Currently, many researchers are using convolutional neural networks(CNN) as a tool to study crowd counting, and they have achieved remarkable research results. However, due to the limited receptive field of CNN, it is difficult to extract global features and model global contextual crowd semantic information, which greatly affects the accuracy of crowd counting. On the other hand, Transformer exhibits excellent capability in extracting global features. Therefore, we propose a crowd counting network named Semantic Information Refinement Network (SIRNet), which combines the advantages of both CNN and Transformer and refines the semantic information of the crowd scenes through a unique feature fusion approach, to address the aforementioned issues. SIRNet consists of three parts: (1) a dual-backbone module consisting of Twins Transformer and CNN, which simultaneously extracts crowd features with global/local semantic information of the crowd; (2) a semantic information fusion module, which fuses the outputs of multiple stages in Twins Transformer and the outputs of CNN branch; (3) a multi-scale residual attention regression module, which reduces counting interference caused by scale differences and background noise, and generates predictive density maps. In addition, we adopt a hybrid supervision approach involving both count-level annotations and location-level annotations to achieve superior counting accuracy. We conduct extensive comparative experiments and ablation experiments on mainstream datasets (ShanghaiTech Part A & Part B, UCF-CC-50, UCF-QNRF, NWPU-Crowd) to demonstrate the effectiveness of the proposed SIRNet in improving counting accuracy.

Glaucoma is a common and severe ocular disease that often leads to vision loss. The information on the optic disc (OD) and blood vessels in fundus images can significantly aid in glaucoma detection. In addition, the use of deep learning models for glaucoma detection is a highly effective approach. We propose a multi-task deep learning model called Multi-GlaucNet that can simultaneously segment the OD and blood vessels, thereby assisting doctors in diagnosing glaucoma. Multi-GlaucNet consists of three modules: the OD segmentation module, blood vessel segmentation module and glaucoma detection module. The OD segmentation module and blood vessel segmentation module both adopt an encoder-decoder structure to segment OD and blood vessels, respectively. The segmentation module is constructed using bottleneck layers in the encoding process and uses Pixel Shuffle and channel attention mechanisms in the decoding process. The detection module uses the ResNet50 network to perform glaucoma detection based on the features extracted from the segmentation modules. Multi-GlaucNet demonstrates outstanding performance in three areas. It achieves a Dice coefficient of 96.7% for OD segmentation on the ORIGA dataset, accuracy of 0.9798 and F1 score of 0.8562 for blood vessel segmentation on a mixed dataset. For glaucoma detection on the REFUGE dataset, it attains the highest accuracy of 0.967 and an area under the curve (AUC) of 0.950. These results validate the effectiveness of Multi-GlaucNet for glaucoma detection. The model's ability to perform multiple tasks with high accuracy and efficiency demonstrates that it is a valuable aiding tool for glaucoma diagnosis.

The goal of class-agnostic counting is to count objects of any category in images. Unlike specific object counting methods (e.g., crowd, vehicle, or crop counting), class-agnostic counting can switch between categories without extensive training, making it more practical for complex real-world applications. The basic process involves extracting features from images, calculating the similarity, and then performing similarity matching to count object instances in the query image. During similarity measurement and matching, image features are converted into one-dimensional vectors. However, some existing methods achieve this through global average pooling, which not only reduces the dimensionality of the channels but also suppresses the diversity of channel feature information, negatively impacting the accuracy of counting results. To address this issue, we propose a Cross-Channel Interaction and Similarity-Aware Network (CISNet) for class-agnostic counting. CISNet consists of four components: (1) feature extraction module; (2) multi-frequency channel self-similarity module that applies a 2D discrete cosine transform to map support image features into a 1D vector, which enhances channel feature diversity and intra-class variability recognition; (3) cross-channel similarity-aware module that optimizes the one-dimensional feature vector of the support image through 1D convolution followed by an activation function, which directly obtains channel weights without reducing feature channel dimensionality; (4) attention feature fusion counting module that integrates the similarity map with the query image feature. We conducted extensive comparative experiments on mainstream datasets (FSC-147, CARPK) to demonstrate the effectiveness of our proposed CISNet in class-agnostic counting tasks.

Incorporating distributed renewable energy sources into heating, power, and cooling systems is facilitating the drive toward intelligent building energy solutions. However, the inherent uncertainties associated with controllable renewable resources pose challenges for the thermo-economic scheduling of smart buildings. Nonetheless, the flexibility inherent in smart buildings can be leveraged through various market mechanisms. Hence, this research introduces a sustainable energy-building system driven by an autonomous solar/dish Stirling engine (SDSE) and wind turbine combined with a sophisticated control strategy and battery storage, which is designed to provide heat and power requirements. The proposed control strategy is also devised to optimize energy generation, ensuring prudent conservation and minimal waste, thereby amplifying overall efficiency and financial viability. The meticulous design of the system is accomplished through advanced MATLAB/Simulink® modeling. A thorough technical sensitivity analysis meticulously hones design parameters, revealing optimal operational thresholds. Simulation outcomes unveil a consistent Stirling engine (SE) efficiency, achieving a pinnacle of 35%, while the SDSE attains over 28%, respectively. The horizontal axis wind turbine, encompassing 100 kW and 500 kW modules, demonstrates power coefficients spanning from 0.18 to 0.09, with corresponding land area requirements ranging from 4.22 m2 to 21.10 m2, emphasizing the pivotal roles of module power and land area optimization. This paper also casts a spotlight on the environmental repercussions of the system, illustrating its potential to avert up to 30,000 kg of CO2 emissions per kWh/year. Moreover, the levelized cost of electricity ranges from 0.13 to 0.16 $/kWh, accompanied by an hourly cost that fluctuates between 3 $/h and 40 $/h, respectively. Conclusively, the developed modeling can be regarded as a significant stride in the realm of hybrid renewable energy systems, replacing the conventional photovoltaic/wind models with cutting-edge solar/wind configurations managed by a sophisticated control strategy and battery storage system.

Energy efficiency has been important since the latter part of the last century. The main object of this survey is to determine the energy efficiency knowledge among consumers. Two separate districts in Bangladesh are selected to conduct the survey on households and showrooms about the energy and seller also. The survey uses the data to find some regression equations from which it is easy to predict energy efficiency knowledge. The data is analyzed and calculated based on five important criteria. The initial target was to find some factors that help predict a person's energy efficiency knowledge. From the survey, it is found that the energy efficiency awareness among the people of our country is very low. Relationships between household energy use behaviors are estimated using a unique dataset of about 40 households and 20 showrooms in Bangladesh's Chapainawabganj and Bagerhat districts. Knowledge of energy consumption and energy efficiency technology options is found to be associated with household use of energy conservation practices. Household characteristics also influence household energy use behavior. Younger household cohorts are more likely to adopt energy-efficient technologies and energy conservation practices and place primary importance on energy saving for environmental reasons. Education also influences attitudes toward energy conservation in Bangladesh. Low-education households indicate they primarily save electricity for the environment while high-education households indicate they are motivated by environmental concerns.

The COVID-19 pandemic has had a catastrophic impact on public health, extending to the food system and people's livelihoods worldwide, including Bangladesh. This study aimed to ascertain the COVID-19 pandemic impacts on livelihood assets in the North-Western areas (Rajshahi and Rangpur) of Bangladesh. Primary data were collected from 320 farmers engaged in high-value agriculture using a multistage sampling method. The data were analysed using first-order structural equation modelling. The findings reveal a significant impact (p < 0.01) of the pandemic on all livelihood assets in Bangladesh. Notably, human assets exhibited the highest impact, with a coefficient of 0.740, followed sequentially by financial (0.709), social (0.684), natural (0.600), physical (0.542), and psychological (0.537) assets. Government-imposed lockdowns and mobility restrictions were identified as the major causes of the pandemic's negative effects on livelihoods, which included lost income, rising food prices, decreased purchasing power, inadequate access to food and medical supplies, increased social insecurity, and a rise in depression, worry, and anxiety among farmers. The effects of COVID-19 and associated policy measures on the livelihoods of high-value crop farmers have reversed substantial economic and nutritional advances gained over the previous decade. This study suggests attention to the sustainable livelihoods of farmers through direct cash transfer and input incentive programs to minimize their vulnerability to a pandemic like COVID-19 or any other crisis in the future.

With the trustworthiness of multimedia data has been challenged by editing tools, image forgery localization aims to identify regions in images that have been modified. Although the existing techniques provide reasonably good results for image forgery localization, with emerging new editing techniques, such models must be retrained and it is highly dependent on the real tampering localization maps. In this paper, we propose an attention-based fusion network that combines the RGB image and noise residual yielding excellent results. Noise residual is commonly regarded as camera model fingerprint, and forgery localization can be detected as deviations from the expected regular pattern. The model consists of three parts: feature extraction, attentional feature fusion, and feature output. The feature extraction module is used to extract RGB image features and noise residuals separately, and the attentional feature fusion module is used to suppress the high frequency components, supplement and enhance model-related artifacts by combining the aforementioned features. Finally, the last module generates images with one channel as the camera model fingerprint. In order to avoid dependence on tampering localization maps, the model is trained with pairs of image patches coming from the same or different camera sensors by means of Siamese network. Experiment results obtained from several datasets show that the proposed technique successfully identifies modified regions, improves the quality of camera model fingerprints, and achieves significantly better performance when compared to the existing techniques.

Reversible information hiding technology can hide secret or sensitive information in the redundant information of the carrier image and completely restore the original image at the receiving end. Current, the difference histogram algorithm appears to be the most attractive for reversible information hiding. However, this technique cannot well balance the embedding capacity and security. To further improve the embedding capacity and security of the difference histogram algorithm, this paper proposes a large-capacity reversible information hiding algorithm based on multi-difference histograms and Gray code. At first, the original image is divided into multiple same-size blocks. Then the blocked image is scrambled with Gray code to improve the system's security. Thereafter, a difference histogram is established for the blocked image and the zero value on the right side of the peak value is selected as the embedding position. Finally, the secret information is embedded. Experimental results show that the proposed algorithm significantly improves the embedding capacity of the carrier image while ensuring the security of the carrier image and the secret information.

In recent years, great progress has been made in the study of crowd counting. Although the crowd counting networks being proposed to solve different problems have achieved satisfactory counting results, the differences of crowd density and scale in the same scene still degrade the overall counting performance. In order to deal with this problem, we propose a Multi-Scale Attention Grading Crowd Counting Network (MSAGNet), which focuses on different crowd densities in the scene by attention mechanism and fuses multi-scale information to reduce scale differences. Specifically, the grading attention feature obtaining module focuses on different densities of people in the scene by attention mechanism, and adaptively assigns corresponding weights to different density regions. Dense regions are given more weights, allowing the model to focus more on that part making the training of that region more accurate and effective. In addition, the multi-scale density feature fusion module fuses the feature maps containing density information to generate the final feature maps. The obtained feature maps contain attention information at different scales, which are density mapped to obtain the estimated density maps. This method can focus on different density regions in the same scene, and simultaneously fuse multi-scale information and attention weight, which can effectively solve the problem of counting dense regions that is difficult to calculate. Extensive experiments on existing crowd counting datasets (UCF_CC_50, ShanghaiTech, UCF-QNRF) show that our method can effectively improve the counting performance.

Makeup transfer aims to extract a specific makeup from a face and transfer it to another face, which can be widely used in portrait beauty, and cosmetics marketing. At present, existing methods can achieve the transfer of the entire facial makeup, but the quality of makeup transfer is not excellent because there may be a mismatch between the two images. In this paper, we propose a facial makeup transfer network based on the Laplacian pyramid, which can better preserve the facial structure from the source image and achieve high-quality transfer results. The model consists of three parts: makeup feature extraction, facial structure feature extraction, and makeup fusion. The makeup extraction part is used to extract the facial makeup from the reference image. And the facial structure feature extraction part is used to extract facial structure from the source image, in order to solve the loss of facial details when extracting facial structural features, we used the method based on Laplacian Pyramid. The makeup fusion part will fuse the facial makeup with facial structure features. Many experiments on the MT dataset have shown that this method can transfer makeup successfully without changing the original facial structure, and achieve advanced performance in various makeup styles.

Accurate crowd counting in congested scenes remain challengeable in the trade-off of efficiency and generalization. For solving this issue, we propose a mobile-friendly solution for the network deployment in high response speed demand scenarios. In order to introduce the profound potential of global crowd representations to lightweight counting model, this work suggests a novel crowd counting aimed mobile vision transformers architecture (CCMTNet), which strives for enhancing the efficiency of the model universality in real-time crowd counting tasks on resource constrained computing devices. The framework of linear CNN network interpolation structure with self-attention blocks endows the model with the ability of local feature extraction and global high-dimensional crowd information processing with low computational cost. In addition, several experimental networks with different scales based on the proposed architecture are comprehensively verified to balance the accuracy loss as compressing the computing costs. Extensive experiments on three mainstream datasets for crowd counting tasks well demonstrate the effectiveness of this proposed network. Particularly, CCMTNet achieves the feasibility of reconciling the counting accuracy and efficiency in comparisons with traditional lightweight CNN networks.

Multi-microgrids have gained interest in academics and industry in recent years. Multi-microgrid (MG) allows the integration of different distributed energy resources (DERs), including intermittent renewables and controllable local generators, and provides a more flexible, reliable, and efficient power grid. This research formulates and proposes a solution for finding optimal location and operation of mobile energy storage (MES) in multi-MG power distribution systems (PDS) with different resources during extreme events to maximize system resiliency. For this purpose, a multi-stage event-based system resiliency index is defined and the impact of the Internet of things (IoT) application in MES operation in multi-MG systems is investigated. Moreover, the demand and price uncertainty impact on multi-MG operational performance indices is presented. This research uses a popular PG & E 69-bus multi-MG power distribution network for simulation and case studies. A new hybrid PSO-TS optimization algorithm is constructed for the simulations to better understand the contributions of MES units and different DERs and IoT on the operational aspects of a multi-MG system. The results obtained from the simulations illustrate that optimal operation of MES and other energy resources, along with the corresponding energy sharing strategies, significantly improves the distribution system operational performance.

With fast-growing computing power and large amounts of data availability, deep learning (DL) algorithms are achieving unprecedented success across different fields. One of its great achievements in health care is medical imaging. Medical image segmentation, such as lung cancer segmentation, is an important tool that facilitates clinical decision systems. U-Net, a recent innovative DL architecture, has shown great promise in segmenting regions of interest in medical images. One of the key advantages of U-Net is that it effectively constructs contracting and expanding paths with symmetric network connection which allows for capturing context information and enabling precise localization in a single network. Although U-Net and its variants have been widely adopted in the medical image segmentation task, there are some limitations that need to be addressed to meet specific requirements, including hardware memory consumption and segmentation accuracy. In this work, we propose a new U-Net based DL architecture, U-PEN (U-net with Progressively Expanded Neuron), that requires less memory on hardware while achieving highly accurate segmentation. The underlying hypothesis behind the proposed architecture is that this model, when compared to existing models, can efficiently capture image context via incorporating nonlinear functions into hidden neurons expansion in the encoder path. The proposed network can eliminate additional convolutional layers thus producing less trainable parameters compared to U-Net. The proposed DL model was tested on two benchmark datasets, namely DRIVE and CHASH_DB1, for different medical image segmentation problems. The experimental results show that the suggested architecture is effective, yielding better performance over U-Net and Residual U-Net in most of the experiments.

In this paper, we propose a novel image encryption method based on logistic chaotic systems and deep autoencoder. In the encryption phase, first, the plaintext image is randomly scrambled by a logistic chaotic system. Then, the random scrambled image is encoded by a deep autoencoder to generate the ciphertext image. In order to obtain the ciphertext image with uniform distribution, we incorporated the uniform distribution constraint into the training of the deep autoencoder. The resulting ciphertext image contains high randomness, which is critical for an excellent image encryption algorithm. Histogram analysis, information entropy analysis, key space analysis, key sensitivity analysis, correlation analysis, and ablation experiments show that the proposed encryption algorithm can effectively resist attacks and has excellent encryption performance while providing high security. (c) 2021 Published by Elsevier B.V.

Nowadays, due to various challenges such as large-scale variation of population, mutual occlusion, perspective distortion and so on, crowd counting has gradually become a hot issue in computer vision. To address the large-scale variation exists in the images, in this paper, we propose a novel multi-scale network called MSNet which aims to maintain continuous variations and count the number of pedestrians accurately. While most state-of-the-arts multi-scale and multi-column networks aim to integrate the scale information of heads with different size, lots of researches still need to do to achieve continuous variations. In MSNet, specifically, the first ten layers of the visual geometry group network(VGG) are used as the backbone to extract the rough features of images and a multi-scale block is employed to maintain the scale information which contains several receptive kernels to obtain a better performance towards the difficulty of scale-variation. Inspired by the knowledge that using multiple small receptive field kernels to replace a single large receptive field will get a better performance, we utilize two dilated convolutions with the receptive field of 5 to replace the large kernel. Our MSNet has moderate increase in computation, and we evaluate our method on three benchmark datasets including ShanghaiTech (Part A: MAE-59.6, RMSE=96.1; Part B: MAE-7.5, RMSE-12.1), UCF-CC-50(MAE-207.9, RMSE=273.8) and UCF-QNRF(MAE-93, RMSE=158) to show the outperformance of our method.

The purpose of this paper is to examine how rising wind energy generation (in MWh) impact the wholesale power market's volatility (in SEK) across four bidding regions in Sweden. Prior investigations show that though the increase in electricity production from wind energy lowers the average day-ahead electricity wholesale prices, however, uncertainty and volatility of market price could rise due to wind energy's intermittent nature. This study results show that Swedish power market experiences higher price volatility in long-run frequency when the generation of wind electricity increases. The reason for this high and volatile electricity price might be found from inflexible baseload power generation. The paper further suggests that volatility in the Swedish power market could be increased due to ambitious renewable electricity target by the Swedish government. The analysis concludes by providing the evidence that further adjustment in regard to the energy and regulatory policies might foster the better integration of a higher share of renewables into the power system. Keywords: Renewable Electricity, Wind Energy, Electricity Market, Price Volatility, Regulatory Policies JEL Classification: Q470 DOI: https://doi.org/10.32479/ijeep.10756

The reliability of the electronic packages depend largely on the selection of suitable interconnect materials based on their mechanical properties. In selecting suitable alternative of Sn-Pb soldering materials, a number of different alloys were proposed as an alternative to the Sn-Pb solder. Most of these are Sn based solder where Sn is the main constituent along with one, two or even three other minor elements. If added in small amount, Bi can improve the wetting ability and reduce melting temperature of lead free solder alloys. It also increases strength of the bulk solder and inhibit the large Ag3Sn formation in the bulk solder. The Anand viscoplastic constitutive model is a popular commercial finite element program built in to many viable FEA packages like ANSYS and ABAQUS. This model uses nine material parameters, and the reliability prediction results are often highly sensitive to the Anand parameters. In this investigation, we have studied the mechanical behavior, and reliability of several different SAC+Bi alloys with various levels of Bismuth. Our goal has been to identify optimal SAC+Bi alloy compositions for various applications and usage environments. The alloys considered were based on SAC305 and SAC405, with various levels of Sn replaced by Bi. The percentages of Bi considered include 1.0%, 2.0%, and 3.0%.In this work, the EDS method was used to determine the approximate chemical composition of the materials. Then uniaxial tensile stress-strain tests were carried out on this SAC+Bi specimens using a micro tension/torsion testing machine with three strain rates (0.001, 0.0001 and 0.00001 (1/sec)), and five different testing temperatures (T = 25, 50, 75, 100 and 125 °C). The temperature dependent mechanical properties of the various new SAC+Bi solders were measured including effective modulus, yield stress, and ultimate tensile strength, and then were compared with those for standard SACN05 (N = 1, 2, 3, 4) lead free alloys. Our findings show that solder alloys with Bi content showed better mechanical properties compared to SACN05, and as the Bi content decreased their strength also decreased correspondingly. The Anand parameters were calculated from each set of stress-strain data, and we used the constitutive model to predict the stress-strain curve at each particular temperature and strain rate used in the experimental testing to evaluate the goodness of fit of the constitutive model to the test data. Good correlation was observed between the experimental curves and the model predictions.