Abstract: A method for detecting a penetration depth of riboflavin in a cornea includes acquiring an optical section of RGB colors and converting it into an image in a CIEL*a*b* color space, extracting a luminance component L* in the CIEL*a*b* color space, performing binarization and Blob analysis to obtain a non-corneal-region-free image; based on the non-corneal-region-free image and the luminance component L* image, extracting boundary points of anterior and posterior corneal surfaces and performing curve fitting, so as to obtain anterior and posterior corneal surface curves; performing image fusion on the anterior and posterior corneal surface curves into the CIEL*a*b* color space to obtain a cornea-only CIEL*a*b* color image; in the cornea-only CIEL*a*b* color image, locating a riboflavin-penetrating region and partitioning the riboflavin-penetrating region into riboflavin-penetrating sites, and performing curve fitting and noise reduction on the riboflavin-penetrating sites to obtain riboflavin the penetration de

Abstract: Data regarding typing by a user may be collected and analyzed in order to assess one or more health conditions or functional states of the user. Each health condition that is assessed may be a disease or a symptom of a disease. For instance, based on the typing data, a computer may assess the presence, severity or probability of, or a change in, one or more symptoms such as: mild cognitive impairment; dementia; impairment of fine motor control; impairment of sensory-motor feedback; or behavioral impairment. A computer may calculate keystroke tensors that encode information about the typing. A computer may select or derive features from the keystroke tensors. These features may be fed into one or more machine learning algorithms, which in turn may output an assessment of a health condition or functional state of the user.

Abstract: Data regarding typing by a user may be collected and analyzed in order to assess one or more health conditions or functional states of the user. Each health condition that is assessed may be a disease or a symptom of a disease. For instance, based on the typing data, a computer may assess the presence, severity or probability of, or a change in, one or more symptoms such as: mild cognitive impairment, dementia, impairment of fine motor control, impairment of sensory-motor feedback, or behavioral impairment. A computer may calculate keystroke tensors that encode information about the typing. A computer may select or derive features from the keystroke tensors. These features may be fed into one or more machine learning algorithms, which in turn may output an assessment of a health condition or functional state of the user.

Abstract: A method for early diagnosis of keratoconus based on multi-modal data considers a mutual relationship between both eyes using four refractive maps for corneas of the both eyes and absolute corneal elevation data, and combines the deep convolutional network method, the traditional support vector machine (SVM) method in machine learning, and the elevation map enhancement method with adjustable best-fit-sphere (BFS) to identify sensitivity and specificity of a focus and balance the sensitivity and specificity. With multi-dimensional comprehensive judgment of a keratoconus morbidity with a patient as a unit, combined with binocular data including both manual selection features and deep network learning from big data, the diagnosis method has higher robustness and accuracy.

Abstract: A method for early diagnosis of keratoconus based on multi-modal data considers a mutual relationship between both eyes using four refractive maps for corneas of the both eyes and absolute corneal elevation data, and combines the deep convolutional network method, the traditional support vector machine (SVM) method in machine learning, and the elevation map enhancement method with adjustable best-fit-sphere (BFS) to identify sensitivity and specificity of a focus and balance the sensitivity and specificity. With multi-dimensional comprehensive judgment of a keratoconus morbidity with a patient as a unit, combined with binocular data including both manual selection features and deep network learning from big data, the diagnosis method has higher robustness and accuracy.

Abstract: Data regarding typing by a user may be collected and analyzed in order to assess one or more health conditions or functional states of the user. Each health condition that is assessed may be a disease or a symptom of a disease. For instance, based on the typing data, a computer may assess the presence, severity or probability of, or a change in, one or more symptoms such as: mild cognitive impairment; dementia; impairment of fine motor control; impairment of sensory-motor feedback; or behavioral impairment. A computer may calculate keystroke tensors that encode information about the typing. A computer may select or derive features from the keystroke tensors. These features may be fed into one or more machine learning algorithms, which in turn may output an assessment of a health condition or functional state of the user.

Abstract: A mobile communication device with an ergonomic feature comprises a housing, a display unit, a first key module, and a second key module. The display unit is arranged on a lower part of one face of the housing, and the first key module is arranged on the housing on the same face as the display unit to locate closely above the display unit. The first key module comprises a plurality of upside keys which are arrayed into a laterally symmetric hexagonal configuration. The second key module comprises a plurality of lateral keys located on one of two opposite lateral surfaces of the housing. The keys of the two key modules are so arranged on the housing that either a right-handed or a left-handed user can conveniently operate the keys not only with a thumb but also the other four fingers while holding the device with one single hand.

Abstract: A mobile communication device with an ergonomic feature comprises a housing, a display unit, a first key module, and a second key module. The display unit is arranged on a lower part of one face of the housing, and the first key module is arranged on the housing on the same face as the display unit to locate closely above the display unit. The first key module comprises a plurality of upside keys which are arrayed into a laterally symmetric hexagonal configuration. The second key module comprises a plurality of lateral keys located on one of two opposite lateral surfaces of the housing. The keys of the two key modules are so arranged on the housing that either a right-handed or a left-handed user can conveniently operate the keys not only with a thumb but also the other four fingers while holding the device with one single hand.

Abstract: A method for checking a wire bonding recipe is provided. Generally, coordinate data of a master recipe is stored. Coordinate data of a slave recipe is stored. The coordinate data of the slave recipe is compared with coordinate data of the master recipe. An error signal is provided if a mismatch is found between the coordinate data of the slave recipe and the coordinate data of the master recipe. A computer readable medium containing program instructions for checking a wire bonding recipe is also provided. The program contains computer readable code for storing coordinate data of a master recipe, computer readable code for storing coordinate data of a slave recipe, computer readable code for comparing the coordinate data of the slave recipe with coordinate data of the master recipe, and computer readable code for providing an error signal if a mismatch is found between the coordinate data of the slave recipe and the coordinate data of the master recipe.

Abstract: A method for checking a wire bonding recipe is provided. Generally, coordinate data of a master recipe is stored. Coordinate data of a slave recipe is stored. The coordinate data of the slave recipe is compared with coordinate data of the master recipe. An error signal is provided if a mismatch is found between the coordinate data of the slave recipe and the coordinate data of the master recipe. A computer readable medium containing program instructions for checking a wire bonding recipe is also provided. The program contains computer readable code for storing coordinate data of a master recipe, computer readable code for storing coordinate data of a slave recipe, computer readable code for comparing the coordinate data of the slave recipe with coordinate data of the master recipe, and computer readable code for providing an error signal if a mismatch is found between the coordinate data of the slave recipe and the coordinate data of the master recipe.