• 한국컴퓨터정보학회논문지
• /
• 제20권5호
• /
• pp.73-81
• /
• 2015

소프트웨어 결함 예측 연구들의 대부분은 입력 개체의 결함 유무를 예측하는 이진 분류 모델들에 관한 것들이다. 하지만 모든 결함들이 같은 심각도를 갖지는 않으므로 예측 모델이 입력 개체의 결함경향성을 몇 개의 심각도 범주로 분류할 수 있다면 훨씬 유용하게 사용될 수 있다. 본 논문에서는 전통적인 복잡도와 크기 메트릭들을 입력으로 하는 심각도 기반 결함 예측 모델을 제안하였다. 학습 알고리즘은 많이 사용되는 네 개의 기계학습 기법들을 사용하였으며, 모델 구조는 삼진 분류 모델로 하였다. 모델 성능 평가를 위해 실험 데이터는 두 개의 NASA 공개 데이터 집합을 사용하였고, 평가 측정치는 Accuracy를 이용하였다. 평가 실험 결과는 역전파 신경망 모델이 두 데이터 집합에 대해 각각 81%와 88% 정도의 Accuracy 값으로 가장 좋은 성능을 보였다.

• Steel and Composite Structures
• /
• 제50권4호
• /
• pp.443-458
• /
• 2024

The construction industry, one of the biggest producers of greenhouse emissions, is under a lot of pressure as a result of growing worries about how climate change may affect local communities. Geopolymer concrete (GPC) has emerged as a feasible choice for construction materials as a result of the environmental issues connected to the manufacture of cement. The findings of this study contribute to the development of machine learning methods for estimating the properties of eco-friendly concrete, which might be used in lieu of traditional concrete to reduce CO₂ emissions in the building industry. In the present work, the compressive strength (f_c) of GPC is calculated using random forests regression (RFR) methodology where natural zeolite (NZ) and silica fume (SF) replace ground granulated blast-furnace slag (GGBFS). From the literature, a thorough set of experimental experiments on GPC samples were compiled, totaling 254 data rows. The considered RFR integrated with artificial hummingbird optimization (AHA), black widow optimization algorithm (BWOA), and chimp optimization algorithm (ChOA), abbreviated as ARFR, BRFR, and CRFR. The outcomes obtained for RFR models demonstrated satisfactory performance across all evaluation metrics in the prediction procedure. For R² metric, the CRFR model gained 0.9988 and 0.9981 in the train and test data set higher than those for BRFR (0.9982 and 0.9969), followed by ARFR (0.9971 and 0.9956). Some other error and distribution metrics depicted a roughly 50% improvement for CRFR respect to ARFR.

• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.107-114
• /
• 2023

Successful implementations of DevOps practices significantly improvise software efficiency, collaboration and security. Most of the organizations are adopting DevOps for faster and quality software delivery. DevOps brings development and operation teams together to overcome all kind of communication gaps responsible for software failures. It relies on different sets of alternative tools to automate the tasks of continuous integration, testing, delivery, deployment and monitoring. Although DevOps is followed for being very reliable and responsible environment for quality software delivery yet it lacks many quantifiable aspects to prove it on the top of other traditional and agile development methods. This research evaluates quantitative performance of DevOps and traditional/ agile development methods based on software metrics. This research includes three sample projects or code repositories to quantify the results and for DevOps integrated selective tool chain; current research considers our earlier proposed and implemented DevOps hybrid model of integrated automation tools. For result discussion and validation, tabular and graphical comparisons have also been included to retrieve best performer model. This comparative and evaluative research will be of much advantage to our young researchers/ students to get well versed with automotive environment of DevOps, latest emerging buzzword of development industries.

• Wind and Structures
• /
• 제36권6호
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.274-276
• /
• 2021

인공지능이 빠르게 발달하면서 의료, 교육, 게임 등 일상생활에 적용되고 있다. 인공지능 알고리즘은 예측 측면에서 언제나 확률적으로 불확실성을 지니고 있다. 기존 제품이나 서비스는 개발자의 의도에 따라 프로그램이 동작하기 때문에, 상호작용에 따른 결과가 명확하며 이에 대한 UX 평가를 할 수 있었다. 하지만, 인공지능이 적용된 서비스는 기존 서비스들과 달리 상호작용에 따른 불확실성으로 인해 위험 요소가 따르고 있다. 이러한 이유로, 인공지능 서비스의 UX 평가는 새로운 체계가 필요하지만, 기존 UX 평가 척도만을 사용하여 평가되고 있다. 인공지능 서비스의 특징을 반영하여, 정확한 UX 평가를 진행할 수 있도록 본 논문에서는 인공지능에 task 위임 적합도, 기존 UX 평가 항목, 기술에 대한 개인적 차이를 포함한 AI-UX 프레임워크를 제안하였다.

• 한국분말재료학회지
• /
• 제20권2호
• /
• pp.85-99
• /
• 2013

Powder metallurgy applied rapid heating to sintering starting year 1900. Since 1970 the study has intensified. Now rapid sintering concepts embrace a spectrum of options ranging from dunk cycles to microwave, induction, exothermic, electric field, and spark approaches. Most of the efforts are targeting reduced microstructure coarsening during sintering, although reduced material decomposition is another common goal. The efforts are impressive for simple shapes and success metrics such a small grain size after densification. Several barriers need to be removed prior to application in powder metallurgy commercial sintering. Rapid heating research needs to focus on significant property gains, accurate product dimensions, and lower costs. So far each property gain obtained with rapid heating is matched by traditional sintering and composition changes. Several examples are cited to show the goals for the next round of innovations.

• 한국전자거래학회지
• /
• 제4권3호
• /
• pp.63-76
• /
• 1999

Internet-based electronic trade has been growing fast. But most users are not yet familiar with the system and find it very difficult to purchase and sell the products in the cyber market place. To handle these problems, agent-based virtual market place system has been proposed where agents instead of individuals participate in trading of goods. Most of the proposed models have been in the two general categories. The first is the direct transaction among sellers and buyers, and the second is the agent-based transaction. However, the transaction is not fair and the best deal can't be guaranteed for both models. In this paper, we propose a new broker based synchronous transaction algorithm which is fair to both parties and guarantees the best deal. Our algorithm is implemented using Visual C++ and the experimental results show that our method is better than the two traditional transaction models in every performance metrics, Number of transactions are increased up to 21% and price adjustment is up to 280% better for some transactions.

• 음성과학
• /
• 제7권4호
• /
• pp.41-47
• /
• 2000

This paper concerns an effective text-prompted speaker verification method to increase the performance of speaker verification. While various speaker verification methods have already been developed, their effectiveness has not yet been formally proven in terms of achieving an acceptable performance level. It is also noted that the traditional methods were focused primarily on single, prompted utterance for verification. This paper, instead, proposes sequential decision method using variable threshold focused at handling two utterances for text-prompted speaker verification. Experimental results show that the proposed speaker verification method outperforms that of the speaker verification scheme without using the sequential decision by a factor of up to 3 times. From these results, we show that the proposed method is highly effective and achieves a reliable performance suitable for practical applications.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 학술발표대회 논문집 제19권 2호
• /
• pp.239-242
• /
• 2000

In the present study, the influence of car body structures to the noise and vibration characteristics has been sought. The numerical modal analysis for the body-in-white is employed to predict the vibratory response of structure, and then followed by the experimental modal testing to confirm the validity of the model. Using the results of numerical simulations with the designated modal parameters, the optimal structural configuration has been deduced. Special interests have been paid to the sensitivity of sound quality to the structural integrity. Since the structural integrity has a close relationship to the structure-born noise, the substantially low frequency range, which is far below the frequency range almost barely sensible by human auditory organ but still quite influential to overall impression, is especially examined. The subjective assessment agrees with the objective evaluation by means of traditional sound measures as well as psychoacoustic metrics.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.