Search

With the arrival of the 5G era, wireless communication technologies and services are rapidly exhausting the limited spectrum resources. Spectrum auctions came into being, which can effectively utilize spectrum resources. Because of the complexity of the electronic spectrum auction network environment, the security of spectrum auction can not be guaranteed. Most scholars focus on researching the security of the single-sided auctions, while ignoring the practical scenario of a secure double spectrum auction where participants are composed of multiple sellers and buyers. Researchers begin to design the secure double spectrum auction mechanisms, in which two semi-honest agents are introduced to finish the spectrum auction rules. But these two agents may collude with each other or be bribed by buyers and sellers, which may create security risks, therefore, a secure double spectrum auction is proposed in this paper. Unlike traditional secure double spectrum auctions, the spectrum auction server with Software Guard Extensions (SGX) component is used in this paper, which is an Ethereum blockchain platform that performs spectrum auctions. A secure double spectrum protocol is also designed, using SGX technology and cryptographic tools such as Paillier cryptosystem, stealth address technology and one-time ring signatures to well protect the private information of spectrum auctions. In addition, the smart contracts provided by the Ethereum blockchain platform are executed to assist offline verification, and to verify important spectrum auction information to ensure the fairness and impartiality of spectrum auctions. Finally, security analysis and performance evaluation of our protocol are discussed.

Abstract Background Ultrasound imaging is the most frequently performed for the patients with chronic hepatitis or liver cirrhosis. However, ultrasound imaging is highly operator dependent and interpretation of ultrasound images is subjective, thus well-trained radiologist is required for evaluation. Automated classification of liver fibrosis could alleviate the shortage of skilled radiologist especially in low-to-middle income countries. The purposed of this study is to evaluate deep convolutional neural networks (DCNNs) for classifying the degree of liver fibrosis according to the METAVIR score using US images. Methods We used ultrasound (US) images from two tertiary university hospitals. A total of 7920 US images from 933 patients were used for training/validation of DCNNs. All patient were underwent liver biopsy or hepatectomy, and liver fibrosis was categorized based on pathology results using the METAVIR score. Five well-established DCNNs (VGGNet, ResNet, DenseNet, EfficientNet and ViT) was implemented to predict the METAVIR score. The performance of DCNNs for five-level (F0/F1/F2/F3/F4) classification was evaluated through area under the receiver operating characteristic curve (AUC) with 95% confidential interval, accuracy, sensitivity, specificity, positive and negative likelihood ratio. Results Similar mean AUC values were achieved for five models; VGGNet (0.96), ResNet (0.96), DenseNet (0.95), EfficientNet (0.96), and ViT (0.95). The same mean accuracy (0.94) and specificity values (0.96) were yielded for all models. In terms of sensitivity, EffcientNet achieved highest mean value (0.85) while the other models produced slightly lower values range from 0.82 to 0.84. Conclusion In this study, we demonstrated that DCNNs can classify the staging of liver fibrosis according to METAVIR score with high performance using conventional B-mode images. Among them, EfficientNET that have fewer parameters and computation cost produced highest performance. From the results, we believe that DCNNs based classification of liver fibrosis may allow fast and accurate diagnosis of liver fibrosis without needs of additional equipment for add-on test and may be powerful tool for supporting radiologists in clinical practice.

Recent user recognition technologies have focused on biometric signals to remotely identify users in the access management, medical welfare, and public sectors. The electrocardiogram (ECG) signal is an individual’s unique electrophysiological signal generated within the body and is difficult to forge or change; thus, it can be used to uniquely identify the user. Existing user identification systems based on ECG signals detect R peaks according to morphological features and use a fiducial-based segmentation process for data normalization. However, this process does not detect a distinct R peak due to motion artifacts generated by the movement of the subject, thereby degrading identification accuracy. To address the problem of decreasing peak accuracy of the fiducial-based segmentation data, this study proposes a user identification system based on one-dimensional neural networks using periodic non-fiducial-based segmentation data that do not overlap in the time domain. The proposed system comprises a preprocessing step for data denoising, a non-fiducial-based and non-overlap segmentation step, and a step for classifying users using a one-dimensional shallow neural network. In the experiment, when using self-acquired 10-second ECG signal data that were divided into non-fiducial and non-overlapping segments, the long short-term memory (LSTM), bidirectional LSTM, and one-dimensional convolutional neural network (CNN) models achieved accuracies of 92.01%, 93.13%, and 95.51%, respectively, with the 1D CNN model exhibiting the best accuracy. The proposed system demonstrated a 25.48% improvement in accuracy on non-fiducial segmented data compared to the 1D CNN model, which achieved an accuracy of 70.03% on fiducial segmented data. Moreover, when tested on publicly available ECG datasets, including MIT-BIH, ECG-ID, and PTB-XL, the proposed system exhibited a user identification accuracy of over 94%, confirming its superior performance.

In recent dentistry research, deep learning techniques have been employed for various tasks, including detecting and segmenting third molars and inferior alveolar nerves, as well as classifying their positional relationships. Prior studies using convolutional neural networks (CNNs) have successfully detected the adjacent area of the third molar and automatically classified the relationship between the inferior alveolar nerves. However, deep learning models have limitations in learning the diverse patterns of teeth and nerves due to variations in their shape, angle, and size across individuals. Moreover, unlike object classification, relationship classification is influenced by the proximity of teeth and nerves, making it challenging to accurately interpret the classified samples. To address these challenges, we propose a masking image-based classification system. The primary goal of this system is to enhance the classification performance of the relationship between the third molar and inferior alveolar nerve while providing diagnostic evidence to support the classification. Our proposed system operates by detecting the adjacent areas of the third molar, including the inferior alveolar nerve, in panoramic radiographs (PR). Subsequently, it generates masked images of the inferior alveolar nerve and third molar within the extracted regions of interest. Finally, it performs the classification of the relationship between the third molar and inferior alveolar nerve using these masked images. The system achieved a mean average precision (mAP) of 0.885 in detecting the region of interest in the third molar. Furthermore, the performance of the existing CNN-based positional relationship classification was evaluated using four classification models, resulting in an average accuracy of 0.795. For the segmentation task, the third molar and inferior alveolar nerve in the detected region of interest exhibited a dice similarity coefficient (DSC) of 0.961 and 0.820, respectively. Regarding the proposed masking image-based classification, it demonstrated an accuracy of 0.832, outperforming the existing method by approximately 3%, thus confirming the superiority of our proposed system.

With the advances in deep learning, including Convolutional Neural Networks (CNN), automated diagnosis technology using medical images has received considerable attention in medical science. In particular, in the field of ultrasound imaging, CNN trains the features of organs through an amount of image data, so that an expert-level automatic diagnosis is possible only with images of actual patients. However, CNN models are also trained on the features that reflect the inherent bias of the imaging machine used for image acquisition. In other words, when the domain of data used for training is different from that of data applied for an actual diagnosis, it is unclear whether consistent performance can be provided by the domain bias. Therefore, we investigate the effect of domain bias on the model with liver ultrasound imaging data obtained from multiple domains. We have constructed a dataset considering the manufacturer and the year of manufacturing of 8 ultrasound imaging machines. First, training and testing were performed by dividing the entire data, in a commonly used method. Second, we have utilized the training data constructed according to the number of domains for the machine learning process. Then we have measured and compared the performance on internal and external domain data. Through the above experiment, we have analyzed the effect of domains of data on model performance. We show that the performance scores evaluated with the internal domain data and the external domain data do not match. We especially show that the performance measured in the evaluation data including the internal domain was much higher than the performance measured in the evaluation data consisting of the external domain. We also show that 3-level classification performance is slightly improved over 5-level classification by mitigating class imbalance by integrating similar classes. The results highlight the need to develop a new methodology for mitigating the machine bias problem so that the model can work correctly even on external domain data, as opposed to the usual approach of constructing evaluation data in the same domain as the training data.

The incidence of cancer among modern people has recently increased due to various reasons such as eating habits, smoking, and drinking. Therefore, medical image analysis for effective disease diagnosis is considered an extremely important diagnostic tool. In particular, endoscopy is used as a representative screening method for diagnosing diseases of the digestive system. However, it is quite difficult to quickly and thoroughly analyze medical data by relying solely on human vision, such as with endoscopy. Therefore, the purpose of this study was to reduce the fatigue of medical staff through the use of automated disease classification of the digestive system. To automate disease classification, we trained a total of six models, ranging from relatively old deep-learning-based models to recently published approaches. Additionally, to increase the number of medical data, which is generally insufficient, we applied data augmentation using two adversarial generative neural network-based models. We utilized Kvasir version 2 data for the experiment and demonstrated that InceptionNet-V3 showed the best performance improvement when data augmentation based on a Star-GAN was applied experimentally. Furthermore, the approach also exhibited good performance in terms of the F1-Score, which was used to evaluate the safety of the model. Thus, we propose a disease classification automation model centered on safer performance.

Due to the advent of the expressions of data other than tabular formats, the topological compositions which make samples interrelated came into prominence. Analogically, those networks can be interpreted as social connections, dataflow maps, citation influence graphs, protein bindings, etc. However, in the case of social networks, it is highly crucial to evaluate the labels of discrete communities. The reason for such a study is the importance of analyzing graph networks to partition the vertices by only using the topological features of network graphs. For each interaction-based entity, a social graph, a mailing dataset, and two citation sets are selected as the testbench repositories. The research mainly focused on evaluating the significance of three artificial intelligence approaches on four different datasets consisting of vertices and edges. Overall, one of these methods so-called "harmonic functions", resulted in the best form to classify those constituents of graph-shaped datasets. This research not only accessed the most valuable method but also determined how graph neural networks work and the need to improve against non-neural network approaches which are faster and computationally cost-effective. Also in this paper, we will show that there is a limit to be accessed by prospective graph neural network variations by using the topological features of trialed networks.

Recently, the tourism trend has been shifting towards the Tourism 2.0 paradigm due to increased travel experiences and the increase in acquiring and sharing information through the Internet. The Tourism 2.0 paradigm requires developing intelligent tourism service tools for positive effects such as time savings and marketing utilization. Existing tourism service tools recommend tourist destinations based on the relationship between tourists and tourist destinations or tourism patterns, so it is difficult to make recommendations in situations where information is insufficient or changes in real time. In this paper, we propose a real-time recommendation system for tourism (R2Tour) that responds to changing situations in real time, such as external factors and distance information, and recommends customized tourist destinations according to the type of tourist. R2Tour trains a machine learning model with situational information such as temperature and precipitation and tourist profiles such as gender and age to recommend the top five nearby tourist destinations. To verify the recommendation performance of R2Tour, six machine learning models, including K-NN and SVM, and information on tourist attractions in Jeju Island were used. As a result of the experiment, R2Tour was verified with accuracy of 77.3%, micro-F1 0.773, and macro-F1 0.415. Since R2Tour trains tourism patterns based on situational information, it is possible to recommend new tourist destinations and respond to changing situations in real time. In the future, R2Tour can be installed in vehicles to recommend nearby tourist destinations or expanded to tasks in the tourism industry, such as a smart target advertising system.

In this paper, to increase the attack success rate, we analyzed the distribution of all collected keyboard data based on the distance of time and keyboard scancode data, which presents the crucial data from the previous study. To achieve this, we derived time-distance based features that have higher attack success rates than in previous studies. The proposed attack method defines 6 features, and evaluates the performance based on 18 datasets. For performance evaluation, the accuracy, precision, recall, F1-score, and AUC of Datasets (1 to 3) were compared, and two experiments showed improved overall performance by at least 10.6 % and up to 16.1 % compared to previous studies in terms of the performance evaluation for each feature, comparison of variations in maximum performance, comparison of variations in performance of each feature, and comparison of variations in overall performance. Moreover, the best accuracy, which represents the probability of password exposure, was 96.7 %, which suggests that our proposed attack method has a higher accuracy than the previous study (96.2 %). In conclusion, we demonstrated that password authentication is neutralized by stealing the user password more effectively. For future research, we will focus on improving the attack success rate with respect to accuracy and overall performance numbers, using not only machine learning, but also deep learning.

Localization plays an important role in the field of Wireless Sensor Networks (WSNs) and robotics. Currently, localization is a very vibrant scientific research field with many potential applications. Localization offers a variety of services for the customers, for example, in the field of WSN, its importance is unlimited, in the field of logistics, robotics, and IT services. Particularly localization is coupled with the case of human-machine interaction, autonomous systems, and the applications of augmented reality. Also, the collaboration of WSNs and distributed robotics has led to the creation of Mobile Sensor Networks (MSNs). Nowadays there has been an increasing interest in the creation of MSNs and they are the preferred aspect of WSNs in which mobility plays an important role while an application is going to execute. To overcome the issues regarding localization, the authors developed a framework of three algorithms named Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF) and Particle Filter (PF) Localization algorithms. In our previous study, the authors only focused on EKF-based localization. In this paper, the authors present a modified Kalman Filter (KF) for localization based on UKF and PF Localization. In the paper, all these algorithms are compared in very detail and evaluated based on their performance. The proposed localization algorithms can be applied to any type of localization approach, especially in the case of robot localization. Despite the harsh physical environment and several issues during localization, the result shows an outstanding localization performance within a limited time. The robustness of the proposed algorithms is verified through numerical simulations. The simulation results show that proposed localization algorithms can be used for various purposes such as target tracking, robot localization, and can improve the performance of localization.

Research on electrocardiogram (ECG) signals has been actively undertaken to assess their value as a next generation user recognition technology, because they require no stimulation and are robust against forgery and modification. However, even within the same user, the heart rate and waveform of ECG signals will vary depending on physical activity, mental effects, and measurement time. Therefore, when data acquired across changes in the user state is used as registered data, an overfitting problem occurs due to data generalization, which degrades the recognition performance for newly acquired data. Therefore, in this paper, we propose parallel ensemble networks to solve the overfitting problem and prevent the degradation. First, ECG signals acquired in various environments are used as the input data of parallel convolutional neural networks (CNNs). Each CNN is set up with different parameters to detect different features. The ECG signals outputted from each network are classified for each subject, and then fused into one database to be used as registered data for re-training. Instead of fusing all the output signals from each network, only the ECG signals of Top-3 networks showing excellent performance are fused and composed of registered data. The reconstructed registered data are used for user recognition, by re-training with time independent comparison data in the CNN. The experimental results of comparing the proposed parallel ensemble networks with those of previous studies using the self-acquired actual ECG signals show that the proposed method achieves recognition performance higher than the previous studies, with an accuracy rate of 98.5%.

As the request for network access and a variety of services, the Internet of Things (IoT) has evolved from special networks with simple functions to global information infrastructure, challenging the current authentication mechanism. Due to the dense population in the massive IoT scenario, the increasing connectivity requirements may aggravate the load of the authentication entity and increase the corresponding processing delay, which may further jeopardize the service and affect the quality of the experience. To solve this problem, especially for the case in which the authentication infrastructure is unavailable, a physical layer authentication method is proposed in this paper, which is based on modified physical authentication flow, a modified PDA algorithm based on soft information, and authentication key randomization based on hash mapping. Through Monte Carlo simulations, it is observed that the proposed physical layer authentication mechanism shows a favorable gain compared with that of the existing methods.

Aesthetic appeal and image quality are two important features of photographs, which play the dominant role when people clean their albums. Currently, the objective image quality assessment has been documented very well whereas the objective aesthetic appeal assessment algorithms are not developed well enough. This paper first subjectively evaluated image quality and aesthetic appeal separately of 339 photographs across different levels of depth of field. With the subjective data, the paper proposed two mathematical models to predict the subjective aesthetic appeal from subjective image quality. More specifically, depth of field, as a common photographic feature, was investigated to see how it influenced aesthetic appeal and image quality. 32 participants were asked to score for the aesthetic appeal and image quality. With these subjective scores, we used two methods - linear regression and deep neural networks - to build models separately to predict aesthetic appeal from image quality. We found that both models worked well on the valid dataset and the performance of the deep neural networks model was better than the linear regression model.

In the above article [1], reference [2] was missing.

Plant diseases are a major cause of reduction in agricultural output, which leads to severe economic losses and unstable food supply. The citrus plant is an economically important fruit crop grown and produced worldwide. However, citrus plants are easily affected by various factors, such as climate change, pests, and diseases, resulting in reduced yield and quality. Advances in computer vision in recent years have been widely used for plant disease detection and classification, providing opportunities for early disease detection, and resulting in improvements in agriculture. Particularly, the early and accurate detection of citrus diseases, which are vulnerable to pests, is very important to prevent the spread of pests and reduce crop damage. Research on citrus pest disease is ongoing, but it is difficult to apply research results to cultivation owing to a lack of datasets for research and limited types of pests. In this study, we built a dataset by self-collecting a total of 20,000 citrus pest images, including fruits and leaves, from actual cultivation sites. The constructed dataset was trained, verified, and tested using a model that had undergone five transfer learning steps. All models used in the experiment had an average accuracy of 97% or more and an average f1 score of 96% or more. We built a web application server using the EfficientNet-b0 model, which exhibited the best performance among the five learning models. The built web application tested citrus pest disease using image samples collected from websites other than the self-collected image samples and prepared data, and both samples correctly classified the disease. The citrus pest automatic diagnosis web system using the model proposed in this study plays a useful auxiliary role in recognizing and classifying citrus diseases. This can, in turn, help improve the overall quality of citrus fruits.

Underwater localization is used as a key element in most applications of underwater communications. Despite the global positioning system (GPS) receivers are usually employed in terrestrial wireless sensor networks, they cannot be exploited for underwater localization. In fact, GPS signals are highly attenuated by the water, by being unusable to a depth of more than a couple of meters, and cannot propagate underwater, especially, in the case of the salt water. In place of RF signals, acoustic signals are the most common mode of communication, and the so-called underwater acoustic sensor networks attracted a significant interest due to their great impact on ocean monitoring and exploration. Hydroacoustics, as the study and application of sound in water, is the foundation of underwater localization, but the existing available methods, classified in range-based versus range-free techniques, are affected by several open problems and research challenges. Therefore, an accurate range-based algorithm for localization needs to be developed, and the demand for expeditiously employing the energy of the sensor nodes is still remaining a distinct feature for underwater wireless sensor networks. Because of these argues, an improved interpretation for underwater localization is presented, by first presenting a general localization algorithm, and afterward deploying the ordinary, beacon nodes in order to find the error and accuracy of sensor localization. After that, we present two localization algorithms named as distance-based and angle-based algorithms. We consider a realistic case, where sensor nodes are not time synchronized and the sound speed in water is unknown. The simulation results exhibit that our algorithms compensate for time synchronization, estimate the mean errors in localization and achieve good localization accuracy.

For a variety of cyber-attacks occurring in a power IoT-Cloud environment, conventional security intrusion incident detection and response technologies typically use pattern- and behavior-based statistical methods. However, they cannot provide fundamental solutions for a security intrusion or attacks, which are becoming more intelligent and diverse as time passes. Therefore, an effective response method that can respond to security intrusions intelligently while using an access control technique based on ontology reasoning is required. This can be achieved by adopting a variety of intelligent reasoning technologies for security intrusion incidents of power systems, such as various reasoning technologies based on the ontology and semantic-web technologies being actively studied in the field of intelligent systems, and malicious code detection technologies based on an intelligent access control model, text mining, and natural language processing technologies. Accordingly, a security context ontology was modeled by analyzing the security vulnerabilities of a power system in a power IoT-Cloud environment, and security context inference rules were defined. Furthermore, this paper presents an appropriate power IoT-Cloud security service framework that can be used in a power IoT-Cloud environment. In addition, a security mechanism that can be efficiently operated in such an environment is implemented. In experiments conducted for this application, attack context scenarios that commonly occur were created using a smart meter as an example, which is an essential power system device. Inference rules were then composed for each attack stage to check the paths of attacks those that exploit the vulnerability of a smart meter system. As a result, it was confirmed that a high level attack detection results can be obtained based on the inference rules.

In this paper, a novel 2-D direction of arrival (DOA) estimation approach based on the tensor technique is proposed for a conformal array in a massive multiple-input-multiple-output system under unknown mutual coupling. By placing sensors uniformly on the cylindrical surface, the received signal expression is formulated with the Khatri-Rao product. An unknown mutual coupling auto-suppression method based on the conformal array is investigated. Then, to utilize the multidimensional information of the received data, a third-order tensor is constructed based on the conformal array signal model, and the signal subspace is provided by higher order singular value decomposition. Finally, the DOAs are estimated by conventional subspace-based algorithms. This approach provides improved DOA estimation performance owing to the utilization of the multidimensional information and the covariance tensor method, with lower SNR and fewer snapshots. The simulation results confirm that the proposed method outperforms the conventional method based on the vector model.

Many network technologies, including cellular, Wifi, and WiMAX, coexist in wireless networks. With the increasing demand on mobility-based network services on account of the popularity of smart devices, users expect network environments in which they can readily access the Internet at any time and place. An effective handover decision is necessary to provide users with continued services while they are mobile. Existing studies on handover have strived to improve the mobility of the object moving and communicating on the ground. However, a traditional handover decision is not suitable for a drone moving and communicating in 3-D space. Therefore, in this paper, parameters that represent the characteristics of drones communicating within 3-D space are defined, including speed limit and coverage. Using these parameters as input variables, a fuzzy inference method for the handover decision is proposed. A fuzzy inference system is composed of four steps. First, terminal-related information is analyzed to select the factors that can affect the drone handover decision. Second, the input data values are converted into membership functions. Third, the reasoning rules for the handover decision are designed and applied. Finally, the handover is decided by considering the current information of the drone. The computation of the number of handover decisions has shown that considering the terminal-related parameters and the network-related parameters has a positive effect on the handover decision.

In this paper, we focus on the radio resource management (RRM) issues in the two-hop Orthogonal Frequency Division Multiple Access (OFDMA) system with heterogeneous quality of service (QoS) requirements. To solve the RRM problem, we first propose a new two-hop frame structure to support the data relay operation from the base station to the relay station and cooperative transmission for the edge users. Then, a two-hop coordinated scheduling algorithm is proposed, which utilizes the proposed two-hop frame structure and considers the corresponding interference status. The proposed two-hop coordinated scheduling algorithm solves the RRM problem of the two-hop OFDMA system with heterogeneous QoS requirements in an iterative manner, and so maximizes the system utility.

This Special Issue aims at collecting several original state-of-the-art research experiences in the area of intelligent applications in the IoT and Sensor networks environment, by analyzing several open issues and perspectives associated with such scenarios, in order to explore novel potentialities and solutions and face with the emerging challenges.