• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.568-570
• /
• 2023

The problem of classifying of age, gender, and race images still poses challenges. Despite deep and machine learning strides, convolutional neural networks (CNNs) remain pivotal in addressing these issues. This paper introduces a novel CNN-based approach for accurate and efficient age, gender, and race classification. Leveraging CNNs with residual blocks, our method enhances learning while minimizing computational complexity. The model effectively captures low-level and high-level features, yielding improved classification accuracy. Evaluation of the diverse 'fair face' dataset shows our model achieving 56.3%, 94.6%, and 58.4% accuracy for age, gender, and race, respectively.

• Journal of Communications and Networks
• /
• v.18 no.3
• /
• pp.327-332
• /
• 2016

The routing protocol for low-power and lossy networks (RPL) is an internet protocol based routing protocol developed and standardized by IETF in 2012 to support a wide range of applications for low-power and lossy-networks (LLNs). In LLNs consisting of resource-constrained devices, the energy consumption of battery powered sensing devices during network operations can greatly impact network lifetime. In the case of inefficient route selection, the energy depletion from even a few nodes in the network can damage network integrity and reliability by creating holes in the network. In this paper, a composite energy-aware node metric ($RER_{BDI}$) is proposed for RPL; this metric uses both the residual energy ratio (RER) of the nodes and their battery discharge index. This composite metric helps avoid overburdening power depleted network nodes during packet routing from the source towards the destination oriented directed acyclic graph root node. Additionally, an objective function is defined for RPL, which combines the node metric $RER_{BDI}$ and the expected transmission count (ETX) link quality metric; this helps to improve the overall network packet delivery ratio. The COOJA simulator is used to evaluate the performance of the proposed scheme. The simulations show encouraging results for the proposed scheme in terms of network lifetime, packet delivery ratio and energy consumption, when compared to the most popular schemes for RPL like ETX, hop-count and RER.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.649-651
• /
• 2018

Since the ubiquitous sensor network is not connected to external power source and operated by its own battery, it is required to maximize the network life using the efficient energy utilization. In a conventional hop count based routing protocol, most sensor nodes are designed with a constant transmission power. In this paper, we propose a routing protocol that prolongs the network lifetime by balancing the power consumption among the nodes by controlling the transmit power according to the residual power of the nodes, and compared the performance of the proposed routing protocol through computer simulations.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.804-812
• /
• 2015

Energy harvesting (EH) technology in the field of wireless sensor networks (WSNs) is gaining increasing popularity through removing the burden of having to replace/recharge depleted energy sources by energy harvester devices. EH provides an alternative source of energy from the surrounding environment; therefore, by exploiting the EH process, WSNs can achieve a perpetual lifetime. In view of this, emphasis is being placed on the design of new medium access control (MAC) protocols that aim to maximize the lifetime of WSNs by using the maximum possible amount of harvested energy instead of saving any residual energy, given that the rate of energy harvested is greater than that which is consumed. Various MAC protocols with the objective of exploiting ambient energy have been proposed for energy-harvesting WSNs (EH-WSNs). In this paper, first, the fundamental properties of EH-WSN architecture are outlined. Then, several MAC protocols proposed for EH-WSNs are presented, describing their operating principles and underlying features. To give an insight into future research directions, open research issues (key ideas) with respect to design trade-offs are discussed at the end of this paper.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.13-14
• /
• 2007

We propose HERAH(Hierarchical Energy-Aware Routing Algorithm for Heterogeneous Wireless Sensor Networks) that is the hierarchical routing algorithm in WSNs and is established on heterogeneous environment. HERAH performs CH selection by considering residual energy level and uses multi-hop communication within cluster. So, HERAH makes improvements in the energy savings and the network lifetime compared with LEACH.

• Journal of information and communication convergence engineering
• /
• v.5 no.1
• /
• pp.29-34
• /
• 2007

This paper proposes a MAC protocol for real-time VBR (rt-VBR) services in wireless ATM networks. The proposed protocol is characterized by a contention-based mechanism of the reservation request, a contention-free polling scheme for transferring the dynamic parameters, and a priority scheme of the slot allocation. The design objective of the proposed protocol is to guarantee the real-time constraint of rt-VBR traffic. The scheduling algorithm uses a priority scheme based on the maximum cell transfer delay parameter. The wireless terminal establishes an rt-VBR connection to the base station with a contention-based scheme. The base station scheduler allocates a dynamic parameter minislot to the wireless terminal for transferring the residual lifetime and the number of requesting slots as the dynamic parameters. Based on the received dynamic parameters, the scheduler allocates the uplink slots to the wireless terminal with the most stringent delay requirement. The simulation results show that the proposed protocol can guarantee the delay constraint of rt-VBR services along with its cell loss rate significantly reduced.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1320-1330
• /
• 2017

Wireless sensor networks for forest monitoring are typically deployed in fields in which manual intervention cannot be easily accessed. An interesting approach to extending the lifetime of sensor nodes is the use of energy harvested from the environment. Design constraints are application-dependent and based on the monitored environment in which the energy harvesting takes place. To reduce energy consumption, we designed a power management scheme that combines dynamic duty cycle scheduling at the network layer to plan node duty time. The dynamic duty cycle scheduling is realized based on a tier structure in which the network is concentrically organized around the sink node. In addition, the multi-paths preserved in the tier structure can be used to deliver residual packets when a path failure occurs. Experimental results show that the proposed method has a better performance.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1582-1590
• /
• 2022

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.135-141
• /
• 2018

Wireless sensor networks (WSN) are composed of a large number of sensor nodes. Battery-powered sensor nodes have limited coverage; therefore, it is more efficient to transmit data via multi-hop communication. The network lifetime is a crucial issue in WSNs and the multi-hop routing protocol should be designed to prolong the network lifetime. Prolonging the network lifetime can be achieved by minimizing the power consumed by the nodes, as well as by balancing the power consumption among the nodes. A power imbalance can reduce the network lifetime even if several nodes have sufficient (battery) power. In this paper, we propose a routing protocol that prolongs the network lifetime by balancing the power consumption among the nodes. To improve the balance of power consumption and improve the network lifetime, the proposed routing scheme adaptively controls the transmission range using a power control according to the residual power in the nodes. We developed a routing simulator to evaluate the performance of the proposed routing protocol. The simulation results show that the proposed routing scheme increases power balancing and improves the network lifetime.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37B no.12
• /
• pp.1186-1194
• /
• 2012

In order to resolve the energy efficiency in wireless sensor networks, a multihop transmission technique is utilized. However, multihop transmission in wireless sensor networks (WSN) has pros and cons. It reduces total energy consumption, while it may cause a severe decrease in network lifetime. To solve this problem, we suggest the so called strike and bargaining algorithm (SBA). The routing path is determined by wages of nodes. Each node negotiates its wage with their neighbor nodes and determine a reasonable value to reach a optimally balanced point. By analysis and simulations, we show SBA can achieve a near optimal solution.