Event cameras offer unparalleled advantages such as high temporal resolution, low latency, and high dynamic range. However, their limited spatial resolution poses challenges for fine-grained perception tasks. In this work, we propose an ultra-lightweight, stream-based event-to-event super-resolution method based on Spiking Neural Networks (SNNs), designed for real-time deployment on resource-constrained devices. To further reduce model size, we introduce a novel Dual-Forward Polarity-Split Event Encoding strategy that decouples positive and negative events into separate forward paths through a shared SNN. Furthermore, we propose a Learnable Spatio-temporal Polarity-aware Loss (LearnSTPLoss) that adaptively balances temporal, spatial, and polarity consistency using learnable uncertainty-based weights. Experimental results demonstrate that our method achieves competitive super-resolution performance on multiple datasets while significantly reducing model size and inference time. The lightweight design enables embedding the module into event cameras or using it as an efficient front-end preprocessing for downstream vision tasks.

Low-Light Image Enhancement (LLIE) remains a challenging task, particularly in preserving object edge continuity and fine structural details under extreme illumination degradation. In this paper, we propose a novel model, DRWKV (Detailed Receptance Weighted Key Value), which integrates our proposed Global Edge Retinex (GER) theory, enabling effective decoupling of illumination and edge structures for enhanced edge fidelity. Secondly, we introduce Evolving WKV Attention, a spiral-scanning mechanism that captures spatial edge continuity and models irregular structures more effectively. Thirdly, we design the Bilateral Spectrum Aligner Block (Bi-SAB) and a tailored MS2-Loss to jointly align luminance and chrominance features, improving visual naturalness and mitigating artifacts. Extensive experiments on five LLIE benchmarks demonstrate that DRWKV achieves leading performance in PSNR, SSIM, and NIQE while maintaining low computational complexity. Furthermore, DRWKV enhances downstream performance in low-light multi-object tracking tasks, validating its generalization capabilities. The code are available at: https://github.com/JackBaixue/DRWKV

Semantic segmentation of Earth Observation (EO) data has advanced significantly from multi-modal inputs, such as RGB imagery and the Digital Surface Model (DSM), which provides complementary contextual and structural information about ground objects. However, the joint use of RGB and DSM presents two distinct challenges: architectural redundancy , an efficiency concern, and cross-modal representational misalignment , a fusion-quality concern. To overcome these limitations, we propose AMMNet, an Asymmetric Multi-Modal Network designed for robust EO semantic segmentation through asymmetric designs tailored for RGB-DSM. The Asymmetric Dual Encoder (ADE) mitigates architectural redundancy by allocating representational capacity asymmetrically, employing a deeper encoder for RGB imagery to capture rich contextual cues and a lightweight encoder for DSM to extract sparse structural features. Asymmetric Prior Fuser (APF) introduces a modality-aware prior matrix into the fusion process, enabling structure-aware contextual representation and reducing cross-modal representational misalignment. Distribution Alignment (DA) module further enhances compatibility by maintaining task-relevant information. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that AMMNet attains superior segmentation performance with reduced computational and memory costs. Results validate the effectiveness of the proposed asymmetric multi-modal design in advancing EO semantic segmentation.

Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment methods like PSNR, SSIM, and LPIPS. However, these full-reference methods, which compare synthesized views to reference views, may not fully capture the perceptual quality of neurally synthesized scenes (NSS), particularly due to the limited availability of dense reference views. Furthermore, the challenges in acquiring human perceptual labels hinder the creation of extensive labeled datasets, risking model overfitting and reduced generalizability. To address these issues, we propose NVS-SQA, a NSS quality assessment method to learn no-reference quality representations through self-supervision without reliance on human labels. Traditional self-supervised learning predominantly relies on the "same instance, similar representation" assumption and extensive datasets. However, given that these conditions do not apply in NSS quality assessment, we employ heuristic cues and quality scores as learning objectives, along with a specialized contrastive pair preparation process to improve the effectiveness and efficiency of learning. The results show that NVS-SQA outperforms 17 no-reference methods by a large margin (i.e., on average 109.5% in SRCC, 98.6% in PLCC, and 91.5% in KRCC over the second best) and even exceeds 16 full-reference methods across all evaluation metrics (i.e., 22.9% in SRCC, 19.1% in PLCC, and 18.6% in KRCC over the second best).

Financial time-series forecasting is critical for maintaining economic stability, guiding informed policymaking, and promoting sustainable investment practices. However, it remains challenging due to various underlying pattern shifts. These shifts arise primarily from three sources: temporal non-stationarity (distribution changes over time), multi-domain diversity (distinct patterns across financial domains such as stocks, commodities, and futures), and varying temporal resolutions (patterns differing across per-second, hourly, daily, or weekly indicators). While recent deep learning methods attempt to address these complexities, they frequently suffer from overfitting and typically require extensive domain-specific fine-tuning. To overcome these limitations, we introduce FinCast, the first foundation model specifically designed for financial time-series forecasting, trained on large-scale financial datasets. Remarkably, FinCast exhibits robust zero-shot performance, effectively capturing diverse patterns without domain-specific fine-tuning. Comprehensive empirical and qualitative evaluations demonstrate that FinCast surpasses existing state-of-the-art methods, highlighting its strong generalization capabilities.

With the rapid development of Virtual Reality (VR) and haptic technology, their applications in education have demonstrated tremendous potential. However, traditional VR learning that incorporates haptic feedback usually has a limited body coverage, and there is a weak alignment between the haptic feedback and the educational content. To address the above-mentioned issues, this study established an environment that combines VR with dynamic somatosensory feedback. Through the simulation of the human blood circulation, it explored the impacts of VR and somatosensory feedback on learning effects. Sixty participants were randomly divided into three groups: the computer-based group, the VR-only group, and the VR with somatosensory feedback group. Self-efficacy, perceived enjoyment, and knowledge retention were evaluated through targeted questionnaires. The results showed that VR with somatosensory feedback significantly outperformed the computer-based and VR-only learning modes. This study provides new insights and practical support for the effective integration of VR and somatosensory feedback technology in educational environments.

Neuromorphic cameras, also known as event cameras, are asynchronous brightness-change sensors that can capture extremely fast motion without suffering from motion blur, making them particularly promising for 3D reconstruction in extreme environments. However, existing research on 3D reconstruction using monocular neuromorphic cameras is limited, and most of the methods rely on estimating physical priors and employ complex multi-step pipelines. In this work, we propose an end-to-end method for dense voxel 3D reconstruction using neuromorphic cameras that eliminates the need to estimate physical priors. Our method incorporates a novel event representation to enhance edge features, enabling the proposed feature-enhancement model to learn more effectively. Additionally, we introduced Optimal Binarization Threshold Selection Principle as a guideline for future related work, using the optimal reconstruction results achieved with threshold optimization as the benchmark. Our method achieves a 54.6% improvement in reconstruction accuracy compared to the baseline method.

The effective extraction of spatial-angular features plays a crucial role in light field image super-resolution (LFSR) tasks, and the introduction of convolution and Transformers leads to significant improvement in this area. Nevertheless, due to the large 4D data volume of light field images, many existing methods opted to decompose the data into a number of lower-dimensional subspaces and perform Transformers in each sub-space individually. As a side effect, these methods inadvertently restrict the self-attention mechanisms to a One-to-One scheme accessing only a limited subset of LF data, explicitly preventing comprehensive optimization on all spatial and angular cues. In this paper, we identify this limitation as subspace isolation and introduce a novel Many-to-Many Transformer (M2MT) to address it. M2MT aggregates angular information in the spatial subspace before performing the self-attention mechanism. It enables complete access to all information across all sub-aperture images (SAIs) in a light field image. Consequently, M2MT is enabled to comprehensively capture long-range correlation dependencies. With M2MT as the foundational component, we develop a simple yet effective M2MT network for LFSR. Our experimental results demonstrate that M2MT achieves state-of-the-art performance across various public datasets, and it offers a favorable balance between model performance and efficiency, yielding higher-quality LFSR results with substantially lower demand for memory and computation. We further conduct in-depth analysis using local attribution maps (LAM) to obtain visual interpretability, and the results validate that M2MT is empowered with a truly non-local context in both spatial and angular subspaces to mitigate subspace isolation and acquire effective spatial-angular representation.

The bio-inspired event cameras or dynamic vision sensors are capable of asynchronously capturing per-pixel brightness changes (called event-streams) in high temporal resolution and high dynamic range. However, the non-structural spatial-temporal event-streams make it challenging for providing intuitive visualization with rich semantic information for human vision. It calls for events-to-video (E2V) solutions which take event-streams as input and generate high quality video frames for intuitive visualization. However, current solutions are predominantly data-driven without considering the prior knowledge of the underlying statistics relating event-streams and video frames. It highly relies on the non-linearity and generalization capability of the deep neural networks, thus, is struggling on reconstructing detailed textures when the scenes are complex. In this work, we propose E2HQV, a novel E2V paradigm designed to produce high-quality video frames from events. This approach leverages a model-aided deep learning framework, underpinned by a theory-inspired E2V model, which is meticulously derived from the fundamental imaging principles of event cameras. To deal with the issue of state-reset in the recurrent components of E2HQV, we also design a temporal shift embedding module to further improve the quality of the video frames. Comprehensive evaluations on the real world event camera datasets validate our approach, with E2HQV, notably outperforming state-of-the-art approaches, e.g., surpassing the second best by over 40% for some evaluation metrics.

Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach's superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.

In cinematic VR applications, haptic feedback can significantly enhance the sense of reality and immersion for users. The increasing availability of emerging haptic devices opens up possibilities for future cinematic VR applications that allow users to receive haptic feedback while they are watching videos. However, automatically rendering haptic cues from real-time video content, particularly from video motion, is a technically challenging task. In this article, we propose a novel framework called "Video2Haptics" that leverages the emerging bio-inspired event camera to capture event signals as a lightweight representation of video motion. We then propose efficient event-based visual processing methods to estimate force or intensity from video motion in the event domain, rather than the pixel domain. To demonstrate the application of Video2Haptics, we convert the estimated force or intensity to dynamic vibrotactile feedback on emerging haptic gloves, synchronized with the corresponding video motion. As a result, Video2Haptics allows users not only to view the video but also to perceive the video motion concurrently. Our experimental results show that the proposed event-based processing methods for force and intensity estimation are one to two orders of magnitude faster than conventional methods. Our user study results confirm that the proposed Video2Haptics framework can considerably enhance the users' video experience.

Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the scenes with dense viewpoints synthesized by NVS and NeRF variants, thus, they often fall short in capturing the perceptual quality, including spatial and angular aspects of NVS-synthesized scenes. Furthermore, the lack of dense ground truth views makes the full reference quality assessment on NVS-synthesized scenes challenging. For instance, datasets such as LLFF provide only sparse images, insufficient for complete full-reference assessments. To address the issues above, we propose NeRF-NQA, the first no-reference quality assessment method for densely-observed scenes synthesized from the NVS and NeRF variants. NeRF-NQA employs a joint quality assessment strategy, integrating both viewwise and pointwise approaches, to evaluate the quality of NVS-generated scenes. The viewwise approach assesses the spatial quality of each individual synthesized view and the overall inter-views consistency, while the pointwise approach focuses on the angular qualities of scene surface points and their compound inter-point quality. Extensive evaluations are conducted to compare NeRF-NQA with 23 mainstream visual quality assessment methods (from fields of image, video, and light-field assessment). The results demonstrate NeRF-NQA outperforms the existing assessment methods significantly and it shows substantial superiority on assessing NVS-synthesized scenes without references. An implementation of this paper are available at https://github.com/VincentQQu/NeRF-NQA.

Light field videos captured in RGB frames (RGB-LFV) can provide users with a 6 degree-of-freedom immersive video experience by capturing dense multi-subview video. Despite its potential benefits, the processing of dense multi-subview video is extremely resource-intensive, which currently limits the frame rate of RGB-LFV (i.e., lower than 30 fps) and results in blurred frames when capturing fast motion. To address this issue, we propose leveraging event cameras, which provide high temporal resolution for capturing fast motion. However, the cost of current event camera models makes it prohibitive to use multiple event cameras for RGB-LFV platforms. Therefore, we propose EV-LFV, an event synthesis framework that generates full multi-subview event-based RGB-LFV with only one event camera and multiple traditional RGB cameras. EV-LFV utilizes spatial-angular convolution, ConvLSTM, and Transformer to model RGB-LFV's angular features, temporal features, and long-range dependency, respectively, to effectively synthesize event streams for RGB-LFV. To train EV-LFV, we construct the first event-to-LFV dataset consisting of 200 RGB-LFV sequences with ground-truth event streams. Experimental results demonstrate that EV-LFV outperforms state-of-the-art event synthesis methods for generating event-based RGB-LFV, effectively alleviating motion blur in the reconstructed RGB-LFV.

Light field imaging can capture both the intensity information and the direction information of light rays. It naturally enables a six-degrees-of-freedom viewing experience and deep user engagement in virtual reality. Compared to 2D image assessment, light field image quality assessment (LFIQA) needs to consider not only the image quality in the spatial domain but also the quality consistency in the angular domain. However, there is a lack of metrics to effectively reflect the angular consistency and thus the angular quality of a light field image (LFI). Furthermore, the existing LFIQA metrics suffer from high computational costs due to the excessive data volume of LFIs. In this paper, we propose a novel concept of "anglewise attention" by introducing a multihead self-attention mechanism to the angular domain of an LFl. This mechanism better reflects the LFI quality. In particular, we propose three new attention kernels, including anglewise self-attention, anglewise grid attention, and anglewise central attention. These attention kernels can realize angular self-attention, extract multiangled features globally or selectively, and reduce the computational cost of feature extraction. By effectively incorporating the proposed kernels, we further propose our light field attentional convolutional neural network (LFACon) as an LFIQA metric. Our experimental results show that the proposed LFACon metric significantly outperforms the state-of-the-art LFIQA metrics. For the majority of distortion types, LFACon attains the best performance with lower complexity and less computational time.

A new heuristic optimization algorithm is presented to solve the nonlinear optimization problems. The proposed algorithm utilizes a stochastic method to achieve the optimal point based on simplex techniques. A dual simplex is distributed stochastically in the search space to find the best optimal point. Simplexes share the best and worst vertices of one another to move better through search space. The proposed algorithm is applied to 25 well-known benchmarks, and its performance is compared with grey wolf optimizer (GWO), particle swarm optimization (PSO), Nelder-Mead simplex algorithm, hybrid GWO combined with pattern search (hGWO-PS), and hybrid GWO algorithm combined with random exploratory search algorithm (hGWO-RES). The numerical results show that the proposed algorithm, called stochastic dual simplex algorithm (SDSA), has a competitive performance in terms of accuracy and complexity.

We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Our key motivation is that credit assignment among agents may not require an explicit formulation as long as (1) the policy gradients derived from a centralized critic carry sufficient information for the decentralized agents to maximize their joint action value through optimal cooperation and (2) a sustained level of exploration is enforced throughout training. Under the centralized training with decentralized execution (CTDE) paradigm, we achieve the former by formulating the centralized critic as a hypernetwork such that a latent state representation is integrated into the policy gradients through its multiplicative association with the stochastic policies; to achieve the latter, we derive a simple technique called adaptive entropy regularization where magnitudes of the entropy gradients are dynamically rescaled based on the current policy stochasticity to encourage consistent levels of exploration. Our algorithm, referred to as LICA, is evaluated on several benchmarks including the multi-agent particle environments and a set of challenging StarCraft II micromanagement tasks, and we show that LICA significantly outperforms previous methods.

Model drifting is one of the knotty problems that seriously restricts the accuracy of discriminative trackers in visual tracking. Most existing works usually focus on improving the robustness of the target appearance model. However, they are prone to suffer from model drifting due to the inappropriate model updates during the tracking-by-detection. In this paper, we propose a novel update-pacing framework to suppress the occurrence of model drifting in visual tracking. Specifically, the proposed framework first initializes an ensemble of trackers, each of which updates the model in a different update interval. Once the forward tracking trajectory of each tracker is determined, the backward trajectory will also be generated by the current model to measure the difference with the forward one, and the tracker with the smallest deviation score will be selected as the most robust tracker for the remaining tracking. By performing such self-examination on trajectory pairs, the framework can effectively preserve the temporal context consistency of sequential frames to avoid learning corrupted information. To further improve the performance of the proposed method, a multi-feature extension framework is also proposed to incorporate multiple features into the ensemble of the trackers. The extensive experimental results obtained on large-scale object tracking benchmarks demonstrate that the proposed framework significantly increases the accuracy and robustness of the underlying base trackers, such as DSST, Struck, KCF, and CT, and achieves superior performance compared with the state-of-the-art methods without using deep models.

The Dynamic Economic Emission Dispatch Problem (DEED) is a well-known problem in the study of thermal power generation. The goal of the DEED is to meet the demand change by arranging the capacities of power generators to reduce fuel cost and emission. In recent years, the high environmental awareness, the decreasing petrochemical energy, and the increasing energy demand such that the DEED is more important and popular than before. Most of algorithms for the DEED are either limited by less than ten power generators or without considering the power generation limit. The former is impractical due to that the number of power generators in current thermal power plants can be up to 14; the latter results in infeasible solutions. To overcome the above two obstacles, a new algorithm called the SSO-DE-SQP hybrid with the Simplified Swarm Optimization (SSO), Differential Evolution (DE), and Sequential Quadratic Programming (SQP) is developed to solve the larger-size DEED with the power generation limit. The performance of the SSO-DE-SQP is demonstrated by comparing with two existing well-known methods: DE-SQP and PSO-SQP with up to 15 generators for the DEED.

In recent years, Convolutional Neural Networks (CNNs) have been widely used in image recognition due to their aptitude in large scale image processing. The CNN uses Back-propagation (BP) to train weights and biases, which in turn makes the error consistently smaller. The most common optimizers that uses a BP algorithm are Stochastic Gradient Decent (SGD), Adam, and Adadelta. These optimizers, however, have been proved to fall easily into the regional optimal solution. Little research has been conducted on the application of Soft Computing in CNN to fix the above problem, and most studies that have been conducted focus on Particle Swarm Optimization. Among them, the hybrid algorithm combined with SGD proposed by Albeahdili improves the image classification accuracy over that achieved by the original CNN. This study proposes the amalgamation of Improved Simplified Swarm Optimization (iSSO) with SGD, hence culminating in the iSSO-SGD which is intended train CNNs more efficiently to establish a better prediction model and improve the classification accuracy. The performance of the proposed iSSO-SGD can be affirmed through a comparison with the PSO-SGD, the Adam, Adadelta, rmsprop and momentum optimizers and their abilities in improving the accuracy of image classification.

Light field (LF) photography is an emerging paradigm for capturing more immersive representations of the real-world. However, arising from the inherent trade-off between the angular and spatial dimensions, the spatial resolution of LF images captured by commercial micro-lens based LF cameras are significantly constrained. In this paper, we propose effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images. Specifically, the proposed models have an hourglass shape, which allows feature extraction to be performed at the low resolution level to save both computational and memory costs. To fully make use of the four-dimensional (4-D) structure information of LF data in both spatial and angular domains, we propose to use 4-D convolution to characterize the relationship among pixels. Moreover, as an approximation of 4-D convolution, we also propose to use spatialangular separable (SAS) convolutions for more computationallyand memory-efficient extraction of spatial-angular joint features. Extensive experimental results on 57 test LF images with various challenging natural scenes show significant advantages from the proposed models over state-of-the-art methods. That is, an average PSNR gain of more than 3.0 dB and better visual quality are achieved, and our methods preserve the LF structure of the super-resolved LF images better, which is highly desirable for subsequent applications. In addition, the SAS convolutionbased model can achieve 3× speed up with only negligible reconstruction quality decrease when compared with the 4-D convolution-based one. The source code of our method is online available at https://github.com/spatialsr/DeepLightFieldSSR.

Nowadays, due to the development of e-commerce, delivery time has become an important factor influencing quality of distribution service. Especially in the urban distribution environment, many factors affect the distribution time, such as traffic condition on peak hours plays an important role in outcomes of the planned schedule. Hence, more and more research devoted to the “Time-depend vehicle routing problem (TDVRP)”. Consider the competitors' factors for obtaining more sales, logistics company should serve customers before other rival distributors. Such problem is called “Time-depend vehicle routing problem in a competitive environment (TDVRPC)” whose main objectives of the problem are to minimize the travel time cost and maximize the sale. Many research papers have presented mathematical models for TDVRPC. The major weakness of the above models is they donot satisfy the “first-in-first-out (FIFO)” property which guarantee that if a vehicle leaves a for at a given time, any other vehicle leaving earlier will arrive earlier. Take into account the possible ways of handling the situation with heterogeneous fleet, so a novel model for the “Time-dependent vehicle routing problem in a competitive environment with heterogeneous fleet (TDVRPCHF)” is presented to satisfy the “FIFO” property. To solve such a problem, a Simplified Swarm Optimization algorithm is proposed and it can also be promoted on the other “time-dependent vehicle routing problem”.

Nowadays, cloud computing and big data are changing the enterprise. Cloud computing, as a new business computing mode, distributes computing tasks across resource pools made up of a large number of computers for large-scale calculation. In the current research on the task assignment problem of cloud computing, most scholars consider single-objective programming, for example minimizing the cost or makespan. However, many other factors can influence the quality of the cloud computing service. Therefore, in order to adapt to the development of practical applications, multi-objective programming should be considered in the task scheduling problem of cloud computing. This paper developed a new algorithm (Multi-Objective Simplified Swarm Optimization, MOSSO) for multi-objective problems, based on the Multi-Objective Particle Swarm Optimization (MOPSO), using the simple and efficient update mechanism of a heuristic algorithm called Simplified Swarm Optimization (SSO). In order to increase the search ability of feasible solution space in this algorithm, this paper designs dynamitic parameters to make the mutation rate large at the early stage to enhance global search ability and the mutation rate small at late stage to enhance local search ability.

Automated person re-identification is a challenging research problem that has many real-world applications, especially in video surveillance. While many recent studies have been focusing on solving the person re-identification problem using full-scale images or video footages, little work has been done to solve the person re-identification problem in a top-down context. In this work, we propose a solution to the top-down reidentification problem that uses the Siamese architecture in conjunction with Convolutional Neural Networks. In our approach, a pair of top-down images is distinguished by a single Siamese network, which is trained to predict the similarity, or a distance between two input images. Experiments have shown that once the model is properly trained, it is able to achieve one-shot, top-down re-identification by learning unseen classes of person in real-time.

Augmented Reality (AR) is investigated as a unique technology to combine virtual and real world together. The key feature of AR is to demonstrate extra information in the field of view for those who interact with the authentic environment. Using AR in education setting helps students to engage in genuine exploration in the real world. In this regard, remote laboratories provide a special platform for AR technology to bridge the gap between theoretical and empirical knowledge. For revealing auxiliary data, object tracking scheme plays an imperative role to make visible invisible issue. In this scheme, Particle Swarm Optimization algorithm (PSO) is one of the most famous algorithm in linear and non-linear object tracking by particular identification of target. Contrary to other modified PSO, Elevated-PSO is adopted to improve diversity of particles when all particles are restricted close to the best predicted solution with the enough similarity. This proposed algorithm regarding to target tracking in AR remote labs can fulfill better solutions in comparison with classic and other improved PSO.

This paper proposes the use of Stacked Denoising Autoencoder to predict the direction of movement of stock indexes based on the historical and volume data of the underlying stocks. The Stacked Denoising Autoencoder is a deep learning method widely used in the field of computer vision which is capable of learning a compact feature representation of the data for stock index prediction. The Hybrid Gravitational Search Algorithm, a swam intelligence based algorithm, is proposed to optimise the hyper-parameters of the deep network which mitigates the hyper-parameter tuning problem of the network.

Recognizing human faces is one of the most popular problems in the field of pattern recognition. Many approaches and methods have been tested and applied on the topic, especially neural networks. This paper proposed a new loss layer that can be replaced at the bottom of a neural network architecture in terms of face recognition, called constrained triplet loss layer (CTLL). In order to make more confident predictions and classifications, this loss layer helps the deep learning model to specify further distinguishable clusters between different people (classes) by placing extra constraints on images of the same person (intra-person) while putting margins on images of a different person (inter-person). This proposed constrained triplet loss layer improved the recognition accuracy on faces by 2%.

How to setup the distribution centers (DC) is not only a general issue but also a quite profound knowledge in real world. This problem called capacitated clustering location problem (CCP), then the previous literature, the target of the CCP is to minimize the sum of distances from each DC to all customers in their cluster. However, some types of the company shipping are different from the above. The DC must ship goods to all customers in its cluster in a cycle time. This delivery way called “one-time delivery” and it can be modeled as Travelling Salesman Problem (TSP). In order to solve this practical problem, a hybrid algorithm, Simplified Swarm Optimization combining with K-harmonic means (SSOKHM) is proposed in this paper for the CCP and using greedy algorithm for the TSP to obtain the minimize shipping costs. Proposed method is applied to several facility location problems from OR library. Numerical results show that the SSOKHM performance is better than using other hybrid clustering algorithms in terms of shipping costs. Finally, we embed the exchange local search for each algorithm. The results are presented that this inspection mechanism can enhance the performance and demonstrate the usefulness in CCP.

In recent decade, reliability has been an important factor which may affect the performance of the system. In order to enhance the system reliability, redundancy allocation problem (RAP) is becoming an increasingly important tool in the stages of planning, designing, and controlling of systems. Moreover, the multi-level redundancy allocation problem (MRAP) and multiple multi-level redundancy allocation problem (MMRAP) are extensions derived from the redundancy allocation problem (RAP) for practical modeling of real-life problems. However, while formulating the model, the two problems mentioned above have some restrictions which may not deal with real world problem and lost its generality. Therefore, this paper formulates a new kind of MRAP called general multi-level redundancy allocation problem (GMRAP) to break the restrictions and generalize previous problems. Furthermore, a novel algorithm called simplified swarm optimization with modular search (SSO-MS) is proposed to solve the GMRAP in this paper. Finally, the results obtained by SSO-MS are compared with those obtained from genetic algorithm and particle swarm optimization algorithm. The comparative results show that the proposed SSO-MS is promising among three algorithms and demonstrate the effectiveness of the proposed model and method.

In the 21th century, the importance of the integration among enterprises has been raised. Many enterprises and managements start to be conscious of supply chain management. In supply chain management, reducing operating cost and satisfying customer demand are the most important things. However, the products may be spoilt during the delivery due to collisions, traffic accident, weather factor, theft and so on. Hence, in this paper, we consider deterioration effect in a three-stage supply chain deteriorated network with a mathematical model. A novel artificial intelligence algorithm named Simplified Swarm Optimization (SSO) is adapted in the above problem to minimize the total operating cost. Extending local search (ELS) is attached to enhance the performance of the original SSO. A numerical example network system is presented to compare the proposed algorithm with Genetic Algorithm (GA) and Particle Swarm Optimization Algorithm (PSO). Results indicate that SSO-ELS provide a better solution than its competitors on the problem.

Moving object tracking in video sequences is an important task in the field of computer vision. In this paper, we propose a new population-based algorithm namely simplified swarm optimization (SSO) for tracking arbitrary objects. In SSO, the object model is first projected into a high-dimensional feature space, then the particles will fly over image pixels to find an optimal match of the target. While searching for the optimum, SSO progressively analyzes the occlusion situation. If any occlusion or disappearance of the target object is detected, the movement rules for the searching particles will be adaptively adjusted to recapture the target object. Experimental results showed that the SSO can robustly track an arbitrary target in various challenging conditions. Furthermore, SSO is capable to have 40% faster in speed and 36% higher in accuracy rate than the traditional PSO for varied environment.

Swarm intelligence has been applied to many research projects in recent years, many scientists are working on developing the full potential of a self-organized and decentralized system to help solving complex problems. In image processing, it also demonstrates fast and accurate in searching solutions for trajectory clustering and precise object tracking. This paper is aim to introduce a novel multiple particle swarms with dynamic convergence approach for object tracking in complicated environment. Our new approach absorbs the advantages of other multi swarm algorithms to optimize the resources and process iteration. So it can provide more accurate and faster tracking result for both linear and non-linear movement pattern when compared to basic PSO and other PSO based algorithms such as inertia weight PSO and constriction factor PSO. In addition, multiple independent populations will not only inherit each of their own attribute's weights through dynamic range convergence, but also influence by each other's solution effects. The experiments have been conducted with different types of testing videos in real environment. The results examined with different types of moving pattern have demonstrated that the new method required less resources and iteration process and could have better tracking performance and scarcely lost target with diverse interferences.

In recent decades, the redundancy allocation problem (RAP) is becoming an increasingly important issue in the initial stages of planning, designing, and controlling of systems. However, RAP in multi-state system (MSSs) still has some restrictions that components have only two performances: perfect functionality and complete failure. Therefore, this paper formulates a new kind of RAP called repairable redundancy allocation problem (RRAP) in multi-state systems (RRAP in MSSs) to break the restrictions. RRAP in MSSs is nearer to reality and widespread in many critical systems. RRAP in MSSs is not only an NP-hard problem, but also a nonlinear integer optimization problem. In order to deal with RRAP in MSSs in a reasonable time, this paper employs an optimization method of soft computing called simplified swarm optimization (SSO). Finally, the results obtained by SSO have been compared with that obtained from genetic algorithm (GA). Computational results show that the SSO is very competitive and effective in this problem.

Object tracking for video and camera image capturing becomes more popular in recent scientific and application domain. Many Scientists in Image Processing try to find an efficient and accurate way to track the objects' moving in real time video applications. Particle Swarm Optimization is one of the most efficient and potential approaches developed to provide linear and non-linear object tracking by identifying special patterns for selected object, and achieving efficient algorithm to calculate random object moving. Compare to classic Kalman Filter, Particle Filter, or other improved PSO, this paper is aim to find a more efficient and precious pathway using categorized particle movement with dynamic inertia weight value in PSO to build a tracking procedure in order to provide better tracking speed and quality result in different types of video records and different visions of object moving. The proposed Categorized PSO based target tracking scheme can achieve better quality when compared to Particle Filter and typical Particle Swarm Optimization methods in our tracking experiments. It has been developed in C++ environment and tested against videos to demonstrate its excellent tracking ability in object retrieval and high accurate in tracking objects movement within other similar object's environment.

Particle Swarm Optimization has been used in many research and application domain popularly since its development and improvement. Due to its fast and accurate solution searching, PSO has become one of the high potential tools to provide better outcomes to solve many practical problems. In image processing and object tracking applications, PSO also indicates to have good performance in both linear and non-linear object moving pattern, many scientists conduct development and research to implement not only basic PSO but also improved methods in enhancing the efficiency of the algorithm to achieve precise object tracking orbit. This paper is aim to propose a new improved PSO by comparing the inertia weight and constriction factor of PSO. It provides faster and more accurate object tracking process since the proposed algorithm can inherit some useful information from the previous solution to perform the dynamic particle movement when other better solution exists. The testing experiments have been done for different types of video, results showed that the proposed algorithm can have better quality of tracking performance and faster object retrieval speed. The proposed approach has been developed in C++ environment and tested against videos and objects with multiple moving patterns to demonstrate the benefits with precise object similarity.

This study applies a penalty guided strategy and the orthogonal array test (OA) based on the Simplified Swarm Optimization algorithm (SSO) to solve the reliability redundancy allocation problems (RRAP) in the series system, the series-parallel system, the complex (bridge) system, and the overspeed protection of gas turbine system. For several decades, the RRAP has been one of the most well known techniques. The maximization of system reliability, the number of redundant components, and the reliability of corresponding components in each subsystem have to be decided simultaneously with nonlinear constraints, acting as one difficulty for the use of the RRAP. In other words, the objective function of the RRAP is the mixed-integer programming problem with the nonlinear constraints. The RRAP is of the class of NP-hard. Hence, in this paper, the SSO algorithm is proposed to solve the RRAP and improve computation efficiency for these NP-hard problems. There are four RRAP problems used to illustrate the applicability and the effectiveness of the SSO. The experimental results are compared with previously developed algorithms in literature. Moreover, the maximum-possible-improvement (MPI) is used to measure the amount of improvement of the solution found by the SSO to the previous solutions. According to the results, the system reliabilities obtained by the proposed SSO for the four RRAP problems are as well as or better than the previously best-known solutions.

Golf Swing is one of the most difficult techniques in sports to perfect, and a smooth swing can't be achieved without a correct process of bodyweight transfer between the feet during the motion, which is known as weight shift in golf. As pointed out by various professional players and coaches, a proper weight shift is critical in hitting a shot with good accuracy and range, and therefore it would be beneficial for golfers to obtain weight shift data corresponding to their swing motions, so that analysis and improvement on the swing pose can be made. Weight shift data collected through common methods such as using electronic scales may contain noise data due to factors such as pre-swing movements, and in order for the data to be useful, it is necessary to distinguish actual swing motion from noise. In this paper a data mining approach named Simplified Swarm Optimization with Sorted Local Search (SSO-SLS), which is based on a variant of Particle Swarm Optimization (PSO), has been proposed to classify golf swing from weight shift data. In the proposed approach a novel Sorted Local Search strategy has been introduced to remedy the issue of premature convergence facing PSO by allowing particles to obtain information from their nearest neighbors and improve swarm diversity. Experiments on UCI datasets and weight shift data in golf show that SSO-SLS is competitive with common classification techniques, and is an ideal approach for classifying golf swing from weight shift.

Radio-frequency identification (RFID) is an automatic identification system which has become a hot topic in the fields of manufacturing, logistics, and so on. The purpose of this research is to propose a methodology for designing the RFID network planning problem (RNP) for application in the Mackay Memorial Hospital in Hsinchu, Taiwan. In this study, the RFID network is first considered as a grid and divided into several small squares. A soft computing methodology called FKB-SSO is proposed to solve the RNP problem based on simplified swarm optimization (SSO) by integrating k-means, fuzzy adaptive resonance theory (fuzzy-ART), and binary search. The proposed FKB-SSO will provide the basis for strategic decisions in constructing the RFID network to reduce the number of RFID readers with a minimal budget under the constraint of 100% coverage rate. The proposed FKB-SSO is more efficient than PSO and experts' manual solution in both run time and solution quality.

Reliability optimization has been a popular area of research, and received significant attention due to the critical importance of reliability in various kinds of systems. Most network reliability optimization problems are only focused on solving simple structured networks (e.g., series-parallel networks) of which the reliability function can be easily obtained in advance. However, modern networks are usually very complex, and it is impossible to calculate the exact network reliability function by using traditional analytical methods in limited time. Hence, a new particle swarm optimization (PSO) based on Monte Carlo simulation (MCS), named MCS-PSO, has been proposed to solve complex network reliability optimization problems. The proposed MCS-PSO can minimize cost under reliability constraints. To the best of our knowledge, this is the first attempt to use PSO combined with MCS to solve complex network reliability problems without requiring knowledge of the reliability function in advance. Compared with previous works to solve this problem, the proposed MCS-PSO can have better efficiency by providing a better solution to the complex network reliability optimization problem.

In a multimodal interface, a user can use multiple modalities, such as speech, gesture, and eye gaze etc., to communicate with a system. As a critical component in a multimodal interface, multimodal input fusion explores the ways to effectively interpret the combined semantic interpretation of user's multimodal inputs. Although multimodal inputs may contain spare information, few multimodal input fusion approaches have tackled how to deal with spare information in multimodal inputs. This paper proposes a novel multimodal input fusion approach to flexibly skip spare information in multimodal inputs and derive semantic interpretation of them. The evaluation about the proposed approach confirms that the approach makes human-computer interaction more natural and smooth.

LifeLog can be used as a stand-alone consumer device to serve as a powerful automated multimedia diary and scrapbook. By using a search engine interface, the user can easily retrieval a specific thread of past transactions, or recall a few seconds ago or from many years earlier in as much detail as is desired, including imagery , audio, or video event. In this paper, we have studied and implemented three audio classification algorithms. The testing results show that KNN is the best classifier to classify the multimedia data.

This paper has proposed and implemented a new optimized and adaptive Error-Resilient Coding based on Statistical Parity Pair Embedding (SPPE). The SPPE can locate errors in the compressed I-frame bit stream and this system design can be applied to the MPEG2 wireless video applications. The SPPE is based on the information hiding technique. This SPPE algorithm is proven to have better performance than other traditional algorithms, and is very suitable for use in multipoint communications. In this paper three Error Concealment (EC) algorithms: Previous Coded Block Linear Error Concealment (PCB-EC), Four Neighbors Linear Error Concealment (4N-EC) and Eight Neighbors Linear Error Concealment (8N-EC) were implemented and tested. We found that the proposed SPPE and 4N-EC algorithm together can achieve PSNR increments of 8.2dB after recovery while other algorithms [1-3] can only improve 1-2dB after recovery.

In video communications over error-prone environments, compressed video is fragile to transmission errors. The decoder side error concealment (EC) is an efficient way to recover a damaged video sequence. Typically traditional video EC algorithms for H.264/AVC intra-frames operate in macroblock (MB) level and they offer a single concealment mode for all frames regardless of frame features. This paper proposes a new multi-mode error concealment (MMEC) algorithm for intra-frames of H.264/AVC. The proposed algorithm provides several different EC modes so that the decoder is able to choose the best modes to conceal errors. By applying the proposed method, a MB can be partitioned into smaller 8 times 8 subblocks, each subblock can be recovered using available temporal or spatial information based on the MB characteristics. If there are any subblocks recovered by using temporal information, these subblocks will be further used for directional spatial EC for the rest subblocks. The proposed new MMEC algorithm has been evaluated and compared with the H.264/AVC reference implementation and two other classical EC algorithms. The experimental results show that the proposed MMEC algorithm can achieve up to 5 dB gains in PSNR therefore significantly improves the video quality.

Video watermarking is an important method of protecting the intellectual property copyright of the video media. It allows embedding of copyright information into the video pictures. In this paper a new hybrid approach of digital video watermarking scheme with an Error Correcting Code (ECC) is proposed. This watermarking scheme maximizes the watermark payload while minimizing the perceptual degradation of video quality caused by the embedded watermark by means of an appropriate choice of embedding position. Two hybrid error correcting codes, BCH(31,8) and Turbo (3,1) with repetition code were implemented and compared. We found that the hybrid approach of BCH(31,8) with repetition code achieved higher error correcting capability than Turbo (3,1) with repetition code under the simulated noise tests.

In this paper, a new error resilient coding system based on the Three Layer Error Control Coding (TLECC) techniques for MPEG2[1] coded video is proposed. The results show that the proposed TLECC system can achieve 100% accuracy in the retrieval of a test sequence signal if the transmission noise is below 5%. This system is very useful for the home entertainment video coding system, and the internet or networked video coding system.

In this paper we propose a new Two Level Clustering Wavelet-based Image REtrieval System (TLWIRES). The TLWIRES provides a two level clustering and searching. The first level is based on colour variations and the second level is based on colour histograms. The experimental results showed that the proposed TLWIRES can have high accuracy and high speed. This system is very suitable for applications such as home multimedia server to search for images.

Many fast search block-matching motion estimation (BMME) algorithms has been developed in order to minimize the search positions and speed up the computation but they do not consider how they can be effectively implemented by hardware. We propose a new regular fast search block-matching motion estimation algorithm named two step search (2SS). The 2SS BMME will then be implemented on the SPACE2 custom computer board which consists of up to 8 Xilinx XC6216 fine-grain, sea-of-gate FPGA chips. The experimental and simulation results show that it can have better algorithmic performance and can be implemented by FPGA chips very cost-effectively for video compression applications. Also, the 30 frames per second real time 2SS BMME video compression can be obtained from the SPACE2 custom computer.

Contour sequence moments (CSM) have been used in the classification of four closed planar shapes. Gupta et al. described a neural network approach for the classification of four closed planar shapes using a contour sequence. In this paper, a backpropagation neural network is used in the recognition of handwritten numerals (from 0 to 9) using contour sequence moments. Experimental results indicate that the neural network approach gives better recognition accuracy when compared with the two conventional statistical classifiers, namely the nearest neighbour and minimum-mean-distance. This CSM technique was compared with geometrical moment (GM) invariants. We found that the recognition accuracy for handwritten character using GSM and neural network is over 95% while GM invariants and neural network can only give 82%.

This paper describes the implementation of a partially connected neural network using FPGAs (field programmable gate arrays) based custom computers. Starting from the training data, a decision tree is generated using the classifier program C4.5. The tree is then used to initialise the architecture of the neural network to a nearly optimum configuration. This initialised partially connected network is then trained using training data. The trained neural network is then implemented by fine-grain Xilinx XC6200 series FPGAs. This implementation requires fewer connections and can provide a very high speed classification for many real-time image recognition applications.

The discrete cosine transform (DCT) is a key step in many image and video coding applications, and its efficient implementation has been extensively studied for software implementations and for custom VLSI. We analyse the use of the distributed arithmetic algorithm for the efficient implementation of the DCT in reconfigurable logic.

The field programmable gate array (FPGA) based custom computer is a new computing paradigm which can provide fast and flexible processing. This paper describes the implementation of 2D DCT algorithms for video compression using a FPGA-based custom computer. Our experimental result shows that by using an FPGA-based custom computer, the speed for processing 2D discrete cosine transforms in video compression can be improved 50 to 100 times when compared with workstation or super-computer implementations.