Recently, image analysis research has been actively conducted due to the accumulation of big image data and the development of deep learning. Image analytics research has different characteristics from other data such as data size, real-time, image quality diversity, structural complexity, and security issues. In addition, a large amount of data is required to effectively analyze images with deep-learning models. However, in many fields, the data that can be collected is limited, so there is a need for meta learning based image analysis technology that can effectively train models with a small amount of data. This paper presents a comprehensive survey of meta-learning-based object-tracking techniques. This approach comprehensively explores object tracking methods and research that can achieve high performance in data-limited situations, including key challenges and future directions. It provides useful information for researchers in the field and can provide insights into future research directions.

Accurate segmentation of magnetic resonance (MR) images is crucial for providing doctors with effective quantitative information for diagnosis. However, the presence of weak boundaries, intensity inhomogeneity, and noise in the images poses challenges for segmentation models to achieve optimal results. While deep learning models can offer relatively accurate results, the scarcity of labeled medical imaging data increases the risk of overfitting. To tackle this issue, this paper proposes a novel fuzzy c-means (FCM) model that integrates a deep learning approach. To address the limited accuracy of traditional FCM models, which employ Euclidean distance as a distance measure, we introduce a measurement function based on the skewed normal distribution. This function enables us to capture more precise information about the distribution of the image. Additionally, we construct a regularization term based on the Kullback-Leibler (KL) divergence of high-confidence deep learning results. This regularization term helps enhance the final segmentation accuracy of the model. Moreover, we incorporate orthogonal basis functions to estimate the bias field and integrate it into the improved FCM method. This integration allows our method to simultaneously segment the image and estimate the bias field. The experimental results on both simulated and real brain MR images demonstrate the robustness of our method, highlighting its superiority over other advanced segmentation algorithms.

Chinese herbal slices (CHS) automated recognition based on computer vision plays a critical role in the practical application of intelligent Chinese medicine. Due to the complexity and similarity of herbal images, identifying Chinese herbal slices is still a challenging task. Especially, easily-confused CHS have higher inter-class and intra-class complexity and similarity issues, the existing deep learning models are less adaptable to identify them efficiently. To comprehensively address these problems, a novel tiny easily-confused CHS dataset has been built firstly, which includes six pairs of twelve categories with about 2395 samples. Furthermore, we propose a ResNeSt-CHS model that combines multilevel perception fusion (MPF) and perceptive sparse fusion (PSF) blocks for efficiently recognizing easilyconfused CHS images. To verify the superiority of the ResNeSt-CHS and the effectiveness of our dataset, experiments have been employed, validating that the ResNeSt-CHS is optimal for easily-confused CHS recognition, with 2.1% improvement of the original ResNeSt model. Additionally, the results indicate that ResNeSt-CHS is applied on a relatively small-scale dataset yet high accuracy. This model has obtained state-of-the-art easily-confused CHS classification performance, with accuracy of 90.8%, far beyond other models (EfficientNet, Transformer, and ResNeSt, etc) in terms of evaluation criteria.

The rapid progress of social media allows more people to express their feelings and opinions online. Many data on social media contains people's emotional information, which can be used for people's psychological analysis and emotional calculation. This research is based on the simplified psychological scale algorithm of multi-theory integration. It aims to accurately analyze people's psychological emotion. According to the comparative analysis of algorithm performance, the results show that the highest recall rate of the algorithm in this study is 95%, while the highest recall rate of the item response theory algorithm and the social network analysis algorithm is 68% and 87%. The acceleration ratio and data volume of the research algorithm are analyzed. The results show that when 400,000 data are calculated in the Hadoop cluster and there are 8 nodes, the maximum acceleration ratio is 40%. When the data volume is 8GB, the maximum scale ratio of 8 nodes is 43%. Finally, we carried out an empirical analysis on the model that compute the population's psychological and emotional conditions. During the analysis, the psychological simplification scale algorithm was adopted and multiple theories were taken into account. Then, we collected negative comments and expressions about Japan's discharge of radioactive water in microblog and compared them with the trend derived by the model. The results were consistent. Therefore, this research model has achieved good results in the emotion classification of microblog comments.

Customer reviews are the second-most reliable source of information, followed by family and friend referrals. However, there are many existing customer reviews. Some online shopping platforms address this issue by ranking customer reviews according to their usefulness. However, we propose an alternative method to rank customer reviews, given that this system is easily manipulable. This study aims to create a ranking model for reviews based on their usefulness by combining product and seller service aspects from customer reviews. This methodology consists of six primary steps: data collection and preprocessing, aspect extraction and sentiment analysis, followed by constructing a regression model using random forest regression, and the review ranking process. The results demonstrate that the ranking model with service considerations outperformed the model without service considerations. This demonstrates the model's superiority in the three tests, which include a comparison of the regression results, the aggregate helpfulness ratio, and the matching score.

Demand response (DR) refers to the customers' active reaction with respect to the changes of market pricing or incentive policies. DR plays an important role in improving network reliability, minimizing operational cost and increasing end users' benefits. Hence, the integration of DR in the microgrid (MG) management is gaining increasing popularity nowadays. This paper proposes a day-ahead MG scheduling framework in conjunction with DR and investigates the impact of DR in optimizing load profile and reducing overall power generation costs. A linear responsive model considering time of use (TOU) price and incentive is developed to model the active reaction of customers' consumption behaviors. Thereafter, a novel multi-swarm sine cosine algorithm (MSCA) is proposed to optimize the total power generation costs in the framework. In the proposed MSCA, several sub-swarms search for better solutions simultaneously which is beneficial for improving the population diversity. A cooperative learning scheme is developed to realize knowledge dissemination in the population and a competitive substitution strategy is proposed to prevent local optima stagnation. The simulation results obtained by the proposed MSCA are compared with other meta-heuristic algorithms to show its effectiveness in reducing overall generation costs. The outcomes with and without DR suggest that the DR program can effectively reduce the total generation costs and improve the stability of the MG network.

Graph-based document models have good capabilities to reveal inter-dependencies among unstructured text data. Natural language processing (NLP) systems that use such models as an intermediate representation have shown good performance. This paper proposes a novel fuzzy graph-based document model and to demonstrate its effectiveness by applying fuzzy logic tools for text summarization. The proposed system accepts a text document as input and identifies some of its sentence level features, namely sentence position, sentence length, numerical data, thematic word, proper noun, title feature, upper case feature, and sentence similarity. The fuzzy membership value of each feature is computed from the sentences. We also propose a novel algorithm to construct the fuzzy graph as an intermediate representation of the input document. The Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metric is used to evaluate the model. The evaluation based on different quality metrics was also performed to verify the effectiveness of the model. The ANOVA test confirms the hypothesis that the proposed model improves the summarizer performance by 10% when compared with the state-of-the-art summarizers employing alternate intermediate representations for the input text.

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

Wireless sensor network (WSN) consists of large number of sensor nodes that are deployed in geographical locations to collect sensed information, process data and communicate it to the control station for further processing. Due the unfriendly environment where the sensors are deployed, there exist many possibilities of malicious nodes which performs malicious activities in the network. Therefore, the security threats affect performance and life time of sensor networks, whereas various security aspects are there to address security issues in WSN namely Cryptography, Trust Management, Intrusion Detection System (IDS) and Intrusion Prevention Systems (IPS). However, IDS detect the malicious activities and produce an alarm. These malicious activities exploit vulnerabilities in the network layer and affect all layers in the network. Existing feature selection methods such as filter-based methods are not considering the redundancy of the selected features and wrapper method has high risk of overfitting the classification of intrusion. Due to overfitting, the classification algorithm fails to detect the intrusion in better manner. The main objective of this paper is to provide the efficient feature selection algorithm which was suitable for any type classification algorithm to detect the intrusion in an effective manner. This paper, the security of the network is addressed by proposing Feature Selection Algorithm using Chi Squared with Ensemble Method (FSChE). The proposed scheme employs the combination of decision tree along with the random forest classification algorithm to form ensemble classifier. The experimental results justify the feasibility of the proposed scheme in terms of attack detection, packet delivery ratio and time analysis by employing NSL KDD cup data Set. The obtained results shows that the proposed ensemble method increases the overall performance by 10% to 25% with respect to mentioned parameters.

Advances in deep learning technology have enabled the generation of more realistic deepfakes, which not only endanger individuals' identities but also exploit vulnerabilities in face recognition systems. The majority of existing deepfake detection methods have primarily focused on RGB-based analysis, offering unreliable performance in terms of detection accuracy and time. To address the issue, a grayscale-based deepfake detection method has recently been proposed. This method significantly reduces detection time while providing comparable accuracy to RGB-based methods. However, despite its significant effectiveness, the "key components" that directly affect the performance of grayscale-based deepfake detection have not been systematically analyzed. In this paper, we target three key components: RGB-to-grayscale conversion method, brightness level in grayscale, and resolution level in grayscale. To analyze their impacts on the performance of grayscale-based deepfake detection, we conducted comprehensive evaluations, including component-wise analysis and comparative analysis using real-world datasets. For each key component, we quantitatively analyzed its characteristics' performance and identified differences between them. Moreover, we successfully verified the effectiveness of an optimal combination of the key components by comparing it with existing deepfake detection methods.

In the upcoming era of transportation, a groundbreaking technology, known as vehicle-to-everything (V2X) communication, is poised to redefine our driving experience and revolutionize traffic management. Real-time and secure communication plays a pivotal role in V2X networks, with the decision-making process being a key factor in establishing communication and determining malicious nodes. The proposed framework utilizes a directed acyclic graph (DAG) to facilitate real-time processing and expedite decision-making. This innovative approach ensures seamless connectivity among vehicles, the surrounding infrastructure, and various entities. To enhance communication efficiency, the entire roadside unit (RSU) region can be subdivided into various sub-regions, allowing RSUs to monitor and govern each sub-region. This strategic approach significantly reduces transaction approval time, thereby improving real-time communication. The framework incorporates a consensus mechanism to ensure robust security, even in the presence of malicious nodes. Recognizing the dynamic nature of V2X networks, the addition and removal of nodes are aligned. Communication latency is minimized through the deployment of computational resources near the data source and leveraging edge computing. This feature provides invaluable recommendations during critical situations that demand swift decision-making. The proposed architecture is further validated using the "veins" simulation tool. Simulation results demonstrate a remarkable success rate exceeding 95%, coupled with a significantly reduced consensus time compared to prevailing methodologies. This comprehensive approach not only addresses the evolving requirements of secure V2X communication but also substantiates practical success through simulation, laying the foundation for a transformative era in transportation.

Employing multiple drones as a swarm to complete missions can sharply improve the working efficiency and expand the scope of investigation. Remote UAV swarms utilize satellites as relays to forward investigation information. The increasing amount of data demands higher transmission rate and complex field network coding (CFNC) is deemed as an effective solution for data return. CFNC applied to UAV swarms enhances transmission efficiency by occupying only two time slots, which is less than other network coding schemes. However, conventional CFNC applied to UAVs is combined with constant coding and modulation scheme and results in a waste of spectrum resource when the channel conditions are better. In order to avoid the waste of power resources of the relay satellite and further improve spectral efficiency, a CFNC transmission scheme with MPSK modulation is proposed in this paper. For the proposed scheme, the satellite relay no longer directly forwards information, but transmits information after processing according to the current channel state. The proposed transmission scheme not only maintains throughput advantage of CFNC, but also enhances spectral efficiency, which obtains higher throughput performance. The symbol error probability (SEP) and throughput results corroborated by Monte Carlo simulation show that the proposed transmission scheme improves spectral efficiency in multiples compared to the conventional CFNC schemes. In addition, the proposed transmission scheme enhances the throughput performance for different topology structures while keeping SEP below a certain value.

This paper introduces a method aimed at diagnosing the presence or absence of lesions by detecting anomalies in Chest X-ray images. The proposed approach is based on the PatchCore anomaly detection method, which extracts a feature vector containing location information of an image patch from normal image data and calculates the anomaly distance from the normal vector. However, applying PatchCore directly to medical image processing presents challenges due to the possibility of diseases occurring only in specific organs and the presence of image noise unrelated to lesions. In this study, we present an image alignment method that utilizes affine transformation parameter prediction to standardize already captured X-ray images into a specific composition. Additionally, we introduce a region-specific abnormality detection method that requires affine-transformed chest X-ray images. Furthermore, we propose a method to enhance application efficiency and performance through feature map hard masking. The experimental results demonstrate that our proposed approach achieved a maximum AUROC (Area Under the Receiver Operating Characteristic) of 0.774. Compared to a previous study conducted on the same dataset, our method shows a 6.9% higher performance and improved accuracy.

In this paper, we introduce a web-based system that leverages the capabilities of the ρ(rho)-algorithm, which is a Structure Information Control Net (SICN)-oriented process mining algorithm, with open-source platforms, including Django, Graphviz, and Cytoscape, to facilitate the rediscovery and visualization of business process models. Our approach involves discovering SICN-oriented process models from process instances from the IEEE XESformatted process enactment event logs dataset. This discovering process is facilitated by the ρ-algorithm, and visualization output is transformed into either a JSON or DOT formatted file, catering to the compatibility requirements of Cytoscape or Graphviz, respectively. The proposed system utilizes the robust Django platform, which enables the creation of a userfriendly web interface. This interface offers a clear, concise, modern, and interactive visualization of the rediscovered business processes, fostering an intuitive exploration experience. The experiment conducted on our proposed web-based process discovery system demonstrates its ability and efficiency showing that the system is a valuable tool for discovering business process models from process event logs. Its development not only contributes to the advancement of process mining but also serves as an educational resource. Readers, students, and practitioners interested in process mining can leverage this system as a completely free process miner to gain hands-on experience in rediscovering and visualizing process models from event logs.

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

This research identifies specific user experience factors that have positive impact on user's behavior intention to use so that a new technology called stretchable display(SD) can be accepted and spread in the market. To show how these factors can be applied to SD home appliances, a few concrete designs have been suggested. In the first stage of the research, the initial concept of innovative product design with stretchable display was derived by developing a scenario that solves the expected experience by home product users through the attributes of the SD technology. In the second stage, a scenario of the product to which a stretchable display was applied was suggested to investigate the expected experience factors that influence the behavior intention to use. As a result of the analysis, users showed a positive intention to use for the factors of Functionality of Space and Life Support, Presentation of Preferences, and Customization of Emotions, provided by the product with SD technology applied. In the next stage, based on the verified user experience factors, multifunctional kitchen appliances design, smart furniture design with flexible surfaces, and smart interior wall tile design have been derived. After all, the differentiated transformable interface designs shown through this process have been suggested as three-dimensional soft-physical button design and attachable design for multi-curved soft furniture. This study is significant as it emphasizes a user-centered design process over a technology-centered approach, enhancing market acceptability and focusing on design features aligned with the user's expected experience.

In this study, a high-speed template matching system is proposed for wafer-vision alignment. The proposed system is designed to rapidly locate markers in semiconductor equipment used for wafer-vision alignment. We optimized and implemented a template-matching algorithm for the high-speed processing of high-resolution wafer images. Owing to the simplicity of wafer markers, we removed unnecessary components in the algorithm and designed the system using a field-programmable gate array (FPGA) to implement high-speed processing. The hardware blocks were designed using the Xilinx ZCU104 board, and the pyramid and matching blocks were designed using programmable logic for accelerated operations. To validate the proposed system, we established a verification environment using stage equipment commonly used in industrial settings and reference-software-based validation frameworks. The output results from the FPGA were transmitted to the wafer-alignment controller for system verification. The proposed system reduced the data-processing time by approximately 30% and achieved a level of accuracy in detecting wafer markers that was comparable to that achieved by reference software, with minimal deviation. This system can be used to increase precision and productivity during semiconductor manufacturing processes.

The construction of virtual indoor spaces is crucial for the development of metaverses, virtual production, and other 3D content domains. Traditional methods for creating these spaces are often cost-prohibitive and labor-intensive. To address these challenges, we present a pipeline for generating digital twins of real indoor environments from RGB-D camera-scanned data. Our pipeline synergizes space structure estimation, 3D object detection, and the inpainting of missing areas, utilizing deep learning technologies to automate the creation process. Specifically, we apply deep learning models for object recognition and area inpainting, significantly enhancing the accuracy and efficiency of virtual space construction. Our approach minimizes manual labor and reduces costs, paving the way for the creation of metaverse spaces that closely mimic real-world environments. Experimental results demonstrate the effectiveness of our deep learning applications in overcoming traditional obstacles in digital twin creation, offering high-fidelity digital replicas of indoor spaces. This advancement opens for immersive and realistic virtual content creation, showcasing the potential of deep learning in the field of virtual space construction.

The current automotive industry is transitioning from Internal Combustion Engine (ICE) vehicles to Electric Vehicles (EVs), adopting a mixed assembly production approach to respond to fluctuating demand. While mixed assembly production offers the advantages of lower investment costs and flexibility in responding to changing demands, the supply of EV components requires more extensive provisioning compared to ICE vehicle components, potentially leading to unexpected issues such as congestion of transport vehicles. This study proposes a digital twin system architecture that uses Discrete Event Simulation (DES) and Business Intelligence (BI) tools to specifically address logistics challenges. The proposed architecture facilitates real-time, data-driven decision making across three layers; Data source, Simulation, and BI. It was implemented in factories engaged in the mixed assembly production of ICE and EV vehicles. The simulation challenges involve a tier 1 vendor supplying parts to Korean automobile manufacturers that produce both ICE and EV parts. A total of 240 scenarios were created to run the simulations. The deployment of the proposed architecture demonstrates its capability to quickly respond to diverse experimental situations and promptly identify potential issues.

The need for secure user authentication in blockchain-based applications has been growing with the increased adoption of Decentralized Identity (DID) credentials in blockchain. Zokrates, a tool designed to protect user privacy within smart contracts, had a limitation in that it could not accept authenticated user information such as credentials, only allowing the use of manually inputted data. In this paper, we propose a smart contract system that securely validates DID credentials to overcome the limitations of traditional centralized authentication systems. This system ensures the safe identification of users within blockchain-based applications by authenticating their identities in a trusted manner within the blockchain. As the demand for user authentication in blockchain rises, this paper emphasizes the significance of a blockchain-based identity verification system that guarantees both privacy and security. Leveraging the Zero-Knowledge Proof method and utilizing the Zokrates tool, this innovative approach aims to provide solutions for the digital identity verification process, thereby expanding the scope of blockchain technology applications. Moreover, we also provide a CLI for each entity. We help anyone who wants to authenticate their identity using the tool to safely verify it on-chain.

As problems such as water pollution and fish species depletion have become serious, a land-based fish farming is receiving a great attention for ensuring stable productivity. In the fish farming, it is important to determine the timing of shipments, as one of key factors to increase net profit on the aquaculture. In this paper, we propose a system for predicting net profit to support decision of timing of shipment using fish farming-related statistical data. The prediction system consists of growth and farm-gate price prediction models, a cost statistics table, and a net profit estimation algorithm. The Gaussian process regression (GPR) model is exploited for weight prediction based on the analysis that represents the characteristics of the weight data of cultured fish under the assumption of Gaussian probability processes. Moreover, the long short-term memory (LSTM) model is applied considering the simple time series characteristics of the farm-gate price data. In the case of GPR model, it allows to cope with data missing problem of the weight data collected from the fish farm in the time and temperature domains. To solve the problem that the data acquired from the fish farm is aperiodic and small in amount, we generate the corresponding data by adopting a data augmentation method based on the Gaussian model. Finally, the estimation method for net profit is proposed by concatenating weight, price, and cost predictions. The performance of the proposed system is analyzed by applying the system to the Korean flounder data.

Many legacy information systems are currently being clouded. This is due to the advantage of being able to respond flexibly to the changes in user needs and system environment while reducing the initial investment cost of IT infrastructure such as servers and storage. The infrastructure of the information system migrated to the cloud is being integrated through the API connections, while being subdivided by using MSA (Micro Service Architecture) internally. DBMS (Database Management System) is also becoming larger after cloud migration. Scale calculation in most layers of the application architecture can be measured and calculated from auto-scaling perspective, but the method of hardware scale calculation for DBMS has not been established as standardized methodology. If there is an error in hardware scale calculation of DBMS, problems such as poor performance of the information system or excessive auto-scaling may occur. In addition, evaluating hardware size is more crucial because it also affects the financial cost of the migration. CPU is the factor that has the greatest influence on hardware scale calculation of DBMS. Therefore, this paper aims to calculate the conversion factor for CPU scale calculation that will facilitate the cloud migration between heterogeneous DBMS. In order to do that, we utilize the concept and definition of hardware capacity planning and scale calculation in the on-premise information system. The methods to calculate the conversion factor using TPC-H tests are proposed and verified. In the future, further research and testing should be conducted on the size of the segmented CPU and more heterogeneous DBMS to demonstrate the effectiveness of the proposed test model.