Search

Vehicle re-identification (ReID) is the task of identifying the same vehicle across numerous cameras. This is a complex classification task, and the fine-grained information and strong discrimination features have proven to be effective in handling the re-identification classification task. However, most existing methods focuses on extracting local area features in combination with global features, while exploring subtle distinguishing features, which is a difficult task, remains an open problem and unsolved. In this paper, we propose a multi-branch enhanced discriminative network (MED) to better extract subtle distinguishing features that have high discriminative power to improve the ReID performance. In the proposed MED method, each feature map obtained by convolutional neural network (CNN) is divided into 4 spatial sub-maps, on each of which, the vertical and the horizontal branches are used to extract the subtle distinguishing features intrinsically contained in sub-areas. The vertical and the horizontal branches are combined with the global branch to perform the ReID task. Moreover, our proposed method is capable of extracting rich fine-grained features without the need of extra manual annotation while maintaining a simple design structure. We conducted extensive experiments on the vehicle ReID datasets (VehicleID and VeRi-776), showing that the proposed MED method outperforms most existing methods. Further, we directly apply the MED method to the pedestrian ReID problem on the Market-1501, DUKEMTMC, and MSMT17 datasets, achieving the state-of-the-art (SOTA) performance as well. This demonstrates that the proposed method has good generality and can be flexibly applied to the ReID tasks.

In the landscape of Korea, having numerous industrial complexes and densely populated residential areas and showing evident seasonal changes, district heating systems (DHS) with large-scale combined heat and power plants (L-CHP) are widely utilized. L-CHP is a combined system consisting of a backpressure turbine and an extraction-condensing turbine. It can transition the operation mode according to the heat and electric load situation, unlike small-scale CHP (S-CHP), which has a single operation mode. This paper defines the physical constraints and the outputs of heat and electricity for L-CHP’s operation modes and intermediate modes, which are the transition processes between operation modes. In addition, a novel optimal scheduling model of DHS based on mixed integer linear programming (MILP) is presented. The DHS comprises L-CHP and auxiliary facilities such as a peak load boiler and electric/thermal storage systems. To demonstrate the proposed optimization model, case studies are conducted with a sample DHS responding to the seasonal heat demands and Korean electricity market prices. The simulations are performed using IBM’s CPLEX Studio IDE 12.8.0.

Video-based person re-identification (re-ID) aims to match the same pedestrian of video sequences across non-overlapping cameras. Video re-ID methods generally adopt frame-level feature extraction for different video frames, but they still lack effective spatio-temporal interaction, easily leading to the multi-frame misalignment problem. In this paper, we propose a Hierarchical Attention-aware Spatio-temporal Interaction (HASI) network, including an Attention-aware Temporal Interaction (ATI) module and a Hierarchical Local-spatial Enhancement (HLE) module for video-based person re-ID. In order to avoid the spatial misalignment between video frames, the ATI module employs multiple Frame-to-Frame Temporal Interaction (2FTI) blocks with the Multi-head Inter-frame Alignment Attention (MIAA) to make the current frame iteratively interact with each rest frame of a video in a positive single-cycle manner, rather than only interacting with the adjacent frame or directly building the relationship of all frames at once. This module can not only obtain the long-range non-adjacent temporal information, but also learn the pairwise frame-to-frame relationships. Moreover, the HLE module is designed to enhance the local fine-grained features from multiple Transformer layers, whilst delivering low-level information to further enrich middle-level and high-level semantic knowledge. Thus, our method can learn multi-perspective pedestrian information, including inter-frame long-range interaction information and intra-frame multi-layer global and local information. Extensive experiments demonstrate the superiority of the proposed HASI method compared with the state-of-the-art methods on the three challenging video-based re-ID datasets, i.e., MARS, iLIDS-VID, and PRID-2011.

Siamese networks have attracted wide attention in visual tracking due to their competitive accuracy and speed. However, the existing Siamese trackers usually leverage a fixed linear aggregation of feature maps, which does not effectively fuse the different layers of features with attention. Besides, most of Siamese trackers calculate the similarity between the template and the search region through a cross‐correlation operation between the features of the last blocks from the two branches, which might introduce the redundant noise information. In order to solve these problems, this study proposes a novel Siamese visual tracking method via cross‐layer calibration fusion, termed SiamCCF. An attention‐based feature fusion module is employed using local attention and non‐local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high‐level semantic information. Moreover, a cross‐layer calibration module can use the fused features to calibrate the features of the last network blocks and build the cross‐layer long‐range spatial and inter‐channel dependencies around each spatial location. Extensive experiments demonstrate that the proposed method has achieved competitive tracking performance compared with state‐of‐the‐art trackers on challenging benchmarks, including OTB100, OTB2013, UAV123, UAV20L, and LaSOT. This study proposes a novel Siamese visual tracking method via cross‐layer calibration fusion, termed SiamCCF. We first employ an attention‐based feature fusion module (FFM) by using local attention and non‐local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high‐level semantic information. Moreover, a cross‐layer calibration module (CCM) can use the fused features to calibrate the features of the last network blocks, and build the long‐range spatial and inter‐channel dependencies around each spatial location between the different layers.

Facial attribute recognition (FAR) is an important and yet challenging multi-label learning task in computer vision. Existing FAR methods have achieved promising performance with the development of deep learning. However, they usually suffer from prohibitive computational and memory costs. In this paper, we propose an identity-aware contrastive knowledge distillation method, termed ICKD, to compress the FAR model. A nonlinear weight-sharing mapping (NWSM) mechanism is firstly designed to avoid the difficulty of directly matching features of the teacher and student networks due to the lower representation ability of the student network. Furthermore, an identity-aware contrastive distillation (ICD) loss is employed to guide the student network to effectively learn the mutual relations between samples with multiple attributes. In addition, an adjustable ladder distillation (ALD) loss is developed to automatically adjust the importance of different distillation points with the progress of training. Extensive experiments demonstrate that our method can significantly improve the performance of student networks and outperforms the existing FAR methods on the public challenging datasets.

System marginal price (SMP) forecasting is essential for power generation companies or virtual transaction operators participating in the electricity market. In forecasting SMP, the load data is one of the most important pieces of information. Therefore, this paper presents a 2-Step method for SMP forecasting after load forecasting. This paper performed feature selection using Shapley additional explanations and Pearson correlation coefficient and adjusted the hyperparameters of the forecasting model by Grid search. Through this, the total load and SMP in 2021 were forecasted, and the forecasting results were presented through MAPE (mean absolute percentage error), nMAE (normalized mean absolute error), and nRMSE (normalized root mean square error). This paper used XGBoost for load forecasting and XGBoost, random forest, light gradient boosting machine, and linear regression for SMP forecasting. As a result of forecasting SMP, in the average of 2021, LGBM and RF ensemble models showed the best performance with 3.33% in MAPE. In addition, when the forecasting results were shown by dividing it into 4 seasons, the ensemble model of LGBM and random forest showed the best performance in MAPE except for spring.

This paper presents a methodology for forecasting hourly loads over seven days, using a separation of weekday and weekend data. The data used for the forecasting included the date, weather, and load data from January 1, 2021, with the forecast being conducted for four weeks from November 1 to 28, 2021. The methodology involved separating the data into weekdays and weekends, conducting separate forecasts for each, selecting features for use in each process, and optimizing the forecasting model's parameters through hyperparameter tuning. To select features, the Shapley Additional Explanations method was used to calculate feature importance, and Pearson correlation coefficients were used to measure linearity between features. This allowed for the selection of input features with high importance while avoiding those with high linearity with other features. The parameters of the forecasting model were optimized through Grid search, and the optimal combination of the XGBoost forecasting model's Learning Rate, n estimators, and Max depth was assessed. After all processes were completed, forecasting was performed, and the forecasting error was presented through Normalized Mean Absolute Error, Mean Absolute Percentage Error, and Normalized Root Mean Squared Error. The results obtained using the proposed algorithm were compared with those obtained without using it. In future studies, the authors plan to investigate forecasting for special dates, such as public holidays, and explore the use of forecasting algorithms that consider the probability of input data.

In this paper, the distributed method for alternating current optimal power flow (AC OPF) based on second order cone programming (SOCP) and consensus alternating direction method of multipliers (ADMM) is proposed. Due to recent trend toward distributed energy resources in distribution systems, the AC OPF problem has become a difficult challenge to distribution market operators. The difficulties of the AC OPF problem are non-convex and long computational time. To secure the convexity, the SOCP is introduced when formulating the problem. The performance of the SOCP is verified by comparing with the direct current optimal power flow, which is a widely known method to secure convexity, in terms of the dispatch and cost of generation. To shorten the computational time, the consensus ADMM is introduced when solving the problem. The OPF problem is decomposed into sub-problems, which account for the power flow of a single bus. Then, the sub-problems are solved using the consensus ADMM, which consists of parallel computing and communication. Finally, the performance of the SOCP and consensus ADMM is verified by a three-bus radial test system. By using the SOCP, the AC OPF becomes a convex problem while maintaining its modeling rigorousness. By using the consensus ADMM, the OPF problem is solved in distributed manner while having the same result of the centralized method. Furthermore, the effect of the ADMM parameter on the convergence speed is verified.

Whole blood analysis reveals crucial information about various physiological and pathological conditions, including cancer metastasis, infection, and immune status, among others. Despite this rich information, the complex composition of whole blood usually required multiple sample preparation steps to purify targeted analytes. Traditionally, whole blood preparation processes, including centrifugation, lysis, dilution, or staining, are usually manually operated by well-trained technicians using bench-top instruments. This preparation can require a large blood volume and cannot be directly integrated with detection systems. Recently, various studies have integrated microfluidics with electrical sensors for whole blood analysis, with a focus on cell-based analysis, such as cell type, number, morphology, phenotype, and secreted molecules. These miniaturized systems require less sample and shorter reaction times. Besides, the sample processing and analysis can be fully integrated and automated with minimal operations. We believe these systems can transfer the current whole blood analysis from hospitals or laboratories into clinics or home settings to enable real-time and continuous health condition monitoring in point-of-care settings.

Since adoption of the Paris Climate Agreement, efforts to reduce greenhouse gases have been conducted worldwide. Particularly in the transportation sector, researches on electric vehicles are actively underway as an effort to reduce air pollutants, and electric vehicles are expected to become a major transportation vehicle by 2030. If electric vehicles replace existing internal combustion engines, much more electricity will be required to charge the electric vehicles, which will affect the power system. To deal with this growing power demand, it is necessary to forecast and analyze the charging pattern of electric vehicles. This paper uses Bayesian inference methods with convolution to forecast the 24-hour charging pattern for electric vehicles. The results were compared with that by linear regression analysis.

Helicobacter pyloriis one of the most common gastric pathogens, affecting at least half the world's population, and is strongly associated with gastritis, peptic ulcer, gastric adenocarcinoma, and lymphoma. We aimed to assess the efficacy, safety, and immunogenicity of a three-dose oral recombinant H pylorivaccine in children in China.

The gas intake system, micro-turbine (MT) system and the absorption chiller within a MT based Distributed Energy System (DES) demonstration project in Shanghai were experimentally modified. An Computer Aided Testing(CAT) system, including exhaust gas flow rate metering, gas temperature, gas pressure and gas composition testing instruments, together with the data acquisition module of MT, was added to continually monitor and record the real-time data of DES, which is the foundation for further MT based DES energy management, optimal operation and control strategies research .

Accurate reduction and stable fixation are important in the treatment of frontal sinus fracture. Usually, metal plates and screws were used because of easy handling and delicate fixation. However, palpability and possibility for secondary operation for plate removal were shortcomings. For improving these problems, we used absorbable mesh plate for fixation of reduced frontal bones.