Undersampling is a popular method to solve imbalanced classification problems. However, sometimes it may remove too many majority samples which lead loss of informative samples. In this article, the hashing-based undersampling ensemble (HUE) proposed deal with problem by constructing diversified training subspaces for undersampling. Samples in class are divided into hashing method. Each subspace corresponds subset consists most from and few surrounding subspaces. These subsets used train an...

N-phenyl-4- (trifluoromethyl) thiazole-2-amine is an important class of fluorinated heterocyclic compounds, particularly in the fields fungicides and insecticides. However, there are very limited reports on synthesis methods such compounds. Here, we report a concise efficient new method for synthesizing this thiazol-2-amine, which has good substrate versatility, strong functional group tolerance, single product structure. We can effectively selectively control structure yield by adding or...

We report a coupling reaction without transition metal catalysis, introducing the efficient synthesis of trifluoroacetylaniline compounds using dibromotrifluoroacetone as trifluoroacetylation reagent. The conditions are mild, requiring only an equivalent amount base to achieve this reaction. substrate has good tolerance for functional groups and wide range substrates. More importantly, we studied biological bactericidal activity two found that com-pound 3z effect, with rate over 99% against...

The probabilistic classification vector machine (PCVM) synthesizes the advantages of both support and relevant machine, delivering a sparse Bayesian solution to problems. However, PCVM is currently only applicable binary cases. Extending multiclass cases via heuristic voting strategies such as one-vs-rest or one-vs-one often results in dilemma where classifiers make contradictory predictions, those might lose benefits outputs. To overcome this problem, we extend propose (mPCVM). Two learning...

Hashing methods are widely used for content-based image retrieval due to their attractive time and space efficiencies. Several dynamic hashing have been proposed tasks in non-stationary environments. However, concept drift problems environment seldomly considered which lead significant deterioration of performance. Therefore, we propose Deep Incremental (DIH). For the learning part, similarity-preserving object codes each newly arriving data chunk computed using product its label matrix a...

A very large volume of images is uploaded to the Internet daily. However, current hashing methods for image retrieval are designed static databases only. They fail consider fact that distribution can change when new added database over time. The changes in include both discovery a class and within owing concept drift. Retraining hash tables using all requires computation effort. This also biased old data huge which leads poor performance In this paper, we propose incremental (ICH) method...

Product color plays a vital role in shaping brand style and affecting users’ purchase decision. However, preferences about product design schemes may vary due to their cognition differences. Although considering perception of has been widely performed by industrial designers, it is not effective support this activity. In order provide users with plentiful solutions as well embody preference into process, involving interactive genetic algorithms (IGAs) an effectual way find optimum solutions....

Images are uploaded to the Internet over time which makes concept drifting and distribution change in semantic classes unavoidable. Current hashing methods being trained using a given static database may not be suitable for nonstationary image retrieval problems. Moreover, directly retraining whole hash table update knowledge coming from new arriving data efficient. Therefore, this paper proposes incremental hash-bit learning method. At arrival of data, bits selected both existing newly by...

Concept drift is prevalent in non-stationary data environments but rarely researched image retrieval. Therefore, more research needed on retrieval so that highly relevant images can still be retrieved when concept drifts happen. Hashing a key technique to allow efficient retrieval, incremental hashing emerges recent years for environments. A state-of-the-art method <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Incremental Hashing</i> (ICH)....

Binary hashing is an effective approach for content-based image retrieval, and learning binary codes with neural networks has attracted increasing attention in recent years. However, the training of difficult due to constraint on hash codes. In addition, are easily affected by input data small perturbations. Therefore, a sensitive autoencoder (SBHA) proposed handle these challenges introducing stochastic sensitivity retrieval. SBHA extracts meaningful features from original inputs maps them...

Current hashing-based image retrieval methods mostly assume that the database of images is static. However, this assumption not true in cases where databases are constantly updated (e.g., on Internet) and there exists problem concept drift. The online (also known as incremental) hashing have been proposed recently for they considered drift problem. Moreover, update hash functions dynamically by generating new codes all accumulated data over time which clearly uneconomical. In order to solve...

Abstract The surface quality of aluminium alloy castings is crucial to control. Aiming address the challenges limited samples and extensive computation in deep learning‐based defect detection for castings, this paper proposes a method based on data enhancement Casting Real‐Time DEtection TRansformer. First, tackle issue small sample sizes uneven distribution sets ECA‐MetaAconC Deep Convolution Generative Adversarial Networks proposed generating defects with fewer employ image augmentation...

Hashing methods help retrieve swiftly in large-scale dataset, which is important for real-world image retrieval. New data produced continually the real world may cause concept drift and inaccurate retrieval results. To address this issue, hashing non-stationary environments are proposed. However, most supervised. In practice, it hard to get exact labels of especially environments. Therefore, we propose unsupervised multi-hashing (UMH) method Thus, UMH, a set hash functions trained added kept...