Earticle

In autonomous driving, environmental perception and decision-making are technologies that acquire signals based on various sensors and generate information that enables obstacle avoidance, emergency stops, and path planning. Such environmental perception technologies are limited in that they depend on expensive sensors such as LIDAR and RADAR, so research on environmental perception technologies using only cameras is actively being conducted. Studies predicting traffic accidents based on dashcam footage have also been performed as part of such research. This is challenging because only limited forward-looking footage can be acquired, and the surrounding environment is dynamic and changes quickly, making analysis difficult. Existing research has focused on learning the spatialtemporal feature representation to solve these problems. This paper extracts the trajectories of the ego-vehicle and surrounding vehicles using Visual SLAM and Multiple Object Tracking algorithms and uses them as inputs to the graph convolutional neural network(GCN) to learn the spatialtemporal feature representation. In addition, the features learned through the GCN are used as inputs to a bayesian neural network(BNN) to predict the probability of accidents, and its ability to predict accidents in advance has been verified by comparison with existing studies.

본 논문에서는 영화에서 인물의 극적인 등장, 등장 인물 간의 관계를 효과적으로 표현하 고자 할 때 주로 사용하는 영화 촬영 기법 ‘아크 트래킹 샷’을 비주얼 노블 게임에 카메 라 연출을 설계 및 구현하여 적용하였다. 비주얼 노블은 소설을 읽듯 이야기 진행에 중 점을 둔 게임의 한 장르로 이미지, 사운드 등 시청각적 요소를 첨가하여 이야기의 몰입 을 돕는다. 그러나 기존 비주얼 노블의 카메라는 정적이며 움직임이 극히 제한되어 있어 플레이어의 이야기 몰입도를 높이기에는 어려움이 있다. 이를 극복하고자 이야기의 전달 이 중요하다는 공통점을 가진 영화의 촬영 기법 아크 트래킹 샷을 3D 게임 엔진에 가상 의 카메라 트래킹 레일을 만들고 카메라에 적용하는 과정을 통해 비주얼 노블의 카메라 연출에 적용하였다. 영화 연출 기법을 비주얼 노블 게임콘텐츠에 적용하면서 기존 비주 얼 노블 연출의 단점을 극복하고 역동적인 카메라 움직임은 플레이어에게 몰입을 유지 시키는 작용을 하며 제작자가 전달하고자 하는 감정과 의미를 더욱 효과적으로 전달할 수 있도록 구현하였다.

In this paper, the film shooting technique 'arc tracking shot', which is mainly used to effectively express the dramatic appearance of characters, relationships between characters, and romantic atmosphere in movies, was actually implemented and applied to Visual Novel game cameras. Visual Novel is a genre of the game that focuses on story progression, as if reading a novel, and helps the story's immersion by adding audiovisual elements such as images and sounds. However, the existing Visual Novel camera is static and has very limited movement, which reduces the player's immersion in the story. In order to overcome this, the film's filming technique arc tracking shot, which has the importance of delivering the story, was introduced to the camera production of Visual Novel through the process of creating a virtual camera tracking rail in a 3D game engine and applying it to the camera. By introducing film production techniques, dynamic camera movements can overcome the shortcomings of the existing Visual Novel production and maintain immersion in the player, and more effectively convey the emotions and meanings the producer wants to convey.

RGB-T 시각적 객체 추적은 가시광(RGB) 영상과 열적외선(TIR)을 병행해 조명·기상 변화 속에서도 대상을 지속 적으로 추적하는 기술이다. 본 연구에서는 이중 스트림 RGB-T 기반 추적기인 BAT에 밀집 Mixture-of- Experts(MoE) 게이팅을 결합한 모달리티 인지 추적기 BATMoE를 제안한다. 제안한 방법은 어텐션 투영 단계의 Q/K/V와 피드포워드 네트워크(FFN)에 MoE 구조를 적용한다. 풀링된 교차 모달 특징에 조건화된 온도 조절 softmax 게이트를 통해 모든 전문가를 밀집하게 혼합하며, 전문가 활용의 편향을 방지하기 위해 균형 정규화 항을 추가하였다. 이러한 설계는 열 교차 현상(Thermal Crossover)이나 저조도 환경과 같은 불리한 조건에서 더 신뢰 도 높은 모달리티의 기여도를 동적으로 강화하면서도, 다른 모달리티의 보완적 정보를 유지할 수 있도록 한다. LaSHeR 데이터 세트에서 수행한 실험 결과, BATMoE는 동일한 학습 및 평가 설정 하에서 기존 BAT 대비 Precision@20과 Success(AUC) 지표 모두에서 일관된 성능 향상을 보였다. 특히 Thermal Crossover, Low Illumination, Partial Occlusion과 같이 모달리티 간 신뢰도 차이가 크게 발생하는 조건에서 성능 개선이 두드 러졌으며, 속성별 분석을 통해 이러한 경향을 확인하였다. 반면 Fast Motion이나 Motion Blur와 같이 RGB와 TIR 모달리티가 동시에 약화하는 조건에서는 성능 향상이 제한적으로 나타났다. 이러한 결과는 MoE 기반 조건 적 응적 구조가 RGB-T 시각적 객체 추적에서 효과적인 융합 메커니즘이 될 수 있음을 보여준다.

We present BATMoE, a modality-aware RGB–T visual object tracker that integrates dense Mixtureof- Experts (MoE) gating into a dual-stream baseline tracker, BAT. The proposed approach applies MoE structures to both the attention projection layers (Q/K/V) and the feed-forward networks within the Transformer encoder. A temperature-controlled softmax gate, conditioned on pooled cross-modal features, densely combines all experts, while a balancing regularization term is introduced to prevent biased expert utilization. This design allows the tracker to dynamically emphasize the more reliable modality under adverse conditions, such as thermal crossover or low illumination, while preserving complementary information from the other modality. Experimental results on the LaSHeR dataset demonstrate that BATMoE consistently outperforms the baseline BAT under identical training and evaluation settings, achieving improvements in both Precision@20 and Success (AUC). Attribute-wise analysis reveals particularly notable gains in conditions where modality reliability varies significantly, including Thermal Crossover, Low Illumination, and Partial Occlusion. In contrast, performance improvements are limited under Fast Motion and Motion Blur scenarios, where both RGB and TIR modalities tend to degrade simultaneously. These results indicate that MoE-based condition-adaptive modeling provides an effective fusion mechanism for RGB–T visual object tracking.

본 연구는 기존의 소비자들의 정보처리과정에서의 연구가 인지적 관점에 초점을 두어서 진행한 연구결과였다면 본 연구는 시선을 중심으로 행동적 관점에서의 연구 결과라는 데에 그 의미가 있다. 연구는 확장된 브랜드 정보에 대한 지각적 평가에 연구의 초점을 두었다. 연구결과를 요약하면 먼저 피 실험자들에게 브랜드 확장 상황에서 확장된 브랜드에 대한 정보가 담겨진 시각적, 언어적으로 구성된 광고 자극물을 제시 하였을 경우에, 피 실험자들은 언어적 요소에 많은 시선적 정보처리를 하는 것으로 나타났다. 이러한 결과는 Rayner(2001)의 연구를 브랜드 확장상황 하에서도 적용할 수 있다는 것을 보여 준 결과라고 할 수 있다. 두 번째 분석으로는 브랜드 확장의 상황을 다중 차원으로 구분하여 살펴보았다. 즉, 제품 컨셉을 쾌락적 컨셉제품과 효용적 컨셉 제품을 각각 구분하고 이러한 구분을 바탕으로 원 브랜드 제품과 확장된 제품 간의 2X2로 확장한 상황 하에서 소비자들이 해당 광고 자극물에 대하여 어떻게 시각적 요소와 언어적 요소에 대하여 시각적 정보를 처리하는가를 분석하였다. 그 결과, 시각적 요소의 경우에는 두 컨셉 간의 상호작용효과는 나타나지 않으며 주효과만 나타났으며, 언어적 요소는 두 효과가 공통적으로 나타나는 것으로 밝혀졌다. 따라서 언어적 요소에 대해서는 확장 컨셉의 제품이 효용적인 제품군인 경우에 더 많은 시선적 정보처리를 하는 것으로 나타나며, 시각적 요소의 경우에는 통계적으로 유의하지 않은 것으로 나타난다.

Most previous researches focus on the view of cogntive information processing approaches based on experiment design while the study adopts behavioral information approach based on eye movement. The visual and verbal element of advertising message toward consumer's attitude of brand extension is illuminated on this research adopting eye tracker. For the purpose of detecting this modality effect, visual and verbal, under the context of brand extension, two experimental analysis is proceeded. In summary, the result shows message element is predominant to the visual element on the context of brand extension. This results is on the similar vein of Rayner(2001)’s goal oriented information process and also confirm that it can apply to the area of study of brand extension. For validating the second hypothesis, multiply mixed brand extension situation, the products are categorized as hedonic and utilitarian value oriented products. In order to verify the second hypothesis, 2X2 product categories are employed. The results show that consumers pay more attention on verbal element than verbal element under the context of cross product concept brand extension. These results confirm that they cast their eye fixation on the message element longer under the cross product concept extension.

본 논문에서는 현재와 이전의 영상 프레임 뿐 만 아니라 영상의 축척과 이전 위치에 주어진 객체의 비율과 위치 추정에 대한 학습 문제로서 사람 추적 문제를 다룬다. 본 논문에서는 회선 신경망 분류기를 이용한 사람 검출 방법을 제안한다. 제안하는 방법은 신경망을 정규화하고 검출 작업을 위한 특징 표현을 자동으로 최적화함으로써 사 람 검출의 정확성을 향상시킨다. 제안하는 방법에서는 감시 영상 시스템에서 실시간 영상이 들어오면 제일 먼저 위 치를 추정하는 작업을 수행하기 위하여 회선신경망을 학습시킨다. 기존의 다른 학습 방법과 달리 회선신경망은 두 쌍의 연속된 영상 프레임으로부터 공간적이고 시간적인 특징을 모두 공동으로 학습시킨다. 회선 신경망에 의해 학습 된 특징을 이용하는 SVM 분류기의 정확성은 회선 신경망의 정확성과 일치한다. 이것은 자동적으로 최적화된 특징의 중요성을 확인시켜 준다. 그러나, 회선 신경망을 이용한 사람 객체의 분류에 대한 계산 시간은 사용된 특징의 타입 과 관계없이 SVM의 것보다 약 40분의 1정도로 작다.

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

Virtual Reality(VR)은 1950년대에 제안된 기술이었지만 최근에서야 활발하게 VR 기기와 콘텐츠 보급이 이루어 지고 있다. 기존의 VR 콘텐츠는 사전에 만들어진 콘텐츠를 사용자가 보ㄴ는 것이 대부분 이었지만, 최근의 컴퓨팅 기술의 급격한 발전 덕분에 작은 사이즈에 사용자의 행동을 추적할 수 있는 기기가 등장함으로서 사용자와 상호작용 을 하는 VR 콘텐츠가 등장할 수 있었다. 뿐만 아니라 VR이 AR과 MR로 확장되고 있으므로, 3가지 가상 환경에서 모두 사용가능하며 효율적인 User Interface(UI)가 필요하다. 본 논문에서는 아이트래킹 센서 기술기반의 UI를 제안한다. 아이트래킹 센서 기반 UI는 사용자가 직접 컨트롤러를 조작하는 부분을 줄임으로서 단순 조작에 사용되 는 시간을 극적으로 낮출 수 있을 뿐만 아니라, 다양한 종류의 컨트롤러를 복합적으로 사용가능하게 함으로서 전용 컨트롤러의 필요성을 낮추었다.

Virtual Reality (VR) was a technology proposed in the 1950s, but it has only recently been actively distributing VR devices and contents. Traditional VR content was mostly pre-created by users, but thanks to the recent rapid development of computing technology, a device capable of tracking the user's behavior in a small size has appeared, and thus the VR content that interacts with the user has appeared. In addition, since VR is expanding to AR and MR, it can be used in all three virtual environments and requires an efficient user interface (UI). In this paper, we propose a UI based on eye tracking sensor technology. The eye tracking sensor-based UI not only dramatically reduces the time used for simple manipulation by reducing the part where the user directly controls the controller, but also reduces the need for a dedicated controller by enabling various types of controllers to be used in combination.

This study employed the eye-tracking method to investigate the nature of game players' visual attention on thegame's GUI(graphic user interface) elements during game play. The genre of the game (shooting and drivinggames), the points of view of the game (1st person vs. 3rd person POV), and the game player's proficiency weretaken into account to examine their effects on the game player's visual attention. A within-between subjectexperimental study was conducted (N=26). The results illustrate that the game genre was not a meaningfulpredictor for neither the frequency or the total duration of visual element per interface element. The point ofview had a significant main effect on the game player's frequent change of their eye movement across differentelements. The proficiency of game player's gaming skill significantly altered the game player's frequency andduration of visual attention. Proficient gamers were more efficient in distributing their visual attention acrossvarious elements of the GUI.

본 연구는 소비자의 호기심을 자극하는 성적소구 광고 중에서 특히 주관적으로 해석하기 쉬운 소주광고 이미지 를 AOI(area of interest) 3영역(얼굴, 몸매, 제품)으로 설정하여 심리 생리학적 지표 중 하나인 아이트래킹을 통해 검증하였다. 분석결과, 광고모델의 시각적 주의, 즉 관심도가 몸매보다는 얼굴에서 높게 나타났다. 남자가 여자보다 몸 매에 관심도가 높을 거라는 예측과는 달리 남녀 모두 몸매보다는 얼굴에 관심도가 높은 것으로 나타났다. 또한, 제품에 대한 재인과 회상은 유의하지 않음을 도출하였다. 본 연구는 성적소구 광고에 대한 남녀 소비자들의 시선의 응시점과 응시시간 등의 시각적 주의의 패턴을 살펴보았다는 점에서 의의를 가지며 소주광고 이미지가 나아가야 할 표현방식과 나아가 적절한 마케팅 방향을 제시함으로써 소주광고 이미지에 긍정적인 영향을 가져다주길 기대한다.

This study analyzes the Soju(Korean alcohol) advertisement image, which is relatively easy to interpret subjectively, among sexual appeal advertisements that stimulate consumers' curiosity, where the image is verified through AOI (area of interest) 3 areas (face, body, product), and eye-tracking, one of the psychophysiological indicators. The result of the analysis reveals that visual attention, the interest in the advertising model, was higher in the face than in the body shape. Contrary to the prediction that men would be more interested in body shape than women, both men and women showed higher interest in the face than a body. Besides, it was derived that recognition and recollection of the product were not significant. This study is significant in terms of examining the pattern of visual attention such as the gaze point and gaze time of male and female consumers on sexual appeal advertisements. In further, the study looks forward to bringing a positive influence to the soju advertisement image by presenting the expression method that the soju advertisement image should pursue as well as the appropriate marketing direction.

본고는 사전 설문지를 통해 소비자의 실시간 댓글에 대한 기능성 수요, 수용 정도 및 선호도를 조사한 뒤 아이트 래킹을 통해 실시간 댓글의 유형 및 구역 위치에 대해 비교분석을 진행하는 연구이다. 연구 결과에 따르면, 실시간 댓글 의 기능성 수요가 비교적 높고, 수용 정도가 비교적 높으며, 실시간 댓글의 기능은 이용자 선호도에 영향을 미치지 않는 것으로 나타났다. 실시간 댓글 유형 중에 문장 하나를 별도의 반투명 사각형으로 했을 경우 스타일의 시각주의도가 가 장 높게 나타났다. 이는 이용자의 시각 행동에 독특한 스타일의 경향성이 있음을 의미한다. 본 연구는 실시간 댓글 중 다양한 유형과 구역 위치의 시각적 주의도를 분석하는 것을 통하여 추후 실시간 댓글의 인터페이스 디자인에 선도적 역할을 할 수 있을 것으로 기대한다.

The study investigated the users’ functional requirement, degree of acceptance and preference of game broadcast real-time review .Secondly it comparatively analyzed the types and locations of game broadcast real-time review through eye tracking tech. The results show that users have high functional requirements and high acceptance for game broadcast real-time review but their preference has no significant correlation with the feature. Among the types of game broadcast real-time review the type with translucent text bubble took the highest visual attention. The above shows that the users’ visual behavior has the tendency of special style. The visual attention analysis results of different types and locations of game broadcast real-time review in the study can play a guiding role in the interface design of real-time review feature in the future.

In complicated scene, in order to solve the temporal occlusion problem of target tracking, a novel particle filter tracking algorithm based on graphical model is proposed. Graphical model is applied to particle filtering in this method. Firstly, dividing the target into several key regions, and extracting the characteristic value of each region. Then, these regions are applied to construct graphical model. In the process of target tracking by using particle filter method, graphical models can compensate for the lacking information of the occluded region. The state of the occluded part can be inferred by the graphical model. Finally, experimental results have demonstrated that the proposed tracking algorithm is effective, and it can reliably track moving target.

In this paper, we propose a fast and robust tracking method based on reversed sparse representation. Be different from other sparse representation based visual tracking methods, the target template is sparsely represented by the candidate particles which are gotten by particle filter. In order to improve the robustness of the method, we use a target template set. Meanwhile, a two level competition mechanism is also introduced. In the first level, each target template is sparsely represented and all the candidate particles compete with each other by a similarity calculation, which is based on sparse coefficients. Then, the winners construct a target candidate set. In the second level, all the target candidates in the target candidate set compete with each other and the one which is the most similar to the template set is considered as the target. In addition, a template set update strategy is proposed to adapt the appearance variations of the target. Experimental results on challenging benchmark video sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.

In this paper, we propose a robust tracking method with a novel appearance model based on fragments-based PCA sparse representation. It samples non-overlapped local image patches within the templates in PCA subspace. Then, the candidate local image patches are sparse represented by the local template patches in PCA subspace. Finally, tracking is continued using the particle filter for propagating sample distributions over time. In addition, the templates are updated online based on incremental subspace learning .Using the fragments-based PCA templates rather than the image templates facilitates the tracker to handle significant illumination and pose change as well as occlusion. Experimental results on challenging videos show that our method can track accurately and robustly, and outperform many other state-of-the- art trackers.

Tracking with a discriminative classifier becomes popular recently. The online updating makes it easy to adapt to target appearance variations. However, this also brings drifting problem. It’s necessary to find a tracking method with strong adaptivity and anti-drifting ability. In this paper, an online semi-supervised boosting method is proposed at first, and based on it, we propose a novel tracking framework that treats samples differently when updating the classifier under different conditions. This tracking framework can significantly alleviate the drifting problem and keep adaptive enough to appearance variations. Experimental results on challenging videos show that our method can track accurately and robustly， and outperform many other state-of-the-art trackers.

To solve the problem of tracking the trajectory of a moving object and learning a deep compact image representation in the complex environment, a novel robust incremental deep learning tracker is presented under the particle filter framework. The incremental deep classification neural network was composed of stacked denoising autoencoder, incremental feature learning and support vector machine to achieve the feature-extracting and classification of particle set. Deep learning is successfully taken to express the image representations obtained effectively. Unsupervised feature learning is used to learn generic image features and transfer learning transforms knowledge from offline training to the online tracking process. The incremental feature learning was consisted of adding features and merging features to online learn compact feature set. Linear support vector machine increases the discretion for target with similar appearance and is further tuned to adapt to appearance changes of the moving object. Compared with the state-of-the-art trackers in the complex environment, the results of experiments on variant challenging image sequences show that incremental deep learning tracker solves the problem of existent trackers more efficiently, it has better robust and more accurate, especially for occlusions, background clutter, illumination changes and appearance changes.

Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency. However, the CT extracts samples around the previous target region within a fixed search radius; the searching area is unsuitable when the target undergoes abrupt acceleration change. Meanwhile, the classifier learns the features of the target online without judgment even the target is fully occluded. Thus, the improper searching area and incorrectly updated features lead to a marked drop in precision of tracking. To solve this issue, a robust target tracking method integrating spatio-temporal model to constrain the searching area is proposed in this paper. Different from CT, the proposed method initially constructs the spatio-temporal model to calculate a confidence map between consecutive frames, and the region with high confidence suggests the high possibility that target exists. Thus the samples can be extracted in the high confidence area. Then, the optimal target location can be estimated with a naive Bayes classifier using sparse coding features. Experiments show that the proposed method outperforms several competing methods in efficiency and robustness.

Based on the analysis of the shortcomings of the current KLT (Kanade-Lucas-Tomasi) algorithm, a new, self-adaptive tracking algorithm is devised. Through introducing a kind of filtering mechanism, interference from surrounding noise and light on the tracked target is reduced. In order to reduce the error in tracking, a method based on forward-backward error approximation is utilized. Since such approximation reduces the number of visual feature points on the target, when the target changes in its shape tracking failure may easily result. In order to prevent this possible failure, a mechanism that appends the feature points is introduced. Experimental comparisons show that the said algorithm is clearly more effective than other similar algorithms.

In this paper, we propose a novel algorithm to deal with the problem of visual tracking in some challenging situations, which is based on sparse representation and multi-scale block. To build target templates, we select distinguishable features between the target and background in each frame of video sequences, dictionary is built by the multi-scale block of target templates. Then, particle filter generates filter distribution in the next frame, the moving target is framed by affine transformation. To describe the current state of the target, we calculate posterior probability for each particle. Finally, the templates are updated online. The experimental results show that the proposed algorithm is superior in accuracy than the classical tracking algorithm, and it has better robustness against to the target posture changes, partial occlusion and illumination variations.

Tracking multiple objects in real-time videos represents a challenging area in the era of computer vision. This paper proposes a new method to track the multiple objects under different environment conditions such as rotation, illumination, blurred, occlusion, and many others. In addition, the kinect color depth image processing is used to estimate the distance of the objects. The tracking of multiple objects is formulated as classification task which competitively use the object features in the different video frames of the video sequences. To obtain the optimal configuration of feature classification, a neural network based framework is presented to make a global influence based on winner pixel estimation between the video frames. The objects are tracked efficiently in less time as compared with SIFT techniques and distance of objects is calculated with kinect based depth image processing. Experimental results are given for real-time scenes, and many experiments are conducted to examine the performance of the proposed approach. The proposed method resulted into efficient tracking of multiple objects in various conditions including rotation, scaling, occlusion, etc. The distance of multiple tracked objects is estimated using the kinect depth processing.

This paper mainly adopts the literature research method, which analyzes the application progress and development overview of the eye tracking technology, as well as the technical features of the eye tracking devices. Combined with the research needs in landscape visual perception, eye tracking technology have application values in the following aspects: landscape attractiveness analysis, safety design of landscape environment, usability design of landscape facilities, landscape perception in motion, quality improvement of landscape information interface, cognitive analysis of physiological vulnerable groups and quality improvement of landscape education. Eye- tracking technology should be used reasonably in the study so as to exploit its advantages to the full and correct its deficiencies. The development of hardware technology and software technology of eye-tracking offers a new perspective and study platform for the study on landscape visual perception, which contributes to improving the scientificity of the study on landscape visual perception.

We are living in a hypercompetitive market. Therefore, companies running online shopping malls must muster their wisdom to make online shopping websites one of their strategic assets. To meet this objective, companies should understand online consumers’ cognitive styles, and then design their online websites according to the styles. In this sense, we focus on two cognitive styles such as systematic type and intuitive type. The former means that consumers may pay more attention to reasonable statements about target product before making decisions, while the latter indicates that consumers may react more sensitively to intuitive information such as images and abstract conjecture. For the sake of novel approach to conducting experiments, we adopted an eye-tracking approach which we believe is more reliable in providing relevant information capable of answering our research questions. For the utilitarian product like notebook computer, systematic type users may show higher TFD (Total Fixation Duration) and FC (Fixation Count) to consumer reviews than intuitive type users. Also, intuitive type users may be more sensitive to special purchase opportunity-giving events information with higher TFD and FC than systematic type users. Through our experiments with an eye-tracking method, we could conclude that a strategic redesign of the online shopping websites is necessary where consumers' cognitive styles need to be significantly considered.