Abstract: A computer system includes one or more memories and one or more processors configured to cause a generative model to generate structural information regarding a chemical compound by inputting a latent representation into the generative model, wherein the generative model has been trained such that differences between structural information regarding other chemical compounds and reconstructions of the structural information regarding the other chemical compounds generated by the generative model are reduced, the reconstructions being generated by inputting latent representations into the generative model, the latent representations being generated based on the structural information regarding the other chemical compounds.

Abstract: Embodiments of the present disclosure provide a wire electric discharge machine (EDM) including a delivery system with one or combination of a wire electrode and a workpiece for delivering the wire electrode and the workpiece into proximity of each other and an energy source for creating electric discharge between the wire electrode and the workpiece. The wire EDM includes a wire electrode position measurement unit including light source to illuminate the wire electrode with encoded illumination pattern and a camera for acquiring a set of images of the wire electrode illuminated by the encoded illumination pattern. The wire EDM includes a processor to reconstruct positions of a segment of the wire electrode at a reconstruction rate greater than an acquisition rate of the camera by utilization of compressive sensing with sparse reconstruction technique and a controller to control the delivery system and the energy source based on the reconstructed positions.

Abstract: A computer system for generating information regarding chemical compound includes one or more memories and one or more processors configured to generate information regarding chemical compound based on a latent variable, and to evaluate the generated information regarding chemical compound based on desired characteristics, wherein generating the information regarding chemical compound is restricted by the desired characteristics.

Abstract: The disclosure relates to data processing methods, computer readable hardware storage devices, and systems for correlating data corresponding to levels of biomarkers with various breast diseases.

Abstract: A film-forming apparatus is connected to a carbon steel cleanup system pipe of a BWR plant. Formic acid and hydrogen peroxide are injected into the circulation pipe of the film-forming apparatus. An iron elution accelerator aqueous solution containing 3000 ppm of formic acid and 1500 ppm of hydrogen peroxide is brought into contact with the inner surface of the cleanup system pipe, and Fe2+ is eluted from the cleanup system pipe by formic acid, and hydroxyl radicals generated from hydrogen peroxide. The film-forming aqueous solution produced from the iron elution accelerator aqueous solution by injecting the nickel formate aqueous solution is brought into contact with the inner surface of the cleanup system pipe, and the Ni ions incorporated into the inner surface by the substitution reaction are reduced by the electrons generated at the time of elution of Fe2+ to form a Ni metal film on the inner surface thereof.

Abstract: Provided are a training device, a disease affection determination device, a machine learning method, and a program that are applicable to various living organisms other than humans without performing time-consuming mapping. The present disclosure provides a machine learning unit that trains a model for a predetermined disease using, as an input, a training feature vector based on an appearance frequency of a plurality of types of substrings in a base sequence obtained from a training sample collected from a learning subject and, as an output, label information indicating whether the learning subject is a subject affected by the predetermined disease or a subject not affected by the predetermined disease.

Abstract: A chemical decontamination method capable of improving the decontamination efficiency of chemical decontamination of a steam dryer in the RPV is provided. In particular, the decontamination method includes feeding a chemical decontamination aqueous solution into a reactor pressure vessel in which a steam dryer is arranged, and after chemical decontamination of the steam dryer, the water level of the chemical decontamination aqueous solution existing in the reactor pressure vessel is lowered to a first water level below the lower end of the steam dryer.

Abstract: Provided are a chemical decontamination method and a chemical decontamination apparatus capable of preventing deterioration of a metal ion exchange resin and performing decontamination at a low cost in a short time. The chemical decontamination method of the invention includes: a reduction decontamination step of supplying a reduction decontamination solution to a decontamination target portion and performing reduction decontamination on a surface of a member constituting the decontamination target portion; a hydrogen peroxide decomposition step of decomposing hydrogen peroxide contained in the reduction decontamination solution after the reduction decontamination step; and a metal ion removing step of removing a metal ion contained in the reduction decontamination solution after the hydrogen peroxide decomposition step.

Abstract: A computer system for generating information regarding chemical compound includes one or more memories and one or more processors configured to generate information regarding chemical compound based on a latent variable, and to evaluate the generated information regarding chemical compound based on desired characteristics, wherein generating the information regarding chemical compound is restricted by the desired characteristics.

Abstract: In various embodiments, the systems and methods described herein relate to generative models. The generative models may be trained using machine learning approaches, with training sets comprising chemical compounds and biological or chemical information that relate to the chemical compounds. Deep learning architectures may be used. In various embodiments, the generative models are used to generate chemical compounds that have desired characteristics, e.g. activity against a selected target. The generative models may be used to generate chemical compounds that satisfy multiple requirements.

Abstract: A film forming apparatus is connected to a carbon steel purification system piping of a BWR plant (S1). Formic acid (surface purification agent) is injected into a circulation piping of the film forming apparatus (S4). A surface purification agent aqueous solution containing 30000 ppm of formic acid is contacted with the inner surface of the purification system piping, and a large amount of Fe2+ is dissolved from the purification system piping, and a large amount of electrons are generated by this dissolution. Thereafter, a formic acid Ni aqueous solution is injected into the surface purification agent aqueous solution to produce a film forming aqueous solution (S5). The film forming aqueous solution storing the electrons is contacted with the inner surface of the purification system piping, and Ni ions incorporated into the inner surface are reduced by the electrons, and a Ni metal film is formed on the inner surface.

Abstract: An aqueous solution of alkali hexahydroxo platinate is produced. As a alkali hexahydroxo platinate, sodium hexahydroxoplatinate or potassium hexahydroxoplatinate is used. The aqueous solution of alkali hexahydroxo platinate is passed through a hydrogen form cation exchange resin layer in a cation exchange resin tower. The aqueous solution of alkali hexahydroxo platinate makes contact with the hydrogen form cation exchange resin of the hydrogen form cation exchange resin layer, thus a suspension of hexahydroxo platinic is generated. If gamma rays are irradiated to the suspension, a platinum oxide colloidal solution in which colloidal particles including a platinum dioxide, a platinum monoxide, and a platinum hydroxide exist is generated. In a platinum oxide colloidal solution, the content of impurities is little and a noble metal compound is dispersed stably in water.

Abstract: Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment is disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, and a model mixing module. The edge device analyzes collected data with a model for a first task, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group, transmits a request for local models to the heterogeneous group, and receives local models from the heterogeneous group. The edge device filters the local models by structure metadata, including second local models, which relate to a second task. The edge device performs a mix operation of the second local models to generate a mixed model which relates to the second task, and transmits the mixed model to the heterogeneous group.

Abstract: To enable disease affection determination by using a neural network to perform learning using data of the expression levels of biomarkers, and to enable extraction of a feature biomarker for a disease by the neural network.

Abstract: Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment is disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, and a model mixing module. The edge device analyzes collected data with a model for a first task, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group, transmits a request for local models to the heterogeneous group, and receives local models from the heterogeneous group. The edge device filters the local models by structure metadata, including second local models, which relate to a second task. The edge device performs a mix operation of the second local models to generate a mixed model which relates to the second task, and transmits the mixed model to the heterogeneous group.

Abstract: In an electrodeposition treatment of an iron-group metal ion-containing liquid, without being influenced by the properties of the iron-group metal ion-containing liquid, iron-group metal ions are efficiently removed from the liquid by precipitation. An anode chamber 2A provided with an anode 2 and a cathode chamber 3A provided with a cathode 3 are separated from each other by a cation exchange membrane 5, an iron-group metal ion-containing liquid is charged into the anode chamber 2A, a cathode liquid is charged into the cathode chamber 3A, and by applying the voltage between the anode 2 and the cathode 3, iron-group metal ions in the liquid in the anode chamber 2A are moved into the liquid in the cathode chamber 3A through the cation exchange membrane 5, so that an iron-group metal is precipitated on the cathode 3.

Abstract: A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.

Abstract: A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.

Abstract: A method in which an anode chamber and a cathode chamber are separated by a cation exchange membrane, an acid solution containing metal ions is introduced into the anode chamber, a cathode solution is introduced into the cathode chamber, and a current is applied across the anode and the cathode, whereby the metal ions in the solution in the anode chamber pass through the cation exchange membrane, move into the cathode solution, and precipitate as metal onto the cathode, wherein there are minimal instances where electrodeposition is impossible or the electrodeposition rate decreases. Pre-adding a salt of the acid contained in the acid solution makes it possible to suppress concentration-diffusion of the acid from the acid solution. Adding a salt of the acid into the cathode chamber makes it possible to reduce the impressed voltage, reduce the amount of hydrogen generated on the cathode, and reduce the amount of power.

Abstract: An aqueous solution of alkali hexahydroxo platinate is produced. As a alkali hexahydroxo platinate, sodium hexahydroxoplatinate or potassium hexahydroxoplatinate is used. The aqueous solution of alkali hexahydroxo platinate is passed through a hydrogen form cation exchange resin layer in a cation exchange resin tower. The aqueous solution of alkali hexahydroxo platinate makes contact with the hydrogen form cation exchange resin of the hydrogen form cation exchange resin layer, thus a suspension of hexahydroxo platinic is generated. If gamma rays are irradiated to the suspension, a platinum oxide colloidal solution in which colloidal particles including a platinum dioxide, a platinum monoxide, and a platinum hydroxide exist is generated. In a platinum oxide colloidal solution, the content of impurities is little and a noble metal compound is dispersed stably in water.