Abstract: Provided are a chromium catalyst precursor, an ethylene oligomerization catalyst including the same, and a method of preparing an ethylene oligomer using the same. More particularly, a chromium catalyst precursor which may oligomerize ethylene with high activity and high selectivity in spite of not using methylaluminoxane (MAO) or modified-methylaluminoxane (MMAO), an oligomerization catalyst including the same, and a method of preparing an ethylene oligomer using the same are provided.

Abstract: Provided is a machine learning-based semiconductor manufacturing yield prediction system and method. A result prediction method according to an embodiment of the present invention comprises: learning different neural network models by classifying different types of data according to their types and respectively inputting the classified different types of data to the different neural network models; and predicting result values by classifying input data according to their types and respectively inputting the classified input data to different neural network models. Therefore, it is possible to apply different neural network models to respective data according to their types, thereby ensuring a neural network model having a structure appropriate for the characteristics of each type of data and thus accurately predicting a result value.

Abstract: A method and a system for sensing fine changes in processing/equipment measurement data are provided. A data change sensing method according to an embodiment of the present invention extracts a part on the basis of a statistical distribution of reference data and comparison data, calculates a target range on the basis of a specification, and discriminates data, included in the target range, among the extracted reference data and comparison data so as to determine data changes. Therefore, fine changes in measurement data for processing or equipment can be sensed in a manufacturing process, thereby enabling pre-estimation of potential quality variability of products and quick preemptive actions for preventing quality degradation.

Abstract: Provided is a machine learning-based semiconductor manufacturing yield prediction system and method. A result prediction method according to an embodiment of the present invention comprises: learning different neural network models by classifying different types of data according to their types and respectively inputting the classified different types of data to the different neural network models; and predicting result values by classifying input data according to their types and respectively inputting the classified input data to different neural network models. Therefore, it is possible to apply different neural network models to respective data according to their types, thereby ensuring a neural network model having a structure appropriate for the characteristics of each type of data and thus accurately predicting a result value.

Abstract: A method and a system for sensing fine changes in processing/equipment measurement data are provided. A data change sensing method according to an embodiment of the present invention extracts a part on the basis of a statistical distribution of reference data and comparison data, calculates a target range on the basis of a specification, and discriminates data, included in the target range, among the extracted reference data and comparison data so as to determine data changes. Therefore, fine changes in measurement data for processing or equipment can be sensed in a manufacturing process, thereby enabling pre-estimation of potential quality variability of products and quick preemptive actions for preventing quality degradation.