Surface electromyogram (sEMG), which is a bio-electrical signal originated from action potentials of nerves and muscle fibers activated by motor neurons, has been widely used for recognizing motion intention of robotic prosthesis for amputees because it enables a device to be operated intuitively by users without any artificial and additional work. In this paper, we propose a training-free unsupervised sEMG pattern recognition algorithm. It is useful for the gesture recognition for the amputees from whom we cannot achieve motion labels for the previous supervised pattern recognition algorithms. Using the proposed algorithm, we can classify the sEMG signals for gesture recognition and the calculated threshold probability value can be used as a sensitivity parameter for pattern registration. The proposed algorithm was verified by a case study of a patient with partial-hand amputation.

This paper proposes a hand-controller mechanism for manually controlled endoscopic surgical instruments. A wire-driven mechanism is typically adapted for endoscopic surgical tools because motors cannot be embedded to the joints due to the size limitation. The wire-driven mechanism requires length control of wires that are pulled and released according to the desired joint angle. It is difficult for the operator to control individual wire lengths intuitively. The hand-controller mechanism should be able to control the wires easily without complex processes. For this purpose, we propose a mechanism that can control the wire lengths with a simple mechanical structure and its optimal design method using genetic algorithm. We show the simulation and experimental results to confirm the proposed mechanism and design methods are useful for the manually controlled endoscopic surgical instrument.

중고선은 신조선과 달리 시장참여자에게 즉각적인 시장 진출입 기회를 제공하기 때문에 해운산업에서 중요한 시장이라 할 수 있 다. 중고선 거래 시 정확한 선가 추정은 향후 장기적인 자본비용의 부담과 직접적인 관련이 있기 때문에 투자의사결정에서 상당히 중요한 요소가 된다. 기존의 중고선시장과 관련된 연구들은 시장의 효율성검증에 치우쳐 있어 정확한 중고선가 추정을 위한 연구는 부족한 실정이다. 본 연구에서는 중고선박 가치추정에 전통적인 계량모델보다 기존연구에서 시도되지 않았던 인공신경망모델을 새롭게 제안하였다. 문헌연구를 통해 중고선 가격에 영향을 미치는 6개 요인(운임, 신조선가격, 총 선복대비 발주량, 해체선 가격, 선령, 사이즈)을 선정하였고, 데이터는 2016년 1월부터 2018년 12월까지 Clarkson에 보고된 파나막스 중고선의 실거래 기록 366건을 이용하였다. 변수선정을 위하여 상관분석과 단계적 회귀분석 실시한 결과 최종적으로 운임, 선령, 사이즈 3개의 변수가 채택되었다. 모델의 설계는 10분할 교차검증으로 인공신경망모델의 파라미터들을 추정하여 진행되었다. 인공신경망 모델의 중고선 가치추정치를 단순 단계적 회귀모형과 비교한 결과 인공신경망모델의 성능이 우수함을 확인하였다. 이 연구는 중고선 선가추정에 미치는 요인들에 대한 통계적인 검증, 성능개선을 위한 기계학습기반의 인공신경망 모델 활용이라는 측면에서 차별적 의미가 있다. 또한 정확한 선가 추정이 요구되는 실무에서 통계적인 합리성과 결과의 정확성이 동시에 만족되는 과학적 모델을 제시하여 실무적으로도 도움이 될 것으로 기대한다.

최근 가상현실 기술의 발전으로 가상의 3D 객체와 자연스러운 상호작용이 가능하도록 하는 사용자 친화적인 손 제스처 인터페이스에 대한 연구가 활발히 진행되고 있다. 그러나 대부분의 연구는 단순하고 적은 종류의 손 제스처만 지원되고 있는 실정이다. 본 논문은 가상환경에서 3D 객체와 보다 직관적인 방식의 손 제스처 인터페이스 방법을 제안한다. 손 제스처 인식을 위 하여 먼저 전처리 과정을 거친 다양한 손 데이터를 이진 결정트리로 1차 분류를 한다. 분류된 데이 터는 리샘플링을 한 다음 체인코드를 생성하고 이에 대한 히스토그램으로 특징 데이터를 구성한다. 이를 기반으로 학습된 MCSVM을 통해 2차 분류를 수행하여 제스처를 인식한다. 본 방법의 검증을 위하여 3D 블록을 손 제스처를 통하여 조작하는 ‘Virtual Block’이라는 게임을 구현하여 실험한 결 과 16개의 제스처에 대해 99.2%의 인식률을 보였으며 기존의 인터페이스보다 직관적이고 사용 자 친화적임을 알 수 있었다.

Hand phones are standard paraphernalia among university students. Factors that motivate them to own the gadget would be of interest to both the students as well as marketers. Hand phone usage is an unexamined field in academic literature, this exploratory study attempts to investigate student purchasing motives in cellular phone markets. It also intends to know the student’s satisfaction with the different services and its future impact on socio economic changes. In this study, undergraduates (n=336) were requested to specify their purchase criteria of hand phone. The instrument used in the study to collect feedback from the respondents contains a combination of open-ended and scaled questions, and some background demographics. The study employed content analysis, Pearson’s correlation, and t-tests as the primary tools to analyze the responses. Results show that brand was rated as the most important factor in student purchase decisions. Other factors, arranged in decreasing order of importance comprise price, product quality, features, durability, availability, promotion, and post purchase service. Brand and price correlated significantly. It is also observed that there is very little difference regarding preference between brand and price in purchasing a hand phone. Marketers may formulate suitable strategies out of the findings to promote hand phones to university undergraduates in Malaysia by emphasizing at brands and price.

본 논문에서는 1인칭 시점 모바일 게임에서 사용 가능한 세 종류의 한 손 조작 방식들을 제 안하고 이들을 평가한다. 기존의 모바일 게임들은 화면에 가상 컨트롤러를 디스플레이하여 사 용자에게 양손으로 조작하도록 하는 방식을 많이 사용하고 있다. 1인칭 시점 모바일 게임의 경 우, 시점 이동을 위해 필요한 기능들이 적기 때문에 한 손을 이용한 조작 방식이 가능하다. 본 논문은 1인칭 시점 이동과 회전을 위한 세 종류의 한 손 조작 방식을 제안하고, AHP 방법으로 평가한다. 실험을 통해, 1인칭 시점 모바일 게임의 경우에는 양손 조작 방식보다 한 손 조작 방 식이 사용자에게 유용함을 증명한다.

The purpose of this study was to examine the effect of horticulture occupation therapy program via healing garden which is increasing the emotional stability and hand Dexterity enhancement on pre-vocational rehabilitation of chronic mental disorder. The current study included 29 patients who were diagnosed as chronic mental disorder under the rehabilitation service at E capital hospital in Seoul from February to December 2010. All of patients participated with agreement in this study, then were divided randomly by experimental (n=17) and control groups (n=12). Therapeutic program was consisted with total 38 sessions, and performed once a week for 10 months. Experimental group was treated with horticultural occupational therapy program using a healing garden (one time), as well as general occupational therapy (four times) in a week. Control group was conducted only general occupational therapy five times a week. To evaluate the effects of program, physical and psychological stress test and hand dexterity test was used before and after program. The program was based on the person-centered therapy, then paired t-test was used to compare the results before and after the program. In the results of present study, there were no significant differences of psychological and physical stress between before and after the therapy in experimental and control group, respectively. However, hand dexterity of experimental group was markedly changed between before (112..4±50.9 sec) and after (82.1±40.6 sec) therapy. Moreover, the speed of performance in GPT was increased with rising therapeutic sessions, indicating the hand dexterity was improved after program. These results demonstrated that horticultural occupation therapy program using the healing garden is beneficial for pre-vocational rehabilitation of chronic mental disorder.

With the object of examining the effects of horticultural therapy based on structural recall by developmental stage on cognitive, emotional, and hand functions of institutionalized elderly, this study executed a horticultural therapy program once a week and through a total of 14 sessions during the period from May 2 to December 5, 2013. The subjects of this study were 34 elders admitted to S Geriatric hospital for geriatric diseases, and they were divided into a control group and an experimental group. Because the program was designed for institutionalized elders who were able to do only indoor activities, it provided various seasonal horticultural activities that could be done even in a limited space by giving materials and subjects that could be recalled by developmental stage. The results of this study are as follows. As to changes in cognitive functions (MSQ) after the horticultural therapy program, the control group showed a decrease as having more negative ranks, and the experimental group showed an increase as having more positive ranks, but such changes in the control and experimental groups were not significant. As to changes in emotional functions after the horticultural therapy program, the control group showed a decrease but without significance in ego integrity as having more negative ranks, and the experimental group showed an increase with significance as having more positive ranks (P=0.020). As to the experimental group’s changes in the sub factors of ego integrity, positive ranks increased in all the sub-factors and the increase was particularly significant in satisfaction with present life (P=0.038). As to changes in life satisfaction, the control group showed increased positive ranks but without significance, and the experimental group showed significantly increased positive ranks (P=0.022). As to the experimental group’s changes in the sub-factors of life satisfaction, changes in denial of the past (P=0.029) and denial of the future (P=0.016) were particularly significant. As to changes in hand functions, both the control and experimental groups showed some improvement in pinch after the horticultural therapy program but the changes were not significant. Grip strength did not change in the control group, and in the experimental group right-hand grip strength was improved slightly more than left-hand one, the difference was not significant. The results of this study suggest that horticultural therapy based on structural recall by developmental stage is effective in improving institutionalized elders’ emotional functions and, consequently, can contribute to higher quality of life, which is the ultimate goal of elders.

This paper proposes a novel method for detection of hand raising poses from images acquired from a single camera attached to a mobile robot that navigates unknown dynamic environments. Due to unconstrained illumination, a high level of variance in human appearances and unpredictable backgrounds, detecting hand raising gestures from an image acquired from a camera attached to a mobile robot is very challenging. The proposed method first detects faces to determine the region of interest (ROI), and in this ROI, we detect hands by using a HOG-based hand detector. By using the color distribution of the face region, we evaluate each candidate in the detected hand region. To deal with cases of failure in face detection, we also use a HOG-based hand raising pose detector. Unlike other hand raising pose detector systems, we evaluate our algorithm with images acquired from the camera and images obtained from the Internet that contain unknown backgrounds and unconstrained illumination. The level of variance in hand raising poses in these images is very high. Our experiment results show that the proposed method robustly detects hand raising poses in complex backgrounds and unknown lighting conditions.

The versatility of a human hand is what the researchers eager to mimic. As one of the attempt, the redundant degree of freedom in the human hand is considered. However, in the force domain the redundant joint causes a control issue. To solve this problem, the force control method for a redundant robotic hand which is similar to the human is proposed. First, the redundancy of the human hand is analyzed. Then, to resolve the redundancy in force domain, the artificial minimum energy point is specified and the restoring force is used to control the configuration of the finger other than the force in a null space. Finally, the method is verified experimentally with a commercial robot hand, called Allegro Hand with a force/torque sensor.

본 연구는 TW3법에서 골성숙 가중치가 가장 높은 7부위를 선정하여 성장판과 골 말단부 사이의 길이를 측정하 여 연령과의 상관관계를 알아보고자 하였다. 실험은 2014년 3월에서 2015년 3월까지 성장판검사를 시행한 소아 72 명(남 36명, 여 36명)을 대상으로 하였으며, 소아 손 전후영상에서 성장판과 골 말단부 사이의 길이를 측정하여 회 귀분석을 하였다. 그 결과 각 연령마다 특정범위에 상응하는 평균과 표준편차 값이 나타났으며, 연령이 증가할수 록 성장판과 골 말단부 사이 길이가 감소하였다. 또한 여아가 남아에 비해 평균값이 작게 나타났으며, 회귀분석 결 과에서 성장판과 골 말단부 부위 측정 길이와 연령이 통계적으로 유의(p<0.001)한 것으로 나타났다. 따라서 소아 손 전후영상에서 TW3법의 응용을 통한 회귀방정식으로 골연령의 예측이 가능함을 알 수 있었다.

This paper describes the development of a hand module of NREX (National Rehabilitation Center Robotic Exoskeleton) designed to assist individuals with sustained neurological impairments such as stroke and spinal cord injuries. To construct a simple and lightweight hand module, the robotic hand adopts a mechanism driven by a motor and moved by two four-bar linkages. The motor facilitates the flexion-extension movements of the thumb and the other four fingers simultaneously. Thus, an individual using the robotic hand module can effectively grip and release objects related to daily life activities. The robotic hand module has been designed to cover the range of motion with respect to its link distance. This hand module can be used in therapeutic rehabilitation as well as for daily life assistance. In addition, this hand module can either be mounted on an NREX or used as a standalone module.

Peg-in-hole assembly is the most representative task for a robot to perform under contact conditions. Various strategies for accomplishing the peg-in-hole task with a robot exist, but the existing strategies are not sufficiently practical to be used for various assembly tasks in a human environment because they require additional sensors or exclusive tools. In this paper, the peg-in-hole assembly experiment is performed with anthropomorphic hand arm robot without extra sensors or devices using “intuitive peg-in-hole strategy”. From this work, the probability of applying the peg-in-hole strategy to a common assembly task is verified.

An adaptive robot hand (AR-Hand) has a stable grasp of different objects in unstructured environments. In this study, we propose an AR-Hand based on a tendon-driven mechanism which consists of 4 fingers and 12 DOFs. It weighs 0.5 kg and can grasp an object up to 1 kg. This hand based on the adaptive grasp mechanism is able to provide a stable grasp without a complex control algorithm or sensor system. The fingers are driven by simple tendon structures with each finger capable of adaptively grasping the objects. This paper presents a method to decide the joint stiffness. The adaptive grasping is verified by various grasping experiments involving objects with different shapes and sizes.

증강현실 기술을 게임에 접목하려는 시도가 많이 이루어지고 있다. 본 논문에서는 실시간으 로 스마트 기기의 카메라로부터 손동작 2차원 영상을 획득하고 HSV 컬러 영역을 활용하여 해 당 색상의 물체 또는 신체를 실시간으로 검출해, 게임의 요소로 활용하여 즐길 수 있는 2D 퍼 즐게임을 개발하였다. 이는 스마트 기기에 컴퓨터 비전을 접목한 형태의 게임으로, 교육 및 엔 터테인먼트 환경에서 스마트 기기의 휴대성과 가상현실 체험의 현장감을 접목시킨 새로운 인터 랙티브 기술이 될 것이다.