Multiple heterogeneous agents are popular for executing pickup and delivery tasks for multiple pairs of customers. The scheduling solutions of agents are expected to complete each task within time windows, even under disturbances. Existing problem models tend to evaluate solutions through multiple simulations based on disturbances. This is time-consuming and implicit. In contrast, this article defines a robustness optimization objective based on the relationship between the agent's arrival time and the time windows for explicit evaluation. Taking robustness together with makespan and cost, the problem is modeled as a triobjective optimization problem. To solve the problem, this article proposes matrix-learning particle swarm optimization (MLPSO) to obtain diversified and high-quality solutions for decision-makers. In MLPSO, solutions are represented as an adjacency matrix of task sequences and an allocation matrix of agents to tasks. Corresponding to the matrix-based representation, solutions are constructed by planning the task order for execution and assigning agents to tasks. A matrix-distance-based learning (MDL) strategy is developed to select neighbors in the decision space for particle update. In this way, good task segments and allocation pairs can be extracted from learning exemplars and current positions to provide stable updating directions for generating high-quality solutions. To further enhance solution convergence and diversity, a dual-space local search (DSLS) is performed on elite and sparse nondominated solutions. Experimental results on 36 instances with various scales show that the proposed MLPSO is significantly better than state-of-the-art algorithms in terms of solution quality and diversity.

Recently, new paradigms of camouflaged object detection (COD), such as referring COD (Ref-COD) and collaborative COD (Co-COD), have been proposed to enhance task performance. However, there remains a lack of in-depth exploration of how to utilize reference information more effectively. In this paper, we introduce in-context learning camouflaged object detection (ICL-COD) as a novel paradigm of COD, which leverages camouflaged image samples and their corresponding annotations as visual examples to guide the model in better perceiving camouflage and recognizing camouflaged objects. We propose the ICL-Camo network, with the design of a context mining module (CMM) to mine fine-grained contextual information contained in the visual examples, and a context guiding module (CGM) that utilizes the contextual information mined from the examples as guidance to shift the attention of the target image features on potential camouflaged regions, thus enhancing its perception of camouflaged objects. Extensive experiments conducted on the COD benchmarks and other relevant tasks demonstrate the effectiveness of our proposed ICL-COD paradigm and ICL-Camo network. Code and results are available at: https://github.com/h0t-zer0/ICL-Camo.

Camouflaged Object Detection (COD) is pivotal for segmenting objects that seamlessly blend into their surroundings. While prior endeavors demonstrate impressive performance through training on predefined labels, they heavily rely on labor-intensive data annotation and struggle to adapt to open-world scenarios. In this light, we propose RA-COD, a training-free paradigm that enables COD by retrieving the most similar samples from the prototype repository. The efficacy of RA-COD hinges on 1) capturing the nuanced resemblance between objects and their environments and 2) excelling in dense prediction tasks. To achieve (1), the crux lies in ensuring diversity and discriminability within the prototype repository. In this context, we propose GenPro, an automated pipeline for crafting Generative Prototypes. GenPro integrates a range of foundation models, including the Diffusion Model, Vision-Language Model, Segment Anything Model (SAM), and DINOv2, in a complementary manner that synergistically generates diverse and distinguishable prototype samples. To achieve (2), we propose C2F to retrieve camouflaged objects in a Coarse-to-Fine regime. We commence with pixel-level retrieval in the feature space, which generates a coarse mask that effectively captures class discrimination and object localization. Further refinement is achieved by extracting bounding boxes from this coarse mask to prompt SAM in generating mask proposals for region-level retrieval. Evaluations on four benchmarks showcase that RA-COD achieves state-of-the-art performance compared to existing training-free methods.

Multi-modal medical image fusion synthesizes functional and structural features from different imaging modalities, providing comprehensive and accurate information for subsequent analysis. Existing fusion techniques based on Transformer often suffer from reduced accuracy and efficiency due to local perceptual limitations and cross-modal computational complexity. Recently, Mamba has proven effective in various uni-modal tasks due to its exceptional ability to model long-range dependency. However, the straightforward and effective cross-modal information flow and interaction based on Mamba remains underdeveloped in multi-modal fusion. In this paper, we propose a novel Holistic Cross-modal Fusion Mamba Network for multi-modal medical image fusion, namelyHCFMaNet. HCFMaNet introduces a new local-aware Mamba which perceives local positional relationships while modeling long-range dependency, thereby capturing richer inter-modal local-global feature representations. Additionally, a novel holistic cross-modal fusion Mamba is designed for explicit cross-modal perception and interaction both in spatial and channel dimensions by cross-spatial interaction and the proposed channel exchange embedding mechanism. Extensive experiments across various medical fusion sub-tasks demonstrate the high accuracy (avg.+22.4%) and effectiveness (avg.+92.7%) of our proposed method. Furthermore, HCFMaNet can be applied to other image fusion tasks, such as multi-exposure and visual-infrared fusion, yielding precise fusion outcomes.

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

Camouflaged Object Detection (COD) seeks to distinguish objects from their highly similar backgrounds. Existing work has essentially focused on isolating camouflaged objects from the environment, demonstrating ever-improving performance but at the cost of extensive annotations and complex optimizations. In this paper, we diverge from this paradigm and shift the lens to isolating the salient environment from the camouflaged object. We introduce EASE, an Environment-Aware unSupErvised COD framework that identifies the environment by referencing an environment prototype library and detects camouflaged objects by inverting the retrieved environmental features. Specifically, our approach (DiffPro) uses large multimodal models, diffusion models, and vision-foundation models to construct the environment prototype library. To retrieve environments from the library and refrain from confusing foreground and background, we incorporate three retrieval schemes: Kernel Density Estimation-based Adaptive Threshold (KDE-AT), Global-to-Local pixel-level retrieval (G2L), and Self-Retrieval (SR). Our experiments demonstrate significant improvements over current unsupervised methods, with EASE achieving an average gain of over 10% on the COD10K dataset. When integrated with SAM, EASE surpasses prompt-based segmentation approaches and performs competitively with state-of-the-art fully-supervised methods. Code is available at https://github.com/xiaohainku/EASE.

At the core of Camouflaged Object Detection (COD) lies segmenting objects from their highly similar surroundings. Previous efforts navigate this challenge primarily through image-level modeling or annotation-based optimization. Despite advancing considerably, this commonplace practice hardly taps valuable dataset-level contextual information or relies on laborious annotations. In this paper, we propose RISE, a RetrIeval SElf-augmented paradigm that exploits the entire training dataset to generate pseudo-labels for single images, which could be used to train COD models. RISE begins by constructing prototype libraries for environments and camouflaged objects using training images (without ground truth), followed by K-Nearest Neighbor (KNN) retrieval to generate pseudo-masks for each image based on these libraries. It is important to recognize that using only training images without annotations exerts a pronounced challenge in crafting high-quality prototype libraries. In this light, we introduce a Clustering-then-Retrieval (CR) strategy, where coarse masks are first generated through clustering, facilitating subsequent histogram-based image filtering and cross-category retrieval to produce high-confidence prototypes. In the KNN retrieval stage, to alleviate the effect of artifacts in feature maps, we propose Multi-View KNN Retrieval (MVKR), which integrates retrieval results from diverse views to produce more robust and precise pseudo-masks. Extensive experiments demonstrate that RISE outperforms state-of-the-art unsupervised and prompt-based methods. Code is available at https://github.com/xiaohainku/RISE.

Antimicrobial peptides (AMPs) are short peptides that play critical roles in diverse biological processes and exhibit functional activities against target organisms. While numerous methods have demonstrated the effectiveness of deep neural networks for AMP identification using sequence features; nevertheless, higher-level peptide characteristics-such as 3D structure and geometric surface features-have not been comprehensively explored. To address this gap, we introduce the SSFGM-Model (Sequence, Structure, Surface, Graph, and Geometric-based Model), a novel framework that integrates multiple feature types to enhance AMP identification. The model represents each peptide sequence as a graph, where nodes are characterized by amino acid features derived from ProteinBERT, ESM-2, and One-hot embeddings. Graph convolutional networks and an attention mechanism are employed to capture high-order structural and sequential relationships. Additionally, surface geometry and physicochemical properties are processed using a geometric neural network. Finally, a feature fusion strategy combines the outputs from these subnetworks to enable robust AMP identification. Extensive benchmarking experiments demonstrate that the SSFGM-Model outperforms current state-of-the-art methods. An ablation study further confirms the critical role of sequence, structural, and surface features in AMP identification. The key contribution of this work is the innovative integration of multiple levels of peptide characteristics and the combination of geometric and graph neural networks. This approach provides a more comprehensive understanding of the sequence-structure-function relationship of peptides, paving the way for more accurate AMP prediction. The SSFGM-Model has a significant potential for applications in the discovery and design of novel AMP-based therapeutics. The source code is publicly available at https://github.com/ggcameronnogg/SSFGM-Model.

Lightweight camouflaged object detection (COD) has garnered increasing attention due to its wide range of real-world applications and its efficiency on mobile devices. Existing lightweight COD methods typically attempt to utilize multi-scale fusion, frequency cues, and texture information to enhance the representation ability of lightweight backbone features. However, they still fall short in detecting precise and continuous object boundaries. To address this issue, we observe that two types of cells in the human visual system make great contributions to boundary perception. Motivated by this, we propose a boundary perception module (BPM) to enhance features with the awareness of fine-grained boundary, by mimicking the boundary perception process of aforementioned cells. In addition, we propose a bidirectional semantic enhancement module (BSEM) to effectively decode multi-level features in a lightweight manner. With BPM and BSEM, our proposed vision-inspired boundary perception network (BPNet) achieves superior performance against state-of-the-art methods and surpasses lightweight COD models by a large margin with the least parameters (3.64 M) and fastest speed (168FPS for the input size of 384 × 384).

RGB-D Salient Object Detection (SOD) aims to identify and highlight the most visually prominent objects from complex backgrounds by leveraging both RGB and depth information. However, depth maps often suffer from noise and inconsistencies due to the imaging modalities and sensor limitations. Additionally, the low-level spatial details and high-level semantic information from multiple levels pose another complexity layer. These issues result in depth maps that may not align well with the corresponding RGB images, causing incorrect foreground and background segmentation. To address these issues, we propose a novel adaptive depth enhancement network (ADENet), which adopts the Depth Feature Refinement (DFR) module to mitigate the negative impact of low-quality depth data and improve the synergy between multi-modal features. We also design a simple yet effective Cross Modality Fusion (CMF) module that combines the spatial and channel attention mechanisms to calibrate single modality features and boost the fusion. The Progressive Multiscale Aggregation (PMA) decoder has also been introduced to integrate multiscale features, promoting more globally retained information. Extensive experiments illustrate that our proposed ADENet is superior to the other 10 state-of-the-art methods on four benchmark datasets.

Multi-modal medical image fusion enhance the representation, aggregation and comprehension of functional and structural information, improving accuracy and efficiency for subsequent analysis. However, lacking explicit cross channel modeling and interaction among modalities results in the loss of details and artifacts. To this end, we propose a novelExplicitChannel-wiseInteractionNetwork for unified multi-modal medical imageFusion, namely ECINFusion. ECINFusion encompasses two components: multi-scale adaptive feature modeling (MAFM) and explicit channel-wise interaction mechanism (ECIM). MAFM leverages adaptive parallel convolution and transformer in multi-scale manner to achieve the global context-aware feature representation. ECIM utilizes the designed multi-head channel-attention mechanism for explicit modeling in channel dimension to accomplish the cross-modal interaction. Besides, we introduce a novel adaptive L-Norm loss, preserving fine-grained details. Experiments demonstrate ECINFusion outperforms state-of-the-art approaches in various medical fusion sub-tasks on different metrics. Furthermore, extended experiments reveal the robust generalization of the proposed in different fusion tasks. In breif, the proposed explicit channel-wise interaction mechanism provides new insight for multi-modal interaction.

Camouflaged Object Detection (COD) aims to segment objects resembling their environment. To address the challenges of extensive annotations and complex optimizations in supervised learning, recent prompt-based segmentation methods excavate insightful prompts from Large Vision-Language Models (LVLMs) and refine them using various foundation models. These are subsequently fed into the Segment Anything Model (SAM) for segmentation. However, due to the hallucinations of LVLMs and insufficient image-prompt interactions during the refinement stage, these prompts often struggle to capture well-established class differentiation and localization of camouflaged objects, resulting in performance degradation. To provide SAM with more informative prompts, we present UpGen, a pipeline that prompts SAM with generative prompts without requiring training, marking a novel integration of generative models with LVLMs. Specifically, we propose the Multi-Student-Single-Teacher (MSST) knowledge integration framework to alleviate hallucinations of LVLMs. This framework integrates insights from multiple sources to enhance the classification of camouflaged objects. To enhance interactions during the prompt refinement stage, we are the first to leverage generative models on real camouflage images to produce SAM-style prompts without fine-tuning. By capitalizing on the unique learning mechanism and structure of generative models, we effectively enable image-prompt interactions and generate highly informative prompts for SAM. Our extensive experiments demonstrate that UpGen outperforms weakly-supervised models and its SAM-based counterparts. We also integrate our framework into existing weakly-supervised methods to generate pseudo-labels, resulting in consistent performance gains. Moreover, with minor adjustments, UpGen shows promising results in open-vocabulary COD, referring COD, salient object detection, marine animal segmentation, and transparent object segmentation.

Traffic Salient Object Detection (TSOD) aims to segment the objects critical to driving safety by combining semantic (e.g., collision risks) and visual saliency. Unlike SOD in natural scene images (NSI-SOD), which prioritizes visually distinctive regions, TSOD emphasizes the objects that demand immediate driver attention due to their semantic impact, even with low visual contrast. This dual criterion, i.e., bridging perception and contextual risk, re-defines saliency for autonomous and assisted driving systems. To address the lack of task-specific benchmarks, we collect the first large-scale TSOD dataset with pixel-wise saliency annotations, named TSOD10K. TSOD10K covers the diverse object categories in various real-world traffic scenes under various challenging weather/illumination variations (e.g., fog, snowstorms, low-contrast, and low-light). Methodologically, we propose a Mamba-based TSOD model, termed Tramba. Considering the challenge of distinguishing inconspicuous visual information from complex traffic backgrounds, Tramba introduces a novel Dual-Frequency Visual State Space module equipped with shifted window partitioning and dilated scanning to enhance the perception of fine details and global structure by hierarchically decomposing high/low-frequency components. To emphasize critical regions in traffic scenes, we propose a traffic-oriented Helix 2D-Selective-Scan (Helix-SS2D) mechanism that injects driving attention priors while effectively capturing global multi-direction spatial dependencies. We establish a comprehensive benchmark by evaluating Tramba and 25 existing NSI-SOD models on TSOD10K, demonstrating Tramba's superiority. Our research establishes the first foundation for safety-aware saliency analysis in intelligent transportation systems. The dataset and code will be made publicly available at https://github.com/mj129/Tramba.

The widespread deployment of Wireless Sensor Networks (WSN) has made network coverage optimization crucial for improving coverage rates. However, traditional methods struggle with challenges such as energy constraints and environmental uncertainties. Metaheuristic (MH) algorithms offer promising solutions. Dung Beetle Optimization (DBO) algorithm is a well-regarded MH approach, but it suffers from slow convergence and a propensity for local optima entrapment in WSN coverage optimization. To overcome these limitations, this study proposes the Enhanced Dung Beetle Optimization with Neighborhood Mutation (ENMDBO). ENMDBO incorporates three key mechanisms: (1) the Exploring Cosine Similarity Transformation (ECST) strategy, which dynamically adjusts individual similarity to balance global exploration and local exploitation, mitigating the risk of local optima; (2) the Neighborhood Solution Mutation Sharing (NSMS) mechanism, which enhances population diversity by sharing positional information among neighbors, improving search efficiency; and (3) the Tolerance Threshold Detection Mutation (TTDM) mechanism, which detects stagnation in fitness to strengthen the algorithm’s global search capabilities. Experiments on the CEC2017 benchmark suite (Dim = 30, 50, 100) show that ENMDBO achieves superior performance compared to state-of-the-art algorithms, approaching the global optimum. Finally, in WSN coverage optimization, ENMDBO achieves an 86.88% coverage rate, representing an 8.92% improvement over the original DBO, while effectively reducing redundancy. These results underscore ENMDBO’s robustness and effectiveness, establishing it as a practical and reliable solution. (Matlab codes of ENMDBO are available at https://ww2.mathworks.cn/matlabcentral/fileexchange/181820-enhanced-dung-beetle-optimization-with-neighborhood-mutation.

In nature, certain objects exhibit patterns that closely resemble their backgrounds, a phenomenon commonly referred to as Camouflaged Object Detection (COD). We argue that existing COD approaches often suffer from insufficient discriminability for these objects, which we attribute to a lack of effective disentangling of foreground and background representations. To address this, we propose a novel Foreground-Background Disentanglement Network (FBD-Net) that enhances foreground-background disentanglement learning to improve discriminability. Specifically, we design an Edge-guided Foreground-Background Decoupling (EFBD) module, which facilitates the separated learning of foreground and background representations. Additionally, we introduce the Foreground-Background Representation Disentangling Head (DisHead) to further boost the discriminative power of the model. The DisHead consists of two objectives: the Edge Objective and the FoBa Objective. Furthermore, we propose three complementary modules: the Context Aggregation Module (CAM) for initial coarse object detection, the Scale-Interaction Enhanced Pyramid (SIEP) for multi-scale information extraction, and the Cross-Stage Adaptive Fusion (CSAF) module for subtle clue accumulation. Extensive experiments demonstrate that both our CNN-based and Transformer-based FBD-Nets outperform 26 state-of-the-art COD methods across four public datasets. Codes will be released on https://github.com/TomorrowJW/FBD-Net-COD .

Existing camouflaged object detection (COD) methods typically have large model parameters and computations, hindering their deployment in real-world applications. Although using lightweight backbones can help alleviate this problem, their weaker feature representation often leads to performance degradation. To address this issue, we observe that frequency information has shown effective for cumbersome networks, but its effectiveness for lightweight ones has not been thoroughly investigated. Biological studies indicate that the human visual system utilizes distinct neural pathways to respond to different frequency stimuli, contributing to specialization and efficiency. Motivated by this, we propose an efficient frequency injection module (FIM) to aid lightweight backbone features by separately injecting detailed high frequency and object-level low frequency cues at each stage. FIM can be used as a plug-and-play component in existing COD networks to enhance backbone features at a low cost. With FIM, our proposed frequency injection network (FINet) achieves competitive performance against most state-ofthe- art methods with much faster speed (692FPS for the input size of 384 x 384) and fewer parameters (3.74M). Source codes will be released at https://github.com/crrcoo/FINet.

Existing salient object detection (SOD) methods mainly rely on U-shaped convolution neural networks (CNNs) with skip connections to combine the global contexts and local spatial details that are crucial for locating salient objects and refining object details, respectively. Despite great successes, the ability of CNNs in learning global contexts is limited. Recently, the vision transformer has achieved revolutionary progress in computer vision owing to its powerful modeling of global dependencies. However, directly applying the transformer to SOD is suboptimal because the transformer lacks the ability to learn local spatial representations. To this end, this paper explores the combination of transformers and CNNs to learn both global and local representations for SOD. We propose a transformer-based Asymmetric Bilateral U-Net (ABiU-Net). The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively. The asymmetric bilateral decoder also consists of two paths to process features from the transformer and CNN encoder paths, with communication at each decoder stage for decoding coarse salient object locations and fine-grained object details, respectively. Such communication between the two encoder/decoder paths enables AbiU-Net to learn complementary global and local representations, taking advantage of the natural merits of transformers and CNNs, respectively. Hence, ABiU-Net provides a new perspective for transformer-based SOD. Extensive experiments demonstrate that ABiU-Net performs favorably against previous state-of-the-art SOD methods. The code is available athttps://github.com/yuqiuyuqiu/ABiU-Net.

Recent studies have confirmed that GPS trajectory can effectively assist in achieving more accurate road extraction from remote sensing images. Therefore, lots of efforts focus on designing effective multi-modal fusion strategies for GPS trajectory and remote sensing image modalities. However, there are still some limitations,e.g., the fusion structures are complex and hinder further improvements. Moreover, the negative impact of redundant information in various modalities is commonly ignored. This paper aims to design a simple yet effective fusion strategy for GPS trajectory and remote sensing image modalities to address the above issues. Inspired by the network pruning algorithm, we design a Cross-Modal Information Propagation (CMIP) mechanism. CMIP utilizes the scaling factors and sparse constraint to distinguish the redundant information of a certain modality that is directly replaced with corresponding information of another modality. We improve the widely-usedL1sparse constraint and propose a novel information balanced constraint which is added on the scaling factors to better identify and prune redundant channels. Embedded in the CMIP mechanism, a multi-modal information propagation network (CMIPNet) is proposed, which can fully explore the complementarities between different modalities to accurately locate roads, especially roads with noise or incomplete information of a certain modality. Since the CMIP is parameter-free and self-adaptive, CMIPNet is lightweight and easy to deploy. The parameter number of CMIPNet can be comparable to single-modal models, which is about 1/3 of the existing multi-modal models. Extensive experiments are performed to demonstrate that CMIPNet outperforms the previous single- and multi-modal road extraction methods.

Salient object detection in natural scene images (NSI-SOD) has undergone remarkable advancements in recent years. However, compared to those of natural images, the properties of remote sensing images (ORSIs), such as diverse spatial resolutions, complex background structures, and varying visual attributes of objects, are more complicated. Hence, how to explore the multiscale structural perceptual information of ORSIs to accurately detect salient objects is more challenging. In this paper, inspired by the superiority of contrastive learning, we propose a novel training paradigm for ORSI-SOD, named Deeply Hybrid Contrastive Learning Based on Semantic Pseudo-Label (DHCont), to force the network to extract rich structural perceptual information and further learn the better-structured feature embedding spaces. Specifically, DHCont first splits the ORSI into several local subregions composed of color- and texture-similar pixels, which act as semantic pseudo-labels. This strategy can effectively explore the underdeveloped semantic categories in ORSI-SOD. To delve deeper into multiscale structure-aware optimization, DHCont incorporates a hybrid contrast strategy that integrates “pixel-to-pixel”, “region-to-region”, “pixel-to-region”, and “region-to-pixel” contrasts at multiple scales. Additionally, to enhance the edge details of salient regions, we develop a hard edge contrast strategy that focuses on improving the detection accuracy of hard pixels near the object boundary. Moreover, we introduce a deep contrast algorithm that adds additional deep-level constraints to the feature spaces of multiple stages. Extensive experiments on two popular ORSI-SOD datasets demonstrate that simply integrating our DHCont into the existing ORSI-SOD models can significantly improve the performance.

Current RGB-D salient object detection (RGB-D SOD) methods mainly develop a generalizable model trained by binary cross-entropy (BCE) loss based on convolutional or Transformer backbones. However, they usually exploit convolutional modules to fuse multi-modality features, with little attention paid to capturing the long-range multi-modality interactions for feature fusion. Furthermore, BCE loss does not explicitly explore intra- and inter-pixel relationships in a joint embedding space. To address these issues, we propose a cross-modality interaction parallel-transformer (CIPT) module, which better captures the long-range multi-modality interactions, generating more comprehensive fusion features. Besides, we propose a pixel-level contrastive learning (PCL) method that improves inter-pixel discrimination and intra-pixel compactness, resulting in a well-structured embedding space and a better saliency detector. Specifically, we propose an asymmetric network (TPCL) for RGB-D SOD, which consists of a Swin V2 Transformer-based backbone and a designed lightweight backbone (LDNet). Moreover, an edge-guided module and a feature enhancement (FE) module are proposed to refine the learned fusion features. Extensive experiments demonstrate that our method achieves excellent performance against 15 state-of-the-art methods on seven public datasets. We expect our work to facilitate the exploration of applying Transformer and contrastive learning for RGB-D SOD tasks.

The rapid spread of the new pandemic, i.e., coronavirus disease 2019 (COVID-19), has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected area segmentation from computed tomography (CT) image, has attracted much attention by serving as an adjunct to increase the accuracy of COVID-19 screening and clinical diagnosis. Although lesion segmentation is a hot topic, traditional deep learning methods are usually data-hungry with millions of parameters, easy to overfit under limited available COVID-19 training data. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional methods are usually computationally intensive. To address the above two problems, we propose MiniSeg, a lightweight model for efficient COVID-19 segmentation from CT images. Our efforts start with the design of an attentive hierarchical spatial pyramid (AHSP) module for lightweight, efficient, effective multiscale learning that is essential for image segmentation. Then, we build a two-path (TP) encoder for deep feature extraction, where one path uses AHSP modules for learning multiscale contextual features and the other is a shallow convolutional path for capturing fine details. The two paths interact with each other for learning effective representations. Based on the extracted features, a simple decoder is added for COVID-19 segmentation. For comparing MiniSeg to previous methods, we build a comprehensive COVID-19 segmentation benchmark. Extensive experiments demonstrate that the proposed MiniSeg achieves better accuracy because its only 83k parameters make it less prone to overfitting. Its high efficiency also makes it easy to deploy and develop. The code has been released at https://github.com/yun-liu/MiniSeg.

Antimicrobial peptides (AMPs) are short peptides that play crucial roles in diverse biological processes and have various functional activities against target organisms. Due to the abuse of chemical antibiotics and microbial pathogens' increasing resistance to antibiotics, AMPs have the potential to be alternatives to antibiotics. As such, the identification of AMPs has become a widely discussed topic. A variety of computational approaches have been developed to identify AMPs based on machine learning algorithms. However, most of them are not capable of predicting the functional activities of AMPs, and those predictors that can specify activities only focus on a few of them. In this study, we first surveyed 10 predictors that can identify AMPs and their functional activities in terms of the features they employed and the algorithms they utilized. Then, we constructed comprehensive AMP datasets and proposed a new deep learning-based framework, iAMPCN (identification of AMPs based on CNNs), to identify AMPs and their related 22 functional activities. Our experiments demonstrate that iAMPCN significantly improved the prediction performance of AMPs and their corresponding functional activities based on four types of sequence features. Benchmarking experiments on the independent test datasets showed that iAMPCN outperformed a number of state-of-the-art approaches for predicting AMPs and their functional activities. Furthermore, we analyzed the amino acid preferences of different AMP activities and evaluated the model on datasets of varying sequence redundancy thresholds. To facilitate the community-wide identification of AMPs and their corresponding functional types, we have made the source codes of iAMPCN publicly available at https://github.com/joy50706/iAMPCN/tree/master. We anticipate that iAMPCN can be explored as a valuable tool for identifying potential AMPs with specific functional activities for further experimental validation.

Camouflaged object detection (COD) involves segmenting objects that share similar patterns, such as color and texture, with their surroundings. Current methods typically employ multiple well-designed modules or rely on edge cues to learn object feature representations for COD. However, these methods still struggle to capture the discriminative semantics between camouflaged objects (foreground) and background, possibly generating blurry prediction maps. To address these limitations, we propose a novel mask-and-edge co-guided separable network (MECS-Net) for COD that leverages both edge and mask cues to learn more discriminative representations and improve detection performance. Specifically, we design a mask-and-edge co-guided separable attention (MECSA) module, which consists of three flows for separately capturing edge, foreground, and background semantics. In addition, we propose a multi-scale enhancement fusion (MEF) module to aggregate multi-scale features of objects. The predictions are decoded in a top-down manner. Extensive experiments and visualizations demonstrate that our CNN-based and Transformer-based MECS-Net outperform 13 state-of-the-art methods on four popular COD datasets. Codes and results are availablehttps://github.com/TomorrowJW/MECS-Net-COD$\ast$.

Robust speaker verification (RSV) under noisy con- ditions is still a challenging task. Recently, some task-specific speech enhancement (SE) approaches are proposed and achieve excellent performance on RSV. However, all these works adopt only one kind of SE network and thus can not remove noise from different aspects, limiting the performance of the RSV task. In this letter, we propose a fused SE framework (FSEF) for RSV, which integrates both T-F masking-based and feature mapping- based SE networks to collect complementary information and improve the robustness against noise. Two FESF-RSV systems are constructed based on two kinds of fusion methods: score fusion and feature fusion. In addition, we present a Multi- Scale Attentive Context Aggregation Network (MSACAN) as the backbone structure in the FSEF. The MSACAN can not only extract and fuse multi-scale features adaptively but also enhance speaker characteristics against noise and interfering speakers. Experiments conducted on the noise-simulated VoxCeleb1 dataset demonstrate both the FSEF and the MSACAN can improve the performance of RSV compared to previous approaches.

Recent progress in salient object detection (SOD) mainly depends on the Atrous Spatial Pyramid Pooling (ASPP) module for multi-scale learning. Intuitively, different input images, different pixels, and different network layers may have different preferences for various feature scales. However, ASPP treats all feature scales as equally important by a simple sum operation. To this end, we propose Attentive Atrous Spatial Pyramid Pooling (A2SPP) by adding a new Cubic Information-Embedding Attention (CIEA) module at each branch of ASPP. In this way, each position in the 3D feature map can automatically learn the feature scales it prefers. Specifically, CIEA consists of Spatial-Embedding Channel Attention (SECA) and Channel-Embedding Spatial Attention (CESA). Instead of the previous direct squeeze and ignoring of one dimension when computing the attention for the other dimension, SECA/CESA attempts to embed spatial/channel information into channel/spatial attention, respectively. In addition, CIEA learns SECA and CESA for each 3D position simultaneously rather than previous separate computation of channel and spatial attention for each 2D position. Incorporating A2SPP and CIEA, the proposed A2SPPNet performs favorably against previous state-of-the-art SOD methods.

The crowd statistics technology has been widely applied to smart classroom, manual roll call and campus security in recent years. However, due to challenges like low resolution, shooting angels and partial overlapping of students in the classroom, it's extremely hard to estimate the number of students accurately. Inspired by the improvements of object detection models in image target classification and location, we implements a classroom crowd statistics system (CCSS) to provide statistical information on the number of students for the construction of the wisdom classroom. In addition, we introduce a new large-scale classroom dataset, which contains 3,070 images in the classroom environment and 106,304 student annotations. To the best of our knowledge, this is the first student counting dataset collected under the classroom settings, which will greatly promote the development of classroom crowd statistics based on deep learning. In order to further improve the accuracy and speed of students detecting, we also modify the YOLOv4 algorithm to make it more adaptive for this task. The experimental results show that our model gains a significant improvement over the selected baselines on the proposed dataset.

Multi-modal fusion aims to capture the semantic interactions between different modalities for many downstream classification tasks. However, previous work usually considers that each modality contributes equal information to the final classification and extracts the global features of each modality for fusion. In this paper, inspired by these two observations, we propose a generic Hierarchical Global-Local feature fusion Network (HGLNet) for multi-modal classification. Specifically, HGLNet has three merits compared to the current work. (1) HGLNet proposes a Global Gated Attention (GGA) module, which adaptively generates weights that represent the contributions of different modalities. (2) HGLNet presents a novel Cross Residual Transformer (CRT) module to capture the fine-grained local interactions. (3) HGLNet utilizes hierarchical information for multi-modal fusion. Extensive experiments on three public datasets demonstrate that HGLNet achieves competitive performance against the state-of-the-art methods for three kinds of multi-modal classification tasks.

The frequent usage of the activity and intent in Android app development makes activity launching communication the focus of app analysis, which inspires the proposal of Activity Launching Test (ALT). Existing static analysis approaches are limited in test case generation and crash triggering of ALT, due to their path-insensitive nature and insufficient intent attribute exploration. This work proposes DALT, an activity test frame-work for launching-related bug detection, which empowers an inter-procedural, context-, flow- and path-sensitive static analysis to generate proper intents as test cases. By tailoring symbolic execution for intent propagation, DALT is able to explore statements in deep code position and extract conditional constraints in diverse launching-related execution paths. Consequently, invalid test paths are substantially reduced via the guidance of the extracted constraints. DALT also supports significantly more intent attribute types and value types of attributes, by reformatting them to be compatible with the commonly used constraint solvers. Extensive comparison experiments have been conducted from diverse validation dimensions. The results demonstrate that compared to the state-of-the-art approach, DALT is more effective in successfully launching activities and detecting bugs hiding in deep positions of the program paths.

Conventional supervised binary classification algorithms have been widely applied to address significant research questions using biological and biomedical data. This classification scheme requires two fully labeled classes of data (e.g. positive and negative samples) to train a classification model. However, in many bioinformatics applications, labeling data is laborious, and the negative samples might be potentially mislabeled due to the limited sensitivity of the experimental equipment. The positive unlabeled (PU) learning scheme was therefore proposed to enable the classifier to learn directly from limited positive samples and a large number of unlabeled samples (i.e. a mixture of positive or negative samples). To date, several PU learning algorithms have been developed to address various biological questions, such as sequence identification, functional site characterization and interaction prediction. In this paper, we revisit a collection of 29 state-of-the-art PU learning bioinformatic applications to address various biological questions. Various important aspects are extensively discussed, including PU learning methodology, biological application, classifier design and evaluation strategy. We also comment on the existing issues of PU learning and offer our perspectives for the future development of PU learning applications. We anticipate that our work serves as an instrumental guideline for a better understanding of the PU learning framework in bioinformatics and further developing next-generation PU learning frameworks for critical biological applications.

Protein secretion has a pivotal role in many biological processes and is particularly important for intercellular communication, from the cytoplasm to the host or external environment. Gram-positive bacteria can secrete proteins through multiple secretion pathways. The non-classical secretion pathway has recently received increasing attention among these secretion pathways, but its exact mechanism remains unclear. Non-classical secreted proteins (NCSPs) are a class of secreted proteins lacking signal peptides and motifs. Several NCSP predictors have been proposed to identify NCSPs and most of them employed the whole amino acid sequence of NCSPs to construct the model. However, the sequence length of different proteins varies greatly. In addition, not all regions of the protein are equally important and some local regions are not relevant to the secretion. The functional regions of the protein, particularly in the N- and C-terminal regions, contain important determinants for secretion. In this study, we propose a new hybrid deep learning-based framework, referred to as ASPIRER, which improves the prediction of NCSPs from amino acid sequences. More specifically, it combines a whole sequence-based XGBoost model and an N-terminal sequence-based convolutional neural network model; 5-fold cross-validation and independent tests demonstrate that ASPIRER achieves superior performance than existing state-of-the-art approaches. The source code and curated datasets of ASPIRER are publicly available at https://github.com/yanwu20/ASPIRER/. ASPIRER is anticipated to be a useful tool for improved prediction of novel putative NCSPs from sequences information and prioritization of candidate proteins for follow-up experimental validation.

Salient object detection (SOD) aims to detect the most prominent objects and regions in the human vision. Since the RGB and depth modalities contain discrepant characteristics and convey the clues of different domains, how to explore the fusion of multi-modal information and the interaction of cross-stage features remain the key problems in RGB-D SOD. In this letter, we propose a cross-stage multi-scale interaction network (CMINet), consisting of a multi-scale spatial pooling (MSP) module and a cross-stage pyramid interaction (CPI) module to interweave the feature maps of different stages in a bottom-up and top-down way. In addition, we also design an adaptive weight fusion (AWF) module to weigh the importance of multimodality features and fuse them. Extensive experiments are conducted on 4 widely used datasets to validate the effectiveness of the proposed CMINet. The results demonstrate that our approach achieves state-of-the-art performance against other 11 methods under 4 evaluation metrics.

RGB-D Salient Object Detection (RGB-D SOD) aims at detecting remarkable objects by complementary information from RGB images and depth cues. Although many outstanding prior arts have been proposed for RGB-D SOD, most of them focus on performance enhancement, while lacking concern about practical deployment on mobile devices. In this paper, we propose mobile asymmetric dual-stream networks (MoADNet) for real-time and lightweight RGB-D SOD. First, inspired by the intrinsic discrepancy between RGB and depth modalities, we observe that depth maps can be represented by fewer channels than RGB images. Thus, we design asymmetric dual-stream encoders based on MobileNetV3. Second, we develop an inverted bottleneck cross-modality fusion (IBCMF) module to fuse multimodality features, which adopts an inverted bottleneck structure to compensate for the information loss in the lightweight backbones. Third, we present an adaptive atrous spatial pyramid (A2SP) module to speed up the inference, while maintaining the performance by appropriately selecting multiscale features in the decoder. Extensive experiments are conducted to compare our method with 15 state-of-the-art approaches. Our MoADNet obtains competitive results on five benchmark datasets under four evaluation metrics. For efficiency analysis, the proposed method significantly outperforms other baselines by a large margin. The MoADNet only contains 5.03 M parameters and runs 80 FPS when testing a$256\times 256$image on a single NVIDIA 2080Ti GPU.

The rapid spread of the new pandemic, i.e., COVID-19, has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected CT area segmentation, has attracted much attention. However, the publicly available COVID-19 training data are limited, easily causing overfitting for traditional deep learning methods that are usually data-hungry with millions of parameters. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive. To address the above problems, we propose MiniSeg, a lightweight deep learning model for efficient COVID-19 segmentation. Compared with traditional segmentation methods, MiniSeg has several significant strengths: i) it only has 83K parameters and is thus not easy to overfit; ii) it has high computational efficiency and is thus convenient for practical deployment; iii) it can be fast retrained by other users using their private COVID-19 data for further improving performance. In addition, we build a comprehensive COVID-19 segmentation benchmark for comparing MiniSeg to traditional methods.

The object-based video forgery detection aims to expose tampered regions from video sequences without any codec information. However, existing methods mainly focus on manually selected features and models for a specific task, either splicing or copy-move, while the general representation ability of deep learning models and the correlation of different forensic features have not been fully explored. In this paper, we propose a dual-stream framework to jointly discover and integrate effective features for object-based video forgery detection. First, two different types of branches are employed to extract discriminative features. Then, after the dual-stream feature fusion, a Conditional Random Field (CRF) layer is utilized to further refine segmentation results. Finally, we consider temporal consistency by incorporating the video tracking strategy. Extensive experiments on four datasets show that the proposed method achieves competitive performance against the state-of-the-art methods.

Antimicrobial peptides (AMPs) are a unique and diverse group of molecules that play a crucial role in a myriad of biological processes and cellular functions. AMP-related studies have become increasingly popular in recent years due to antimicrobial resistance, which is becoming an emerging global concern. Systematic experimental identification of AMPs faces many difficulties due to the limitations of current methods. Given its significance, more than 30 computational methods have been developed for accurate prediction of AMPs. These approaches show high diversity in their data set size, data quality, core algorithms, feature extraction, feature selection techniques and evaluation strategies. Here, we provide a comprehensive survey on a variety of current approaches for AMP identification and point at the differences between these methods. In addition, we evaluate the predictive performance of the surveyed tools based on an independent test data set containing 1536 AMPs and 1536 non-AMPs. Furthermore, we construct six validation data sets based on six different common AMP databases and compare different computational methods based on these data sets. The results indicate that amPEPpy achieves the best predictive performance and outperforms the other compared methods. As the predictive performances are affected by the different data sets used by different methods, we additionally perform the 5-fold cross-validation test to benchmark different traditional machine learning methods on the same data set. These cross-validation results indicate that random forest, support vector machine and eXtreme Gradient Boosting achieve comparatively better performances than other machine learning methods and are often the algorithms of choice of multiple AMP prediction tools.

Convolutional neural network (CNN) has been successfully used for the identification of motif occupancy. However, the CNN architecture requires varying length instead of fixed-length filters due to different motif lengths. Moreover, plain neural networks with single point estimation for weights suffer from over-fitting, which is more likely to occur as increasing parameters for multi-scale modeling.Hence, we have designed a Bayesian Multi-scale CNN. The model employs convolutional filters of different scales to extract latent features of DNA sequence, and incorporates Bayesian architecture which regards multi-scale weights as random variables. We further stack two sequential convolutional operations for mean and variance respectively, and apply Bayes by Back prop for posterior estimation of weights. Results have shown that our method not only improved the prediction performance for motif occupancy identification, but also prevented over-fitting due to the capability of Bayesian neural network. The model has also developed a measure of uncertainty estimation for model assessment.

MOTIVATION: Carbohydrate-active enzymes (CAZymes) are extremely important to bioenergy, human gut microbiome, and plant pathogen researches and industries. Here we developed a new amino acid k-mer-based CAZyme classification, motif identification and genome annotation tool using a bipartite network algorithm. Using this tool, we classified 390 CAZyme families into thousands of subfamilies each with distinguishing k-mer peptides. These k-mers represented the characteristic motifs (in the form of a collection of conserved short peptides) of each subfamily, and thus were further used to annotate new genomes for CAZymes. This idea was also generalized to extract characteristic k-mer peptides for all the Swiss-Prot enzymes classified by the EC (enzyme commission) numbers and applied to enzyme EC prediction. RESULTS: This new tool was implemented as a Python package named eCAMI. Benchmark analysis of eCAMI against the state-of-the-art tools on CAZyme and enzyme EC datasets found that: (i) eCAMI has the best performance in terms of accuracy and memory use for CAZyme and enzyme EC classification and annotation; (ii) the k-mer-based tools (including PPR-Hotpep, CUPP and eCAMI) perform better than homology-based tools and deep-learning tools in enzyme EC prediction. Lastly, we confirmed that the k-mer-based tools have the unique ability to identify the characteristic k-mer peptides in the predicted enzymes. AVAILABILITY AND IMPLEMENTATION: https://github.com/yinlabniu/eCAMI and https://github.com/zhanglabNKU/eCAMI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Permission mechanisms serve as the main measure to protect users privacy and security in Android applications. Modern smartphone operating systems (Android 6.0 and later versions) prompt users to regulate permissions using ask-on-first-use policy. Much research has been done to dynamically regulate permissions depending on user preferences and contexts in modern operation systems. However, all these techniques have limitations-they heavily rely on users' current or historical decisions on granting permissions, ignoring the fact that users are not experts on privacy protection, i.e., whether a permission shall be granted. In this work, we propose a system to automatically recommend runtime-permission to users. The main idea behind is that the application descriptions reflecting functional information can be used to analyze whether a permission is needed by the application. In more details, using description mining, we extract multiple topics and build a topic-permission mapper. Given an application as input, we first decide which topics it belongs to and then recommend the permissions according to the topic-permission mapper. As the output, besides binary recommendation of "allow" or "deny" recommendations, we provide explanations for the recommendations to uncover the reason for users. We implemented our approach in a tool- AutoPer, and evaluated the approach using 28,850 Android applications from Google Play. The experiments show that our approach achieves a fairly good performance with an accuracy of 81.0%, which demonstrates the effectiveness of AutoPer for permission recommendation.

Previous work on learning representation for patients from Electronic Health Records (EHRs) has succeeded in assisting medical diagnosis. Three perspectives of records, patient symptoms, medical treatments and diagnosis codes, are consisted in EHRs. However, existing approaches on patient representation learning take one perspective of patient symptoms and medical treatments into consideration, which miss out the latent correlations between them. Actually, based on the sequence of hospital visits, physical symptoms and associated treatments together affect the diagnosis and recovery of patients. In this paper, we propose Patient2vec, a novel model to learn the bi-dimensional representation for patients by jointly extracting features from physical symptoms and medical treatments. We introduce RNN model into Patient2vec to learn the sequential context-aware features of visits. The learned representations are then fed into a classifier to diagnosis prediction. Experiments on public dataset through multi-classification tasks indicate that Patient2vec achieves up to 76% improvement in area under the ROC curve (AUC) on average, demonstrating that our method significantly outperforms single dimension representation for patients.

It is widely accepted that the top sides of neural networks convey high-level semantic features and the bottom sides contain low-level details. Therefore, most of recent salient object detection models aim at designing effective fusion strategies for the side-output features of convolutional neural networks (CNNs). Although significant progress has been achieved in this direction, the network architectures become more and more complex, which will make the future improvement difficult and heavily engineered. Moreover, the manually designed fusion strategies would be sub-optimal due to the large search space of possible solutions. To address above problems, we propose an Automatic Top-Down Fusion (ATDF) model, in which the global information at the top sides are flowed into bottom sides to guide the learning of low layers. We design a novel module at each side to control the information flowed into a specific side, called valve module, by which each side is expected to receive the necessary top information. We perform extensive experiments to demonstrate that ATDF is simple yet effective and thus opens a new path for saliency detection. Code is available at https://github.com/yun-liu/ATDF.

Recommendation service in mobile app markets decently helps users choose their preferred apps. Though a lot of recommendation service models are proposed in recent years, it is still challenging to tackle extreme sparse app data and get a relatively satisfactory recommendation performance. The reason can be concluded as that traditional recommendation models either focus on limited features or stand aside from deep training. In this paper, we propose knowledge-based deep factorization machine (KDFM), a recommendation model inspired by techniques of factorization machine and attentive deep learning, and apply it in the recommendation service for mobile apps. The KDFM aims to make full use of the rich categorical and textual knowledge in the app market for better performance. To achieve this goal, a topical attention representation component, which contains three typical parts (Word2Vec, BiLSTM and Topical Attention), is constructed. Such representation not only avoids the dimension explosion brought by traditional models, but also preserves the textual semantics for better recommendation. Through extensive experiments conducted on a large number of collected app samples, the KDFM achieves better performance compared with state-of-art rating recommendation models in terms of the rating prediction. In addition, the benefits brought by the usage of attention mechanism and topical representation are confirmed through the comparison experiments.

Review-Based Software Improvement (RBSI for short) has drawn increasing research attentions in recent years. Relevant efforts focus on how to leverage the underlying information within reviews to obtain a better guidance for further updating. However, few efforts consider the Projects Without sufficient Reviews (PWR for short). Actually, PWR dominates the software projects, and the lack of PWR-based RBSI research severely blocks the improvement of certain software. In this paper, we make the first attempt to pave the road. Our goal is to establish a generic framework for sharing suitable and informative reviews to arbitrary PWR. To achieve this goal, we exploit techniques of code clone detection and review ranking. In order to improve the sharing precision, we introduce Convolutional Neural Network (CNN) into our clone detection, and design a novel CNN based clone searching module for our sharing system. Meanwhile, we adopt a heuristic filtering strategy to reduce the sharing time cost. We implement a prototype review sharing system RSharer and collect 72,440 code-review pairs as our ground knowledge. Empirical experiments on hundreds of real code fragments verify the effectiveness of RSharer. RSharer also achieves positive response and evaluation by expert developers.

Review-based software development has become increasingly prevalent in recent years. Existing efforts aiming at either informative evaluation or sentiment analysis are mainly from the perspective of the reviewers, while neglecting the attitude and behavior of the developers. Such efforts inevitably suffer from recommendation bias in practice, and thus benefit little for the improvement of user reviews.In this paper, we attempt to bridge the gap between user review and developer reply, and conduct a systematic study for review reply in development forums, especially in Chinese mobile system forums. To this end, we concentrate on three research questions: 1) should a targeted review be replied; 2) how long time it should be replied; 3) does traditional review analysis help to pursue a reply for certain review? To answer such questions, given certain review datasets, we perform a systematical study including the following three stages: 1) a binary classification for reply behavior prediction, 2) a regression for prediction of reply time, 3) a systematic factor study for the relationship between traditional review analysis and reply performance. To enhance the accuracy of prediction and analysis, we proposed a CNN-based weak-supervision analysis framework, which exploits manifold techniques from NLP and deep learning. We validate our approach via extensive comparison experiments. The results show that our analysis framework is effective. More importantly, we have uncovered several interesting findings, which provide valuable guidance for further review improvement and recommendation.

BACKGROUND: Antibiotic resistance has become an increasingly serious problem in the past decades. As an alternative choice, antimicrobial peptides (AMPs) have attracted lots of attention. To identify new AMPs, machine learning methods have been commonly used. More recently, some deep learning methods have also been applied to this problem. RESULTS: In this paper, we designed a deep learning model to identify AMP sequences. We employed the embedding layer and the multi-scale convolutional network in our model. The multi-scale convolutional network, which contains multiple convolutional layers of varying filter lengths, could utilize all latent features captured by the multiple convolutional layers. To further improve the performance, we also incorporated additional information into the designed model and proposed a fusion model. Results showed that our model outperforms the state-of-the-art models on two AMP datasets and the Antimicrobial Peptide Database (APD)3 benchmark dataset. The fusion model also outperforms the state-of-the-art model on an anti-inflammatory peptides (AIPs) dataset at the accuracy. CONCLUSIONS: Multi-scale convolutional network is a novel addition to existing deep neural network (DNN) models. The proposed DNN model and the modified fusion model outperform the state-of-the-art models for new AMP discovery. The source code and data are available at https://github.com/zhanglabNKU/APIN.

Android defect prediction has proved to be useful to reduce the manual testing effort for finding bugs. In recent years, researchers design metrics related to defects and analyze historical information to predict whether files contain defects using machine learning. However, those models learn to predict defects based on the characteristics of programs while ignoring the internal information, e.g., the functional and semantic information within the source code. This paper proposes a model, HIRER, to learn the functional and semantic information to predict whether files contain defects automatically for Android applications. Specifically, HIRER learns internal information within the source code based on the high-frequency keywords extracted from programs' Abstract Syntax Trees (ASTs). It gets rule-based programming patterns from high-frequency keywords and uses Deep Belief Network (DBN), a deep neutral network, to learn functional and semantic features from the programming patterns. We implement a defect testing system with five machine learning techniques based on HIRER to predict defective files in source code automatically. Then, we apply it on four open source Android applications. The results show that learned functional and semantic features can predict more defects than traditional metrics. In different versions of MMS, Gallery2, Bluetooth, Calendar open source applications, HIRER improves the AUC of the predicted results respectively in average.

Access control is a significant strategy to protect security and privacy. Due to electronization of health information, medical access control attracts lots of attention in the research community. The existing medical access control approaches mainly focus on doctors' roles and behaviors, such as role-based access control (RBAC) and risk-based access control. However, various therapeutic regimens can also lead to unauthorized access. The current researches do not consider access control authorization in terms of therapeutic regimens. In this work, we present an access control model based on therapeutic regimen. Our model, TRAC, proposes an access strategy by analyzing feasibility of therapeutic regimens. Our experiments show the effectiveness of TRAC in terms of precision. Moreover, our model also contributes to choosing better therapeutic regimens for patients.

One of the major software safety issues is memory leak. Moreover, detecting memory leak vulnerabilities is challenging in static analysis. Existing static detection tools find bugs by collecting programs' information in the process of scanning source code. However, the current detection tools are weak in efficiency and accuracy, especially when the targeted program contains complex branches. This paper proposes a projection-based approach to detect memory leaks in C source code with complex control flows. According to the features of memory allocation and deallocation in C source code, this approach projects the original control flow graph of a program to a simpler one, and it reduces the analysis complexity. Besides, this paper implements a memory-leak detection tool-PML_Checker, and evaluates the tool by comparing with three open-source static detection tools on both public benchmarks and study test cases. The experimental results show that PML_Checker reports the most memory leak vulnerabilities among the four existing tools with complex control flows and complex data types, and PML_Checker obtains higher efficiency and accuracy on public benchmarks.

Due to the increasing complexity of web and client application's structure, security problem has become more and more critical. Among all the threats reported, SQL Injection Attacks (SQLIAs) have always been top-ranked in recent years, and network logs, which are very important for the detection of SQLIA, are often utilized to analyze the user's attacking behaviors. However, the collection of network logs is often compromised due to the growing complexity of network structure, leading to a great challenge to the log-based SQLIA detection. In view of this, this paper proposes a novel approach to the detection of SQLIA based on log analyzing with Hidden Markov Model (HMM), combined with statistical characteristic and feature matching. At first, we build browsing behavior models of attackers and legal users. Furthermore, we use HMM to restore user's browsing procedure from the customised user logs. Finally, the method detects SQLIAs by analyzing the behavior of users in reality, without requiring sensitive information submitted by users. Our experiments show that the proposed method can detect possible SQLIAs and identify malicious users effectively, and has higher accuracy in comparison with the Kmeans method.

SQL Injection Vulnerability (SQLIV) has been the top-ranked threat to the Web security consistently for many years. Penetration tests, which are a most widely adopted technique to detect SQLIV, are usually affected by testing inaccuracy. This problem is even worse in inferencebased, blind penetration tests for online Web sites, where Web page variations (such as those caused by inbuilt dynamic modules or user interactions) may lead to a large number of False Positives (FP). We present a novel approach called Inferential Metamorphic Testing (IMT) to reduce FP in SQLIV penetration tests. First, we define the notion of Inferential Metamorphic Relations (IMR), which is inherited from Mutational Metamorphic Testing (MMT). Second, we present a set of logic operators and mutation operators for generating IMR and deducting the background testing context. Finally, we present an iterative IMT process, which is based on the heuristic IMR generation and the background testing context deduction. Our empirical study demonstrates the effectiveness of our approach by a comparison to three famous SQLIV penetration test tools.

Extract Method is a widely used refactoring operation to improve method comprehension and maintenance. Much research has been done to extract codefragments within the method body to form a new method. Criteria used for identifying extractable code is usually centered around degrees of cohesiveness, coupling and length of the method. However, automatic method extraction techniques have not been highly successful, since it can be hard to concretizethe criteria. In this work, we present a novel system that learns these criteria for Extract Method refactorings from open source repositories. We extractstructural and functional features, which encode the concepts of complexity, cohesion and coupling in our learning model, and train it to extract suitablecode fragments from a given source of a method. Our tool, GEMS, recommends a ranked list of code fragments with high accuracy and greatspeed. We evaluated our approach on several open source repositories and compared it against three state-of-the-art approaches-SEMI, JExtract andJDeodorant. The results on these open-source data show the superiority of our machine-learning-based approach in terms of effectiveness. We develop GEMS asan Eclipse plugin, with the intention to support software reliability through method extraction.

Among all the Web application security issues, SQL Injection Vulnerability (SQLIV) is one of the most serious problems. How to test SQLIV effectively is of great importance. To address this issue, this paper describes a novel approach that is the utilization of Feature Matrix (FM) model for SQLIV black-box penetration test. Firstly, FM is introduced, which integrates the general SQLIV penetration test features for SQLIV. Each row of the matrix is defined as a test pattern, named Global Test Pattern (GTP). Then, GTP Selection (GTPS) process is used to select legal GTPs for general SQLIV penetration test. Secondly, to find out the optimum FM during SQLIV penetration test procedure automatically, Dynamic Matrix Selection (DMS) algorithm is described, which is based on dynamic tree pruning. Finally, a prototype tool SQLEXP is developed, the experiments of which are carried out under the context of two target Web applications and about 30000 real Internet URLs. The results show that the proposed approach can effectively improve the testing effect for SQLIV penetration test compared with two benchmarking testing tools.

Access control is an extremely important and error-prone practice during web application. The emergence of NoSQL databases and the flexible data models they bring impose new challenges on the implementation of access control within web applications. This paper presents Scout, a novel methodology for discovering access control vulnerabilities in existing web applications. Meanwhile (1) features of NoSQL database can be addressed and (2) neither application source code nor server-side session information from the developers is required. This paper implements a prototype of Scout, which targets MongoDB backend web applications. By automatically discovering the protocol layer in the web application stack, Scout introduces a data access operation model precisely representing the MongoDB actions performed in the web application, as well as inferring the access control policies. The prototype is shown to be able to identify comprehensive access control vulnerabilities in MongoDB backend web applications, and generate detailed report as the facilitator to manually fix the identified vulnerabilities.

The heavy use of event-callback mechanism in frameworks like Android causes challenges for static analysis. Modelling of callback mechanisms for Android applications (app for short) is becoming a major method to address such challenges. In this work, we aim to construct a generic callback-related model that supports path-sensitive analysis. We consider three unresolved challenges in the existing modelling approaches: 1) building connections between different components; 2) identifying path-sensitive conditions; 3) handling the system-driven callbacks and fine-grained lifecycle callbacks. We propose algorithms for constructing a generic path-sensitive callback model and present a prototype model constructor, AndroChecker, to validate our approach. We evaluate 20 real-world apps using AndroChecker. The evaluation result shows that our method and tool have a strong capability in modelling path conditions and inter-component invocations.

For trust in software, developers spend much effort debugging to ensure that software behaviors as expected. Spectrum-based fault localization techniques (SFL) make use of runtime coverage of program elements, like statements, branches and du-pairs, and then check codes in the order of the rank of suspiciousness. So, correct elements with higher suspiciousness than faulty elements cause the loss of precision. In this paper, we focus on a situation where suspiciousness calculated according to coverage and outcome, i.e. Successful or failing, is higher than it should be. It is found that when a branch structure is repeatedly executed, which is normal in real-life programs, and all of its branches are covered within a run, a branch related to faults could lead other branches to be doubted. To reduce effects between branches, we do the following things: First, we utilize branches to monitor program behaviors, second, we take test cases with high similarities as triggered by the same fault, third, for branches mentioned, we propose an algorithm to infer which branch is more likely to be faulty in the failure, finally, experiments based on Siemens benchmark set and flex show that our approach is useful to heighten the ranking of faulty elements by reducing suspiciousness of correct branches.

SQL Injection Vulnerability (SQLIV) is one of the topmost serious threats to web applications. Penetration test is one of the most important approaches to detect SQLIV. The test case generation issue critically affects the effectiveness of penetration test. Thus, research on the approaches to improve coverage and efficiency of test case generation process in SQLIV penetration test is of great importance. This paper proposes a formalized SQLIV test case generation model. i) We propose Global Test Rule (GTR), which is used to generate test cases in the process of SQLIV detection. ii) We present SQL injection vulnerability Test Matrix (SQLTM) model, which is a three dimensional matrix, to generate the set of GTR. iii) Based on the GTR generated by the above steps, we propose a Multiple Phases Detection Approach (MPDA) to implement the dynamic generation of test cases and detection procedure control, and then we give its algorithms in detail. Experiment results show that our approach can improve the coverage, precision and efficiency of SQLIV detection by a comparison with two real products for enterprise projects.

Internet-scale software becomes an important mode of constructing software systems with the development of internet. Open, dynamic and uncontrollable Internet environment makes dependability evaluation of Internet-scale software very important. It is lack of a dependability evaluation model that analyzes system architecture from the most foundational elements and integrate aspects that impacts on the system, such as the technical, organizational, decisional and human aspects. This paper proposes an evaluation model of dependability for Internet-scale software on the basis of Bayesian Networks. The model analyzes the structure of Internet-scale software and establishes an evaluation system of dependability for Internet-scale software including static metrics, dynamic metrics, prior metrics and correction metrics. It integrates subjective and objective factors which impact on system quality. In this paper, we build Bayesian Network according to the structure analysis and refer to a bottom-up method that use Bayesian reasoning to analyses and calculate entity dependability and integration dependability layer by layer. A unified dependability of the whole system is worked out and is corrected by objective data. The analysis of experiment in a real system proves that the model in this paper is capable of evaluating the dependability of Internet-scale software clearly and objectively. Moreover, it offers effective help to the design, development, deployment and assessment of Internet-scale software.

Binarization of natural images is important for text location and content-based analysis. In this work, a new adaptive method is introduced. It is able to improve the binarization results on the degraded images, such as the complex background, the non-uniform illumination, the variations of text font, size, color, and line orientation. The presented method contains three main stages. Firstly, original threshold of each pixel is calculated to produce some candidate blocks. Secondly, the new inter- and intra-block features are extracted from the candidates based on the characteristics of text. Finally, each block is scored from 0 to s using the mentioned features. The blocks with low scores are considered as subcomponents of background. After extensive experiments, our method demonstrated superior performance against two well-known techniques on the ICDAR 2005 competition dataset.

A novel adaptive binarization method based on wavelet filter is proposed in this paper, which shows comparable performance to other similar methods and processes faster, so that it is more suitable for real-time processing and applicable for mobile devices. The proposed method is evaluated on complex scene images of ICDAR 2005 Robust Reading Competition, and experimental results provide a support for our work.

In this paper, we present a new tool, RL_Detector, which performs static analysis to detect resource leaks for C programs. The algorithm is inter-procedural and path-sensitive, and it is based on an underlying resource management property: the data flow from resource allocation point must reach resource deallocation point, otherwise the resource is leaked. For each resource, it symbolically executes the program to collect the constraints of all the paths and recorded as some sets. Then the data flow condition can be computed through these sets of all the paths. Finally, the resource leak detection is reduced to the satisfiability of DFC (the Data Flow Condition). It has been effective at detecting resource leak in the SPEC2000 benchmarks and in an open source software project, the actual test results show that the tool keeps the false positive rate below 10% and works on millions of lines of code in a matter of minutes.