• 제목/요약/키워드: Neural network prediction

검색결과 1,960건 처리시간 0.023초

Enhancing Wind Speed and Wind Power Forecasting Using Shape-Wise Feature Engineering: A Novel Approach for Improved Accuracy and Robustness

  • Mulomba Mukendi Christian;Yun Seon Kim;Hyebong Choi;Jaeyoung Lee;SongHee You
    • International Journal of Advanced Culture Technology
    • /
    • 제11권4호
    • /
    • pp.393-405
    • /
    • 2023
  • Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

Activity recognition of stroke-affected people using wearable sensor

  • Anusha David;Rajavel Ramadoss;Amutha Ramachandran;Shoba Sivapatham
    • ETRI Journal
    • /
    • 제45권6호
    • /
    • pp.1079-1089
    • /
    • 2023
  • Stroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurrent neural network, this study provides a novel dataset of stretching, upward stretching, flinging motions, hand-to-mouth movements, swiping gestures, and pouring motions for improved model training and testing of stroke-affected patients. A MATLAB application is used to output textual and audible prediction results. A wearable sensor with a triaxial accelerometer is used to collect preprocessed real-time data. The model is trained with features extracted from the actual patient to recognize new actions, and the recognition accuracy provided by multiple datasets is compared based on the same baseline model. When training and testing using the new dataset, the baseline model shows recognition accuracy that is 11% higher than the Activity Daily Living dataset, 22% higher than the Activity Recognition Single Chest-Mounted Accelerometer dataset, and 10% higher than another real-world dataset.

The Detection of Well-known and Unknown Brands' Products with Manipulated Reviews Using Sentiment Analysis

  • Olga Chernyaeva;Eunmi Kim;Taeho Hong
    • Asia pacific journal of information systems
    • /
    • 제31권4호
    • /
    • pp.472-490
    • /
    • 2021
  • The detection of products with manipulated reviews has received widespread research attention, given that a truthful, informative, and useful review helps to significantly lower the search effort and cost for potential customers. This study proposes a method to recognize products with manipulated online customer reviews by examining the sequence of each review's sentiment, readability, and rating scores by product on randomness, considering the example of a Russian online retail site. Additionally, this study aims to examine the association between brand awareness and existing manipulation with products' reviews. Therefore, we investigated the difference between well-known and unknown brands' products online reviews with and without manipulated reviews based on the average star rating and the extremely positive sentiment scores. Consequently, machine learning techniques for predicting products are tested with manipulated reviews to determine a more useful one. It was found that about 20% of all product reviews are manipulated. Among the products with manipulated reviews, 44% are products of well-known brands, and 56% from unknown brands, with the highest prediction performance on deep neural network.

Comparison of artificial intelligence models reconstructing missing wind signals in deep-cutting gorges

  • Zhen Wang;Jinsong Zhu;Ziyue Lu;Zhitian Zhang
    • Wind and Structures
    • /
    • 제38권1호
    • /
    • 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.

단백질 서열의 상동 관계를 가중 조합한 단백질 이차 구조 예측 (Prediction of Protein Secondary Structure Using the Weighted Combination of Homology Information of Protein Sequences)

  • 지상문
    • 한국정보통신학회논문지
    • /
    • 제20권9호
    • /
    • pp.1816-1821
    • /
    • 2016
  • 단백질은 대부분의 생물학적 과정에서 중대한 역할을 수행하고 있으므로, 단백질 진화, 구조와 기능을 알아내기 위하여 많은 연구가 수행되고 있는데, 단백질의 이차 구조는 이러한 연구의 중요한 기본적 정보이다. 본 연구는 대규모 단백질 구조 자료로부터 단백질 이차 구조 정보를 효과적으로 추출하여 미지의 단백질 서열이 가지는 이차 구조를 예측하려 한다. 질의 서열과 상동관계에 있는 단백질 구조자료내의 서열들을 광범위하게 찾아내기 위하여, 탐색에 사용하는 프로파일의 구성에 질의 서열과 유사한 서열들을 사용하고 갭을 허용하여 반복적인 탐색이 가능한 PSI-BLAST를 사용하였다. 상동 단백질들의 이차구조는 질의 서열과의 상동 관계의 강도에 따라 가중되어 이차 구조 예측에 기여되었다. 이차 구조를 각각 세 개와 여덟 개로 분류하는 예측 실험에서 상동 서열들과 신경망을 동시에 사용하여 93.28%와 88.79%의 정확도를 얻어서 기존 방법보다 성능이 향상되었다.

Increasing Splicing Site Prediction by Training Gene Set Based on Species

  • Ahn, Beunguk;Abbas, Elbashir;Park, Jin-Ah;Choi, Ho-Jin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제6권11호
    • /
    • pp.2784-2799
    • /
    • 2012
  • Biological data have been increased exponentially in recent years, and analyzing these data using data mining tools has become one of the major issues in the bioinformatics research community. This paper focuses on the protein construction process in higher organisms where the deoxyribonucleic acid, or DNA, sequence is filtered. In the process, "unmeaningful" DNA sub-sequences (called introns) are removed, and their meaningful counterparts (called exons) are retained. Accurate recognition of the boundaries between these two classes of sub-sequences, however, is known to be a difficult problem. Conventional approaches for recognizing these boundaries have sought for solely enhancing machine learning techniques, while inherent nature of the data themselves has been overlooked. In this paper we present an approach which makes use of the data attributes inherent to species in order to increase the accuracy of the boundary recognition. For experimentation, we have taken the data sets for four different species from the University of California Santa Cruz (UCSC) data repository, divided the data sets based on the species types, then trained a preprocessed version of the data sets on neural network(NN)-based and support vector machine(SVM)-based classifiers. As a result, we have observed that each species has its own specific features related to the splice sites, and that it implies there are related distances among species. To conclude, dividing the training data set based on species would increase the accuracy of predicting splicing junction and propose new insight to the biological research.

일기 예보와 예측 일사 및 일조를 이용한 태양광 발전 예측 (Photovoltaic Generation Forecasting Using Weather Forecast and Predictive Sunshine and Radiation)

  • 신동하;박준호;김창복
    • 한국항행학회논문지
    • /
    • 제21권6호
    • /
    • pp.643-650
    • /
    • 2017
  • 무한한 에너지원을 가진 태양광 발전은 기상 에 의존하기 때문에 발전량이 매우 간헐적이다. 따라서 태양광 발전량의 불확실성을 줄이고 경제성을 향상시키기 위하여 정확한 발전량 예측기술이 필요하다. 기상청은 3일간 기상정보를 예보하지만 태양광 발전 예측에 높은 상관관계가 있는 일조량과 일사량은 예보하지 않는다. 본 연구에서는 기상청에서 3일간 예보하는 기상요소인 기온, 강수량, 풍향, 풍속, 습도, 운량 등을 이용하여, 일조 및 일사량을 예측하였으며, 예측된 일사 및 일조량을 이용하여, 실시간 태양광 발전량을 예측하는 딥러닝 모델을 제안하였다. 결과로서 예측된 기상요소로 발전량을 예측하는 모델보다 제안 모델이 MAE, RMSE, MAPE 등의 오차율 지표에서 더 좋은 결과를 보여주었다. 또한, 기계 학습의 한 종류인 서포트 벡터 머신을 사용하는 것보다 DNN을 사용하는 것이 더 낮은 오차율 지표를 보여주었다.

신경망 및 통계 기법 기반의 기계학습을 이용한 유류유출 및 기상 예측 연구 동향 (A Survey on Oil Spill and Weather Forecast Using Machine Learning Based on Neural Networks and Statistical Methods)

  • 김경도;김용혁
    • 한국융합학회논문지
    • /
    • 제8권10호
    • /
    • pp.1-8
    • /
    • 2017
  • 정확한 예측은 미래에 일어날 현상에 대해 효과적으로 준비 혹은 대처 할 수 있게 해준다. 특히, 기상 현상은 인간의 생활과 밀접한 연관이 있으며, 발생할 수 있는 기상 및 재난 예측을 통해 인명, 재산 등의 피해로부터 예방 할 수 있게 해준다. 해상에서 발생할 수 있는 재난 중 하나인 유류유출 사고에 대해 빠르고 효과적으로 대응하기 위해서는 유출유의 이동과 주변 해역의 기상을 정확하게 예측하는 것이 중요하다. 본 논문에서는 분류 및 회귀 예측과 관련된 연구에서 준수한 성능 및 예측 가능성을 보여준 기계학습 기법으로 서포트 벡터 머신, 가우시안 프로세스, 다층 퍼셉트론, 방사기저함수 네트워크의 총 4 개의 기계학습 기법을 선별하였다. 선별한 기계학습 기법을 이용하여 유류유출의 탐지와 바람, 강우량, 오존 등의 기상 데이터를 예측하는 연구들의 연구 방법과 결과 등을 설명하며 이를 활용한 기계학습 기반 유류유출 예측 모델의 적용 가능성을 제시한다.

절대 유사 임계값 기반 사례기반추론과 유전자 알고리즘을 활용한 시스템 트레이딩 (System Trading using Case-based Reasoning based on Absolute Similarity Threshold and Genetic Algorithm)

  • 한현웅;안현철
    • 한국정보시스템학회지:정보시스템연구
    • /
    • 제26권3호
    • /
    • pp.63-90
    • /
    • 2017
  • Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

RNN-LSTM을 이용한 태양광 발전량 단기 예측 모델 (Short Term Forecast Model for Solar Power Generation using RNN-LSTM)

  • 신동하;김창복
    • 한국항행학회논문지
    • /
    • 제22권3호
    • /
    • pp.233-239
    • /
    • 2018
  • 태양광 발전은 기상 상태에 따라 간헐적이기 때문에 태양광 발전의 효율과 경제성 향상을 위해 정확한 발전량 예측이 요구된다. 본 연구는 목포 기상대에서 예보하는 기상 데이터와 영암 태양광 발전소의 발전량 데이터를 이용하여 태양광 발전량 단기 딥러닝 예측모델을 제안하였다. 기상청은 기온, 강수량, 풍향, 풍속, 습도, 운량 등의 기상요소를 3일간 예보한다. 그러나 태양광 발전량 예측에 가장 중요한 기상요소인 일조 및 일사 일사량 예보하지 않는다. 제안 모델은 예보 기상요소를 이용하여, 일조 및 일사 일사량을 예측 하였다. 또한 발전량은 기상요소에 예측된 일조 및 일사 기상요소를 추가하여 예측하였다. 제안 모델의 발전량 예측 결과 DNN의 평균 RMSE와 MAE는 0.177과 0.095이며, RNN은 0.116과 0.067이다. 또한, LSTM은 가장 좋은 결과인 0.100과 0.054이다. 향후 본 연구는 다양한 입력요소의 결합으로 보다 향상된 예측결과를 도출할 수 있을 것으로 기대된다.