Number Of Negative Samples Research Articles

A multi-strategy ontology mapping method based on cost-sensitive SVM

As the core of ontology integration, the task of ontology mapping is to find the semantic relationship between ontologies. Nevertheless, most existing ontology mapping methods only rely ontext information to calculate entity similarity, thereby disregarding semantic nuances and necessitating substantial manual intervention. Therefore, this paper introduces an ontology mapping method. Based on the traditional ontology mapping method, the process employs a deep learning model to mine the semantic information of entity concepts, entity properties and ontology structure to obtain the embedding vector. We use the similarity mechanism to calculate the similarity between different embedding vectors, and combine the similarity values obtained from multiple strategy entities into a similarity matrix. The similarity matrix serves as input to the support vector machine (SVM), and the ontology mapping problem is finally transformed into a binary classification problem. However, since the number of mapped pairs is much larger than the number of non-mapped pairs, the number of positive samples in the data set is much smaller than the number of negative samples. Therefore, based on the traditional SVM, the paper adopts cost-sensitive strategy to deal with the class imbalance problem. In comparative evaluations against contemporary ontology mapping techniques, our method demonstrates a noteworthy 5.0% enhancement in recall and a 3.0% improvement in F1 score when tested on both public benchmark datasets and domain-specific datasets.

MAMLCDA: A Meta-Learning Model for Predicting circRNA-Disease Association Based on MAML Combined With CNN.

Circular RNAs (circRNAs) exist in vivo and are a class of noncoding RNA molecules. They have a single-stranded, closed, annular structure. Many studies have shown that circRNAs and diseases are linked. Therefore, it is critical to build a reliable and accurate predictor to find the circRNA-disease association. In this paper, we presented a meta-learning model named MAMLCDA to identify the circRNA-disease association, which is based on model-agnostic meta-learning (MAML) combined with CNN classification. Specifically, similarities between diseases and circRNAs are extracted and integrated to characterize their relationships, and k-means is used to cluster majority samples and select a certain number of samples from each cluster to obtain the same number of negative samples as the positive samples. To further reduce the dimension of the features and save operation time, we applied probabilistic principal component analysis (PPCA) to compact the integrated circRNA and disease similarity network feature vectors. The feature vectors are converted into images. At this time, the prediction problem is transformed into the 2-way 1-shot problem of the image and input into the model with MAML as the meta-learner and CNN as the base-learner. Comparison results of five-fold cross-validation on two benchmark datasets illustrate that MAMLCDA outperforms several state-of-the-art approaches with the best accuracies of 95.33% and 98%. Therefore, MAMLCDA can help to understand the pathogenesis of complex diseases at the circRNA level.

A Negative Sample-Free Graph Contrastive Learning Algorithm

Self-supervised learning is a new machine learning method that does not rely on manually labeled data, and learns from rich unlabeled data itself by designing agent tasks using the input data as supervision to obtain a more generalized representation for application in downstream tasks. However, the current self-supervised learning suffers from the problem of relying on the selection and number of negative samples and the problem of sample bias phenomenon after graph data augmentation. In this paper, we investigate the above problems and propose a corresponding solution, proposing a graph contrastive learning algorithm without negative samples. The model uses matrix sketching in the implicit space for feature augmentation to reduce sample bias and iteratively trains the mutual correlation matrix of two viewpoints by drawing closer to the distance of the constant matrix as the objective function. This method does not require techniques such as negative samples, gradient stopping, and momentum updating to prevent self-supervised model collapse. This method is compared with 10 graph representation learning algorithms on four datasets for node classification tasks, and the experimental results show that the algorithm proposed in this paper achieves good results.

ABNS: Association-based negative sampling for collaborative filtering

The purpose of the recommendation systems (RS) is to provide personalized information filtering for users by analyzing their interactions with items. However, the sparsity of data in RS, which means that the number of negative samples is much larger than the number of positive samples, causes the necessity of the negative sampling method. Previous work has shown that an appropriate negative sampling method, rather than simple random negative sampling, can significantly improve the performance of recommendation algorithms. Unfortunately, the existing works have significant shortcomings in explainability and computational complexity. To remedy these shortcomings, we conducted a theoretical analysis of the gradient of the Bayesian Personalized Ranking (BPR) loss function and propose an explainable negative sampling method. Moreover, we conducted experiments on real-world datasets and find that the proposed negative sampling method improves the recommendation performance by an average of 10.23% over uniform negative sampling. Finally, the effectiveness of the proposed method is demonstrated through comparison with other methods and hyperparameter sensitivity analysis.

Radar Echo Recognition of Gust Front Based on Deep Learning

Gust fronts (GFs) belong to the boundary layer convergence system. A strong GF can cause serious wind disasters, so its automatic monitoring and identification are very helpful but difficult in daily meteorological operations. By collecting convective weather processes in Hubei, Jiangsu, and other regions of China, 1422 GFs from 106 S-band new-generation weather radar (CINRAD/SA) volume scan data are labeled as positive samples by means of human–computer interaction, and the same number of negative samples are randomly tagged from no GF radar data. A deep learning dataset including 2844 labels with a positive and negative sample ratio of 1:1 is constructed, and 80%, 10%, and 10% of the dataset are separated as training, validation, and test sets, respectively. Then, the training dataset is expanded to 273,120 samples by data augmentation technology. Since the height of a GF is generally less than 1.5 km, three deep-learning-based models are trained for GF automatic recognition according to the distance from the radars. Three models (M1, M2, M3) are trained with the data at a 0.5° elevation angle from 65 to 180 km away from the radars, at 0.5° and 1.5° angles from 40 to 65 km, and at 0.5°, 1.5°, and 2.4° angles within 40 km, respectively. The precision, confusion matrix, and its derived indicators including receiver operating characteristic curve (ROC) and the area under ROC (AUC) are used to evaluate the three models by the test set. The results show that the identification precisions of the models are 97.66% (M1), 90% (M2), and 90.43% (M3), respectively. All the hit rates are over 89%, the false positive rates are less than 11%, and the critical success indexes (CSIs) surpass 82%. In addition, all the optimal critical points on the ROC curves are close to (0, 1), and the AUC values are above 0.93. These results suggest that the three models can effectively achieve the automatic discrimination of GFs. Finally, the models are demonstrated by three GF events detected with Qingpu, Nantong, and Cangzhou radars.

Study of Dittrichia Graveolens Extracts Effect against Staphylococcus Aureus Isolated from Urinary Tract Infections and Burns

the current study was aimed to estimate the activity of D. graveolens extract against Staphylococcus aureus isolated from urinary tract infection and burns . In this study, 150 samples were collected from urine and burns from patients attending and lying in hospitals (Azadi General - Kirkuk General - Public Health Laboratory) after consulting the specialist doctor and referring the patient to the laboratory, taking information for each sample and recording it in the special questionnaire form for different ages and genders for the period from December 2021. Until March 2022. The effect of different concentrations of aqueous and alcoholic extracts of the D. graveolens plant on the growth of microorganisms (bacteria) was studied. The results showed The current study showed that the number of positive samples containing various bacterial growths was 102 (68%), while the number of negative samples that did not show bacterial growth was 48 (38%). the total of S. aureus isolates was 31(30.39 %) as 20(64.5%) of the isolates were isolated from urine, while 11(35.5%) were isolated from burns. The results of the study demonstrated the effect of cold water and ethanol alcohol plant extracts from the Dittrichia graveolens plant on the growth of S.aureus isolates which isolated from urinary tract and burns infections using extraction devices. These isolates are known to be pathogenic and have high resistance to antibiotics under study. The ethanol extracts showed significant results, with the highest inhibition value reaching 14.44 at a concentration of 200 mg/mL, while the cold water extracts did not show any significant results.

Study of Dittrichia Graveolens Extracts Effect against Staphylococcus Aureus Isolated from Urinary Tract Infections and Burns

the current study was aimed to estimate the activity of D. graveolens extract against Staphylococcus aureus isolated from urinary tract infection and burns . In this study, 150 samples were collected from urine and burns from patients attending and lying in hospitals (Azadi General - Kirkuk General - Public Health Laboratory) after consulting the specialist doctor and referring the patient to the laboratory, taking information for each sample and recording it in the special questionnaire form for different ages and genders for the period from December 2021. Until March 2022. The effect of different concentrations of aqueous and alcoholic extracts of the D. graveolens plant on the growth of microorganisms (bacteria) was studied. The results showed The current study showed that the number of positive samples containing various bacterial growths was 102 (68%), while the number of negative samples that did not show bacterial growth was 48 (38%). the total of S. aureus isolates was 31(30.39 %) as 20(64.5%) of the isolates were isolated from urine, while 11(35.5%) were isolated from burns. The results of the study demonstrated the effect of cold water and ethanol alcohol plant extracts from the Dittrichia graveolens plant on the growth of S.aureus isolates which isolated from urinary tract and burns infections using extraction devices. These isolates are known to be pathogenic and have high resistance to antibiotics under study. The ethanol extracts showed significant results, with the highest inhibition value reaching 14.44 at a concentration of 200 mg/mL, while the cold water extracts did not show any significant results.

When is Burkholderia cepacia complex truly eradicated in adults with cystic fibrosis? A 20-year follow up study

BackgroundBurkholderia cepacia complex (BCC) infection in cystic fibrosis (CF) is associated with increased morbidity and mortality. Current UK guidance recommends segregation of people with CF according to infection status. To date there is no universally agreed consensus on the number of negative samples or time interval since last isolation of BCC for eradication to be deemed successful. MethodsAll cases of new BCC isolation at Manchester Adult Cystic Fibrosis Centre were followed-up between May 2002–May 2022. The number of subsequent positive and negative sputum samples for BCC were recorded, as well as eradication treatment received. Eradication was deemed successful if there were ≥3 negative sputum samples and no further positive sputum samples for the same species and strain ≥12 months until the end of follow-up. ResultsOf 46 new BCC isolation, 25 were successfully eradicated and 21 resulted in chronic infection. 5 (16.7%) cases with exclusively negative sputum samples 6–12 months after initial isolation had subsequent samples that were culture-positive for BCC and 3 (10.7%) cases with exclusively negative sputum samples after 12–24 months had subsequent culture-positive samples. Cases where BCC was eradicated had a greater median number of days of eradication treatment (42, IQR 21–63) compared to those in whom BCC isolation resulted in chronic infection (28, IQR 14–42), p = 0.04. ConclusionsA cautious approach to segregation should be maintained after new isolation of BCC in CF, as some individuals with ≥3 negative samples 12–24 months after initial isolation had subsequent sputum samples culture-positive for BCC.

Effect of oral antiseptics on the viral load of SARS-CoV-2: A randomized controlled trial.

In the oral cavity, which plays an important role in the transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), it is possible to reduce the viral load of SARS-CoV-2 with antiseptics, thereby minimizing the transmission of the virus during dental procedures. The aim of this study was to clinically evaluate the effect of the hypochlorous acid (HClO) and povidone-iodine (PVP-I) solutions on the oral viral load of SARS-CoV-2. This randomized controlled trial was conducted on 75 patients hospitalized in the COVID-19 ward of a local hospital. All the patients included in the study were within the first 24 h of hospitalization and the first 5 days of coronavirus disease 2019 (COVID-19) symptoms. The viral load of mouthwash samples was measured with the cycle threshold (Ct) value of SARS-CoV-2 through a realtime reverse transcription polymerase chain reaction (RT-PCR). The patients were divided into 3 groups. The effect on the patient's SARS-CoV-2 viral load was investigated after gargling the mouths and throats for 30 s with HClO, PVP-I and isotonic saline. First, a sample was taken after gargling with isotonic saline, then another sample was taken after gargling for 30 s with a particular antiseptic to determine the viral load of SARS-CoV-2. Comparing the before and after mouthwash samples from all 3 groups, there were no statistically significant differences in the Ct values before and after gargling (p > 0.05). However, there were statistically significant differences in the number of negative samples after the use of HClO and PVP-I, which were positive before gargling (p < 0.05). In the light of the data obtained in this study, there is insufficient evidence that gargling with HClO or PVP-I reduces viral load. Taken together, these findings imply no role for antiseptics in the transmission of SARS-CoV-2 by the aerosol generated during dental procedures, or more generally, SARS-CoV-2 infection control.

Comparison of Deep Learning Methods for Detecting and Counting Sorghum Heads in UAV Imagery

With the rapid development of remote sensing with small, lightweight unmanned aerial vehicles (UAV), efficient and accurate crop spike counting, and yield estimation methods based on deep learning (DL) methods have begun to emerge, greatly reducing labor costs and enabling fast and accurate counting of sorghum spikes. However, there has not been a systematic, comprehensive evaluation of their applicability in cereal crop spike identification in UAV images, especially in sorghum head counting. To this end, this paper conducts a comparative study of the performance of three common DL algorithms, EfficientDet, Single Shot MultiBox Detector (SSD), and You Only Look Once (YOLOv4), for sorghum head detection based on lightweight UAV remote sensing data. The paper explores the effects of overlap ratio, confidence, and intersection over union (IoU) parameters, using the evaluation metrics of precision P, recall R, average precision AP, F1 score, computational efficiency, and the number of detected positive/negative samples (Objects detected consistent/inconsistent with real samples). The experiment results show the following. (1) The detection results of the three methods under dense coverage conditions were better than those under medium and sparse conditions. YOLOv4 had the most accurate detection under different coverage conditions; on the contrary, EfficientDet was the worst. While SSD obtained better detection results under dense conditions, the number of over-detections was larger. (2) It was concluded that although EfficientDet had a good positive sample detection rate, it detected the fewest samples, had the smallest R and F1, and its actual precision was poor, while its training time, although medium, had the lowest detection efficiency, and the detection time per image was 2.82-times that of SSD. SSD had medium values for P, AP, and the number of detected samples, but had the highest training and detection efficiency. YOLOv4 detected the largest number of positive samples, and its values for R, AP, and F1 were the highest among the three methods. Although the training time was the slowest, the detection efficiency was better than EfficientDet. (3) With an increase in the overlap ratios, both positive and negative samples tended to increase, and when the threshold value was 0.3, all three methods had better detection results. With an increase in the confidence value, the number of positive and negative samples significantly decreased, and when the threshold value was 0.3, it balanced the numbers for sample detection and detection accuracy. An increase in IoU was accompanied by a gradual decrease in the number of positive samples and a gradual increase in the number of negative samples. When the threshold value was 0.3, better detection was achieved. The research findings can provide a methodological basis for accurately detecting and counting sorghum heads using UAV.

URINARY TRACT INFECTION IN KERBALA GOVERNORATE CHILDREN, CAUSES AND INFLUENCING FACTORS

Urinary tract infections (UTI) is one of the most frequent types of bacterial infection in humans; children are not an exemption, UTI is so common among young ages; it caused by pathological germs (kidneys, bladder, urethra, prostate). It is one of the significant difficulties facing the health sector in third-world nations, affecting children of all ages. UTI is are one of the severe problems that place a financial burden on the healthcare system, as the number of incidents worldwide might exceed 150 million in a single year, and infants and children are more prone to the disease's risks. This study was conducted on (1334) children ( males 611/ 45.8%, females723/54.2%) between the ages of one day - 12 years who visited Karbala governorate hospitals and some children's clinics in the governorate to determine whether the injuries are related to the months of the year, the environment, the parent's educational level and if females or males are more affected. The number of samples that gave positive results was 525(66.62%), and the number of negative samples was 263(33.38%). This study showed that the highest percentage of positive samples was recorded in January 54(10.29%), and the lowest rate of infection was recorded on April 36 (6.86%). This study found significant differences in the distribution of disease cases between residents of the rural environment 356 (69.13% and residents of the urban environment 169(61.9%). The educational level of the parents directly and significantly affects urinary tract infections in children. The highest incidence of urinary tract infection was in school-aged 143 (27,24%). The lowest incidence was in newborns, 42(8.0%) among all gender. The study showed significant differences (0.05) in the distribution of injuries between males and females between different age groups, where the highest injury was recorded among females school-aged 102 (33.77%).

Evaluation of Anti-nuclear Antibodies (ANA) Patterns for aging population in Hong Kong

Abstract Objective Our aim was to investigate the association among aging population, sex and Antinuclear Antibody (ANA) patterns expressed in Hong Kong population for improving the autoimmune diagnosis by using ANA HEp-2 slides under fluorescent microscope. Methods A total of 50 blood samples from aging population in both males and females were collected and examined under fluorescent microscope. In this research, a HEp-2 complete Kits (Bio-Rad Kallestad) with the methodology of indirect fluorescent antibody (IFA). Positive ANA patterns classified in International Consensus on ANA Patterns (ICAP) are distinguished. Results In this experiment, we obtained that the number of positive samples was 43 (86%), the number of suspected (weak) positive samples was 9 (21%) and the number of negative samples was 7 (14%). In 43 positive samples, 24 out of 27 females (88.9%) and 19 out of 23 males (82.6%) were aged between 70 – 91. 21 in 43 positive samples in the result were within age group 70–78 (48.8%). 17 in 43 positive samples in the result were within age group 80–88 (39.5%). 5 in 43 positive samples in the result were within age group 90–92 (11.6%). The most frequent positive ANA patterns included AC10 – (7 patients, median age = 81, 20%), AC19 – (6 patients, median age = 82, 17%), and AC7 – Few Nuclear Dots (5 patients, median age = 84, 15%). We found that ANA positivity rate was significantly higher in female than the male in Hong Kong (6.3%). Conclusion Our data indicated that female aged 70–78 is more likely to result higher positivity rate of ANA than male. According to data of our study, this significantly supports the further study of the trend in the aging population who are easier to have an ANA related autoimmune disease to take better care for elderly in Hong Kong.

Experimental and Mathematical Optimization of a Pooling Test for Detection of SARS-CoV-2 in a Population with Low Viral Load.

BackgroundA pooling test is a useful tool for mass screening of coronavirus disease 2019 (COVID-19) in the pandemic era. We aimed to optimize a simple two-step pooling test by estimating the optimal pool size using experimental and mathematical validation.Materials and MethodsExperimental pools were created by mixing one positive respiratory sample with various numbers of negative samples. We selected positive samples with cycle threshold (Ct) values greater than 32 to validate the efficiency of the pooling test assuming a high likelihood of false-negative results due to low viral loads. The positivities of the experimental pools were investigated with a single reverse-transcription polymerase chain reaction (RT-PCR) using the U-TOP™ COVID-19 Detection Kit Plus (Seasun Biomaterials, Daejeon, Korea). We used the Dorfman equation to calculate the optimal size of a pooling test mathematically.ResultsViral RNA could be detected in a pool with a size up to 11, even if the Ct value of a positive sample was about 35. The Dorfman equation showed that the optimal number of samples in a pool was 11 when the prevalence was assumed to be 0.66% based on the test positivity in Daejeon, Korea from April 1, 2020 to November 10, 2020. The efficiency of the pooling test was 6.2, which can save 83.9 of 100 individual tests.ConclusionEleven samples in a pool were validated optimal experimentally assuming a prevalence of 0.66%. The pool size needs modification as the pandemic progresses; thus, the prevalence should be carefully estimated before pooling tests are conducted.

Expression of ANA patterns by Indirect Fluorescent Assay in a local Hong Kong population from private sector

Abstract Objective Our aim was to investigate the association among age, sex and Antinuclear Antibody (ANA) patterns expressed in Hong Kong population for improving the autoimmune diagnosis by using ANA HEp-2 slides under fluorescent microscope. Methods A total of 65 blood samples from both male and female were collected and examined under fluorescent microscope. Haemolysed samples were excluded. In this research, a HEp-2 complete Kits with the methodology of indirect fluorescent antibody (IFA) was utilized for the detection and semi - quantification of antinuclear antibodies to distinguish positive ANA patterns classified in International Consensus on ANA Patterns (ICAP) for human body. Results In this experiment, we obtained that the number of positive samples was 6 (9%), the number of suspected (weak) positive samples was 4 (6%) and the number of negative samples was 55 (85%). In 6 positive samples, they were all females aged between 59 – 89. 5 in 6 positive samples in the result were over age 69 (83%). The positive ANA patterns included AC2 – Speckled, AC3 – Centromere, AC6 – Discrete Nuclear Dots, AC7 – Discrete Nuclear Dots, and AC8 – Nucleolar patterns separately. No AC-29 - DNA topoisomerase I was examined and resulted. We found that Hong Kong have a higher distribution of ANA positive frequency for female (9.23%) than male. Conclusion Our data indicated that ANA patterns were found in female aged above 69 is more likely to suffer from autoimmune disease related to ANA, providing an important foundation for considering and studying the trend in the elderly who are easier to have an ANA related autoimmune disease in Hong Kong.

Multiple Random Empirical Kernel Learning with Margin Reinforcement for imbalance problems

Imbalance problems arise in real-world applications when the number of negative samples far exceeds the number of positive samples, such as medical data. When solving the classification of imbalance problems, the samples located near the decision hyperplane contribute more to the decision hyperplane, and the samples far from the decision hyperplane contribute less to the decision hyperplane. So we can consider giving higher weights to the samples near the decision hyperplane, but they are sensitive to noise, and too much emphasis on them may lead to unstable performance. This paper proposes a Margin Reinforcement (MR) method to overcome the above dilemma. Because the imbalance problem is a cost-sensitive problem, MR gives positive samples a uniform high weight to improve the misclassification cost of the positive sample. For negative samples, according to their entropy, samples away from the decision surface and noise samples mixed in the positive samples are given a smaller weight, in order to improve the efficiency and robustness of the algorithm. Therefore, MR can emphasize the importance of samples located in overlapping regions of positive and negative classes and ignore the effects of noise samples to produce superior performance. Multiple Random Empirical Kernel Learning (MREKL) has proven to be effective and efficient in dealing with balance problems. In order to improve the performance of MREKL on imbalanced datasets, MR is introduced into MREKL to propose a novel Multiple Random Empirical Kernel Learning with Margin Reinforcement (MREKL-MR). MREKL-MR efficiently map the samples into low-dimensional feature spaces, then utilizes the MR approach to reenforce the importance of margin samples and decrease the effects of noise samples. Experimental results on 28 imbalanced datasets indicate that MREKL-MR is superior to comparison algorithms. Finally, the effectiveness of MREKL-MR in dealing with imbalance problems is verified on the Heart Failure dataset.

How to balance the bioinformatics data: pseudo-negative sampling

BackgroundImbalanced datasets are commonly encountered in bioinformatics classification problems, that is, the number of negative samples is much larger than that of positive samples. Particularly, the data imbalance phenomena will make us underestimate the performance of the minority class of positive samples. Therefore, how to balance the bioinformatic data becomes a very challenging and difficult problem.ResultsIn this study, we propose a new data sampling approach, called pseudo-negative sampling, which can be effectively applied to handle the case that: negative samples greatly dominate positive samples. Specifically, we design a supervised learning method based on a max-relevance min-redundancy criterion beyond Pearson correlation coefficient (MMPCC), which is used to choose pseudo-negative samples from the negative samples and view them as positive samples. In addition, MMPCC uses an incremental searching technique to select optimal pseudo-negative samples to reduce the computation cost. Consequently, the discovered pseudo-negative samples have strong relevance to positive samples and less redundancy to negative ones.ConclusionsTo validate the performance of our method, we conduct experiments base on four UCI datasets and three real bioinformatics datasets. According to the experimental results, we clearly observe the performance of MMPCC is better than other sampling methods in terms of Sensitivity, Specificity, Accuracy and the Mathew’s Correlation Coefficient. This reveals that the pseudo-negative samples are particularly helpful to solve the imbalance dataset problem. Moreover, the gain of Sensitivity from the minority samples with pseudo-negative samples grows with the improvement of prediction accuracy on all dataset.

Learning to Predict Drug Target Interaction From Missing Not at Random Labels

The prediction of Drug-Target Interaction (DTI) is an important research direction in bioinformatics as it greatly shortens the development cycle of new drugs. State-of-the-art computational methods for DTI prediction adopt a binary classification framework. The supervision is incomplete, i.e. only a small amount of DTIs are known and treated as positive instances, while the rest are unknown and treated as negative. Two severe problems occur in such a framework: (1) the number of negative samples is overwhelming and (2) a negative label cannot rule out the possibility of a positive drug-target interaction. In this paper, we address the problem of learning from incomplete labels in DTI prediction. The key assumption here is that labels are missing not at random. For example, negative DTI labels are more likely to be missing because biomedical researchers prioritize to study DTIs that are more likely to be positive. We introduce a novel probabilistic model, factorization with non-random missing labels (FNML). It models the generative process for the DTI labels (i.e. the labels are positive or negative) and responses (i.e. the labels are observed or missing). In particular, the probability of observing or missing a label is associated with the sign of the label. In order to further reduce prediction variance and improve prediction accuracy on highly imbalanced DTI datasets, we present FNML-EN, an ensemble scheme which is designed specifically for FNML model. We conduct comprehensive experiments on the latest DTI database, demonstrating the superior and robust performance of the proposed models.

Recognition of Protein Pupylation Sites by Adopting Resampling Approach.

With the in-depth study of posttranslational modification sites, protein ubiquitination has become the key problem to study the molecular mechanism of posttranslational modification. Pupylation is a widely used process in which a prokaryotic ubiquitin-like protein (Pup) is attached to a substrate through a series of biochemical reactions. However, the experimental methods of identifying pupylation sites is often time-consuming and laborious. This study aims to propose an improved approach for predicting pupylation sites. Firstly, the Pearson correlation coefficient was used to reflect the correlation among different amino acid pairs calculated by the frequency of each amino acid. Then according to a descending ranked order, the multiple types of features were filtered separately by values of Pearson correlation coefficient. Thirdly, to get a qualified balanced dataset, the K-means principal component analysis (KPCA) oversampling technique was employed to synthesize new positive samples and Fuzzy undersampling method was employed to reduce the number of negative samples. Finally, the performance of our method was verified by means of jackknife and a 10-fold cross-validation test. The average results of 10-fold cross-validation showed that the sensitivity (Sn) was 90.53%, specificity (Sp) was 99.8%, accuracy (Acc) was 95.09%, and Matthews Correlation Coefficient (MCC) was 0.91. Moreover, an independent test dataset was used to further measure its performance, and the prediction results achieved the Acc of 83.75%, MCC of 0.49, which was superior to previous predictors. The better performance and stability of our proposed method showed it is an effective way to predict pupylation sites.

TLD target tracking algorithm based on dynamic capture

In order to improve the ability of processing video image with high frame rate and meet the real-time requirement in higher resolution video tracking goal, DC-TLD target tracking algorithm, which is based on TLD algorithm and the theory of capturing sample dynamically, is proposed. Firstly, DC-TLD takes the target location of the previous frame as the predicted value of the current frame. Secondly, it calculates the threshold r of negative samples for ensuring that the number of negative samples is sufficient. Thirdly, it accesses the samples by index. The results of experiments show that DC-TLD is more robust and more efficient.

CTL-DNNet: Effective Circular Traffic Light Recognition with a Deep Neural Network

This paper proposed an algorithm for a deep learning network for identifying circular traffic lights (CTL-DNNet). The sample labeling process uses translation to increase the number of positive samples, and the similarity is calculated to reduce the number of negative samples, thereby reducing overfitting. We use a dataset of approximately 370[Formula: see text]000 samples, with approximately 20[Formula: see text]000 positive samples and approximately 350[Formula: see text]000 negative samples. The datasets are generated from images taken at the Beijing Garden Expo. To obtain a very robust method for the detection of traffic lights, we use different layers, different cost functions and different activation functions of the depth neural network for training and comparison. Our algorithm has evaluated autonomous vehicles in varying illumination and gets the result with high accuracy and robustness. The experimental results show that CTL-DNNet is effective at recognizing road traffic lights in the Beijing Garden Expo area.