• 해양환경안전학회지
• /
• 제29권1호
• /
• pp.24-35
• /
• 2023

급격한 산업화와 도시화로 인해 해양 오염이 심각해지고 있으며, 이러한 해양 오염을 실효적으로 관리하기 위해 수질평가지수(Water Quality Index, WQI)를 마련하여 활용하고 있다. 하지만 수질평가지수는 다소 복잡한 계산과정으로 인한 정보의 손실, 기준값 변동, 실무자의 계산오류, 통계적 오류 등의 불확실성(uncertainty)을 내포하고 있다. 이에 따라 국내·외에서 인공지능 기법을 활용하여 수질평가지수를 예측하기 위한 연구가 활발히 이루어지고 있다. 본 연구에서는 해양환경측정망 자료(2000 ~ 2020년)를 활용하여 우리나라 전 해역 즉, 5개의 생태구에 대한 WQI를 추정할 수 있는 가장 적합한 인공지능기법을 도출하기 위해 총 6가지의 기법(RF, XGBoost, KNN, Ext, SVM, LR)을 실험하였다. 그 결과, Random Forest 기법이 다른 기법에 비해 가장 우수한 성능을 보였다. Random Forest 기법의 WQI 점수 예측값과 실제값의 잔차 분석 결과, 모든 생태구에서 시간적 및 공간적 예측 성능이 우수한 것으로 나타났다. 이를 통해 본 연구에서 개발한 Random Forest 기법은 높은 정확도를 바탕으로 우리나라 전해역에 대한 WQI를 예측 가능할 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.670-691
• /
• 2013

In RSSI-based RFID(Radio Frequency IDentification) indoor localization system, the signal path loss model of each sub-region is different from others in the whole localization area due to the influence of the multi-path phenomenon and other environmental factors. Therefore, this paper divides the localization area into many sub-regions and constructs separately the signal path loss model of each sub-region. Then an improved LANDMARC method is proposed. Firstly, the deployment principle of RFID readers and tags is presented for constructing localization sub-region. Secondly, the virtual reference tags are introduced to create a virtual signal strength space with RFID readers and real reference tags in every sub-region. Lastly, k nearest neighbor (KNN) algorithm is used to locate the target object and an error compensating algorithm is proposed for correcting localization result. The results in real application show that the new method enhances the positioning accuracy to 18.2% and reduces the time cost to 30% of the original LANDMARC method without additional tags and readers.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.369-376
• /
• 2021

One of the most active areas of research in the field of affective computing and signal processing is emotion recognition. This paper proposes emotion recognition of low-resource (Sindhi) language. This work's uniqueness is that it examines the emotions of languages for which there is currently no publicly accessible dataset. The proposed effort has provided a dataset named MAVDESS (Mehran Audio-Visual Dataset Mehran Audio-Visual Database of Emotional Speech in Sindhi) for the academic community of a significant Sindhi language that is mainly spoken in Pakistan; however, no generic data for such languages is accessible in machine learning except few. Furthermore, the analysis of various emotions of Sindhi language in MAVDESS has been carried out to annotate the emotions using line features such as pitch, volume, and base, as well as toolkits such as OpenSmile, Scikit-Learn, and some important classification schemes such as LR, SVC, DT, and KNN, which will be further classified and computed to the machine via Python language for training a machine. Meanwhile, the dataset can be accessed in future via https://doi.org/10.5281/zenodo.5213073.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.345-352
• /
• 2022

Conducting AI-based fusion business due to the increment of ICT fusion medical device has been expanded. In addition, AI-based medical devices help change existing medical system on treatment into the paradigm of customized treatment such as preliminary diagnosis and prevention. It will be generally promoted to the change of medical device industry. Although the current demand forecasting of medical biotechnology commercialization is based on the method of Delphi and AHP, there is a problem that it is difficult to have a generalization due to fluctuation results according to a pool of participants. Therefore, the purpose of the paper is to predict demand forecasting for identifying promising technology based on building up big data in medical biotechnology. The development method is to employ candidate technologies of keywords extracted from SCOPUS and to use word2vec for drawing analysis indicator, technological distance similarity, and recommended technological similarity of top-level items in order to achieve a reasonable result. In addition, the method builds up academic big data for 5 years (2016-2020) in order to commercialize technology excavation on demand perspective. Lastly, the paper employs global data studies in order to develop domestic and international demand for technology excavation in the medical biotechnology field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1200-1215
• /
• 2023

With the development of IoT and artificial intelligence, location-based services are getting more and more attention. For solving the current problem that indoor positioning error is large and generalization is poor, this paper proposes a Model Stacking Algorithm for Indoor Positioning System using WiFi fingerprinting. Firstly, we adopt a model stacking method based on Bayesian optimization to predict the location of indoor targets to improve indoor localization accuracy and model generalization. Secondly, Taking the predicted position based on model stacking as the observation value of particle filter, collaborative particle filter localization based on model stacking algorithm is realized. The experimental results show that the algorithm can control the position error within 2m, which is superior to KNN, GBDT, Xgboost, LightGBM, RF. The location accuracy of the fusion particle filter algorithm is improved by 31%, and the predicted trajectory is close to the real trajectory. The algorithm can also adapt to the application scenarios with fewer wireless access points.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.669-681
• /
• 2023

과일 나무의 생육을 평가하는 중요한 지표인 엽록소 함량을 추정하는데 비교적 많은 노동력의 투입이 요구되고 오랜 시간이 소요되는 기존의 파괴 조사 대신 비파괴적 조사 방식인 원격탐사기술을 적용하기 위한 연구가 시도되고 있다. 이 연구에서는 2년(2021, 2022) 간 무인기 기반의 초분광 영상을 이용하여 배나무 잎의 엽록소 함량을 비파괴적으로 추정하는 연구를 수행하였다. 영상 처리로 추출된 배나무 캐노피(canopy)의 단일 band 반사율은 시간 변화에 따라 불안정한 복사 효과를 최소화하기 위해 밴드비화(band rationing) 되었다. 밴드비(band ratios)를 입력 변수로 머신러닝 알고리즘인 elastic-net, k-nearest neighbors (KNN)과 support vector machine을 사용하여 추정(calibration, validation) 모델들을 개발하였다. Full band ratios 기반 추정 모델들의 성능과 비교하여 계산 비용 절감과 재현성 향상에 유리한 key band ratios를 선정하였다. 결과적으로 모든 머신러닝 모델에서 full band ratios를 이용한 calibration에 coefficient of determination (R²)≥0.67, root mean squared error (RMSE)≤1.22 ㎍/cm², relative error (RE)≤17.9%)와 validation에 R²≥0.56, RMSE≤1.41 ㎍/cm², RE≤20.7% 성능을 비교하였을 때, key band ratios 네 개가 선정되었다. 머신러닝 모델들 사이에 validation 성능에는 비교적 큰 차이가 없어 calibration 성능이 가장 높았던 KNN 모델을 기준으로 삼았으며, 그 key band ratios는 710/714, 718/722, 754/758, 758/762 nm가 선정되었다. Calibration에서 R²=0.80, RMSE=0.94 ㎍/cm², RE=13.9%와 validation에서 R²=0.57, RMSE=1.40 ㎍/cm², RE=20.5%를 나타내었다. Validation의 기준으로 한 성능 결과는 배나무 잎 엽록소 함량을 추정하기에 충분하지 않았지만, 앞으로의 연구에 기준이 될 key band ratios를 선정했다는 것에 의미가 있다. 추후 연구에서는 추정 성능을 향상하기 위해 지속적으로 추가 데이터세트를 확보하여 선정된 key band ratios의 신뢰성 검증과 함께 실제 과원에 재현 가능한 추정 모델로 고도화할 필요가 있다.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.343-350
• /
• 2020

In the era of the Fourth Industrial Revolution in the digital revolution is taking place, various attempts have been made to provide various contents in a digital environment. In this paper, agent-recruitment service system based on collaborative deep learning is proposed for the intelligent head hunting service. The service system is improved from previous research [7] using collaborative deep learning for more reliable recommendation results. The Collaborative deep learning is a hybrid recommendation algorithm using "Recurrent Neural Network(RNN)" specialized for exponential calculation, "collaborative filtering" which is traditional recommendation filtering methods, and "KNN-Clustering" for similar user analysis. The proposed service system can expect more reliable recommendation results than previous research and showed high satisfaction in user survey for verification.

• Journal of applied mathematics & informatics
• /
• 제40권3_4호
• /
• pp.563-575
• /
• 2022

Many organizations seek statistical modelling facilitated by data analytics technologies for determining the prediction models associated with M&A (Merger and Acquisition). By combining these data analytics tool alongside with data collection approaches aids organizations towards M&A decision making, followed by achieving profitable insights as well. It promotes for better visibility, overall improvements and effective negotiation strategies for post-M&A integration. This paper explores on the impact of pre and post integration of M&A in a standard organizational setting via devising a suitable statistical model via employing techniques such as Naïve Bayes, K-nearest neighbour (KNN), and Decision Tree & Support Vector Machine (SVM).

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.886-887
• /
• 2023

This paper is about the development of kiosks that provide four types of service. Simple UI and educational videos solve the complexity of existing kiosks and provide an intuitive and convenient screen to users. In addition, the AR function, which is a three-dimensional form, shows directions and store representative images. After storing user information in the DB, a learning model is generated using user-based KNN collaborative filtering to provide a recommendation menu. As a result, it is possible to increase user convenience through kiosks using metaverse and AI recommendation services. It is also expected to solve digital alienation of social classes who have difficulty using kiosks.

• Steel and Composite Structures
• /
• 제42권6호
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.