Abstract: Methods and systems for computationally processing data with a multi-layer convolutional neural network (CNN) having an input and output layer, and one or more intermediate layers are described. Input data represented in a form of evaluations of continuous functions on a sphere may be received at a computing device and input to the input layer. The input layer may compute outputs as covariant Fourier space activations by transforming the continuous functions into spherical harmonic expansions. The output activations from the input layer may be processed sequentially through each of the intermediate layers. Each, intermediate layer may apply Ciebsch-Gordan transforms to compute respective covariant Fourier space activations as input to an immediately next layer, without computing any intermediate inverse Fourier transforms or forward Fourier transforms.

Abstract: A detachable submersible pump with a modular design includes a motor module and a pump chamber module. The motor module includes an upper cover, a motor, a motor cover, and an impeller. The pump chamber module includes a housing, a water outlet, a connecting pipe, and a lock nut. The water outlet is arranged on one side of the housing. The lock nut is sleeved on the connecting pipe and is connected to the water outlet by threads. Each of two sides of the upper cover is provided with a pressable elastic buckle. Each of two sides of the housing is provided with a clamping hole. The impeller is placed inside the housing.

Abstract: Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: A computer-implemented method of interactive machine learning in which a user is provided with predicted results from a trained machine learning model. The user can take the predicted results and either: i) adjust the predicted results an input the adjusted results as new data; or ii) adjust the predicted data to retrain the model.

Abstract: A computer-implemented method of interactive machine learning in which a user is provided with predicted results from a trained machine learning model. The user can take the predicted results and adjust the predicted data to retrain the model.

Abstract: Machine learning segmentation methods and systems that perform segmentation quickly, efficiently, cheaply, and optionally provides an interactive feature that allows a user to alter the segmentation until a desired result is obtained. The automated machine learning segmentation tool receives all potentially important attributes and provides segmentation of items. It also receives information about important features of the data and finds how best to differentiate between groups using cluster-based machine learning algorithms. In addition, visualization of the segmentation explains to a user how the segmentation was obtained.

Abstract: A method and system for a machine learning cluster analysis of historical lead time data, which is augmented by one or more features. The data can also he divided into groups, based on time-density of the data, with clustering performed on each group. Furthermore, clustering can also be projected onto two dimensions. In addition, the historical lead time data is separated into a plurality of tolerance zones based on tolerance criteria. The clusters are separated in accordance with a tolerance zone of each group; and further separated according to one or more lead time identifiers to provide one or more separated clusters.

Abstract: A dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, weather data and financial data related to locations and dates within the supply chain.

Abstract: A ship including at least two hull sections spliced together along the axial direction of the ship. The two adjacent hull sections are connected through a splicing structure. The splicing structure includes a first matching structure and a second matching structure. The first matching structure includes a protrusion and a groove that are in a vertical inserting fit. The second matching structure includes a fixed base and a rotating base for rotating to press the fixed base. The hull sections of the present invention are stable to connect and convenient to disassemble and assemble.

Abstract: The present disclosure provides a system and a method for manipulating a robotic device. The system includes a human interface device for obtaining information associated with a position and/or movement of a user's finger using the human interface device; and a robotic device for simulating the position and/or movement of the user's finger in real time. The robotic device is in communication with the human interface device. The operating system of the robotic device of the present disclosure can accurately simulate the functions of human hand.

Abstract: A dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, weather data and financial data related to locations and dates within the supply chain.

Abstract: A dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, and to divide historical lead time data into clusters based on seasonality and linearity. The machine learning results are further processed to adjust future planned lead times and to identify sources in the supply chain that contribute to large deviations between historical planned lead times and actual lead times.

Abstract: An optical element driving mechanism is provided. The optical element driving mechanism includes a fixed portion, a movable portion, a driving assembly, and a circuit unit. The movable portion is movably connected to the fixed portion, and holds an optical element. The driving assembly drives the movable portion to move relative to the fixed portion. The circuit unit includes a base, a plate-connecting portion, and a layer-connecting portion. The plate-connecting portion is partially embedded in the base. The layer-connecting portion is disposed on the base. The driving assembly is electrically connected to the layer-connecting portion. The thickness of the plate-connecting portion is different from the thickness of the layer-connecting portion.

Abstract: A foldable miter saw and folding method of miter saw are disclosed. The foldable miter saw includes a base unit, a workable, and a cutting unit. The cutting unit includes a support arm pivotally mounted on the worktable, a saw blade, and a driver. The miter saw folding method includes the step of biasing the cutting unit relative to the base unit and the step of rotating the support arm relative to the base unit and the worktable to change the cutting unit from a working position to a folded position, thus reducing the vertical space occupied by the cutting unit and facilitating delivery, storage and package of the foldable miter saw.

Abstract: Foldable miter saws and a folding method of miter saws are disclosed. The foldable miter saws includes a base unit, a worktable, and a cutting unit. The cutting unit includes a support arm pivotally mounted on the worktable, a saw blade, and a driver. The miter saw folding method includes the step of biasing the cutting unit relative to the base unit and the step of rotating the support arm relative to the base unit and the worktable to change the cutting unit from a working position to a folded position, thus reducing the vertical space occupied by the cutting unit and facilitating delivery, storage and package of the foldable miter saws.