• Journal of Biosystems Engineering
• /
• v.23 no.6
• /
• pp.571-582
• /
• 1998

The PLS(Partial Least Square) and ANN(Artificial Neural Network) were introduced to develop the soluble solids content prediction model of apples which is followed by making a subsequent selection of photosensor. For the optimal PLS model, number of factors needed for spectrum analysis were increased until the convergence of prediction residual error sum of squares. Analysis has shown that even part of the overall wavelength with no pretreatment may turn out better performing. The best PLS model was found in the 800 to 1,100nm wavelength region without pretreatment of second derivation, having $R^2$=0.9236, bias= -0.0198bx, SEP=0.2527bx for unknown samples. On the other hand, for the ANN model the second derivation led to higher performance. On partial range of 800 to 1,100nm wavelengh region, prediction model with second derivation for unknown samples reached $R^2$=0.9177, SEP=0.2903bx in contrast to $R^2$=0.7507, SEP =0.4622bx without pretreatment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4271-4294
• /
• 2018

Communication cost is the most important factor in Wireless Sensor Networks (WSNs), as exchanging control keying messages consumes a large amount of energy from the constituent sensor nodes. Time-based Dynamic Keying and En-Route Filtering (TICK) can reduce the communication costs by utilizing local time values of the en-route nodes to generate one-time dynamic keys that are used to encrypt reports in a manner that further avoids the regular keying or re-keying of messages. Although TICK is more energy efficient, it employs no re-encryption operation strategy that cannot determine whether a healthy report might be considered as malicious if the clock drift between the source node and the forwarding node is too large. Secure SOurce-BAsed Loose Synchronization (SOBAS) employs a selective encryption en-route in which fixed nodes are selected to re-encrypt the data. Therefore, the selection of encryption nodes is non-adaptive, and the dynamic network conditions (i.e., The residual energy of en-route nodes, hop count, and false positive rate) are also not focused in SOBAS. We propose an energy efficient selection of re-encryption nodes based on fuzzy logic. Simulation results indicate that the proposed method achieves better energy conservation at the en-route nodes along the path when compared to TICK and SOBAS.

• Transactions on Electrical and Electronic Materials
• /
• v.6 no.6
• /
• pp.262-271
• /
• 2005

In order to achieve timely and accurate fault detection of plasma etching process, neural network based time series modeling has been applied to reactive ion etching (RIE) using two different in-situ plasma-monitoring sensors called optical emission spectroscopy (OES) and residual gas analyzer (RGA). Four different subsystems of RIE (such as RF power, chamber pressure, and two gas flows) were considered as potential sources of fault, and multiple degrees of faults were tested. OES and RGA data were simultaneously collected while the etching of benzocyclobutene (BCB) in a $SF_6/O_2$ plasma was taking place. To simulate established TSNNs as incipient fault detectors, each TSNN was trained to learn the parameters at t, t+T, ... , and t+4T. This prediction scheme could effectively compensate run-time-delay (RTD) caused by data preprocessing and computation. Satisfying results are presented in this paper, and it turned out that OES is more sensitive to RF power and RGA is to chamber pressure and gas flows. Therefore, the combination of these two sensors is recommended for better fault detection, and they show a potential to the applications of not only incipient fault detection but also incipient real-time diagnosis.

• Journal of Korean Society of Water and Wastewater
• /
• v.31 no.4
• /
• pp.289-296
• /
• 2017

Pulp and paper industry produces large volumes of wastewater and residual sludge waste, resulting in many issues in relation to wastewater treatment and sludge disposal. Contaminants in pulp and paper wastewater include effluent solids, sediments, chemical oxygen demand (COD), and biological oxygen demand (BOD), which should be treated by wastewater treatment processes such as coagulation and biological treatment. However, few works have been attempted to predict the treatment efficiency of pulp and paper wastewater. Accordingly, this study presented empirical models based on experimental data in laboratory-scale coagulation tests and compared them with statistical models such as artificial neural network (ANN). Results showed that the water quality parameters such as turbidity, suspended solids, COD, and UVA can be predicted using either linear or expoential regression models. Nevertheless, the accuracies for turbidity and UVA predictions were relatively lower than those for SS and COD. On the other hand, ANN showed higher accuracies than the emprical models for all water parameters. However, it seems that two kinds of models should be used together to provide more accurate information on the treatment efficiency of pulp and paper wastewater.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.12
• /
• pp.1106-1114
• /
• 2012

In order to provide high data rate and real time services under maritime environment, link-level performance of ship ad-hoc network (SANET) based on 3GPP LTE and IEEE 802.11p (WAVE) specifications are investigated and discussed in this paper. The measured maritime channel, whose delay spread is longer than the length of guard interval (GI) of both 3GPP LTE and IEEE 802.11p specifications, is adopted for the link-level simulations. For the purpose of eliminating inter-symbol interference (ISI) due to insufficient GI length, double antenna pattern (DAP) scheme and advanced time-domain decision-feedback equalizer (DFE) are proposed for LTE and WAVE systems, respectively. The proposed DFE removes the ISI in a same manner as the residual inter-symbol interference cancellation (RISIC) algorithm, but the inter-carrier interference (ICI) is reduced via cyclicity removal instead of cyclicity restoration used in the RISIC algorithm. Compared with existing schemes, our proposed DFE is a robust technique to overcome the severe ISI channel which has a comparatively large delay spread. Based on simulation results, not only comparisons between systems are discussed, but also some reformative suggestions are given.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.674-683
• /
• 2021

A trust-aware secure routing protocol (TSRP) for wireless sensor networks is proposed in this paper to defend against varieties of attacks. First, each node calculates the comprehensive trust values of its neighbors based on direct trust value, indirect trust value, volatilization factor, and residual energy to defend against black hole, selective forwarding, wormhole, hello flood, and sinkhole attacks. Second, any source node that needs to send data forwards a routing request packet to its neighbors in multi-path mode, and this continues until the sink at the end is reached. Finally, the sink finds the optimal path based on the path's comprehensive trust values, transmission distance, and hop count by analyzing the received packets. Simulation results show that TSRP has lower network latency, smaller packet loss rate, and lower average network energy consumption than ad hoc on-demand distance vector routing and trust based secure routing protocol.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1728-1742
• /
• 2023

In this paper, we extended a hierarchical clustering technique, which is the most researched in the sensor network field, and studied a dynamic differential clustering technique to minimize energy consumption and ensure equal lifespan of all sensor nodes while considering the mobility of sinks. In a sensor network environment with mobile sinks, clusters close to the sinks tend to consume more forwarding energy. Therefore, clustering that considers forwarding energy consumption is desired. Since all clusters form a hierarchical tree, the number of levels of the tree must be considered based on the size of the cluster so that the cluster size is not growing abnormally, and the energy consumption is not concentrated within specific clusters. To verify that the proposed DDC protocol satisfies these requirements, a simulation using Matlab was performed. The FND (First Node Dead), LND (Last Node Dead), and residual energy characteristics of the proposed DDC protocol were compared with the popular clustering protocols such as LEACH and EEUC. As a result, it was shown that FND appears the latest and the point at which the dead node count increases is delayed in the DDC protocol. The proposed DDC protocol presents 66.3% improvement in FND and 13.8% improvement in LND compared to LEACH protocol. Furthermore, FND improved 79.9%, but LND declined 33.2% when compared to the EEUC. This verifies that the proposed DDC protocol can last for longer time with more number of surviving nodes.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.439-449
• /
• 2023

In an era marked by the increasing use of drones and the growing demand for indoor surveillance, the development of a robust application for detecting and tracking both drones and humans within indoor spaces becomes imperative. This study presents an innovative application that uses FMCW radar to detect human and drone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applications with Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objects present in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clustering drone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned and classified into either humans or drones by employing a deep learning model. A trio of models, including Deep Neural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and the outcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy for identifying drone clusters and a noteworthy 96.75% accuracy for human clusters.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.