http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Subjective Evaluation of Ultra-high Definition (UHD) Videos
( Tariq Rahim ),( Soo Young Shin ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.6
This paper presents a detailed subjective quality assessment for the ultra-high definition (UHD) videos having frame rates of 30fps and 60 fps. The subjective assessment is based on the ITU-R BT-500 recommendations, where double stimulus continuous quality scale (DSCQS-type II) test is performed for the evaluation of the perceived quality of the user’s in terms of differential mean opinion score (DMOS). Encoding of the UHD videos by opting encoders i.e. H.264/AVC, H.265/HEVC, and VP9 at five different quantization parameter (QP) levels is done to investigate the perceived user’s quality of experience (QoE) given as DMOS. Moreover, the encoding efficiency as the encoding time for each encoder and qualitative performance by employing full-reference (FR) quality metrics are presented in this work.
Deep Learning-based Colorectal Cancer Detection in Endoscopic Images
Tariq Rahim,Arslan Musaddiq,Dong Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
Colorectal cancer (CRC) is the most prevalent cancer found in the small bowel of the human gastrointestinal (GI) tract. Polyps are antecedents to CRC and are detected in approximately half of the people at age 50 within the GI. In this paper, an improved version of You Only Live Once (YOLO) is presented for the detection of polyp within the endoscopic images. We have improved the YOLOv3-tiny model by adding more convolutional layers to extract enriched and deeper features. For fair benchmarking, the efficacy of the proposed model is evaluated against the default version of YOLOv3-tiny in terms of recall, precision, F1-score, and F2-score.
Federated Learning Framework for Intelligent IoT Networks
Arslan Musaddiq,Tariq Rahim,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
The use of Internet of Things (IoT) devices has increased significantly due to their diverse application areas. The IoT sensors are normally deployed in a complicated environment. Maintaining these tiny devices is challenging and often incurs high system costs. These devices are expected to handle data processing and communication tasks independently. For network layer communication, a reinforcement learning mechanism is utilized to generate routing table entries intelligently. The Q-values in RL algorithm may have error variance in nodes having similar environmental conditions. Thus, federated reinforcement learning (FRL) is proposed to represents the fair estimation of Q-value. The proposed FRL mechanism enhances the communication capabilities of IoT networks. The performance evaluation of the proposed mechanism is provided through Contiki 3.0 Cooja simulation.