Compatibility Review for Object Detection Enhancement through Super-Resolution.

With the introduction of deep learning, a significant amount of research has been conducted in the field of computer vision in the past decade. In particular, research on object detection (OD) continues to progress rapidly. However, despite these advances, some limitations need to be overcome to enable real-world applications of deep learning-based OD models. One such limitation is inaccurate OD when image quality is poor or a target object is small. The performance degradation phenomenon for small objects is similar to the fundamental limitations of an OD model, such as the constraint of the receptive field, which is a difficult problem to solve using only an OD model. Therefore, OD performance can be hindered by low image quality or small target objects. To address this issue, this study investigates the compatibility of super-resolution (SR) and OD techniques to improve detection, particularly for small objects. We analyze the combination of SR and OD models, classifying them based on architectural characteristics. The experimental results show a substantial improvement when integrating OD detectors with SR models. Overall, it was demonstrated that, when the evaluation metrics (PSNR, SSIM) of the SR models are high, the performance in OD is correspondingly high as well. Especially, evaluations on the MS COCO dataset reveal that the enhancement rate for small objects is 9.4% higher compared to all objects. This work provides an analysis of SR and OD model compatibility, demonstrating the potential benefits of their synergistic combination. The experimental code can be found on our GitHub repository.

Bi-LSTM-Augmented Deep Neural Network for Multi-Gbps VCSEL-Based Visible Light Communication Link.

With the remarkable advances in vertical-cavity surface-emitting lasers (VCSELs) in recent decades, VCSELs have been considered promising light sources in the field of optical wireless communications. However, off-the-shelf VCSELs still have a limited modulation bandwidth to meet the multi-Gb/s data rate requirements imposed on the next-generation wireless communication system. Recently, employing machine learning (ML) techniques as a method to tackle such issues has been intriguing for researchers in wireless communication. In this work, through a systematic analysis, it is shown that the ML technique is also very effective in VCSEL-based visible light communication. Using a commercial VCSEL and bidirectional long short-term memory (Bi-LSTM)-based ML scheme, a high-speed visible light communication (VLC) link with a data rate of 13.5 Gbps is demonstrated, which is the fastest single channel result from a cost-effective, off-the-shelf VCSEL device, to the best of the authors' knowledge.

Advanced Network Sampling with Heterogeneous Multiple Chains.

Recently, researchers have paid attention to many types of huge networks such as the Internet of Things, sensor networks, social networks, and traffic networks because of their untapped potential for theoretical and practical outcomes. A major obstacle in studying large-scale networks is that their size tends to increase exponentially. In addition, access to large network databases is limited for security or physical connection reasons. In this paper, we propose a novel sampling method that works effectively for large-scale networks. The proposed approach makes multiple heterogeneous Markov chains by adjusting random-walk traits on the given network to explore the target space efficiently. This approach provides better unbiased sampling results with reduced asymptotic variance within reasonable execution time than previous random-walk-based sampling approaches. We perform various experiments on large networks databases obtained from synthesis to real-world applications. The results demonstrate that the proposed method outperforms existing network sampling methods.

Residual Energy Analysis in Cognitive Radios with Energy Harvesting UAV under Reliability and Secrecy Constraints.

The integration of unmanned aerial vehicles (UAVs) with a cognitive radio (CR) technology can improve the spectrum utilization. However, UAV network services demand reliable and secure communications, along with energy efficiency to prolong battery life. We consider an energy harvesting UAV (e.g., surveillance drone) flying periodically in a circular track around a ground-mounted primary transmitter. The UAV, with limited-energy budget, harvests radio frequency energy and uses the primary spectrum band opportunistically. To obtain intuitive insight into the performance of energy-harvesting, and reliable and secure communications, the closed-form expressions of the residual energy, connection outage probability, and secrecy outage probability, respectively, are analytically derived. We construct the optimization problems of residual energy with reliable and secure communications, under scenarios without and with an eavesdropper, respectively, and the analytical solutions are obtained with the approximation of perfect sensing. The numerical simulations verify the analytical results and identify the requirements of length of sensing phase and transmit power for the maximum residual energy in both reliable and secure communication scenarios. Additionally, it is shown that the residual energy in secure communication is lower than that in reliable communication.

Cognitive Interference Cancellation with Digital Channelizer for Satellite Communication.

The concept of Internet of Things (IoT) has attracted much research attention for the realization of a smart society. However, the radio transmission coverage of the existing IoT solutions is not enough to connect lots of devices deployed over wide areas. Therefore, satellite networks have been considered as one of the most attractive solutions to wide cell coverage of IoT, i.e., global-scaled IoT. In satellite communication, a digital channelizer is one of the most significant parts that support multiple transponders. Owing to their wide coverage, satellite communication systems are more vulnerable to interference than other types of wireless communication systems. In this study, a cognitive interference cancellation using the inherent properties of a digital channelizer is considered. The proposed method detects a subchannel corrupted by interference and omits it. A simple energy detection method and a modified version are proposed for detection of interference. In the modified (i.e., improved) method, the number of required signal blocks to achieve the target detection performance can be reduced, i.e., the detection performance is improved with the same number of blocks, by exploiting the property of the fast Fourier transform (FFT) algorithm. Detection performance such as false alarm and detection probabilities are analyzed, and the validity of the analysis is verified with numerical results. It is also shown that an interference lower than a certain level in the proposed approach does not need to be cancelled.

Recurrence Rates and Characteristics of Phyllodes Tumors Diagnosed by Ultrasound-guided Vacuum-assisted Breast Biopsy (VABB).

BACKGROUND/AIM: Recently, the development of ultrasonography (US)-guided vacuum-assisted breast biopsy (VABB) has enabled the excision of benign breast tumors with normal surrounding breast tissues; thus, complete excision is possible without residual tumor tissue. We sought to identify the clinicopathological characteristics and recurrence rates of benign phyllodes tumors diagnosed by US-guided VABB. PATIENTS AND METHODS: Data from 11,221 US-guided VABBs performed at the Gangnam Cha Medical Center over 12 years were analyzed. Eighty-three lesions were diagnosed as benign phyllodes tumors; 67 with >24 months of follow-up data were investigated. All lesions were excised using an 8-gauge probe without residual tissue; patients underwent follow-up US every 3-6 months. RESULTS: Five patients (7.46%) experienced local recurrence during a mean follow-up period of 27.8 months; no distant metastases occurred. The mean tumor size was 3.0 cm in the recurrence group and 1.87 cm in the non-recurrence group (p=0.05). CONCLUSION: Benign phyllodes tumors excised and diagnosed using VABB showed a low recurrence rate during the follow-up period; thus, these tumors, particularly those <3 cm, can be safely monitored with ultrasonography instead of performing immediate re-excision.

Clinicopathological Analysis of Ultrasound-guided Vacuum-assisted Breast Biopsy for the Diagnosis and Treatment of Breast Disease.

BACKGROUND/AIM: To evaluate the usefulness and safety of vacuum-assisted breast biopsy (VABB) for breast lesion diagnosis and treatment. PATIENTS AND METHODS: Clinical and histopathological data of 8,748 patients, who underwent 11,221 VABB procedures were analyzed. RESULTS: Most patients (58.2%) were <40 years old. Most lesions (39.6%) were 0.6-1.0 cm in diameter while 3.2% were ≥3.0 cm; fibroadenomas were the most common (46.6%). Eight (14% of 57) cases of atypical ductal hyperplasia were underestimated. The positive predictive values (PPVs) of breast imaging reporting and data system (BI-RADS) ultrasound category were 0.6%, 3.4%, 34.8%, 66.2%, and 93.8% for category 3, 4a, 4b, 4c, and 5 lesions, respectively. The mean number of core specimens was 9.5±8.8; the mean procedure time was 3.4±2.7 min. No residual lesions were found in 94.4% of the 7,480 patients. CONCLUSION: VABB could replace ultrasound-guided core biopsy and surgical excisional biopsy for the diagnosis of breast disease and the treatment of benign breast lesions.

Macrolide resistance trends in beta-hemolytic streptococci in a tertiary Korean hospital.

PURPOSE: Erythromycin-resistant beta-hemolytic streptococci (BHS) has recently emerged and quickly spread between and within countries throughout the world. In this study, we evaluate the antimicrobial susceptibility patterns and erythromycin resistance mechanisms of BHS during 2003-2004. MATERIALS AND METHODS: The MICs of seven antimicrobials were determined for 204 clinical isolates of BHS from 2003 to 2004. Resistance mechanisms of erythromycin-resistant BHS were studied by the double disk test as well as by polymerase chain reaction (PCR). RESULTS: Compared with our previous study, resistance among Streptococcus pyogenes isolates to a variety of drugs decreased strikingly: from 25.7% to 4.8% in erythromycin; 15.8% to 0% in clindamycin; and 47.1% to 19.0% in tetracycline. The prevalent phenotypes and genotypes of macrolide-lincosamide-streptograminB (MLSB) resistance in Streptococcus pyogenes isolates have been changed from the constitutive MLSB phenotype carrying erm(B) to the M phenotype with mef(A) gene. In contrast with Streptococcus pyogenes, resistance rates to erythromycin (36.7%), clindamycin (43.1%), and tetracycline (95.4%) in Streptococcus agalactiae isolates did not show decreasing trends. Among the Streptococcus dysgalactiae subsp. equisimilis isolates (Lancefield group C, G), resistance rates to erythromycin, clindamycin, tetracycline and chloramphenicol were observed to be 9.4%, 3.1%, 68.8%, and 9.4%, respectively. CONCLUSION: Continual monitoring of antimicrobial resistance among large-colony-forming BHS is needed to provide the medical community with current data regarding the resistance mechanisms that are most common to their local or regional environments.