• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권2호
• /
• pp.251-254
• /
• 2016

An energy-efficient object matching accelerator is proposed for mobile object recognition based on matching prediction scheme. Conventionally, vocabulary tree has been used to save the external memory bandwidth in object matching process but involved massive internal memory transactions to examine each object in a database. In this paper, a novel object matching accelerator is proposed based on matching predictions to reduce unnecessary internal memory transactions by mitigating non-target object examinations, thereby improving the energy-efficiency. Experimental results show a 26% reduction in power-delay product compared to the prior art.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• Advances in Energy Research
• /
• 제8권3호
• /
• pp.175-184
• /
• 2022

The dual-fuel technology, which uses gaseous fuel as the main fuel and liquid as the pilot fuel, is an appealing technology for reducing the exhaust emissions. The current study proposes emission models based on ANFIS for a dual-fuel using producer gas (PG)-diesel engine. Emissions measurements were taken at different engine load levels and fuel injection timings. The proposed model predictions were examined using statistical methods. With R2 values in the range of 0.9903 to 0.9951, the established ANFIS model was found to be consistently robust in predicting emission characteristics. The mean absolute percentage deviate in range 1.9 to 4.6%, and mean squared error varies in range 0.0018 to 13.9%. The evaluation of the ANFIS model developed shows a reliable claim of intrinsic sensitivity, strength, and outstanding generalization. The presented meta-model can be used to simulate the engine's operation in order to create an efficient control tool.

• Journal of Mechanical Science and Technology
• /
• 제17권4호
• /
• pp.477-483
• /
• 2003

An independent kinematic hardening material model in which the reverse yielding point is defined by the Bauschinger effect factor (BEF) , has been defined for stainless steel SUS 304. The material model and the BEF are obtained experimentally and represented mathematically as continuous functions of effective plastic strain. The material model has been incorporated in a non-linear stress analysis for the prediction of reverse yielding in thick-walled cylinders during the autofrettage process of these vessels. Residual stress distributions of the independent kinematic hardening material model at the onset of reverse yielding are compared with residual stresses of an isotropic hardening model showing the significant effect of the BEF on reverse yielding predictions. Critical pressures of direct and reverse yielding are obtained for the most commonly used cylinders and a range of permissible internal pressures for an efficient autofrettaged process is recommended.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• Structural Engineering and Mechanics
• /
• 제54권6호
• /
• pp.1217-1244
• /
• 2015

In this research a theoretical and numerical study on a bridge damage detection procedure is presented based on vibration measurements collected from a set of accelerometers. This method, referred to as "Adjoint Variable Method", is a sensitivity-based finite element model updating method. The approach relies on minimizing a penalty function, which usually consists of the errors between the measured quantities and the corresponding predictions attained from the model. Moving mass is an interactive model and includes inertia effects between the model and mass. This interactive model is a time varying system and the proposed method is capable of detecting damage in this variable system. Robustness of the proposed method is illustrated by correct detection of the location and extension of predetermined single, multiple and random damages in all ranges of speed and mass ratio of moving vehicle. A comparative study on common sensitivity and the proposed method confirms its efficiency and performance improvement in sensitivity-based damage detection methods. In addition various possible sources of error, including the effects of measurement noise and initial assumption error in stability of method are also discussed.

• International Journal of Aeronautical and Space Sciences
• /
• 제15권4호
• /
• pp.383-395
• /
• 2014

According to the requirement of wing weight estimation and frequent adjustments during aircraft conceptual design, a wing weight estimation method considering the constraints of structural strength and stiffness is proposed to help designers make wing weight estimations rapidly and accurately. This method implements weight predictions on the basis of structure weight optimization with stiffness constraints and strength constraints, which include achievement of wing shape parametric modeling, rapid structure layout, finite element (FE) model automated generation, load calculation, structure analysis, weight optimization, and weight computed based on modeling. A software tool is developed with this wing weight estimation method. This software can realize the whole process of wing weight estimation with the method and the workload of wing weight estimation is reduced because much of the work can be completed by the software. Finally, an example is given to illustrate that this weight estimation method is effective.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2002년도 제35회 춘계학술대회
• /
• pp.137-142
• /
• 2002

The fluid mechanics and operating conditions of gas-lubricated proceeding bearings in micro rotating machinery such as micro polarization modulator and micro gas turbine are different from their larger size ones. Due to non-continuum effects, there is a slip of gas at the walls. Thus in this paper, the slip flow effect is considered to estimate the pressure distribution and load-carrying capacity of micro gas-lubricated proceeding bearings as the local Knudsen number at the minimum film thickness is greater than 0.01. Based on the compressible Reynolds equation with slip flow, the static characteristics of micro gas-lubricated proceeding bearings are obtained. Numerical predictions compare the pressure distribution and load capacity considering slip flow with the performance of micro proceeding bearings without slip f]ow for a range of bearing numbers and eccentricities. The results clearly show that the slip flow effect on the static characteristics is considerable and becomes more significant as temperature increases.

• Structural Engineering and Mechanics
• /
• 제65권6호
• /
• pp.699-706
• /
• 2018

In the present contribution, fracture resistance of U-notched GPPS members under mixed mode I/III loading conditions is assessed by using the Averaged Strain Energy Density (ASED) criterion. This criterion has been founded based on the ASED parameter averaged over a well-defined control volume embracing the notch edge. The validation of the theoretical criterion predictions is evaluated through comparing with the results of a series of mixed mode I/III fracture tests conducted on rectangular-shaped GPPS specimens weakened by a single edge U-notch. A recently developed apparatus for mixed mode I/III fracture experiments is employed for measuring the fracture loads of the specimens. The test samples are fabricated with different notch tip radii with the aim of evaluating the influence of this major feature of the U-notched components on the mixed mode I/III fracture behavior. It is shown that the onset of brittle fracture in U-notched GPPS specimens under various combinations of tension and out-of-plane shear can well be predicted by means of the ASED criterion.