Abstract: The present disclosure provides a light-emitting package. The light-emitting package includes a main body, a cavity disposed in the cavity, a base plane in the cavity and a light-emitting element. The light-emitting element is disposed in the cavity and connected to the base plane. The light-emitting element includes a substrate and a semiconductor stack on the substrate. The substrate includes a side wall, and the side wall incudes a first cutting trace. The main body includes a step portion disposed in the cavity and it surrounds the light-emitting element. The step portion comprises a first height relative to base plane, and the first cutting trace comprises a second height relative to the base plane. The second height is greater than the first height.

Abstract: An implantable micro-biosensor a substrate, a first electrode, a second electrode, a third electrode, and a chemical reagent layer. The first electrode is disposed on the substrate and used as a counter electrode. The second electrode is disposed on the substrate and spaced apart from the first electrode. The third electrode is disposed on the substrate and used as a working electrode. The chemical reagent layer at least covers a sensing section of the third electrode so as to permit the third electrode to selectively cooperate with the first electrode or the first and second electrodes to measure a physiological signal in response to the physiological parameter of the analyte.

Abstract: An implantable micro-biosensor a substrate, a first electrode, a second electrode, a third electrode, and a chemical reagent layer. The first electrode is disposed on the substrate and used as a counter electrode. The second electrode is disposed on the substrate and spaced apart from the first electrode. The third electrode is disposed on the substrate and used as a working electrode. The chemical reagent layer at least covers a sensing section of the third electrode so as to permit the third electrode to selectively cooperate with the first electrode or the first and second electrodes to measure a physiological signal in response to the physiological parameter of the analyte.

Abstract: The present invention provides a micro biosensor for reducing a measurement interference when measuring a target analyte in the biofluid, including: a substrate; a first working electrode configured on the surface, and including a first sensing section; a second working electrode configured on the surface, and including a second sensing section which is configured adjacent to at least one side of the first sensing section; and a chemical reagent covered on at least a portion of the first sensing section for reacting with the target analyte to produce a resultant. When the first working electrode is driven by a first working voltage, the first sensing section measures a physiological signal with respect to the target analyte. When the second working electrode is driven by a second working voltage, the second conductive material can directly consume the interferant so as to continuously reduce the measurement inference of the physiological signal.

Abstract: In a method of cleaning a lithography system, during idle mode, a stream of air is directed, through a first opening, into a chamber of a wafer table of an EUV lithography system. One or more particles is extracted by the directed stream of air from surfaces of one or more wafer chucks in the chamber of the wafer table. The stream of air and the extracted one or more particle are drawn, through a second opening, out of the chamber of the wafer table.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: Training of a machine vision model, a segmentation model, is performed by using an acquisition function for a small number of pixels of one or more training images. The acquisition function uses first mutual information and second mutual information to identify unlabelled pixels which are labelled with high uncertainty when predicting possible label values. Training, prediction of labels, identifying pixels with highly uncertain labels, obtaining labels only for those pixels with highly uncertain labels and retraining are performed iteratively to finally provide the machine vision model. The iterative approach uses very few labelled pixels to obtain the final machine vision model. The machine vision model accurately labels areas of a data image.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: A problem of supervised learning is overcome by using patches to discover objects in unlabeled training images. The discovered objects are embedded in a pattern space. An AI machine replaces manual entry steps of training with a machine-centric process including clustering in a pixel space, clustering in latent space and building the pattern space based on different losses derived from pixel space clustering and latent space clustering. A distance structure in the pattern space captures the co-occurrence of patterns due to frequently appearing objects in training image data. Embodiments provide image representation based on local image patch naturally handles the position and scale invariance property that is important to effective object detection. Embodiments successfully identifies frequent objects such as human faces, human bodies, animals, or vehicles from unorganized data images based on a small quantity of training images.

Abstract: A problem of imbalanced big data is solved by decoupling a classifier into a neural network for generation of representation vectors and into a classification model for operating on the representation vectors. The neural network and the classification model act as a mapper classifier. The neural network is trained with an unsupervised algorithm and the classification model is trained with a supervised active learning loop. An acquisition function is used in the supervised active learning loop to speed arrival at an accurate classification performance, improving data efficiency. The accuracy of the hybrid classifier is similar to or exceeds the accuracy of comparative classifiers in all aspects. In some embodiments, big data includes an imbalance of more than 10:1 in image classes. The hybrid classifier reduces labor and improves efficiency needed to arrive at an accurate classification performance, and improves recognition of previously-unrecognized images.

Abstract: A server trains a neural network by feeding a first set of input time-series data of one or more sensors of a first processing chamber that is within specification to the neural network to produce a corresponding first set of output time-series data. The server calculates a first error. The server feeds a second set of input time-series data from corresponding one or more sensors associated with a second processing chamber under test to the trained neural network to produce a corresponding second set of output time-series data. The server calculates a second error.

Abstract: Embodiments provide techniques for compressing sensor data collected within a manufacturing environment. One embodiment monitors a plurality of runs of a recipe for fabricating one or more semiconductor devices within a manufacturing environment to collect runtime data from a plurality of sensors within the manufacturing environment. The collected runtime data is compressed by generating, for each of the plurality of sensors and for each of the plurality of runs, a respective representation of the corresponding runtime data that describes a shape of the corresponding runtime data and a magnitude of the corresponding runtime data. A query specifying one or more runtime data attributes is received and executed against the compressed runtime data to generate query results, by comparing the one or more runtime data attributes to at least one of the generated representations of runtime data.

Abstract: A display apparatus includes a plurality of gate drivers, a scan indication signal transmission line, a plurality of subsidiary transmission lines, and a plurality of auxiliary lines. The gate drivers are sequentially coupled in series to each other. The scan indication signal transmission line is configured to transmit a scan indication signal. The subsidiary transmission lines are sequentially coupled between two adjacent gate drivers, respectively. The auxiliary lines are respectively disposed between the scan indication signal transmission line and the subsidiary transmission lines. One of the auxiliary lines is selected to be electrically coupled to the scan indication signal transmission line and the corresponding subsidiary transmission line.

Abstract: A server trains a neural network by feeding a first set of input time-series data of one or more sensors of a first processing chamber that is within specification to the neural network to produce a corresponding first set of output time-series data. The server calculates a first error. The server feeds a second set of input time-series data from corresponding one or more sensors associated with a second processing chamber under test to the trained neural network to produce a corresponding second set of output time-series data. The server calculates a second error.

Abstract: A display apparatus includes a plurality of gate drivers, a scan indication signal transmission line, a plurality of subsidiary transmission lines, and a plurality of auxiliary lines. The gate drivers are sequentially coupled in series to each other. The scan indication signal transmission line is configured to transmit a scan indication signal. The subsidiary transmission lines are sequentially coupled between two adjacent gate drivers, respectively. The auxiliary lines are respectively disposed between the scan indication signal transmission line and the subsidiary transmission lines. One of the auxiliary lines is selected to be electrically coupled to the scan indication signal transmission line and the corresponding subsidiary transmission line.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: A method for detecting an anomaly in sensor data generated in a substrate processing apparatus is disclosed herein. A plurality of data sets is received. A first data set from a first sensor and second data set from a second sensor are selected. The first second sensors are defined as a sensor pair. A reference correlation is generated by selecting a subset of values in each data set for each of the first and second data sets. A difference of remaining data correlation outside the subset of values in each data set to the reference correlation is normalized. The normalized data set is filtered to smooth the normalized difference to avoid isolated outliers with high chance of false positive candidates. One or more anomalies are identified. Process parameters of the substrate processing apparatus are adjusted, based on the one or more identified anomalies from the filtered data set.

Abstract: A method for detecting an anomaly in sensor data generated in a substrate processing apparatus is disclosed herein. A plurality of data sets is received. A first data set from a first sensor and second data set from a second sensor are selected. The first second sensors are defined as a sensor pair. A reference correlation is generated by selecting a subset of values in each data set for each of the first and second data sets. A difference of remaining data correlation outside the subset of values in each data set to the reference correlation is normalized. The normalized data set is filtered to smooth the normalized difference to avoid isolated outliers with high chance of false positive candidates. One or more anomalies are identified. Process parameters of the substrate processing apparatus are adjusted, based on the one or more identified anomalies from the filtered data set.

Abstract: Embodiments provide techniques for compressing sensor data collected within a manufacturing environment. One embodiment monitors a plurality of runs of a recipe for fabricating one or more semiconductor devices within a manufacturing environment to collect runtime data from a plurality of sensors within the manufacturing environment. The collected runtime data is compressed by generating, for each of the plurality of sensors and for each of the plurality of runs, a respective representation of the corresponding runtime data that describes a shape of the corresponding runtime data and a magnitude of the corresponding runtime data. A query specifying one or more runtime data attributes is received and executed against the compressed runtime data to generate query results, by comparing the one or more runtime data attributes to at least one of the generated representations of runtime data.