BACKGROUND: Integrative use of multi-omics data can enhance genomic prediction, yet its application remains challenged by the high cost, temporal specificity, and instability of transcriptomic signals across developmental stages. To address these limitations, it is crucial to utilize small, high-quality multi-omics datasets to efficiently identify stable, major-effect SNPs that can be applied to larger populations with genomic data alone. We propose AbGP (Attention-based Genomic Prediction), a framework designed to extract these robust genomic features. RESULTS: Using a discovery population of Huaxi cattle (HX_A, n = 218) with matched genotype and transcriptome data, AbGP employed a self-attention mechanism to identify a compact, high-value subset of SNPs (top 1.25%). The model’s predictive power was validated in a large, independent population (HX_B, n = 1496), where it significantly outperformed GBLUP and machine learning baselines for economic traits. CONCLUSION: AbGP effectively distills complex multi-omics information into a small subset of key SNPs that capture essential non-linear genetic architectures. This approach improves prediction accuracy and model stability, facilitating practical deployment in Huaxi cattle breeding.

The gated recurrent unit (GRU) networks are widely used in engineering applications due to the excellent performance. But, the flexibility of the proportion of update information to reset information is weak in GRU networks. To tackle this issue, this article proposes a fractional-order GRU (FOGRU) with a memory unit for the state of charge (SOC) estimation of lithium-ion batteries (LIBs). First, the Hausdorff difference is introduced into the GRU network to gain the fractional-order memory unit. Then, the range of the order is rigorously analyzed to ensure the convergence of the improved structure in the FOGRU network, and the adjustment rule of orders in the FOGRU network is to adaptively tune the FOGRU network. Finally, the experiment results show that the FOGRU network achieves a satisfactory effect in the SOC estimation of LIBs.

Foundation model CLIP has garnered significant attention worldwide in recent years due to its tremendous capabilities in various domains of deep learning. However, the knowledge acquired from image-text pairs in CLIP cannot be sufficiently transferred to dense prediction tasks like referring image segmentation. In this paper, we propose an effective framework, termed RISC, to thoroughly exploit the potential of CLIP to boost high-quality referring image segmentation. Specifically, to transfer the remarkable knowledge from CLIP to the pixel-text level, we introduce a CLIP-driven Dense Decoder to integrate features at different scales and modalities from CLIP in a fine-grained manner. Furthermore, to maximize the vision-text matching capabilities from CLIP, a Lightweight Pixel Refiner is proposed to generate masks with distinct boundaries through point sampling and matching strategies. Extensive experiments demonstrate that our approach outperforms the previous state- of-the-art methods by a notable margin on three widely-used datasets (RefCOCO, RefCOCO+ and RefCOCOg).

Incorporating the genotypic and phenotypic of the correlated traits into the multi-trait model can significantly improve the prediction accuracy of the target trait in animal and plant breeding, as well as human genetics. However, in most cases, the phenotypic information of the correlated and target trait of the individual to be evaluated was null simultaneously, particularly for the newborn. Therefore, we propose a machine learning framework, MAK, to improve the prediction accuracy of the target trait by constructing the multi-target ensemble regression chains and selecting the assistant trait automatically, which predicted the genomic estimated breeding values of the target trait using genotypic information only. The prediction ability of MAK was significantly more robust than the genomic best linear unbiased prediction, BayesB, BayesRR and the multi trait Bayesian method in the four real animal and plant datasets, and the computational efficiency of MAK was roughly 100 times faster than BayesB and BayesRR.

Nowadays, advances in high-throughput sequencing benefit the increasing application of genomic prediction (GP) in breeding programs. In this research, we designed a Cosine kernel-based KRR named KCRR to perform GP. This paper assessed the prediction accuracies of 12 traits with various heritability and genetic architectures from four populations using the genomic best linear unbiased prediction (GBLUP), BayesB, support vector regression (SVR), and KCRR. On the whole, KCRR performed stably for all traits of multiple species, indicating that the hypothesis of KCRR had the potential to be adapted to a wide range of genetic architectures. Moreover, we defined a modified genomic similarity matrix named Cosine similarity matrix (CS matrix). The results indicated that the accuracies between GBLUP_kinship and GBLUP_CS almost unanimously for all traits, but the computing efficiency has increased by an average of 20 times. Our research will be a significant promising strategy in future GP.

Blockchain is an innovated and revolutionized technology, which has attracted wide attention from academia and industry. At present, blockchain has been widely used in certificate management and credential delivery in network access authentication. In a large-scale multidomain Internet of Things (IoT) environment, one of the important issues is cross-domain key sharing and secure data exchange between different IoT. In this paper, aiming at the multidomain authentication requirements of the IoT, this paper introduces the blockchain cross-chain technology into the cross-domain authentication process of the IoT and proposes an effective cross-domain authentication scheme of the IoT based on the improved PBFT algorithm. First, an architecture of blockchain-based cross-domain authentication is proposed. Then, the block data structure is designed in order to enhance the function of access authentication. Third, the authentication process is realized by intelligent contract. The authentication information is encrypted and distributed by a key sharing method to ensure the security of authentication data. Simulation results show that the proposed scheme has significant advantages in security and availability.

BACKGROUND: Running multiple-chain Markov Chain Monte Carlo (MCMC) provides an efficient parallel computing method for complex Bayesian models, although the efficiency of the approach critically depends on the length of the non-parallelizable burn-in period, for which all simulated data are discarded. In practice, this burn-in period is set arbitrarily and often leads to the performance of far more iterations than required. In addition, the accuracy of genomic predictions does not improve after the MCMC reaches equilibrium. RESULTS: Automatic tuning of the burn-in length for running multiple-chain MCMC was proposed in the context of genomic predictions using BayesA and BayesCπ models. The performance of parallel computing versus sequential computing and tunable burn-in MCMC versus fixed burn-in MCMC was assessed using simulation data sets as well by applying these methods to genomic predictions of a Chinese Simmental beef cattle population. The results showed that tunable burn-in parallel MCMC had greater speedups than fixed burn-in parallel MCMC, and both had greater speedups relative to sequential (single-chain) MCMC. Nevertheless, genomic estimated breeding values (GEBVs) and genomic prediction accuracies were highly comparable between the various computing approaches. When applied to the genomic predictions of four quantitative traits in a Chinese Simmental population of 1217 beef cattle genotyped by an Illumina Bovine 770 K SNP BeadChip, tunable burn-in multiple-chain BayesCπ (TBM-BayesCπ) outperformed tunable burn-in multiple-chain BayesCπ (TBM-BayesA) and Genomic Best Linear Unbiased Prediction (GBLUP) in terms of the prediction accuracy, although the differences were not necessarily caused by computational factors and could have been intrinsic to the statistical models per se. CONCLUSIONS: Automatically tunable burn-in multiple-chain MCMC provides an accurate and cost-effective tool for high-performance computing of Bayesian genomic prediction models, and this algorithm is generally applicable to high-performance computing of any complex Bayesian statistical model.

LDA transformation is one of the popular feature dimension reduction techniques for the feature extraction in most handwritten Chinese characters recognition systems. The integration of the feature extraction and LDA transformation can be viewed as a two-directional feature transformation procedure, one is the pixel-level feature transformation by the summing up or blurring, another is by the LDA matrix, and the transformation coefficients are set empirically in the former. In this paper, we proposed a feature optimization method based on the gradient feature extraction by using the two-directional 2DLDA, which can find the optimal transformation coefficients in two directions. A series of experiments on the randomly selected 15 groups of the similar Chinese character samples from HCL2000 have indicated that, our method can effectively improve the recognition performance, the error rate reduction reaches 45.02% comparing to the traditional method, showing the effectiveness of the proposed approach.

Most online handwriting word recognition (HWR) approaches proceed by segmenting words into isolate characters which are recognized separately. Inspired by results in cognitive psychology, holistic word recognition approaches provides another effective way to deal the problem of HWR. In this paper, we propose a new method for rotation free online unconstrained Chinese word recognition through a holistic approach. By a gravity center balancing skew detection and correction method, the rotation ranging from 0deg to 360deg of a Chinese handwritten word can be detected. Through the process of preprocessing, feature extraction using elastic meshing technique and classification, the handwritten words with characters even connected or partially overlapped can be recognized through a holistic approach. Experiments were performed on 8888 categories of 1,137,664 unconstrained handwritten Chinese word samples. Experimental results for randomly rotated unconstrained cursive handwritten Chinese word data demonstrated that the proposed method can achieve about 96.58% recognition accuracy.

Writer adaptive handwriting recognition, which has potential of increasing accuracies for a particular user, is the process of converting a writer-independent recognition system to a writer-dependent one. In this paper, we provide a general incremental learning solution for linear discriminant analysis (LDA) on the basis of previous researches, and propose an Incremental LDA (ILDA) based writer adaptive online handwriting recognition method. The adaptation is performed by modifying both the prototypes and the LDA transformation matrix through ILDA algorithm. It includes: (1) modifying prototypes in original feature space; (2) updating the LDA transformation matrix; (3) projecting the updated prototypes to LDA feature space. Experiments are performed on two datasets, the writer-dependent dataset, in which the writing style is consistent with the incremental training data, and the writer-independent dataset. The results demonstrated that our proposed method can reduce as much as 46.35% error rate on the writer-dependent dataset with only 0.20% accuracy loss on the writer-independent dataset. It indicates that our proposed method can significantly increase the recognition accuracy for a particular writer while has minor effects for general writers.

SIFT descriptor has been widely applied in computer vision and object recognition, but has not been explored in the field of handwritten Chinese character recognition. In this paper we proposed a novel SIFT based feature for offline handwritten Chinese character recognition. The presented feature is a modification of SIFT descriptor taking into account of the characteristics of handwritten Chinese samples. In our approach, global elastic meshing is first constructed and then the related gradient code of each sub-region is accumulated dynamically. Experiments using MQDF classifier show our featurepsilas effectiveness with a recognition rate of 97.868%, which outperforms original SIFT feature and two traditional features, Gabor feature and gradient feature.

A vision-based fast postal envelope identification system for moving machine printed Chinese postal envelopes is proposed. Our system uses a high-speed camera to capture the image of envelopes running on the convey device and then recognizes the postal address and postcode on the envelopes. A vocabulary of 4590 categories of characters are supported, which include 4516 frequently used Chinese characters defined in GB2312-80, 62 alphanumeric characters, and 12 punctuation marks and symbols. The supported font styles include Song, Fang Song, Kai, Hei, etc. with the printed font size of no less than 7.5 points. The experimental results on 761 mail images representing 25,060 characters show that an envelope with an average of 32.9 characters can be processed and recognized within 81.38 milliseconds and the character recognition rate of postal address is 98.72%. Furthermore, our system also provides the function to store the envelope images and their recognition results into database in real time, which can be used in subsequent envelopes tracking and management. The experimental results with live mails on site indicate that our system can reach a speed of 21,000 mails per hour, and the character recognition rate of postal address is as high as 98.92%. Besides, our system can be conveniently equipped on the envelope processing devices in postal service center.

In this paper, an online handwritten Chinese character segmentation method is proposed. It is based on a dynamic programming algorithm, which uses geometrical features extracted from the handwritten strokes. The algorithm is carried out in two stages: pre-segmentation and recognition-based segmentation. The experimental results on 2363 sentences, representing nearly 70,000 characters and more than 370,000 strokes, show that the pre-segmentation stage keeps incorrect segmentation rate below 1% with an over-segmentation rate limited to 11%. The final correct segmentation rate is about 88%, without using any language model, indicating the effectiveness of proposed approach.

A directional feature extraction approach based on stroke directional decomposition of a Chinese character is proposed. Without extracting the skeleton or contour of the character, the four directional sub-patterns, namely, horizontal (-), vertical (|), left up diagonal (/) and right up diagonal () sub-patterns could be obtained directly from analyzing the stroke directional characteristics of the character. Five kinds of line-density based elastic meshing methods are presented to extract cellular directional features. Experimentation on a total of 18800 handwritten samples from 940 categories produces a recognition rate of 92.71%, showing the effectiveness of the proposed approach.

We study partial parallel interference cancellation in DS-CDMA system with delay estimation errors. The aforementioned work showed that by multiplying symbol estimates by a factor less than unity in early stages of cancellation, the performance of parallel cancellation can be improved relative to full ("brute force") cancellation. Shan and Rappaport (see IEEE GlobeCom'98, vol.3, p.2615-20, 1998) shows that the BER performance is a function of the factor and the "best factor" can be far less than one. In practical system, delay estimation errors need to be considered. This paper considers the effect of tracking errors on the selecting of "best factor". We show that due to the timing error the interference cancellation is less reliable and less factor of cancellation need to be employed.

Partial parallel interference cancellation in a DS-CDMA system with tracking errors is studied. The aforementioned work showed that by multiplying symbol estimates by a factor less than unity in the early stages of cancellation, the performance of parallel cancellation can be improved relative to full ("brute force") cancellation. Shan and Rappaport (see IEEE GlobeCom'98, vol.3, p.2615-20, 1998) shows that the BER performance is a function of the factor and the "best factor" can be far less than one. In a practical system, tracking errors need to be considered. This paper considers the effect of timing errors on the selection of the "best factor". We show that due to the timing error the interference cancellation is less reliable and a smaller factor of cancellation need to be employed.