• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.99-109
• /
• 2023

The darknet is frequently referred to as the hub of illicit online activity. In order to keep track of real-time applications and activities taking place on Darknet, traffic on that network must be analysed. It is without a doubt important to recognise network traffic tied to an unused Internet address in order to spot and investigate malicious online activity. Any observed network traffic is the result of mis-configuration from faked source addresses and another methods that monitor the unused space address because there are no genuine devices or hosts in an unused address block. Digital systems can now detect and identify darknet activity on their own thanks to recent advances in artificial intelligence. In this paper, offer a generalised method for deep learning-based detection and classification of darknet traffic. Furthermore, analyse a cutting-edge complicated dataset that contains a lot of information about darknet traffic. Next, examine various feature selection strategies to choose a best attribute for detecting and classifying darknet traffic. For the purpose of identifying threats using network properties acquired from darknet traffic, devised a hybrid deep learning (DL) approach that combines Recurrent Neural Network (RNN) and Bidirectional LSTM (BiLSTM). This probing technique can tell malicious traffic from legitimate traffic. The results show that the suggested strategy works better than the existing ways by producing the highest level of accuracy for categorising darknet traffic using the Black widow optimization algorithm as a feature selection approach and RNN-BiLSTM as a recognition model.

• Journal of Korean Foot and Ankle Society
• /
• v.27 no.4
• /
• pp.137-143
• /
• 2023

Purpose: Autologous osteochondral transplantation (AOT) is indicated for patients with a large osteochondral lesion of the talus (OLT), accompanying subchondral cyst, and the failure of bone marrow stimulation (BMS) procedures. Despite the many reports on the clinical results of surgical treatment for medial osteochondral lesions, those of lateral lesions are rare. This paper reports the intermediate-term clinical outcomes after AOT for lateral OLTs. Materials and Methods: Twenty-one patients with lateral OLTs were followed up for at least three years after AOT. The clinical evaluations comprised the Foot and Ankle Outcome Score (FAOS) and Foot and Ankle Ability Measure (FAAM). The radiographic assessment included the irregularity of the articular surface (subchondral plate), the progression of degenerative arthritis, and the changes in talar tilt angle and anterior talar translation. Results: The mean FAOS and FAAM scores improved significantly from 42.1 to 89.5 and 39.5 to 90.6 points, respectively, at the final follow-up (p<0.001). The radiological evaluation revealed two cases (9.5%) of articular step-off ≥2 mm and 1 case (4.8%) of progressive arthritis. The mean talar tilt angle and anterior talar translation improved significantly. As postoperative complications, there was one case of a local wound problem, one case of superficial peroneal nerve injury, and one case of donor site morbidity. At a mean follow-up of 62.3 months, no patient showed a recurrence of instability or required reoperation for OLT. Conclusion: AOT for the lateral OLTs demonstrated satisfactory intermediate-term clinical outcomes, including daily and sports activity abilities. Most OLT could be accessed through lateral ligament division and capsulotomy, and the incidence of iatrogenic complications, such as recurrent sprains or chronic instability, was minimal. AOT appears to be an effective and relatively safe treatment for patients with large lateral osteochondral lesions unresponsive to conservative therapy, with subchondral cysts, or with failed primary BMS.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.605-611
• /
• 2023

Accidents at construction sites have a very high rate of fatalities due to the nature of being prone to severe injury patients. In order to reduce the mortality rate of severely injury patients, quick response is required, and some systems that detect accidents using AI technology and cameras have been devised to respond quickly to accidents. However, since existing accident detection systems use only a single camera, there are blind spots, Thus, they cannot detect all accidents at a construction site. Therefore, in this paper, we present the system that minimizes the detection blind spot by using multiple cameras. Our implemented system extracts feature points from the images of multiple cameras with the YOLO-pose library, and inputs the extracted feature points to a Long Short Term Memory-based recurrent neural network in order to detect accidents. In our experimental result, we confirme that the proposed system shows high accuracy while minimizing detection blind spots by using multiple cameras.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.840-860
• /
• 2021

Imaging plays a key role in the diagnosis and characterization of thyroid diseases, and the information provided by imaging studies is essential for management planning. A referral guideline for imaging studies may help physicians make reasonable decisions and minimize the number of unnecessary examinations. The Korean Society of Thyroid Radiology (KSThR) developed imaging guidelines for thyroid nodules and differentiated thyroid cancer using an adaptation process through a collaboration between the National Evidence-based Healthcare Collaborating Agency and the working group of KSThR, which is composed of radiologists specializing in thyroid imaging. When evidence is either insufficient or equivocal, expert opinion may supplement the available evidence for recommending imaging. Therefore, we suggest rating the appropriateness of imaging for specific clinical situations in this guideline.

• Korean Journal of Radiology
• /
• v.22 no.1
• /
• pp.63-71
• /
• 2021

Objective: To identify the CT findings associated with treatment failure after antibiotic therapy for acute appendicitis. Materials and Methods: Altogether, 198 patients who received antibiotic therapy for appendicitis were identified by searching the hospital's surgery database. Selection criteria for antibiotic therapy were uncomplicated appendicitis with an appendiceal diameter equal to or less than 11 mm. The 86 patients included in the study were divided into a treatment success group and a treatment failure group. Treatment failure was defined as a resistance to antibiotic therapy or recurrent appendicitis during a 1-year follow-up period. Two radiologists independently evaluated the following CT findings: appendix-location, involved extent, maximal diameter, thickness, wall enhancement, focal wall defect, periappendiceal fat infiltration, and so on. For the quantitative analysis, two readers independently measured the CT values at the least attenuated wall of the appendix by drawing a round region of interest on the enhanced CT (HU_post) and non-enhanced CT (HU_pre). The degree of appendiceal wall enhancement (HU_sub) was calculated as the subtracted value between HU_post and HU_pre. A logistic regression analysis was used to identify the CT findings associated with treatment failure. Results: Sixty-four of 86 (74.4%) patients were successfully treated with antibiotic therapy, with treatment failure occurring in the remaining 22 (25.5%). The treatment failure group showed a higher frequency of hypoenhancement of the appendiceal wall than the success group (31.8% vs. 7.8%; p = 0.005). Upon quantitative analysis, both HU_post (46.7 ± 21.3 HU vs. 58.9 ± 22.0 HU; p = 0.027) and HU_sub (26.9 ± 17.3 HU vs. 35.4 ± 16.6 HU; p = 0.042) values were significantly lower in the treatment failure group than in the success group. Conclusion: Hypoenhancement of the appendiceal wall was significantly associated with treatment failure after antibiotic therapy for acute appendicitis.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.50 no.1
• /
• pp.41-48
• /
• 2024

Objectives: Botulinum toxin type A (BTX), a powerful neurotoxin, can be an effective treatment choice for diverse muscular disorders and can reduce abnormal muscle activities. Abnormal movements of the mandible can be caused by involuntary and uncontrolled contractions of the lateral pterygoid muscle (LP) in various pathological situations. Previous reports have shown that BTX can reduce abnormal contractions of the LP. However, needle placement into the LP for BTX injection requires skill, experience, and sufficient anatomical knowledge. To place the needle precisely into the LP, ultrasonography (USG) can be used as an effective needle-guidance modality. USG is a non-invasive imaging modality able to create real-time images without any potential risks, including radiation exposure. Patients and Methods: The patients who had been performed USG-guided BTX injection into the LP using an intraoral approach were included in this study with a literature review and case presentations. Using the USG, four patients received BTX injections to treat recurrent temporomandibular dislocation and oromandibular dystonia resulting from involuntary LP activity. Result: Involuntary movements of the mandible were improved successfully in all patients, and showed satisfactory results without significant complication. Conclusion: The intraoral approach could prevent potential complications during needle placement. USG-guided BTX injection is an effective, convenient, and safe method that provides real-time imaging without unnecessary pain to the patient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.49-55
• /
• 2024

This paper proposes PredFeed Net, a neural network model that mimics the food distribution of fish farming experts. Unlike existing food distribution automation systems, PredFeed Net predicts food distribution by learning the food distribution patterns of experts. This has the advantage of being able to learn using only existing environmental data and food distribution records from food distribution experts, without the need to experiment by changing food distribution variables according to the environment in an actual aquarium. After completing training, PredFeed Net predicts the next food ration based on the current environment or fish condition. Prediction of feed ration is a necessary element for automating feed ration, and feed ration automation contributes to the development of modern fish farming such as smart aquaculture and aquaponics systems.

• Journal of the Korean Society of Radiology
• /
• v.81 no.1
• /
• pp.207-212
• /
• 2020

Adenomyoepithelioma (AME) is a rare breast neoplasm composed of both epithelial and myoepithelial cells with biphasic proliferation. Although most AMEs are benign, malignant transformation of either or both cellular components may occur. This report describes an unusual rapid local tumor recurrence a month after excision of the myoepithelial carcinoma arising in an AME. Ultrasound and MRI showed small recurrent masses in the superficial part of a hematoma. This report suggests the benefit of immediate postoperative breast imaging in patients with malignant AME with potential for local recurrence, such as those with narrow resection margins or high mitotic activity.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.18-26
• /
• 2023

The building energy management system (BEMS), a system designed to efficiently manage energy production and consumption, aims to address the variable nature of power consumption within buildings due to their physical characteristics, necessitating stable power supply. In this context, accurate prediction of building energy consumption becomes crucial for ensuring reliable power delivery. Recent research has explored various approaches, including time series analysis, statistical analysis, and artificial intelligence, to predict power consumption. This paper analyzes the strengths and weaknesses of the Prophet model, choosing to utilize its advantages such as growth, seasonality, and holiday patterns, while also addressing its limitations related to data complexity and external variables like climatic data. To overcome these challenges, the paper proposes an algorithm that combines the Prophet model's strengths with the gated recurrent unit (GRU) to forecast short-term (2 days) and medium-term (7 days, 15 days, 30 days) building energy consumption. Experimental results demonstrate the superior performance of the proposed approach compared to conventional GRU and Prophet models.