• ETRI Journal
• /
• v.42 no.5
• /
• pp.658-668
• /
• 2020

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to end-device service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• Journal of the Ergonomics Society of Korea
• /
• v.32 no.2
• /
• pp.159-165
• /
• 2013

Objective: The aim of this study was to predict human performance time in finding objects on multi-display monitors using ACT-R cognitive architecture. Background: Display monitors are one of the representative interfaces for interaction between people and the system. Nowadays, the use of multi-display monitors is increasing so that it is necessary to research about the interaction between users and the system on multi-display monitors. Method: A cognitive model using ACT-R cognitive architecture was developed for the model-based evaluation on multi-display monitors. To develop the cognitive model, first, an experiment was performed to extract the latency about the where system of ACT-R. Then, a menu selection experiment was performed to develop a human performance model to find objects on multi-display monitors. The validation of the cognitive model was also carried out between the developed ACT-R model and empirical data. Results: As a result, no significant difference on performance time was found between the model and empirical data. Conclusion: The ACT-R cognitive architecture could be extended to model human behavior in the search of objects on multi-display monitors.. Application: This model can help predicting performance time for the model-based usability evaluation in the area of multi-display work environments.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.801-809
• /
• 2010

This paper presents a statistical model-based noise suppression approach for voice recognition in a car environment. In order to alleviate the spectral whitening and signal distortion problem in the traditional decision-directed Wiener filter, we combine a decision-directed method with an original spectrum reconstruction method and develop a new two-stage noise reduction filter estimation scheme. When a tradeoff between the performance and computational efficiency under resource-constrained automotive devices is considered, ETSI standard advance distributed speech recognition font-end (ETSI-AFE) can be an effective solution, and ETSI-AFE is also based on the decision-directed Wiener filter. Thus, a series of voice recognition and computational complexity tests are conducted by comparing the proposed approach with ETSI-AFE. The experimental results show that the proposed approach is superior to the conventional method in terms of speech recognition accuracy, while the computational cost and frame latency are significantly reduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1849-1876
• /
• 2022

Wireless Sensor Network (WSN) is considered as an integral part of the Internet of Things (IoT) for collecting real-time data from the site having many applications in industry 4.0 and smart cities. The task of nodes is to sense the environment and send the relevant information over the internet. Though this task seems very straightforward but it is vulnerable to certain issues like energy consumption, delay, throughput, etc. To efficiently address these issues, this work develops a cross-layer model for the optimization between MAC and the Network layer of the OSI model for WSN. A high value of duty cycle for nodes is selected to control the delay and further enhances data transmission reliability. A node measurement prediction system based on the Kalman filter has been introduced, which uses the constraint based on covariance value to decide the scheduling scheme of the nodes. The concept of duty cycle for node scheduling is employed with a greedy data forwarding scheme. The proposed Duty Cycle-based Greedy Routing (DCGR) scheme aims to minimize the hop count, thereby mitigating the energy consumption rate. The proposed algorithm is tested using a real-world wastewater treatment dataset. The proposed method marks an 87.5% increase in the energy efficiency and reduction in the network latency by 61% when validated with other similar pre-existing schemes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4203-4223
• /
• 2021

Accelerated by the Internet of Things (IoT), the need for further technical innovations and developments within wireless communications beyond the fifth generation (B5G) networks is up-and-coming in the past few years. High altitude platform station (HAPS) communication is expected to achieve such high levels that, with high data transfer rates and low latency, millions of devices and applications can work seamlessly. The HAPS has emerged as an indispensable component of next-generations of wireless networks, which will therefore play an important role in promoting massive IoT interconnectivity with 6G. The performance of communication and key technology mainly depend on the characteristic of channel, thus we propose an efficient Markov chain based channel model, then analyze the HAPS communication system's uplink capability and swing effect through experiments. According to the simulation results, the efficacy of the proposed scheme is proven to meet the requirements of ubiquitous connectivity in future IoT enabled by 6G.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.736-743
• /
• 2022

Construction workers experience a high rate of fatal incidents from mobile equipment in the industry. One of the major causes is the decline in the acoustic condition of workers due to the constant exposure to construction noise. Previous studies have proposed various ways in which audio sensing and machine learning techniques can be used to track equipment's movement on the construction site but not on the audibility of safety signals. This study develops a novel framework to help automate safety surveillance in the construction site. This is done by detecting the audio sound at a different signal-to-noise ratio of -10db, -5db, 0db, 5db, and 10db to notify the worker of imminent dangers of mobile equipment. The scope of this study is focused on developing a signal processing model to help improve the audible sense of mobile equipment for workers. This study includes three-phase: (a) collect audio data of construction equipment, (b) develop a novel audio-based machine learning model for automated detection of collision hazards to be integrated into intelligent hearing protection devices, and (c) conduct field experiments to investigate the system' efficiency and latency. The outcomes showed that the proposed model detects equipment correctly and can timely notify the workers of hazardous situations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• Food Science of Animal Resources
• /
• v.37 no.5
• /
• pp.646-653
• /
• 2017

Alcalase hydrolysis of liquid egg white was used to produce 5-hydroxytryptophan (HTP) under various conditions and investigate the sleep-potentiating activity of liquid egg white hydrolysate (LEH) on pentobarbital-induced sleep. Alcalase hydrolysis yielded the highest content of 5-HTP ($13.50{\mu}g/mL$), while neutrase hydrolysis showed the lowest 5-HTP content ($5.23{\mu}g/mL$). The liquid egg white to water ratio (1:1) was optimal for the production of 5-HTP with high amino-nitrogen (A-N) content and degree of hydrolysis. The 5-HTP, amino-nitrogen, and degree of hydrolysis increased until 24 h of hydrolysis and slightly increased thereafter during hydrolysis with 2% and 5% enzyme addition. 5-HTP administration at doses of 6 and 9 mg/kg significantly increased sleep duration and decreased sleep latency time compared to that in the control (p<0.05). LEH (150 mg/mouse), which was equivalent to 5-HTP at 6 mg/kg, significantly decreased sleep latency time and increased sleep duration time compared to that in the control (p<0.05). Oral administration of LEH showed sleep-potentiating effects because of 5-HTP. The sleep-potentiating activity of LEH may have occurred through 5-HTP in our pentobarbital-induced sleep model. LEH may be a valuable alternative to sleep enhancement and may be used as a sleep-potentiating agent.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.34 no.1
• /
• pp.37-44
• /
• 2020

Previous studies have reported an association between poor sleep and various symptoms and diseases, such as fatigue, obesity, depression, and anxiety. The effects of poor sleep may differ by age and sex. In addition, sleep characteristics and their effects may vary according to Sasang constitutional type. The aim of this study was to investigate the associations between sleep quality, fatigue, and quality of life and to assess whether these differ by constitutional type. Participants were individuals aged 40-69 years living in two Korean communities in 2012-2014. Sleep quality, fatigue, and quality of life were measured using the Pittsburgh Sleep Quality Index (PSQI), the Fatigue Severity Scale, and the 12-item Short Form Health Survey, respectively. The effects of total PSQI score and PSQI component scores were analyzed using a generalized additive model. A Korean Sasang constitutional diagnostic questionnaire was used to assess Sasang constitution. Data for 5,793 participants were analyzed. Poor sleep quality was related to greater fatigue, and lower physical and mental quality of life. The PSQI components including subjective sleep quality, sleep latency, sleep disturbances, use of sleep medications, and daytime dysfunction were associated with fatigue and physical and mental quality of life. Sleep quality was significantly lower in So-Eum compared to So-Yang and Tae-Eum. PSQI component scores for fatigue and quality of life differed significantly by Sasang constitution: for Tae-Eum, sleep latency and use of sleep medications; for So-Eum, daytime dysfunction; and for So-Yang, use of sleep medications and daytime dysfunction. The effects of different aspects of sleep quality differ by Sasang constitution. To improve sleep quality, interventions need to be tailored to constitutional type.