High-capacity steganographic schemes often involve considerable modifications to the cover image structure, which can adversely affect its visual fidelity and undermine the imperceptibility requirement. Conversely, prioritizing visual fidelity typically restricts the embedding capacity. To address this trade-off, this paper proposes a color image steganography scheme based on a GAM-CBAM dual-attention mechanism. The proposed method integrates two key attention modules: the global attention module (GAM) enhances feature modelling capability, whereas the convolutional block attention module (CBAM) enables precise embedding region localization and dynamic feature weight assignment, effectively suppressing redundant information and reducing detection risk. The encoding network adopts an improved U-Net architecture with global attention to optimize feature extraction, whereas the decoding network incorporates CBAM to increase reconstruction accuracy. Experiments conducted on the COCO dataset for 256 × 256 color image steganography demonstrate the scheme’s superiority: PSNR improvement of 2.1687 dB (cover/stego image) and 1.489 dB gain (secret/reconstructed image) at a 1-byte per-pixel embedding capacity. These results validate the method’s significant improvements in visual fidelity and information recovery accuracy compared with the prior U-Net-based methods.

Constructing a good cost function is crucial for minimizing embedding distortion in image steganography. Recently, deep learning-based adaptive cost learning in image steganography has achieved significant advancements. For GAN-based image steganography, an encoder-decoder structure is typically employed by the generator. However, the continual encoding process often results in a lack of detailed information. Even if the image resolution is restored through skip connections, the generator will still be limited. To address the issue, this paper proposes a novel GAN structure named UMSA-GAN. Firstly, we design a residual attention mechanism, Res-CBAM, integrated into the generator network, which enables focusing on high-frequency regions in the cover image. Secondly, multi-scale feature information is also fused using skip connections, which enables the generator to learn more shallow features. Finally, unlike most of the previous works that only utilized Xu-Net as the discriminator, dual steganalyzers are also introduced as the discriminator to further enhance performance. Extensive comparative experiments demonstrate that UMSA-GAN effectively learns features from the cover images and generates better embedding probability maps. Compared to traditional and state-of-the-art GANbased steganographic methods, UMSA-GAN exhibits superior security performance. In addition, the rationality and superiority of UMSA-GAN are further verified by a large number of ablation studies.

The accurate prediction of a lithium-ion battery’s State of Health is of critical importance for efficient battery health management. Existing data-driven estimation methodologies grapple with issues such as high model complexity and a dearth of guidance from prior knowledge, which impose constraints on their efficacy. This work introduces a novel cross-modal distillation network for battery State of Health estimation, structured around a TransformerEncoder as the teacher network and a Convolutional Neural Network as the student network. Initially, the teacher model is pre-trained offline using State of Health degradation data to learn the degradation patterns. The directly measurable feature data (such as voltage, temperature, and current) is subsequently fed into the student network for online training and computation of a hard loss. the student network’s output is then directed into the pre-trained the teacher network to compute a soft loss, thereby offering prior knowledge of degradation laws and steering the optimization process of the student network. Rigorous experiments are conducted utilizing various datasets, with the outcomes validating the superior estimation accuracy and degradation rule adherence of the model. Notably, among five different models, this model demonstrates the best performance on almost all datasets, achieving an RMSE of 0.0097 and an MAE of 0.0065 on Cell1 of the Oxford dataset. Moreover, the model also demonstrates robust performance across different usage scenarios, inclusive of multi-battery estimation. Furthermore, this paper also introduces a fine tuning method for State of Health predictions only using the first half of the data. Comparative analysis with other models underscores the competitiveness of the proposed model, showcasing its potential for broader application.

Arithmetic operations on images are important primary transformations that can be applied to many complicated image operations. We mainly study the intensity-based arithmetic operations on the QIRHSI quantum image representation model to facilitate the development of quantum image processing. The quantum circuits and unitary matrices for four arithmetic operations including reverse, complement, addition, and subtraction are proposed. Finally, the complexity analysis of quantum networks is illustrated to show the effectiveness of the proposed arithmetic operations. (C) 2022 SPIE and IS&T

Numerous high-throughput omics studies have been conducted in schizophrenia, providing an accumulated catalog of susceptible variants and genes. The results from these studies, however, are highly heterogeneous. The variants and genes nominated by different omics studies often have limited overlap with each other. There is thus a pressing need for integrative analysis to unify the different types of data and provide a convergent view of schizophrenia candidate genes (SZgenes). In this study, we collected a comprehensive, multidimensional dataset, including 7819 brain-expressed genes. The data hosted genome-wide association evidence in genetics (eg, genotyping data, copy number variations, de novo mutations), epigenetics, transcriptomics, and literature mining. We developed a method named mega-analysis of odds ratio (MegaOR) to prioritize SZgenes. Application of MegaOR in the multidimensional data resulted in consensus sets of SZgenes (up to 530), each enriched with dense, multidimensional evidence. We proved that these SZgenes had highly tissue-specific expression in brain and nerve and had intensive interactions that were significantly stronger than chance expectation. Furthermore, we found these SZgenes were involved in human brain development by showing strong spatiotemporal expression patterns; these characteristics were replicated in independent brain expression datasets. Finally, we found the SZgenes were enriched in critical functional gene sets involved in neuronal activities, ligand gated ion signaling, and fragile X mental retardation protein targets. In summary, MegaOR analysis reported consensus sets of SZgenes with enriched association evidence to schizophrenia, providing insights into the pathophysiology underlying schizophrenia.

This paper is concerned with the better security of quantum image secret sharing (QISS) algorithm. The improved QISS (IQISS) scheme is implemented on both quantum gray image (FRQI) and quantum color image (MCQI). The new IQISS scheme comprises efficient sharing process and recovering process. The core idea of the sharing process is to combine encryption and measurement for two types of quantum secret images to acquire the quantum shadow images. In the recovering process, strip operation is firstly utilized on the shadow images. Afterwards, the decryption algorithm is used to recover the original quantum secret image. Experiments demonstrate that significant improvements in the security are in favor of the proposed approach.

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Hormonal therapy adherence is challenging for many patients with hormone-receptor-positive breast cancer. Gaining intuition into their adherence behavior would assist in improving outcomes by pinpointing, and eventually addressing, why patients fail to adhere. While traditional adherence studies rely on survey-based methods or electronic medical records, online health communities provide a supplemental data source to learn about such behavior and often on a much larger scale. In this paper, we focus on an online breast cancer discussion forum and propose a framework to automatically extract hormonal therapy adherence behavior (HTAB) mentions. The framework compares medical term usage when describing when a patient is taking hormonal therapy medication and interrupting their treatment (e.g., stop/pause taking medication). We show that by using shallow neural networks, in the form of wordlvec, the learned features can be applied to build efficient HTAB mention classifiers. Through medical term comparison, we find that patients who exhibit an interruption behavior are more likely to mention depression and their care providers, while patients with continuation behavior are more likely to mention common side effects (e.g., hot flashes, nausea and osteoporosis), vitamins and exercise.

In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to the two domains by adding two adaptive functions to it respectively. In the common space, the target domain data points are weighted and matched to the target domain in term of distributions. The weighting terms of source domain data points and the target domain classification responses are also regularized by the local reconstruction coefficients. The novel transfer learning framework is evaluated over some benchmark cross-domain data sets, and it outperforms the existing state-of-the-art transfer learning methods.

We propose a novel semi-supervised structured output prediction method based on local linear regression in this paper. The existing semi-supervise structured output prediction methods learn a global predictor for all the data points in a data set, which ignores the differences of local distributions of the data set, and the effects to the structured output prediction. To solve this problem, we propose to learn the missing structured outputs and local predictors for neighborhoods of different data points jointly. Using the local linear regression strategy, in the neighborhood of each data point, we propose to learn a local linear predictor by minimizing both the complexity of the predictor and the upper bound of the structured prediction loss. The minimization problem is solved by sub-gradient descent algorithms. We conduct experiments over two benchmark data sets, and the results show the advantages of the proposed method.

Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here, we make a novel observation that this is partially due to naive adoption of mainstream numerical optimization (e.g., Newton method) and failing to tailor for secure computing. This work presents a contrasting perspective: customizing numerical optimization specifically for secure settings. We propose a seemingly less-favorable optimization method that can in fact significantly accelerate privacy-preserving logistic regression. Leveraging this new method, we propose two new secure protocols for conducting logistic regression in a privacy-preserving and distributed manner. Extensive theoretical and empirical evaluations prove the competitive performance of our two secure proposals while without compromising accuracy or privacy: with speedup up to 2.3x and 8.1x, respectively, over state-of-the-art; and even faster as data scales up. Such drastic speedup is on top of and in addition to performance improvements from existing (and future) state-of-the-art cryptography. Our work provides a new way towards efficient and practical privacy-preserving logistic regression for large-scale studies which are common for modern science.

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc.

Complexity in clinical workflows can lead to inefficiency in making diagnoses, ineffectiveness of treatment plans and uninformed management of healthcare organizations (HCOs). Traditional strategies to manage workflow complexity are based on measuring the gaps between workflows defined by HCO administrators and the actual processes followed by staff in the clinic. However, existing methods tend to neglect the influences of EMR systems on the utilization of workflows, which could be leveraged to optimize workflows facilitated through the EMR. In this paper, we introduce a framework to infer clinical workflows through the utilization of an EMR and show how such workflows roughly partition into four types according to their efficiency. Our framework infers workflows at several levels of granularity through data mining technologies. We study four months of EMR event logs from a large medical center, including 16,569 inpatient stays, and illustrate that over approximately 95% of workflows are efficient and that 80% of patients are on such workflows. At the same time, we show that the remaining 5% of workflows may be inefficient due to a variety of factors, such as complex patients.

ACKNOWLEDGMENTS I am very fortunate to have received help and inspiration from numerous people during my Master's study, for which I feel always grateful. First of all, I would like to thank my advisor, Dr. Bradley A. Malin, who is extremely intelligent and supportive. This thesis would not have been possible without his guiding me in the right direction and contributing insightful discussions. His emphasis on perfec-tionism has constantly stimulated me to improve both in terms of sciences and my writing. Dr. Malin has also been very patient and supportive even when the project experienced technical drawbacks. I would also like to thank our collaborators, in particular, Dr. Murat Kantarcioglu of the University of Texas, Dallas, who is very knowledgeable in the field and has been essential to the technical merits of the project by proposing insightful suggestions and creative solutions. Dr. William S. Bush (of the Department of Biomedical Informatics then) also contributed a lot to the project and educated me with his ample domain knowledge and computational skills. Dr. Raymond Heatherly also provided helpful feedback and assistance with the experiments and my writing. Also, I would like to thank Drs. Joshua C. Denny and Dana Crawford for their continuous guidance on the problem motivation and data processing. I also owe gratitude to my committee member, Dr. Yuan Xue, who is very supportive and has been involved since the early discussions of the project and offered helpful feedback. I feel extremely honored to have her on my committee, and am always grateful for her time and efforts in helping improve my manuscript and the project in general. Table Page V.1 Per-SNP running time for SecureMA and the proportion of the time dedicated to the division process (mean and standard deviation in seconds).. 28 v LIST OF FIGURES Figure Page III.1 The Setup step of the SecureMA protocol: cryptographic keys are generated and disseminated. The public key (for encryption) is broadcast to the mediator and local sites, while the private key (for decryption) is split into secret shares (SK 1 , ..., SK K) which are securely transmitted to the respective data managers.. III.2 The SecureMA protocol (secure computation step). (a) The process begins when a scientist submits a meta-analysis study inquiry. Each data manager in the study submits encrypted local statistics (e.g., effect size and the inverse of its variance) to the Mediator for secure summation. (b) The Mediator …

MOTIVATION:Sharing genomic data is crucial to support scientific investigation such as genome-wide association studies. However, recent investigations suggest the privacy of the individual participants in these studies can be compromised, leading to serious concerns and consequences, such as overly restricted access to data. RESULTS:We introduce a novel cryptographic strategy to securely perform meta-analysis for genetic association studies in large consortia. Our methodology is useful for supporting joint studies among disparate data sites, where privacy or confidentiality is of concern. We validate our method using three multisite association studies. Our research shows that genetic associations can be analyzed efficiently and accurately across substudy sites, without leaking information on individual participants and site-level association summaries. AVAILABILITY AND IMPLEMENTATION:Our software for secure meta-analysis of genetic association studies, SecureMA, is publicly available at http://github.com/XieConnect/SecureMA. Our customized secure computation framework is also publicly available at http://github.com/XieConnect/CircuitService.