Task In Applications Research Articles

Structural entropy minimization combining graph representation for money laundering dentification

AbstractMoney laundering identification (MLI) is a challenging task for financial AI research and application due to its massive transaction volume, label sparseness, and label bias. Most of the existing MLI methods focus on individual-level abnormal behavior while neglecting the community factor that money laundering is a collaborative group crime. Furthermore, the massive volume of transactions and the issue of label shifting also impede the application of supervised or semi-supervised models. To this end, this paper proposes an efficient community-oriented algorithm, namely SEGE, to identify money laundering based on structural entropy minimization (SEM) with graph embedding in an unsupervised approach. Experiments on both a private real-world money laundering network and a public synthetic dataset show that our SEGE algorithm derives prominent performance and outperforms the parameterized learning-based graph representation methods. Moreover, we find that there are pervasive sub-communities in the real-world money laundering network. Based on our local algorithm, we propose a real combat strategy against the money laundering group, in which when we have several scattered suspicious accounts in the transaction network, we are able to retrieve the whole money laundering group by the union of sub-communities with both high precision and high recall rates.

Rotational Convolution Design in Convolutional Neural Networks for Direct 3D Electromagnetic Tomography

The three-dimensional (3D) reconstruction of Electromagnetic Tomography (EMT) is an important task for many applications, such as the non-destructive testing of inner defects in rail systems. Additionally, image reconstruction algorithms utilizing deep learning methods have been verified to be useful in recent years. Therefore, the interpretability of deep learning is a question that is relevant to its application in other areas. This paper proposes an innovative rotational convolution pattern, Conv-P, for convolutional neural network (CNN) image reconstruction in a 3D EMT system. This pattern is based on the projection relationships inherent in tomographic imaging, where each convolution is performed on adjacent projections along the excitation rotation direction. The advantage of this pattern is that it can generate the convolution process by utilizing the 3D structural information from real sensors. To verify the effectiveness of this convolution pattern, we constructed a 3D dual-layer 16-coil EMT model and tested its image reconstruction performance. The results demonstrate that, compared with two common convolution patterns, Conv-P achieves a 4.7% and 4.1% increase in the Image Correlation Coefficient (CC), a 19.8% and 13.1% reduction in the Relative Image Error (IE), a 0.67% and 1.59% increase in the Peak Signal-to-Noise Ratio (PSNR), and a 3.24% and 0.74% increase in the Structural Similarity Index Measure (SSIM).

Research on small sample target detection for underwater robot

Purpose The purpose of this paper is to propose a whole set of methods for underwater target detection, because most underwater objects have small samples, low quality underwater images problems such as detail loss, low contrast and color distortion, and verify the feasibility of the proposed methods through experiments. Design/methodology/approach The improved RGHS algorithm to enhance the original underwater target image is proposed, and then the YOLOv4 deep learning network for underwater small sample targets detection is improved based on the combination of traditional data expansion method and Mosaic algorithm, expanding the feature extraction capability with SPP (Spatial Pyramid Pooling) module after each feature extraction layer to extract richer feature information. Findings The experimental results, using the official dataset, reveal a 3.5% increase in average detection accuracy for three types of underwater biological targets compared to the traditional YOLOv4 algorithm. In underwater robot application testing, the proposed method achieves an impressive 94.73% average detection accuracy for the three types of underwater biological targets. Originality/value Underwater target detection is an important task for underwater robot application. However, most underwater targets have the characteristics of small samples, and the detection of small sample targets is a comprehensive problem because it is affected by the quality of underwater images. This paper provides a whole set of methods to solve the problems, which is of great significance to the application of underwater robot.

Partial and cost-minimized computation offloading in hybrid edge and cloud systems

Nowadays, numerous mobile devices (MDs) provide nearly anytime and anywhere services, running on top of various computation-intensive applications. However, bearing limited battery, bandwidth, computing, and storage resources, MDs cannot completely execute all tasks of such applications in real-time. Cloud data centers (CDCs) possess enormous resources and energy, which can help execute tasks offloaded from MDs. Nonetheless, CDCs reside in remote sites, thereby leading to long transmission latency. In recent years, small base stations (SBSs) have emerged to offer close proximity, high bandwidth, and low latency services to their nearby and limited MDs. However, it becomes a new challenge to minimize the total system cost in a complex and heterogeneous architecture. To address it, this work proposes an energy-minimized partial computation offloading technique. First, a limited optimization problem of cost minimization for the system is formulated. Afterward, an improved hybrid meta-heuristic algorithm is developed, which synergistically combines a Metropolis acceptance criterion of simulated annealing and genetic operations. One uniqueness of the proposed algorithm is that it simultaneously determines task allocation among MDs, an SBS, and a CDC, the transmission power of MDs, and bandwidth allocation of wireless channels between MDs and SBS. Experiments with real-life tasks from Google data centers have shown that the proposed Genetic Simulated-annealing-based Particle swarm optimization (GSP) significantly achieves lower system cost and faster convergence speed than benchmark peers.

Image convolution techniques integrated with YOLOv3 algorithm in motion object data filtering and detection.

In order to address the challenges of identifying, detecting, and tracking moving objects in video surveillance, this paper emphasizes image-based dynamic entity detection. It delves into the complexities of numerous moving objects, dense targets, and intricate backgrounds. Leveraging the You Only Look Once (YOLOv3) algorithm framework, this paper proposes improvements in image segmentation and data filtering to address these challenges. These enhancements form a novel multi-object detection algorithm based on an improved YOLOv3 framework, specifically designed for video applications. Experimental validation demonstrates the feasibility of this algorithm, with success rates exceeding 60% for videos such as "jogging", "subway", "video 1", and "video 2". Notably, the detection success rates for "jogging" and "video 1" consistently surpass 80%, indicating outstanding detection performance. Although the accuracy slightly decreases for "Bolt" and "Walking2", success rates still hover around 70%. Comparative analysis with other algorithms reveals that this method's tracking accuracy surpasses that of particle filters, Discriminative Scale Space Tracker (DSST), and Scale Adaptive Multiple Features (SAMF) algorithms, with an accuracy of 0.822. This indicates superior overall performance in target tracking. Therefore, the improved YOLOv3-based multi-object detection and tracking algorithm demonstrates robust filtering and detection capabilities in noise-resistant experiments, making it highly suitable for various detection tasks in practical applications. It can address inherent limitations such as missed detections, false positives, and imprecise localization. These improvements significantly enhance the efficiency and accuracy of target detection, providing valuable insights for researchers in the field of object detection, tracking, and recognition in video surveillance.

Robust and efficient FISTA-based method for moving object detection under background movements

Moving object detection is a fundamental task in many video processing applications, such as video surveillance. The robustness and efficiency of background subtraction make it one of the most common methods for detecting moving objects from a video stream. However, adapting background models with moving cameras remains challenging. Major issues include maintaining the model given viewpoint alterations and compensating motions considering depth variations. Moreover, gradual illumination changes, dynamic backgrounds, and complex motions intensify over time in moving camera scenarios, further complicating background model maintenance. In this context, this paper proposes a novel Robust and Online Tensor-based model named ROTAB that incorporates a more implicit consideration of the relationship between sequential frames than the previous methods, allowing for better adaptation to background changes. Moreover, we propose an Improved version of FISTA named IFISTA that employs two strategies to reduce oscillatory behavior and minimize iterations, improving stability and efficiency. Practically, the combination of IFISTA and ROTAB (IFISTA-ROTAB) demonstrates suitable performance for real-time applications. Quantitative and qualitative experiments are conducted on three large-scale datasets, namely CDnet 2014, BMC 2012 and LASIESTA showing the superiority of IFISTA-ROTAB with a gain from two up to seven percent in average.

Визуализация в задачах реконструкции данных

Many application tasks of multidimensional data analysis which describe the state of real physical or other systems face with difficulties. This is a consequence of the low-quality source data, including missing values, the probability of errors or unreliability of measurements. Incomplete data can become an obstacle for research using many modern informational methods. The current work examines the potential and capabilities of visual analytics tools for preliminary preparation, correction or complete analysis of primary data volumes. A promising area of application of the approach discussed in the study is the targeted use of visualization capabilities as a data analysis tool. The implementation of specialized visual metaphors is used to solve problems of processing and interpreting data, the sources of which are cyberphysical systems of different complexity levels. Such systems operate in an autonomous or partially controlled mode. A characteristic feature of these systems is the presence of a large number of sensors that collect various types of data. Such data differ in the capacity of the corresponding information channels, their speed and reliability. Examples of such cyberphysical systems are unmanned aerial vehicles (UAVs), robotic stations, and multimodal monitoring systems. These systems can function in conditions where it is difficult to obtain objective observation experience (deep-sea robots). The effective use of data collected by cyberphysical monitoring systems is a condition for solving a large number of application and research tasks.

Robotic Arm Trajectory Tracking Using Image Processing and Kinematic Equations

This study presents a novel approach for scanning and obtaining object contours within a workspace using a camera and subsequently following these 2-D contours to another region with the assistance of an end effector. The process begins with the determination of boundary lines of object images through advanced image processing methodologies. Subsequently, a conversion from camera pixel coordinates to robot metric coordinates is performed to facilitate trajectory planning for the robotic arm. The trajectory of the robot arm, and consequently, the path followed by the end effector, is determined based on these metric coordinates. The article provides a detailed exposition of the methodology, including the mathematical background and experimental study, showcasing the efficacy and accuracy of the proposed approach in real-world scenarios. This research contributes to the advancement of robotic systems capable of precise trajectory tracking and manipulation tasks in diverse applications.

Comparison of in-plane compression of additively manufactured Ti6Al4V 2D auxetic structures: Lattice design, manufacturing speed, and failure mode

The metal-based 2D auxetic lattice structures hold the potential for multifunctional tasks in aerospace applications. However, the compression response of those manufactured by powder bed fusion process is underexplored. This study proposes a comprehensive comparison of in-plane quasi-static compression performance of 2D auxetic lattice structures, utilizing three designs (anti-tetrachiral (ATC), double arrow-headed (DAH), and tree-like re-entrant (TLR)), manufactured with stiff Ti6Al4V by the electron beam powder bed fusion process (PBF-EB) with various manufacturing speeds. The results revealed unique failure patterns and superior energy absorptions among 2D lattice structures in the literature. TLR design enhanced energy absorption by overcoming failures between DAH columns and exhibited the lowest standard deviations in specific energy absorption (SEA) values (9.75 %–12.62 %). Besides, Kernel average misorientation (KAM) values followed the order of DAH, TLR, and ATC, and inversely correlated with SEA values. ATC structures with the lowest KAM outperformed DAH and TLR by 47.5 % and 6.44 %, respectively. Scan speed variations affected SEA and porosity values differently for each lattice design while exhibiting similar microstructure characteristics. The findings in this study propose a significant contribution to the development of aerospace sandwich structures where harsh environments exist and employment of 2D topologies are required.

Decoupling User Relationships Guides Information Diffusion Prediction (Student Abstract)

Information diffusion prediction is a critical task for many social network applications. However, current methods are mainly limited by the following aspects: user relationships behind resharing behaviors are complex and entangled. To address these issues, we propose MHGFormer, a novel multi-channel hypergraph transformer framework, to better decouple complex user relations and obtain fine-grained user representations. First, we employ designed triangular motifs to decouple user relations into three different level hypergraphs. Second, a position-aware hypergraph transformer is used to refine user relation and obtain high-quality user representations. Extensive experiments conducted on two social datasets demonstrate that MHGFormer outperforms state-of-the-art diffusion models across several settings.

Expressive Forecasting of 3D Whole-Body Human Motions

Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications. However, existing works typically concentrate on foretelling the major joints of the human body without considering the delicate movements of the human hands. In practical applications, hand gesture plays an important role in human communication with the real world, and expresses the primary intention of human beings. In this work, we are the first to formulate whole-body human pose forecasting task, which jointly predicts future both body and gesture activities. Correspondingly, we propose a novel Encoding-Alignment-Interaction (EAI) framework that aims to predict both coarse (body joints) and fine-grained (gestures) activities collaboratively, enabling expressive and cross-facilitated forecasting of 3D whole-body human motions. Specifically, our model involves two key constituents: cross-context alignment (XCA) and cross-context interaction (XCI). Considering the heterogeneous information within the whole-body, XCA aims to align the latent features of various human components, while XCI focuses on effectively capturing the context interaction among the human components. We conduct extensive experiments on a newly-introduced large-scale benchmark and achieve state-of-the-art performance. The code is public for research purposes at https://github.com/Dingpx/EAI.

VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning

Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (e.g., texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks. Our code is provided at the following repository: https://github.com/sugar-fly/VSFormer.

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering domains (e.g., software engineering and security) can be time-consuming and costly, without mentioning the domain gaps between training and inference data if the model needs to be applied to confidential datasets. In this paper, we study the task of seed-guided fine-grained entity typing in science and engineering domains, which takes the name and a few seed entities for each entity type as the only supervision and aims to classify new entity mentions into both seen and unseen types (i.e., those without seed entities). To solve this problem, we propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus using the contextualized representations of pre-trained language models. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types. Extensive experiments on two datasets covering four domains demonstrate the effectiveness of SEType in comparison with various baselines. Code and data are available at: https://github.com/yuzhimanhua/SEType.

THGFormer: Time-Aware Hypergraph Learning for Multimodal Social Media Popularity Prediction (Student Abstract)

Social media popularity prediction of multimodal user-generated content (UGC) is a crucial task for many real-world applications. However, existing efforts are often limited by missing inter-instance correlations and UGC temporal patterns. To address these issues, we propose a novel time-aware hypergraph Transformer framework, THGFormer. It fully represents inter-instance and intra-instance relations by hypergraphs, captures the temporal dependencies with a time encoder, and enhances UGC's representations via a neighborhood knowledge aggregation. Extensive experiments conducted on two real-world datasets demonstrate that THGFormer outperforms state-of-the-art popularity prediction models across several settings.

Framework for Agent-Based Multistage Application Partitioning Algorithm in Mobile Cloud Computing

The idea of computational offloading is quickly catching on in the world of mobile cloud computing (MCC). Today’s applications have heavy demands on power and computing resources, creating issues with energy consumption, storage capacity, and mobile device performance. Mobile devices may efficiently offload their calculations to cloud servers using the offloading paradigm and then get the processed results back onto the device. The investigation relates to identifying the specific application components that should be offloaded and run remotely and which parts are supposed to be treated locally. The applications need to be partitioned to differentiate between remote and local codes. In this paper, an agent-based multistage graph partitioning (ABMP) scheme is proposed. The framework of the scheme is based on three-tier architecture that includes mobile, cloudlet, and cloud for the execution of application tasks. The main goal is to provide an efficient partitioning and offloading scheme in the mobile cloud computing area. The results show that incorporating both agent-based multistage graph partitioning and offloading algorithms yields superior performance as compared to previous methods in terms of reducing execution costs and conserving battery life for mobile devices.

Maintaining the completion-time mechanism for Greening tasks scheduling on DVFS-enabled computing platforms

AbstractThe key factor in reducing the consumed energy when dependent-tasks applications are scheduled on DVFS-enabled computing platforms is task execution time slots. The unique and axiomatic approach to reduce the energy consumption on such platforms involves scaling down the execution frequency of each task within its execution time slot, provided a suitable scaling-down frequency is available. Regrettably, scheduling algorithms often shrink task execution time slots due to minimizing task completion times. This paper presents BlueMoon, a mechanism that reschedules the application tasks to extend the execution time slot of each task while ensuring that the overall completion time of the application tasks remains unaffected. BlueMoon is implemented and tested on numerous schedules of application graphs. The experimental results, conducted through computer simulations, demonstrate that BlueMoon substantially extends the execution time slots of tasks when compared to other mechanisms.

A two-stream conditional generative adversarial network for improving semantic predictions in urban driving scenes

Semantic segmentation is a well-studied topic and one of the most challenging tasks in computer vision applications, such as autonomous driving. Deep learning approaches based on convolutional neural networks (CNN) have demonstrated exceptional success on this task in recent years. Despite this success, existing approaches are plagued by higher-order inconsistencies between the ground truth images and the ones predicted by the segmentation model. This paper proposes a novel post-processing scheme based on adversarial learning to counter these inconsistencies. Such a scheme can be combined with a variety of existing CNN-based semantic segmentation networks to improve their segmentation performances. The proposed scheme is a Two-Stream Conditional Generative Adversarial Network (TScGAN), with one stream having initial semantic segmentation masks predicted by an existing CNN, while the other stream utilizes scene images to retain high-level information under a supervised residual network structure. In addition, TScGAN incorporates a novel dynamic weighting mechanism, which leads to significant and consistent gains in segmentation performance. Several comparative tests on public benchmark driving databases, including Cityscapes, Mapillary, and Berkeley DeepDrive100K, demonstrate the effectiveness of the proposed method when used with state-of-the-art CNN-based semantic segmentation models. Furthermore, the ablation experiment proved the structural rationality of our two-stream structure. The code for TScGAN could be found at https://github.com/epan-utbm/TScGAN-for-Improving-Semantic-Predictions

An adaptive fault detection model based on variational auto-encoders and unsupervised transfer learning

Aiming at the problem of insufficient generalization of fault detection in traditional machine learning, an SDN controller fault detection method based on unsupervised transfer learning is proposed. The method mainly includes two parts. (1) A Gaussian mixture variational autoencoder based on the autoregressive flow is proposed. First, the encoder and decoder of variational autocoding are improved with gated recurrent units, and the improved variational autocoding can process time series data. Secondly, the gated recurrent unit is improved by using the gravitational search algorithm, which speeds up the search of the weight of the gated recurrent unit. Further, considering that the latent space of the variational autoencoder is a single Gaussian distribution, and the complex data in reality is often too simple to be represented by a single Gaussian distribution. (2) Aiming at the problem of poor generalization of fault detection models in practical scenarios, a domain adaptive fault detection algorithm based on multi-kernel maximum mean difference and intra-class distance constraints is proposed. Map the features into the manifold space to eliminate the distortion of the features in the original space. After mapping, the distance between fields needs to be measured, and the maximum mean difference of a single kernel cannot determine which kernel function is more suitable for the current task in practical applications. Therefore, the maximum mean difference based on multi-core is introduced to measure between the two fields. The experimental results show that the algorithm proposed improves the accuracy about 5% compared with the previous algorithm.

Comprehensive Evaluation of 10 Docking Programs on a Diverse Set of Protein-Cyclic Peptide Complexes.

Cyclic peptides have emerged as a highly promising class of therapeutic molecules owing to their favorable pharmacokinetic properties, including stability and permeability. Currently, many clinically approved cyclic peptides are derived from natural products or their derivatives, and the development of molecular docking techniques for cyclic peptide discovery holds great promise for expanding the applications and potential of this class of molecules. Given the availability of numerous docking programs, there is a pressing need for a systematic evaluation of their performance, specifically on protein-cyclic peptide systems. In this study, we constructed an extensive benchmark data set called CPSet, consisting of 493 protein-cyclic peptide complexes. Based on this data set, we conducted a comprehensive evaluation of 10 docking programs, including Rosetta, AutoDock CrankPep, and eight protein-small molecule docking programs (i.e., AutoDock, AudoDock Vina, Glide, GOLD, LeDock, rDock, MOE, and Surflex). The evaluation encompassed the assessment of the sampling power, docking power, and scoring power of these programs. The results revealed that all of the tested protein-small molecule docking programs successfully sampled the binding conformations when using the crystal conformations as the initial structures. Among them, rDock exhibited outstanding performance, achieving a remarkable 94.3% top-100 sampling success rate. However, few programs achieved successful predictions of the binding conformations using tLEaP-generated conformations as the initial structures. Within this scheme, AutoDock CrankPep yielded the highest top-100 sampling success rate of 29.6%. Rosetta's scoring function outperformed the others in selecting optimal conformations, resulting in an impressive top-1 docking success rate of 87.6%. Nevertheless, all the tested scoring functions displayed limited performance in predicting binding affinity, with MOE@Affinity dG exhibiting the highest Pearson's correlation coefficient of 0.378. It is therefore suggested to use an appropriate combination of different docking programs for given tasks in real applications. We expect that this work will offer valuable insights into selecting the appropriate docking programs for protein-cyclic peptide complexes.

IWO-IGA—A Hybrid Whale Optimization Algorithm Featuring Improved Genetic Characteristics for Mapping Real-Time Applications onto 2D Network on Chip

Network on Chip (NoC) has emerged as a potential substitute for the communication model in modern computer systems with extensive integration. Among the numerous design challenges, application mapping on the NoC system poses one of the most complex and demanding optimization problems. In this research, we propose a hybrid improved whale optimization algorithm with enhanced genetic properties (IWOA-IGA) to optimally map real-time applications onto the 2D NoC Platform. The IWOA-IGA is a novel approach combining an improved whale optimization algorithm with the ability of a refined genetic algorithm to optimally map application tasks. A comprehensive comparison is performed between the proposed method and other state-of-the-art algorithms through rigorous analysis. The evaluation consists of real-time applications, benchmarks, and a collection of arbitrarily scaled and procedurally generated large-task graphs. The proposed IWOA-IGA indicates an average improvement in power reduction, improved energy consumption, and latency over state-of-the-art algorithms. Performance based on the Convergence Factor, which assesses the algorithm’s efficiency in achieving better convergence after running for a specific number of iterations over other efficiently developed techniques, is introduced in this research work. These results demonstrate the algorithm’s superior convergence performance when applied to real-world and synthetic task graphs. Our research findings spotlight the superior performance of hybrid improved whale optimization integrated with enhanced GA features, emphasizing its potential for application mapping in NoC-based systems.