, 14.1% and35.1% were very low-, low-, intermediate-and high-risk tumors, respectively. The rate of positivity was 96.4% for c-Kit, 87.1% for CD34, 96.9% for delay of germination 1（DOG-1）, 8.0% for S-100, 31.0% for smooth muscle actin（SMA） and 5.1% for desmin. However, the prognostic value of each was limited. Multivariate analysis showed that age, tumor size, mitotic index, tumor site, occurrence of curative resection and postoperative imatinib were independent prognostic factors. Furthermore, we found that high-risk patients benefited significantly from postoperative imatinib（P〈0.001）, whereas intermediate-risk patients did not（P=0.954）.Conclusions： Age, tumor size, mitotic index, tumor site, occurrence of curative resection and postoperative imatinib were independent prognostic factors in patients with GISTs. Moreover, determining whether intermediate-risk patients can benefit from adjuvant imatinib would be of considerable interest in future studies.

Serological Targeted Analysis of an ITIH4 Peptide Isoform: A Preterm Birth Biomarker and Its Associated SNP Implications

Over 11% of all pregnancies in the US result in preterm birth, greatly contributing to perinatal morbidity and mortality （Goldenberg and Rouse, 1998）. Preterm birth etiologies remain largely unknown, and effective prevention methods have yet to be developed. The use of biofluid （e.g., serum or urine） for the analysis of the naturally occurring peptidome （MW 〈 4000） as a source of biomarkers has been reported for different diseases （Villanueva et al., 2006; Ling et al., 2010a, 2010b, 2010c, 2011）. Mass spectrometry-based profiling of naturally occurring peptides can provide an extensive in- ventory of serum peptides derived from either high-abundant endogenous circulating proteins or cell and tissue proteins （Liotta and Petricoin, 2006）.

Methods for bearings-only underwater target motion analysis

The problem of estimation of underwater target motion parameters via bearings only is the most of ten encountered and most difficult to solve in the underwater target motion analysis.As the bearings-only target motion analysis is a nonlinear and multiextremal global optimization problem, so most classical estimation methods often lead the solution to convergence to one of the local extremes other than the global extreme, especially, when the noise of target bearing observation is added. In this paper we propose to use the Generalized Least Square method on the rough estimation of target motion parameters, and then use the Sequential Uniform Design method to gain a more precise estimation on the bases of rough estimation.The latter ensures that the result convergences to the global extreme. The algorithm based on the above two methods is profitable for the bearings-only target motion analysis even under conditions of large bearing observation error.

Passive bearings-only target motion analysis based on association of multiple arrays

The method for Bearings-Only Target Motion Analysis (BO-TMA) based on bearing measurements fusion of two arrays is studied. The algorithms of pseudolinear processing, extended Kalman filter and maximum likelihood estimation are presented. The results of simulation experiments show that the BO-TMA method based on association of multiple arrays not only makes contributions towards eliminating maneuvers needed by bearings-only TMA based on single array,but also improves the stabilization and global convergence for varied estimation algorithms.

Local-linear-prediction analysis for underwater acoustic target radiated noise

Local-linear-prediction in phase space is performed for the underwater acoustic target radiated noise. Relation curve of average prediction error versus neighboring points' number is calculated. The result is used in judging the nonlinearity of radiated noise time series, and obtaining the appropriate form and coefficients of predicting model. The line and continuous spectral component are predicted respectively. Choice of some model parameters minimizing the prediction error is also discussed.

Genome-wide Analysis of Smad Targets Reveals the Role of BMP Signaling in Embryonic Stem Cell Fate Determination

Embryonic stem (ES) cells are under precise control of both intrinsic self-renewal gene regulatory network and extrinsic growth factor-triggered signaling cascades.

Comparison of different pseudo-linear estimators for vision-based target motion estimation

Vision-based target motion estimation based Kalman filtering or least-squares estimators is an important problem in many tasks such as vision-based swarming or vision-based target pursuit.In this paper,we focus on a problem that is very specific yet we believe important.That is,from the vision measurements,we can formulate various measurements.Which and how the measurements should be used?These problems are very fundamental,but we notice that practitioners usually do not pay special attention to them and often make mistakes.Motivated by this,we formulate three pseudo-linear measurements based on the bearing and angle measurements,which are standard vision measurements that can be obtained.Different estimators based on Kalman filtering and least-squares estimation are established and compared based on numerical experiments.It is revealed that correctly analyzing the covariance noises is critical for the Kalman filtering-based estimators.When the variance of the original measurement noise is unknown,the pseudo-linear least-squares estimator that has the smallest magnitude of the transformed noise can be a good choice.

Feature Extraction of Radar Range Profiles Based on Normalized Central Moments

The normalized central moments are widely used in pattern recognition because of scale and translation invariance. The moduli of normalized central moments of the 1-dimensional complex range profiles are used here as feature vector for radar target recognition. The common feature extraction method for high resolution range profile obtained by using Fourier-modified direct Mellin transform is inefficient and unsatisfactory in recognition rate And. generally speaking, the automatic target recognition method based on inverse synthetic aperture radar 2-dimensional imaging is not competent for real time object identification task because it needs complicated motion compensation which is sometimes too difficult to carry out. While the method applied here is competent for real-time recognition because of its computational efficiency. The result of processing experimental data indicates that this method is good at recognition.

Theoretical analysis of lens array for uniform irradiation on target in multimode fiber lasers

We propose and demonstrate a scheme to smooth and shape the on-target patterns in multimode fiber lasers, which includes expanding-collimating system and lens array （LA）. A smooth pattern with flat-top and sharp-edge profiles can be obtained with the irradiation nonuniformity decreasing significantly. We analyze the effects of the parameters such as defocus distance, the tilt angles, the number of the incident fiber lasers, and the diffraction-weakened LA on the uniformity irradiation of target by numerical simulations.

Analysis of Trace-Level Volatile Compounds in Fresh Turf Crop （Lolium perenne L.） by Gas Chromatography Quadrupole Time-of-Flight Mass Spectrometry

In the traditional research of volatile compounds, some trace-level compounds could not be identified by gas chromatography-mass spectrometry. Target and post-targeted methods were applied in the investigation of trace-level volatile compounds in fresh turf crop （Lolium perenne L.） based on gas chromatography in combination with hybrid quadrupole time-of-flight mass spectrometry. According to literatures published, a target analysis was performed by using retention index, accurate masses of characteristic ions and second-stage mass spectra （MS2 spectra）. And a series of experiments showed that low electron impact energy was beneficial to the improvement of the abundances of low abundance molecular ion peak. peak was beneficial to qualitative analysis. Totally, 60 Enhancing the abundances of low abundance molecular ion volatile compounds were identified, the great majority cornpounds of which were benzeneacetaldehyde （14.8%）, 2,5-dimethyl-pyrazine （9.6%）, and hexanal （9.3%）. Identification was complied by mass spectral search, retention index and accurate masses of characteristic ions.

Exploration of Target Spaces in the Human Genome for Protein and Peptide Drugs

After decades of development,protein and peptide drugs have now grown into a major drug class in the marketplace.Target identification and validation are crucial for the discovery of protein and peptide drugs,and bioinformatics prediction of targets based on the characteristics of known target proteins will help improve the efficiency and success rate of target selection.However,owing to the developmental history in the pharmaceutical industry,previous systematic exploration of the target spaces has mainly focused on traditional small-molecule drugs,while studies related to protein and peptide drugs are lacking.Here,we systematically explore the target spaces in the human genome specifically for protein and peptide drugs.Compared with other proteins,both successful protein and peptide drug targets have many special characteristics,and are also significantly different from those of small-molecule drugs in many aspects.Based on these features,we develop separate effective genome-wide target prediction models for protein and peptide drugs.Finally,a user-friendly web server,Predictor Of Protein and Pept Ide drugs’therapeutic Targets(POPPIT)(http://poppit.ncpsb.org.cn/),is established,which provides not only target prediction specifically for protein and peptide drugs but also abundant annotations for predicted targets.

Effects of antibiotic antitumor drugs on nucleotide levels in cultured tumor cells:an exploratory method to distinguish the mechanisms of antitumor drug action based on targeted metabolomics

Nucleotide pools in mammalian cells change due to the influence of antitumor drugs,which may help in evaluating the drug effect and understanding the mechanism of drug action.In this study,an ion-pair RP-HPLC method was used for a simple,sensitive and simultaneous determination of the levels of 12 nucleotides in mammalian cells treated with antibiotic antitumor drugs(daunorubicin,epirubicin and dactinomycin D).Through the use of this targeted metabolomics approach to find potential biomarkers,UTP and ATP were verified to be the most appropriate biomarkers.Moreover,a holistic statistical approach was put forward to develop a model which could distinguish 4 categories of drugs with different mechanisms of action.This model can be further validated by evaluating drugs with different mechanismsof action.This targeted metabolomics study may provide a novel approach to predict the mechanism of action of antitumor drugs.

Moving scanning emitter tracking by a single observer using time of interception:Observability analysis and algorithm

The target motion analysis（TMA） for a moving scanning emitter with known fixed scan rate by a single observer using the time of interception（TOI） measurements only is investigated in this paper.By transforming the TOI of multiple scan cycles into the direction difference of arrival（DDOA） model,the observability analysis for the TMA problem is performed.Some necessary conditions for uniquely identifying the scanning emitter trajectory are obtained.This paper also proposes a weighted instrumental variable（WIV） estimator for the scanning emitter TMA,which does not require any initial solution guess and is closed-form and computationally attractive.More importantly,simulations show that the proposed algorithm can provide estimation mean square error close to the Cramer-Rao lower bound（CRLB） at moderate noise levels with significantly lower estimation bias than the conventional pseudo-linear least square（PLS） estimator.

A New Concept for Regulatory Water Monitoring Via High-Performance Liquid Chromatography Coupled to High-Resolution Mass Spectrometry

A combined approach of target,suspected target and non-target screening using liquid chromatography-high-resolution mass spectrometry(LC-HRMS)was used to develop a new concept for water monitoring.With the current LC-MS/MS target approach for water monitoring,all targets can be quantified,but no additional information about the sample is collected.With the new concept,it is possible to detect 97%of the target compounds with a simplified quantification method without losing accuracy.Furthermore,a suspect target screening can be performed to get broader qualitative information about the water samples.In addition,the non-target screening offers the possibility to identify unknown micropollutants.All three evaluation steps depend on the same analytical measurement so that a lot of measurement and quality assurance effort can be saved.This concept could change water monitoring and assessment,and make it much more efficiently without losing information.There is a chance to measure less but learn more about the water bodies.

Periodic acoustic source tracking using propagation delayed measurements

There exist a large class of acoustic sources which have an underlying periodic phenomenon. Unlike the well-studied Bearings-Only Tracking(BOT) of an aperiodic acoustic source,this paper considers the problem of tracking a periodic acoustic source. For periodic acoustic tracking, the signal emission time is known. However, the true measurement reception time is unknown because it is corrupted by noise due to propagation delay. We augment the sensor’s signal reception time onto bearing measurements, and the information of the delay constraint is included in the original bearing measurements to compensate for the propagation delay. A Cubature Kalman Filter(CKF) is used for periodic acoustic source tracking, in which measurement prediction cannot be obtained directly because the sensor’s position at the true measurement reception time is unknown.We solve this problem by using the implicit Gauss-Helmert Sensor Model(GHSM) for estimating the sensor’s position, which consists of the sensor’s motion equation and the known measured sensor’s signal reception time equation related to the state. Then a CKF based on the GHSM(CF-GHSM) is developed for periodic acoustic tracking. Illustrative examples demonstrate that the CF-GHSM algorithm is better than other algorithms for periodic acoustic source tracking.