Understanding Human Hand Gestures for Learning Robot Pick-and-Place Tasks

Programming robots by human demonstration is an intuitive approach, especially by gestures. Because robot pick-and-place tasks are widely used in industrial factories, this paper proposes a framework to learn robot pick-and-place tasks by understanding human hand gestures. The proposed framework is composed of the module of gesture recognition and the module of robot behaviour control. For the module of gesture recognition, transport empty (TE), transport loaded (TL), grasp (G), and release (RL) from Gilbreth's therbligs are the hand gestures to be recognized. A convolution neural network (CNN) is adopted to recognize these gestures from a camera image. To achieve the robust performance, the skin model by a Gaussian mixture model (GMM) is used to filter out non-skin colours of an image, and the calibration of position and orientation is applied to obtain the neutral hand pose before the training and testing of the CNN. For the module of robot behaviour control, the corresponding robot motion primitives to TE, TL, G, and RL, respectively, are implemented in the robot. To manage the primitives in the robot system, a behaviour-based programming platform based on the Extensible Agent Behavior Specification Language (XABSL) is adopted. Because the XABSL provides the flexibility and re-usability of the robot primitives, the hand motion sequence from the module of gesture recognition can be easily used in the XABSL programming platform to implement the robot pick-and-place tasks. The experimental evaluation of seven subjects performing seven hand gestures showed that the average recognition rate was 95.96%. Moreover, by the XABSL programming platform, the experiment showed the cube-stacking task was easily programmed by human demonstration.

Enhanced data consistency of a portable gait measurement system

A gait measurement system is a useful tool for rehabilitation applications. Such a system is used to conduct gait experiments in large workplaces such as laboratories where gait measurement equipment can be permanently installed. However, a gait measurement system should be portable if it is to be used in clinics or community centers for aged people. In a portable gait measurement system, the workspace is limited and landmarks on a subject may not be visible to the cameras during experiments. Thus, we propose a virtual-marker function to obtain positions of unseen landmarks for maintaining data consistency. This work develops a portable clinical gait measurement system consisting of lightweight motion capture devices, force plates, and a walkway assembled from plywood boards. We evaluated the portable clinic gait system with 11 normal subjects in three consecutive days in a limited experimental space. Results of gait analysis based on the verification of within-day and between-day coefficients of multiple correlations show that the proposed portable gait system is reliable.

Reciprocal regulatory interaction between human herpesvirus 8 and human immunodeficiency virus type 1

Human herpesvirus 8 (HHV8) is the primary viral etiologic agent in Kaposi's sarcoma (KS). However, individuals dually infected with both HHV8 and human immunodeficiency virus type 1 (HIV-1) show an enhanced prevalence of KS when compared with those singularly infected with HHV8. Host immune suppression conferred by HIV infection cannot wholly explain this increased presentation of KS. To better understand how HHV8 and HIV-1 might interact directly in the pathogenesis of KS, we queried for potential regulatory interactions between the two viruses. Here, we report that HHV8 and HIV-1 reciprocally up-regulate the gene expression of each other. We found that the KIE2 immediate-early gene product of HHV8 interacted synergistically with Tat in activating expression from the HIV-1 long terminal repeat. On the other hand, HIV-1 encoded Tat and Vpr proteins increased intracellular HHV8-specific expression. These results provide molecular insights correlating coinfection with HHV8 and HIV-1 with an unusually high incidence of KS.

Economic analysis of lung volume reduction surgery as part of the National Emphysema Treatment Trial. NETT Research Group

BACKGROUND

In today's cost-conscious health care environment, obtaining timely and accurate economic information regarding new medical technologies has become extremely important. The National Emphysema Treatment Trial, a multicenter, randomized controlled trial of lung volume reduction surgery (LVRS) plus medical therapy, versus medical therapy for patients with severe emphysema, includes a parallel cost-effectiveness analysis.

METHODS

The analysis is designed to determine the cost-effectiveness of LVRS versus medical therapy for those who are eligible for the procedure. After describing theoretical foundations of cost-effectiveness analysis as they apply to this study, we describe the economic and quality of life data that are being collected alongside the clinical trial, methods of analysis, and approach to presenting the results.

RESULTS

The cost-effectiveness of LVRS relative to medical therapy will be presented as costs per quality-adjusted life years gained.

CONCLUSIONS

This analysis will provide timely economic data that can be considered alongside the clinical results of the National Emphysema Treatment Trial. As one of the largest clinical trials to include a parallel, prospective cost-effectiveness analyses, this study will also provide valuable practical information about conducting an economic analysis alongside a multicenter clinical trial.

Measurement of health outcomes in treatment effectiveness evaluations: conceptual and methodological challenges

Major challenges in the evaluation of the "end results" of health services include ensuring that concepts are correctly defined and measured, that the validity of measures used in different applications and populations is well documented, and that observed effects can be clearly interpreted. Health status is the most widely interpretable concept to apply in the context of health services. Quality of life connotes inclusion of the environment outside the context of the person and of health care and may or may not be health related, depending on the evaluation context and the impact of disease and treatment. All concepts and constructs must be defined in reference to their theoretical origin and to a model of relationships among different concepts. Modern test theory offers the potential for individualized, comparable assessments and for the careful examination and application of different measurement models. Selection and critique of measures should be based on the intended application and accumulated evidence for that application. Thus, there are no valid instruments per se. Validity in use, including responsiveness, interpretation of effects, and generalizability to diverse populations, is the most important measurement characteristic for treatment effectiveness. An evaluation of the validity of preference-based measures is particularly important for the interpretation and comparability of outcomes in cost-effectiveness evaluations. The successful translation of research into policy and practice is limited by the extent to which these critical issues are addressed in actual treatment evaluations.

Health status of Medicare enrollees in HMOs and fee-for-service in 1994

We compared the health status of 863 health maintenance organization (HMO) enrollees with that of 4,576 non-enrollees, controlling for demographics and area of residence, using 1994 data from the Medicare Current Beneficiary Survey (MCBS). HMO respondents were less likely to report fair or poor health, functional impairment, or heart disease. Average predicted costs based on various health-status measures were substantially lower for HMO respondents than for respondents in fee-for-service (FFS) arrangements. The Medicare payment formula for HMOs does not adequately adjust for the better health and consequent lower expected costs of HMO enrollees. The addition of health-status measures would improvement payment accuracy and reduce average HMO payments significantly below current levels.

Seroepidemiology of measles in southern Taiwan: two years after implementation of the measles elimination program

The seroprevalence of the measles antibody in southern Taiwan 2 years after the launch of the two-dose measles elimination program was studied using serological surveillance. Sera from 868 healthy inhabitants were collected from January to December 1993. Measles IgG antibody was detected by enzyme-linked immunosorbent assay. Measles antibody was found in 82% of infants under 3 months of age, 26% of those between 4 and 9 months and 54% of those between 10 and 15 months of age. The most common reason for postponement of vaccination was due to concomitant illness during the scheduled vaccination period. The presence of measles antibody rose sharply in children over 15 months of age, reached 90% among preschool-aged children and was 93% in school-aged children. These data suggest that a high immunization coverage rate was achieved in children over 15 months of age (92%) and that a third measles immunization at age 12 is not necessary. Future strategies for measles control should aim at increasing the immunization coverage for children between 9 and 15 months of age.

Office visits to ophthalmologists and other physicians for eye care among the U.S. population, 1990

Despite growth in the use of ophthalmologic care in the last decade, little is known about the use of eye care services and patterns of physician contact across population subgroups. As the U.S. population grows older, such information is crucial in planning strategies for treatment and prevention of eye disorders as well as in identifying potential problems in access and use of eye care. Using the 1990 National Ambulatory Medical Care Survey data, a descriptive statistical analysis was employed to profile the possible variations in eye care-related office visits to ophthalmologists and other physicians across demographic groups. In 1990, a total of 49.3 million visits that were related primarily to an ocular disorder were made to physicians' offices; 43.8 million (89 percent) of these were visits to ophthalmologists and 5.4 million (11 percent) to other physicians. Use of ambulatory eye care varied across demographic subgroups. Those ages 65 or older had a substantially higher rate of eye care related outpatient visits per 1,000 persons per year compared with the rest of the population (743.6 per 1,000 versus 118.5 per 1,000, P < 0.001). Women had a higher rate than men (216.0 per 1,000 versus 177.0 per 1,000, 0.01; P < 0.05). Blacks had a substantially lower rate than whites (143.2 per 1,000 versus 194.6 per 1,000, 0.001; P < 0.01). Those who visited ophthalmologists' offices also differed from those who visited other physicians' offices in terms of their age, sex, race, health insurance status, and disease characteristics. It is important to devote increased attention to the prevention of vision loss among the population groups that have a higher risk of developing eye diseases and that also may have underused or have less access to care. Results from this analysis, in combination with data on the prevalence of ocular disorders for different population groups, provide useful information to identify these high-risk groups.

The socioeconomic aspects of laser refractive surgery

Excimer laser photorefractive keratectomy (PRK) has shown promising results in preliminary studies. However, even if long-term safety and efficacy are demonstrated, questions have been raised about its viability from a cost-effectiveness perspective. We analyzed the economic investment of elective excimer laser PRK both from the societal and individual perspectives. When the present value of likely expenses associated with excimer laser PRK and follow-up care are compared with those entailed in wearing soft contact lenses, PRK is roughly equivalent to daily wear soft contact lenses over a 10-year horizon and considerably less expensive than extended-wear soft contact lenses. When the analytic perspective is extended to 20 years, excimer laser PRK is a less expensive investment than both daily wear and extended-wear soft contact lenses.

Health insurance coverage and medical care utilization among working-age Americans with visual impairment

As access and cost of medical care emerge as the fundamental issues in the discussion of reforming the nation's health care system, more attention needs to be devoted to the understanding of how visual impairment and functional disability in general affects an individual's access to health insurance as well as medical care utilization. Based on the 1984 Survey of Income and Program Participation (SIPP), we estimate that only 57.5% of 7.0 million working-age (15-64 years old) visually impaired Americans, compared with 79.0% of those not visually impaired, have private health insurance coverage. Moreover, an estimated 1.5 million visually impaired working-age Americans are not covered by any form of health insurance, public or private. This 20.7% uninsurance rate is significantly higher than the 14.1% reported among those who are not visually impaired (p < 0.001). Multivariate logistic regression also supports the inverse association between visual impairment and insurance coverage. On the other hand, multivariate logistic regression suggests a positive association between visual impairment and utilization of outpatient medical services. Although there is a trend toward higher utilization of inpatient services as well among the visually impaired, the finding is not statistically significant. These findings suggest that visual impairment poses a barrier to accessing health insurance, even when controlling for income, education, and employment status. On the other hand, regardless of the health insurance status, visually impaired Americans are likely to have utilized more physician services, but not the hospital services, than the non-visually impaired.

Practice patterns of the office-based ophthalmologist

Practice patterns of office-based ophthalmologists were characterized using data collected from the National Ambulatory Medical Care Survey (NAMCS) of 1989, a national probability sample survey conducted by the National Center for Health Statistics. The sample includes office visits made between 1989 and 1990 to nonfederally-employed physicians primarily engaged in office-based practice. Over 38 million office-based patient visits documented in the NAMCS were analyzed. Fifty-two percent of patients (20.4 million) were over 65 years old; 90% (34.9 million) were white, with blacks and Asians accounting for 5% (1.9 million) and 3% (1.1 million) of visits, respectively. The leading primary diagnoses and professional activity associated with the visits were cataract/cataract surgery 23% (8.9 million), disorders of refraction 19.5% (7.5 million), and glaucoma 13% (4.9 million). Over 40% (16.1 million) of visits were for visual dysfunction, abnormal appearance, or abnormal sensation. Nearly 33% (12.5 million) were related to either a diagnostic/screening session or some form of treatment. The duration of visits ranged from 6 to 10 minutes (22.9%), 11 to 15 minutes (29.8%), and 31 minutes or longer (6.7%); 74% (28.1 million) of the patients were asked to return for a follow-up visit at a specified time, and 13% to return if needed. The major sources of reimbursement for office visits were Medicare (41%, 15.6 million); Blue Cross/Blue Shield (13%, 5 million); and other commercial insurance (15.5%, 5.8 million).

Lessening the burden of diabetes. Intervention strategies

OBJECTIVE

To evaluate the impact of primary and secondary interventions on the development of complications from diabetes, we modeled the effects of primary and secondary interventions for diabetes on a single well-studied complication, diabetic retinopathy.

RESEARCH DESIGN AND METHODS

A model was developed to predict cumulative incidence of retinopathy in IDDM and NIDDM. Risk functions are based on duration of diabetes. The effects of intervention strategies were simulated by altering the retinopathy risk. The effects of the simulations were assessed using cumulative incidence.

RESULTS

Simulations of delaying the onset of IDDM from 2 to 8 yr and decreasing the retinopathy rates by 20-80% were performed for each type of retinopathy. Simulating primary prevention shifted the cumulative incidence curves to the right, and simulating secondary intervention shifted the curves downward. Primary prevention was less effective than secondary prevention. This difference was more apparent for IDDM than for NIDDM, where disease duration and exposure to retinopathy risk were shorter. All interventions shifted the development of retinopathy to later in life.

CONCLUSIONS

The greatest effect on cumulative incidence of all forms of retinopathy occurs when primary and secondary interventions are combined.

Cost-effectiveness of screening and cryotherapy for threshold retinopathy of prematurity

BACKGROUND

Retinopathy of prematurity (ROP) is the leading cause of blindness among premature infants. A recent National Eye Institute-sponsored prospective, multicenter trial investigating the use of cryotherapy for treatment of ROP demonstrates a significant reduction in blindness and low vision for patients with sight-threatening (stage 3+) ROP.

METHOD

A microsimulation model is presented to determine the cost-effectiveness of cryotherapy for ROP. Simulations are performed for three subpopulations of premature infants with birth weights 500 through 749 g, 750 through 999 g, and 1000 through 1249 g, and for three screening strategies--weekly, biweekly, and monthly.

RESULTS

Appropriately timed screening for and treatment of ROP is predicted to result in a gain of 3899 to 4648 quality-adjusted-life-years and a net governmental budgetary savings of $38.3 to $64.9 million for each annual US birth cohort of 28,321 premature infants (500 through 1249 g). The cost per quality-adjusted-life-year gained is $2488 to $6045, depending on different screening strategies.

CONCLUSIONS

Of greatest importance is the finding that properly timed screening and treatment for ROP is not only cost saving but may save approximately 320 infants per year from a lifetime of blindness.

Cost-effectiveness of the screening and treatment of diabetic retinopathy. What are the costs of underutilization?

Diabetic retinal disease remains a leading cause of visual disability among those of working age. Controlled trials have demonstrated that timely diagnosis and photocoagulation treatment can reduce significantly the likelihood of visual impairment in affected diabetic patients. Using a prospective simulation model, we show that an annual screening and treatment program saves thousands of years of vision and reduces medical expenditures over the lifetime of a cohort of Swedish Type I diabetic patients.

Detecting and treating retinopathy in patients with type I diabetes mellitus. Savings associated with improved implementation of current guidelines. American Academy of Ophthalmology

Diabetic retinopathy is the leading cause of acquired blindness among Americans of working age. The resulting economic and societal burdens are of profound magnitude. Epidemiologic and clinical trials data were used to analyze the impact of improved recruitment of patients with Type I diabetes mellitus into screening and treatment programs. The analysis predicted annual savings of $101.0 million and 47,374 person-years-sight at the currently estimated 60% screening and treatment implementation level. If all patients received appropriate eye care, the predicted savings exceed 167.0 million and 79,236 person-years-sight. Approximately two thirds of all savings result from treatment of proliferative diabetic retinopathy, while nearly one third arises from treatment of clinically significant macular edema. Additional savings of $9571 are realized with each recruitment of a newly diagnosed patient with diabetes. Initiating screening immediately upon diagnosis of diabetes, rather than the currently recommended 5-year deferral, would be cost effective if 1 additional individual in 56 were recruited. This model suggests that improved delivery of ophthalmic care to patients with diabetes would yield substantial financial and visual savings, thus making major recruitment programs such as the National Eye Institute's National Eye Health Education Program and the American Academy of Ophthalmology's Diabetes 2000, both economically and clinically effective.