• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.190-194
• /
• 2023

By looking the importance of communication, data delivery and access in various sectors including governmental, business and individual for any kind of data, it becomes mandatory to identify faults and flaws during cyber communication. To protect personal, governmental and business data from being misused from numerous advanced attacks, there is the need of cyber security. The information security provides massive protection to both the host machine as well as network. The learning methods are used for analyzing as well as preventing various attacks. Machine learning is one of the branch of Artificial Intelligence that plays a potential learning techniques to detect the cyber-attacks. In the proposed methodology, the Decision Tree (DT) which is also a kind of supervised learning model, is combined with the different cross-validation method to determine the accuracy and the execution time to identify the cyber-attacks from a very recent dataset of different network attack activities of network traffic in the UNSW-NB15 dataset. It is a hybrid method in which different types of attributes including Gini Index and Entropy of DT model has been implemented separately to identify the most accurate procedure to detect intrusion with respect to the execution time. The different DT methodologies including DT using Gini Index, DT using train-split method and DT using information entropy along with their respective subdivision such as using K-Fold validation, using Stratified K-Fold validation are implemented.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_1
• /
• pp.967-976
• /
• 2023

Currently, with the thriving development in the field of solar energy, the widespread adoption of solar grid-connected power conversion systems is rapidly expanding. As the market continues to grow, the efficiency of solar power conversion systems is steadily increasing, while prices are rapidly decreasing. Photovoltaic panels often produce low output voltages, and Boost converters are commonly employed to elevate and stabilize these voltages. They are also utilized for implementing Maximum Power Point Tracking (MPPT), ensuring the full utilization of solar power generation. Recently, synchronous control techniques have been introduced, using controllable switching devices like Si IGBT or SiC MOSFET to replace the diodes in the original circuits. However, this has raised concerns related to costs. This paper offers a compromise solution, considering both the performance and economic factors of the converter. It proposes a hybrid high-efficiency synchronous converter structure that combines Si IGBT and SiC MOSFET. Additionally, the proposed topology has been practically implemented and tested, with results confirming its feasibility and cost-effectiveness.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• Wind and Structures
• /
• v.38 no.1
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.752-770
• /
• 2019

The purpose of this study is to incorporate telemarketing processes to improve telemarketing performance. For this application, we have attempted to mix the model of machine learning to extract potential customers with personalisation techniques to derive recommended products from actual contact. Most of traditional recommendation systems were mainly in ways such as collaborative filtering, which predicts items with a high likelihood of future purchase, based on existing purchase transactions or preferences for products. But, under these systems, new users or items added to the system do not have sufficient information, and generally cause problems such as a cold start that can not obtain satisfactory recommendation items. Also, indiscriminate telemarketing attempts can backfire as they increase the dissatisfaction and fatigue of customers who do not want to be contacted. To this purpose, this study presented a multi-purpose hybrid recommendation algorithm to achieve two goals: to select customers with high possibility of contact, and to recommend products to selected customers. In addition, we used subscription data from telemarketing agency that handles insurance products to derive realistic applicability of the proposed recommendation system. Our proposed recommendation system would certainly solve the cold start and scarcity problem of existing recommendation algorithm by using contents information such as customer master information and telemarketing history. Also. the model could show excellent performance not only in terms of overall performance but also in terms of the recommendation success rate of the unpopular product.

• Journal of Internet Computing and Services
• /
• v.17 no.5
• /
• pp.89-95
• /
• 2016

In a software testing domain, test case prioritization techniques improve the performance of regression testing, and arrange test cases in such a way that maximum available faults be detected in a shorter time. User-sessions and cookies are unique features of web applications that are useful in regression testing because they have precious information about the application state before and after making changes to software code. This approach is in fact a user-session based technique. The user session will collect from the database on the server side, and test cases are released by the small change configuration of a user session data. The main challenges are the effectiveness of Average Percentage Fault Detection rate (APFD) and time constraint in the existing techniques, so in this paper developed an intelligent framework which has three new techniques use to manage and put test cases in group by applying useful criteria for test case prioritization in web application regression testing. In dynamic weighting approach the hybrid criteria which set the initial weight to each criterion determines optimal weight of combination criteria by evolutionary algorithms. The weight of each criterion is based on the effectiveness of finding faults in the application. In this research the priority is given to test cases that are performed based on most common http requests in pages, the length of http request chains, and the dependency of http requests. To verify the new technique some fault has been seeded in subject application, then applying the prioritization criteria on test cases for comparing the effectiveness of APFD rate with existing techniques.

• Journal of Communications and Networks
• /
• v.2 no.1
• /
• pp.76-84
• /
• 2000

Communication systems, including cell-based mobile communication systems, multiple satellite communication systems of multi-beam satellite systems, require reliable handoff methods between cell-to-cell, satellite-to-satellite of beam-to-team, respectively. Recent measurement of a CDMA cellular system indicates that the system is in handoff at about 35% to 70% of an average call period. Therefore, system reliability during handoff is one of the major system performance parameters and eventually becomes a factor in the overall system capacity. This paper presents novel and improved techniques for handoff in cellular communications, multi-beam and multi-satellite systems that require handoff during a session. this new handoff system combines the soft handoff mechanism currently implemented in the IS-95 CDMA with code and packet diversity combining techniques and an iterative decoding algorithm (Turbo Coding). the Turbo code introduced by Berrou et all. has been demonstrated its remarkable performance achieving the near Shannon channel capacity [1]. Recently. Turbo codes have been adapted as the coding scheme for the data transmission of the third generation international cellular communication standards : UTRA and CDMA 2000. Our proposed encoder and decoder schemes modified from the original Turbo code is suitable for the code and packet diversity combining techniques. this proposed system provides not only an unprecedented coding gain from the Turbo code and it iterative decoding, but also gain induced by the code and packet diversity combining technique which is similar to the hybrid Type II ARQ. We demonstrate performance improvements in AWGN channel and Rayleigh fading channel with perfect channel state information (CSI) through simulations for at low signal to noise ratio and analysis using exact upper bounding techniques for medium to high signal to noise ratio.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2698-2717
• /
• 2019

This paper proposes a multi-stage encryption technique to enhance the level of secrecy of image to facilitate its secured transmission through the public network. A great number of researches have been done on image secrecy. The existing image encryption techniques like visual cryptography (VC), steganography, watermarking etc. while are applied individually, usually they cannot provide unbreakable secrecy. In this paper, through combining several separate techniques, a hybrid multi-stage encryption technique is proposed which provides nearly unbreakable image secrecy, while the encryption/decryption time remains almost the same of the exiting techniques. The technique consecutively exploits VC, steganography and one time pad (OTP). At first it encrypts the input image using VC, i.e., splits the pixels of the input image into multiple shares to make it unpredictable. Then after the pixel to binary conversion within each share, the exploitation of steganography detects the least significant bits (LSBs) from each chunk within each share. At last, OTP encryption technique is applied on LSBs along with randomly generated OTP secret key to generate the ultimate cipher image. Besides, prior to sending the OTP key to the receiver, first it is converted from binary to integer and then an asymmetric cryptosystem is applied to encrypt it and thereby the key is delivered securely. Finally, the outcome, the time requirement of encryption and decryption, the security and statistical analyses of the proposed technique are evaluated and compared with existing techniques.