Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
At this moment, the Republic of Indonesia is continuing to develop nation-made weapon and armory, to support the industry of national defense. One of the newest achievements in rifle making is the SS-2 type. Therefore, it needs more evaluation in ergonomic aspects, in order to avoid occurrence of aspects of the weapon which could cause bad effect to the shooting performance and the health of soldiers in long term. This matter could be eliminated in the making process of the SS-2, consider more intensely on its ergonomic aspects. Noise is a part of ergonomic concern which has been one crucial matter in industry, especially in manufacturing plants. Noise has been proven to cause bad effects on human's health. In analyzing noise generates by firing sound observation on three primary acoustic factors are needed These factors are sound intensity (dB), frequency (Hz), and duration of sound exposure (ms). ANOVA analysis, correlation analysis, maximum permissible impulse noise, and continuous sound analysis are used to draw the relation between shooting position (standing, squat, prone), and the acoustic (noise) factors, relation between noise factors and shooter performance, and the maximum number of permissible impulse noise (firing sauna) per day. Based on those analyses, the noise impact on soldiers' health and performance could be seen therefore any preventive measures in dealing with noise impact can be implemented.

Abstrak :
Fixation points, as the stopping location of eye movements, can be extracted to generate valuable information about a picture or an object. This information is valuable as it enables the identification of the area/part of the picture that attracts people’s attention, which can be used as a consideration when making decisions in the future, for example in marketing. For this reason, in this study, a Neural Network (NN) model was developed to predict the fixation points of a picture. Specifically, the authors experimented with various transfer and training functions in the NN in order to determine which causes the fewest errors. The results show that the method used is applicable in practice since it produces MAPE (Mean Absolute Percent Error) of around 13–15% and MSE (Mean Squared Error) of 0.9–1.1%.