• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.95-103
• /
• 2009

We investigated the perceptual structure of Korean consonants by analyzing the confusion among consonants in various vowel contexts. The 36 CV syllable types combined by 18 consonants and 2 vowels (/i/ and /u/) were presented with masking noises or in degraded intensity. The confusion data were analyzed by the INDSCAL (Individual Difference Scaling), ADCLUS (Additive Clustering) and the probability of the transmitted information. The results were compared with those of a previous study with /a/ vowel context (Bae and Kim, 2002). The overall results showed that the laryngeal features-aspiration, lax and tense-are the most salient features in the perception of Korean consonant regardless of vowel contexts, but the perceptual saliency of place features varies across vowel conditions. In high vowel (front and back vowel) contexts, sibilant consonants were perceptually salient compared to in low vowel contexts. In back vowel contexts, grave (labial and velar) consonants were perceptually salient. These findings imply that place features and vowel features strongly interact in speech perception as well as in speech production. All statistical measures from our confusion data ensured that the perceptual structure of Korean consonants correspond to the hierarchical structure suggested in the feature geometry (Clements, 1991). We discuss the link between speech perception and production as the basis of phonology.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.4B no.2
• /
• pp.47-53
• /
• 2004

The salient pole rotor type single phase SRM (switched reluctance motor) uses radial and axial direction magnetic flux simultaneously. Therefore, the output power per unit volume is very high and the shaft length is shorter than other types of SRMs with the same output. Furthermore, it can be manufactured with low cost owing to its simple structure and driving circuit. The prototype was designed using the theory of the traditional rotating machine and 3D FEM analysis. On this paper, the experiment apparatus, which includes the fabricated prototype in previous researches, was fabricated to measure the current and voltage of the prototype. Then the flux linkage, inductance and magnetic co-energy were calculated using the experimental results. Finally, the measured magnetic co-energy was compared with the simulated magnetic co-energy.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.4
• /
• pp.280-286
• /
• 1998

This paper proposes a novel method to reduce the torque ripple due to the non-ideality of the current sensing parts in vector-controlled inverter-fed AC motor drive systems. For PMSM(Permanent Magnet Synchronous Motor), motor output torque equations are derived in terms of their offset voltages and different voltage transducing gains. And the effects of phase current errors on motor torque are analyzed for both salient PMSM and non-salient PMSM. The proposed method can eliminate the torque ripple by nulling the offset voltages and setting the voltage transducing gains to the same value. To verify the proposed method, digital simulations are carried out for non-salient PMSM.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1220-1230
• /
• 2015

An autonomous valet parking (AVP) system is designed to locate a vacant parking space and park the vehicle in which it resides on behalf of the driver, once the driver has left the vehicle. In addition, the AVP is able to direct the vehicle to a location desired by the driver when requested. In this paper, for an AVP system, we introduce technology to recognize a parking space using image sensors. The proposed technology is mainly divided into three parts. First, spatial analysis is carried out using a height map that is based on dense motion stereo. Second, modelling of road markings is conducted using a probability map with a new salient-line feature extractor. Finally, parking space recognition is based on a Bayesian classifier. The experimental results show an execution time of up to 10 ms and a recognition rate of over 99%. Also, the performance and properties of the proposed technology were evaluated with a variety of data. Our algorithms, which are part of the proposed technology, are expected to apply to various research areas regarding autonomous vehicles, such as map generation, road marking recognition, localization, and environment recognition.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.11
• /
• pp.664-670
• /
• 2004

This paper presents a new velocity estimation strategy of a non-salient permanent magnet synchronous motor (PMSM) drive without high frequency signal injection or special PWM pattern. This approach is based on the d-axis current regulator output voltage of the drive system that has the information of rotor position error. The rotor velocity can be estimated through a rotor position tracking PI controller that controls the position error to zero. For zero and low speed operation, PI controller gains of rotor position tracking controller have a variable structure according to the estimated rotor velocity. In order to boost the bandwidth of PI controller around zero speed, a loop recovery technique is applied to the control system. The proposed method only requires the flux linkage of permanent magnet and is insensitive to the parameter estimation error and variation. The designers can easily determine the possible operating range with a desired bandwidth and perform the vector control even at low speeds. The experimental results show the satisfactory operation of the proposed sensorless algorithm under rated load conditions.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.29 no.6
• /
• pp.399-409
• /
• 2017

This study numerically investigates the characteristics of the velocity field including the average flow velocity, longshore current and turbulent kinetic energy acting as the main external forces of the salient formed behind the permeable submerged breakwaters. Shoreline response is also predicted by the longshore-induced flux. In this paper, a three-dimensional numerical wave tank based on the OLAFOAM, CFD open source code, is utilized to simulate the velocity field around permeable submerged breakwaters under the formation condition of salient. The characteristics of the velocity field around permeable submerged breakwaters with respect to the gap width between breakwaters and the installing position away from the shoreline under a range of regular waves for different wave height are evaluated. The numerical results revealed that as the gap width between breakwaters increases, the longshore currents become stronger. Furthermore, as the gap width becomes narrower, the point where flow converges moves from the center of the breakwater to the head part. As a result, it is possible to understand the formation of the salient formed behind the submerged breakwaters. In addition, it was found that the longshore currents caused by the gap width between breakwaters and the installation position away from the shoreline are closely related to the turbulent kinetic energy.

• Journal of The Korean Association For Science Education
• /
• v.38 no.1
• /
• pp.43-55
• /
• 2018

In this study, we investigated high school students' analogy generating processes using the think-aloud method. Twelve high school students in Seoul participated in this study. The students were asked to generate analogies on ionic bonding and were also interviewed after their activities. Their activities and interviews were recorded and videotaped. After classifying the analogy generating processes into the three stages-encoding, exploring sources, and mapping, several process components were identified. The analyses of the results indicated that they checked the target concept given and selected one for a salient attribute among many attributes of the target concept at the stage of encoding. After selecting the salient attribute, they translated the salient attribute that is a scientific term into an everyday term, which is named as 'extracting salient similarities.' At the stage of exploring sources, they chose the sources based on salient similarities and chose the final source through circular processes, which included the process components of 'evaluating the sources' and 'discarding the sources.' At the final stage, they added the attributes to analogs and mapping them to the attributes of the target concept, which is named as 'mapping shared attributes.' There were some cases that 'mapping shared attributes' appeared after they specified the situation of analogs or assumed new situation, which is named as 'specifying the situations.' Some students recognized unshared attributes in their analogs.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1121-1135
• /
• 2005

This paper proposes a moving object extraction method using the contrast map and salient points. In order to make the contrast map, we generate three-feature maps such as luminance map, color map and directional map and extract salient points from an image. By using these features, we can decide the Attention Window(AW) location easily The purpose of the AW is to remove the useless regions in the image such as background as well as to reduce the amount of image processing. To create the exact location and flexible size of the AW, we use motion feature instead of pre-assumptions or heuristic parameters. After determining of the AW, we find the difference of edge to inner area from the AW. Then, we can extract horizontal candidate region and vortical candidate region. After finding both horizontal and vertical candidates, intersection regions through logical AND operation are further processed by morphological operations. The proposed algorithm has been applied to many video sequences which have static background like surveillance type of video sequences. The moving object was quite well segmented with accurate boundaries.

• International Commerce and Information Review
• /
• v.8 no.2
• /
• pp.3-35
• /
• 2006

Until now, most of the studies about the internet service have focused mainly on the adoption of on-line(wired) internet services, while there have relatively been very few studies about the adoption and usage of wireless or mobile internet services. The generic model explaining the adoption behaviors of wireless internet services has not been made yet. Previous studies of that area is not so easy to find. The purposes of this paper are two-folds. The first is to find the factors affecting the users' intention and commitment behavior of mobile internet services. The second is to find the relative importance of the factors in users making decisions about users' usage intention and commitment behavior. In the theoretical part of this paper, the precedent studies concerning the technology acceptance model and the theories of on-line internet services adoption, the theories of the mobile internet services, are reviewed and analyzed.