http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Samee Ullah Khan,Hikmat Yar,Habib Khan,Sumin Lee,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.06
Fire detection is a significant attempt for preserving public safety in complex surveillance environments. Although advances in deep learning for fire detection, the task remains challenging due to the natural irregularity in fire images, including differences in lighting conditions, occlusions, and background complexity. To address these challenges, we present a novel framework for fire detection named fire channel attention network (FCAN), which is capable of differentiating challenging fire scenes. Our approach is motivated by the need to enhance the accuracy of fire detection by selectively emphasizing the most informative channels of the input image through a channel attention (CA). Furthermore, our model captures the salient features from the input image and suppresses the irrelevant ones, thereby overcoming the aforementioned challenges of fire detection. The FCAN is evaluated on two benchmark datasets and surpassed existing methods in terms of accuracy and F1 score. The proposed model demonstrates the effectiveness of fire detection, highlighting its potential for practical applications in fire safety and prevention.
Kattiya Samee,Jakrapong Pongpeng 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.5
Construction equipment management by contractors demonstrates investment efficiency and service performance, which can affect the construction project and corporate performance. Although many studies have considered the components of construction equipment management, project performance and corporate performance, the causal relationships among these components have not been explored to date. This study explores these relationships. The research method included the collection of contractors’ opinions regarding the importance of these factors. Structural Equation Modeling (SEM) was employed to determine the causal relationships among the data. The results indicate four factors of construction equipment management, with their weights of relative importance, affect project and corporate performance. Selection management exhibits the greatest effect (33%); this is followed by operations management (27%), maintenance and repair management (25%), and retirement and replacement management (15%). Regarding the factors for measuring project performance, the quality and time factors were ranked first and second in importance, respectively. The customer factor was the most important factor for describing corporate performance. The findings of this study enable a greater understanding of these causal relationships, providing a starting point for improving the project and corporate procedures of equipment management.
Structural Equation Model for Construction Equipment Selection and Contractor Competitive Advantages
Kattiya Samee,Jakrapong Pongpeng 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.1
The selection and use of appropriate construction equipment contributes to operational efficiency and contractor competitive advantages. However, numerous factors are involved in the selection of suitable construction equipment. A review of the existing literature revealed a lack of research on the causal relationships between construction equipment selection factors and contractor competitive advantages. Therefore, this study attempted to identify the selection factors through a survey of contractors’ opinions on the levels of importance of the factors that are relevant to construction equipment selection and competitive advantages. The survey data were analyzed using Structural Equation Modeling (SEM). The results suggest the following six major selection factors and their respective weights of relative importance: compatibility with site characteristics (25%), services and maintenance (19%), costs (15%), safety and environmental effects (14%), ease of acquisition (14%), and technology and innovation (13%). These selection factors influence contractor competitive advantages in terms of financial stability, corporate image and reputation, bidding opportunity, and technical capacity, and their weights of relative importance are 31%, 25%, 22%, and 22%, respectively. The findings of this study shed light on the causal relationships between the selection of appropriate construction equipment and contractor competitive advantages.
데이터 주석 및 모델 성능 향상을 위한 능동적 학습 접근
Hikmat Yar,Samee Ullah Khan,Tanveer Hussain,Min Je Kim,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2022 한국차세대컴퓨팅학회 학술대회 Vol.2022 No.05
Deep learning models achieved a lot of success due to the availability of labeled training data. In contrast, labeling a huge amount of data by a human is a time-consuming and expensive solution. Active Learning (AL) efficiently addresses the issue of labeled data collection at a low cost by picking the most useful samples from a large number of unlabeled datasets However, current AL techniques largely depend on regular human involvement to annotate the most uncertain/informative samples in the collection. Therefore, a novel AL-based framework is proposed comprised of proxy and active models to reduce the manual labeling costs. In the proxy model, VGG-16 is trained on chunks of labeled data that later act as an annotator decision. On the other hand, in the active model, unlabeled is passed to Inception-V3 using the sampling strategy. The uncorrected predicted samples are then forwarded to the proxy model for annotation and considered those data have a high confidence score. The empirical results verify that our proposed model is the best in terms of annotation and accuracy.
MARK SEQUENCES IN TRIPARTITE MULTIDIGRAPHS
Pirzada, S.,Samee, U. The Korean Society for Computational and Applied M 2009 Journal of applied mathematics & informatics Vol.27 No.5
A tripartite $\gamma$-digraph is an orientation of a tripartite multigraph that is without loops and contains at most $\gamma$ edges between any pair of vertices from distinct parts. In this paper, we obtain necessary and sufficient conditions for sequences of non-negative integers in non-decreasing order to be the sequences of numbers, called marks (or $\gamma$-scores), attached to the vertices of a tripartite $\gamma$-digraph.
머신 러닝 기법을 활용한 무인 항공기 기반 재난 영상 분류
Altaf Hussain,Samee Ullah Khan,Fath U Min Ullah,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.05
Recently due to natural disasters, the world is facing huge ecological, social, economic, and loss of precious lives. Traditionally during natural disasters, emergency response teams are physically visiting different areas to inspect and stop their further damages. Therefore, the existing monitoring system is facing issues such as human accessibility and unable to analyze disaster in real-time. To address these issues, we propose a machine learning inspired framework for automatically recognized disaster scenes that contains three main steps. In the first step preprocessing is applied for condense and normalize the image dimension. Next, histogram of oriented gradient (HOG) descriptor is utilize to extract discriminative features and extracted features are classified through SVM. Finally in testing step, in case of disaster scenes our system trigger notification to nearby disaster management centers to take an appropriate action. We provide comprehensive experiments on various machine learning approaches among them we obtain 64% accuracy on HOG with SVM.
건물의 전력 소비 예측을 위한 어텐션 기반 이중 스트림 딥러닝 네트워크를 활용한 개선된 전력 소비 예측
Noman Khan,Samee Ullah Khan,Altaf Hussain,Sumin Lee,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.06
A crucial component of designing intelligent and ecologically friendly environments nowadays is electricity consumption forecasting. The generation of energy can be enhanced to effectively meet the population's rising requirements by using the prediction of future electricity consumption. Due to the broad variety of consumption patterns, it is difficult to anticipate the energy requirements of buildings. Therefore, this work uses a dual-steam approach with multi-head attention to anticipate the power consumption of the building to address this issue and produce precise predictions. The proposed network concurrently learns temporal representations through a Bidirectional Gated Recurrent Unit (BGRU) and spatial patterns through Atrous Convolutional Neural Network (ACNN). The obtained features are combined to create a single feature vector that is used as the input for the multi-head attention, which finds the features that are most suited to forecasting the electricity consumption of a building. Finally, the dense layer receives the effective features and uses them to forecast short-term power consumption. In this paper, the proposed dual-stream network with attention outperforms competing models, achieving the lowest error value for hourly building power consumption prediction, according to experimentation on the household electricity consumption dataset.
이상행동 및 행동 인식 모델 학습 및 테스트를 위한 시스템 UI 설계에 대한 연구
이수민,권찬민,Tanveer Hussain,Samee Ullah Khan,Waseem Ullah,Noman Khan,Zulfiqar Ahmad Khan,이미영,백성욱 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.05
인공지능을 활용한 사업이 활발히 진행되면서 범죄 예방 및 안전분야와 관련하여 이상행동 및 행동 인식에 대한 연구와 관심이 높아지고 있다. 하지만 딥러닝 등 인공지능 모델을 생성하는 것은 전문 지식이 없는 경우 많은 어려움이 따른다. 본 논문에서는 사용자가 편리하게 딥러닝 모델을 생성할 수 있도록 데이터셋을 제공하고 이상행동 및 행동 인식 기술을 API화하여 인터페이스에서 호출하는 방식을 사용하는 사용자 친화적인 모델 학습 및 테스트를 위한 시스템 UI를 제안하였다. 본 논문에서 제안한 시스템은 딥러닝에 대한 사전 지식이 없는 사용자가 편리하게 딥러닝 모델을 생성할 수 있을 것으로 기대된다.