449results about How to "Lose weight" patented technology

The invention relates to a weight-losing enzyme and a preparation method thereof, and belongs to the technical field of biology, and the weight-losing enzyme comprises a fruit enzyme, a vegetable enzyme, a seed enzyme and a lotus leaf extract; the fruit enzyme is obtained by performing enzymolysis on mixed fruit pulp of apples, lemons, grapefruits and haws through pectinase, performing enzymolysis through pepsase and performing co-fermentation through bifidobacterium longum and lactobacillus acidophilus; the vegetable enzyme is obtained by performing enzymolysis on mixed vegetable pulp of wax gourd pulp, celery and spinach through pectinase, performing enzymolysis through pepsin and performing fermentation through lactobacillus plantarum and bifidobacterium adolescentis; the seed enzyme is obtained by carrying out trypsin enzymolysis on mixed powder of semen raphani and phaseolus calcaratus, then carrying out nattokinase enzymolysis and then fermenting with bifidobacterium breve; the lotus leaf extract is obtained by sequentially carrying out enzymolysis on lotus leaves through hemicellulase, snail protease and nattokinase. All the components are matched for use, so that the weight-losing food has the effects of promoting digestion, inhibiting fat absorption, regulating intestinal flora, promoting metabolism and the like, and has a good weight-losing effect.

The invention discloses a photovoltaic module, a preparation method and a welding tool, and relates to the technical field of photovoltaic modules. The photovoltaic module comprises one or more battery strings, each battery string comprises a plurality of battery pieces, a plurality of high-temperature welding strips and a plurality of low-temperature welding strips, and the high-temperature welding strips and the low-temperature welding strips are connected with the battery pieces in series. Each battery piece is provided with a plurality of first main grids; each high-temperature welding strip is connected in series with two corresponding first main grids of two adjacent battery pieces; and each low-temperature welding strip is arranged between the two adjacent first main grids on the battery pieces and is connected with the two adjacent battery pieces in series. According to the embodiment, the high-temperature welding strip and the low-temperature welding strip are arranged in the photovoltaic module at the same time, and part of the main grids in the battery piece are reserved, so that the purposes of reducing the silver paste cost and the gram weight of an adhesive film can be achieved, and the problem that the photovoltaic module is prone to failure in the outdoor long-term operation process is solved.

The invention belongs to the technical field of mariculture, and particularly relates to a flexible deep sea truss aquaculture net cage which comprises a flexible net cage system, a stock bin barrel system is arranged in the middle of the flexible net cage system, and an overwater suspension corridor assembly is arranged between the top end of the flexible net cage system and the top end of the stock bin barrel system. An anchor cable system is arranged on the outer side of the circumference of the flexible net cage system. By designing the flexible net cage system, the weight of the culture net cage is increased by filling viscoplastic filling materials through the bottom annular thick supporting pipes and the stand columns, the gravity center of the net cage is reduced, and the safety of the culture net cage in the putting process and the stability in actual operation are improved; other supporting pipes, supporting pieces, stand columns in the stock bin barrel system and transverse annular supporting pipes are filled with seawater, net cage throwing is assisted, and balance weight is simple; due to the integral structural design, the net cage has seawater corrosion resistance, is firm in structure, can bear the impact of large waves and seawater, has certain water permeability and can keep the circulation of seawater.

The invention provides a pipeline defect assessment method and system based on multi-source data fusion, and the method comprises the following steps: collecting the data of the operation state of a pipeline body through a related collection device, and marking the state and fault type of the pipeline, so as to construct a training set and a test set; and preprocessing the static data of the pipeline, wherein the preprocessing comprises data cleaning, standardization and feature extraction. And optimizing the extreme learning machine by using a bird flock algorithm, analyzing static data and evaluating pipeline defects. Preprocessing the image data of the pipeline body, wherein the preprocessing comprises image conversion, enhancement and denoising; and evaluating the circumferential weld defect based on the pre-trained VGG16 model. And performing decision-level fusion on a defect evaluation conclusion obtained by static data analysis and circumferential weld image analysis by using a D-S evidence reasoning algorithm to obtain a final evaluation result. The method effectively improves the accuracy and reliability of pipeline defect evaluation, and has wide application prospects and important practical value.

The invention discloses an unmanned aerial vehicle target detection method based on an improved YOLOv5 algorithm, and belongs to the technical field of unmanned aerial vehicle target detection. According to the unmanned aerial vehicle target detection method, through the improvement of respectively calculating anchor frame parameters on feature maps with different scales, the detection capability of a model on targets with different scales is improved, and the detection efficiency is improved. And especially for a small target and a large target, more accurate positioning can be realized. And meanwhile, the generalization ability of the model in a complex scene is enhanced, and diversified target distribution can be better adapted. The calculation process of the anchor frame parameters is optimized, the workload of manually adjusting the anchor frame parameters is reduced, and the automation degree of the model is improved. Through multi-scale anchor frame parameter fusion, the precision of the detection frame is improved, and the overall performance of unmanned aerial vehicle target detection is further improved; and meanwhile, the FPN and PAN structures of the Neck part effectively fuse the characteristics of different scales, so that the target positioning and identification capability of the network is improved, and the detection precision is improved.

The invention discloses a multi-head self-attention mechanism-based disease and insect pest identification method for an improved residual network. The method comprises the following steps of: acquiring data; preprocessing the data; a multi-head self-attention mechanism is added behind the residual network, and an improved residual network model is formed; the trained model is evaluated; the trained weight file is transferred into the raspberry Pi, and the raspberry Pi is connected with a camera, so that the plant diseases and insect pests of the trees can be detected in real time. According to the method, a multi-head self-attention mechanism is added on the basis of a ResNet18 network structure, projection matrixes of different queries, keys and values are used each time to generate different attention sub-spaces, and finally outputs of all the sub-spaces are spliced together to form final output, so that the weight of key feature information is enhanced, and the recognition precision of the model is further improved. The method is used for preventing and treating forestry diseases and insect pests, improves forestry income and has wide research and market application prospects.

The invention relates to the technical field of agricultural machinery, in particular to a multifunctional fruit huller. Comprising a case, and an eccentric rolling and screening device, a spiral screening and conveying device, a drying device and a collecting device which are mounted in the case from top to bottom; the eccentric rolling and screening device is provided with an eccentric rolling roller and a screening barrel and is used for rolling and screening fruits, then the fruits are conveyed to the drying device through the spiral screening and conveying device, and the drying device is used for drying the seeds and conveying the seeds into the collecting device; the motor and the transmission device are installed in the machine box, and the motor drives the eccentric rolling and screening device and the spiral screening and conveying device to operate through the transmission device. The device can be conveniently carried to mountainous areas where fruit trees live, fruits can be hulled on site after being picked, transportation is convenient, and the hulled seeds can be dried.

The invention relates to application of mouse combined lactobacillus. According to the application disclosed by the invention, the lactobacillus murins DSM 28683 can be applied to the preparation of a product for treating type 2 diabetes mellitus or a product for reducing body fat. A T2D mouse is subjected to intragastric administration by using the Ligilbacillus murins DSM 28683, and it is found that the Ligilbacillus murins DSM 28683 can significantly improve metabolism of the T2D mouse, effectively improve insulin sensitivity of the T2D mouse, reduce body weight and improve fatty liver, and has a good application prospect in treatment of type 2 diabetes mellitus.

The invention relates to the technical field of photovoltaic inverters, in particular to a photovoltaic inverter controller parameter identification method and system, and the method comprises the steps: building a mathematical model of a photovoltaic inverter controller, and determining controller parameters needing to be identified; the mathematical model is converted into a difference equation through transformation decoupling operation; the input and output quantity of an inverter controller is obtained in real time to serve as the input quantity of an identification system, and the preset performance index minimization serves as the optimal adaptive value estimation of an optimization algorithm; and stopping iteration when the parameters of the controller to be identified reach preset precision, and outputting estimated values of the parameters of the controller. The method has the advantages that the optimal solution is found through the idea of minimizing the residual module value, the randomness of identifying the parameters of the controller is greatly reduced, the accuracy of the identification result is improved, online identification and synchronous identification of all the parameters can be achieved, and step-by-step identification of all the parameters is avoided.

The invention relates to a foam concrete light-weight embankment capable of alternately maintaining traffic by lifting a longitudinal slope during reconstruction and expansion of a road, which adopts foam concrete to construct and expand the embankment and to lift the embankment by the longitudinal slope, so that the dead weight of the embankment is reduced, the settlement amount of a new roadbed is reduced, the differential settlement between the new roadbed and the old roadbed is reduced, and the later maintenance cost is reduced; during foam concrete construction, a plurality of reinforcing mesh anchoring measures are set layer by layer, so that the stability of the reinforcing meshes in the foam concrete pouring process is improved, and the construction quality of the light embankment is further improved; the new roadbed and the old roadbed are anchored through the reinforcing mesh hanging type supports, the Z-shaped supports and the claw-shaped supports, and the integrity between the original roadbed and the widened longitudinal slope lifting embankment is improved.

The invention discloses an application of probiotics Blauria winteriae in the preparation of a medicine or food for improving or treating the inflammatory bowel disease of children, and relates to the field of medicines or foods for improving or treating the inflammatory bowel disease of children. According to the invention, the probiotic Blauria wexlerae is used as an effective component to be prepared into medically and food acceptable dosage forms, so that the children inflammatory bowel disease can be obviously improved or treated, and the application value of the probiotic is improved.

The invention discloses a multi-quality skeleton sequence action recognition method based on course learning, and the method comprises the steps: collecting a large number of videos which comprise human body actions and are provided with action category labels, and dividing the videos into a training set and a test set; extracting coordinate information of human body joint points of each frame of image in the video, and generating a continuous skeleton sequence; performing data enhancement on the skeleton sequence; according to the method, a neural network model for action recognition is constructed, then data of a training set is input into the neural network model in batches, the neural network model is trained until a preset round number is reached, in the process of training the model, prior knowledge and posterior knowledge are dynamically adjusted to evaluate sample difficulty, and in addition, the training efficiency is improved. The concept of learning the center of gravity is introduced, and the learning center of gravity gradually transits from an early simple sample to a difficult sample in different stages. The method provided by the invention can improve the recognition efficiency and the recognition accuracy.

The invention discloses a satiety sugar-controlling fat-reducing composition and a preparation method and application thereof, the satiety sugar-controlling fat-reducing composition comprises hydrogel particles, a white kidney bean extract, a mulberry leaf extract, alpha-lipoic acid, L-carnitine, a lotus leaf extract, medium chain triglyceride, polyethylene glycol and sorbitol, and the composition is a tablet. The components are matched with one another to effectively adjust the leptin level, improve appetite, increase energy consumption, adjust the fat metabolism process, reduce fat accumulation, improve fat consumption, inhibit the activity of alpha-amylase, reduce the conversion of carbohydrates into fat, block heat and fat intake, promote gastrointestinal motility and enhance the immunity of the human body. The effects of remarkably reducing the fat content and the body weight are achieved.

The invention relates to the technical field of urban pipe network detection, in particular to a pipe diameter self-adaptive pipeline interior detection robot which comprises a main machine box, a sliding rod, a rotary drum, a transmission assembly A, a driving assembly, an annular mounting shell, a transmission assembly B and an oil pumping mechanism. The two ends of the mainframe box are each connected with a guide head, an annular oil cavity is formed in each guide head, and a guide pipe is arranged on each guide head. And the other end of the sliding rod is connected with the roller. The rotary drums are inserted into the guide pipes on the corresponding sides respectively, and spline shafts are arranged in the rotary drums and inserted into the sliding rods. The transmission assembly A is in transmission connection with the spline shaft and the rotating shaft. The annular mounting shell sleeve is connected with the mainframe box, and an X-ray flaw detector is arranged on the annular mounting shell. The transmission assembly B is in transmission connection with the annular mounting shell and the driving assembly. The oil pumping mechanism is communicated with the annular oil cavities in the guide heads on the two sides. The device is high in detection efficiency and low in energy consumption, and synchronous adjustment of the distance between the rollers on the two guide heads is achieved through one oil pumping mechanism.

The invention discloses a training method of a small sample image detection model and an image detection method, and belongs to the technical field of deep learning, and the base class training method comprises the steps: training an original image detection model through employing a support image set, a marked query image, and each target class in a class until the total loss is converged, obtaining a base class image detection model; support features and semantics of a target category are embedded and input into a variational auto-encoder, and compared with support features and reconstruction features of a specific category, potential vectors in a VAE intermediate process contain general features of more types of prototypes; potential vectors containing semantic information are sampled from the distribution, and feature aggregation is carried out on the potential vectors and query features, so that the estimated new class center is closer to a real class center; in addition, the reconstruction loss, the KL divergence, the classification loss, the regression loss and the semantic consistency loss in the VAE form the total loss, so that the training precision can be greatly improved.

The invention provides a cellulose composite carbon aerogel and a preparation method thereof, and the cellulose composite carbon aerogel is prepared by taking cellulose nanofibers and carbon nanotubes as raw materials, mixing and dispersing the raw materials through dispersoid, and then preparing cellulose nanofiber / carbon nanotube composite carbon aerogel through bidirectional freezing, freeze drying and high-temperature carbonization. The invention also provides an application of the cellulose composite carbon aerogel in the aspect of a battery electrode, and the cellulose composite carbon aerogel has an ultra-large specific surface area and an excellent compression ratio under ultra-low density, and shows super-hydrophilicity, high electrochemical activity, good compression resilience, good structural stability and certain mechanical strength; and the method can be used for various electrochemistry-based water-based flow batteries. The invention solves the technical problem that the existing cellulose carbon aerogel is poor in compressibility and mechanical strength, and belongs to the technical field of batteries.

The invention provides an emergency rescue unmanned aerial vehicle, and belongs to the technical field of unmanned aerial vehicles. Comprising a main body and two sets of wing frames, the two sets of wing frames are fixedly connected to the outer wall of the main body, adjusting holes are formed in the tops of the wing frames, the supporting mechanism is arranged in the two sets of adjusting holes, the supporting mechanism comprises two sets of adjustable supporting legs, and the two sets of adjustable supporting legs are slidably connected into the two sets of adjusting holes respectively. The supporting mechanisms are used for supporting the main body, and the buffering mechanisms are arranged at the bottoms of the adjustable supporting legs. The unmanned aerial vehicle is buffered through the elastic force of a plurality of buffer springs during landing, and the phenomenon that in the landing process of the unmanned aerial vehicle carrying emergency rescue articles, the adjustable supporting legs are bent and deformed due to the fact that impact force is too large due to gravity superposition of the device and the emergency rescue articles is avoided; and the phenomenon that vibration force is transmitted into the main body to cause damage to elements in the main body is avoided, and the service life of the equipment is prolonged.

The utility model provides a roof photovoltaic assembly transportation device which comprises a carrying vehicle and a guide rail set used for bearing the carrying vehicle, and the guide rail set is arranged on a roof. The carrier comprises a bearing part for bearing the photovoltaic module and a guide wheel group arranged at the bottom of the bearing part, and the guide wheel group is matched with the guide rail group; the front end and / or the rear end of the bearing part are / is connected with a handle. According to the roof photovoltaic module transporting device, the guide rail set is arranged, and a foundation is laid for the carrying vehicle to move on a roof. By arranging the bearing piece, the carrying vehicle can bear the photovoltaic module; the guide wheel set is arranged at the bottom of the bearing part and matched with the guide rail set, so that the carrying vehicle can move on the roof along the guide rail set; the front end and / or the rear end of the bearing part are / is connected with the handle, so that a worker can conveniently push the carrier, and the photovoltaic module can be quickly transported to each assembly point along the guide rail group, so that the working efficiency can be improved, and the construction management difficulty and cost can be reduced. In addition, the photovoltaic module is carried through the carrying vehicle, so that the safety of the photovoltaic module and carrying personnel can be better guaranteed.

The present application provides a point cloud processing method, device, equipment and storage medium. The method includes: obtaining the current frame point cloud collected by the point cloud acquisition device and the global model; wherein the global model is obtained by fusion of the historical frame point cloud collected by the point cloud acquisition device; any three-dimensional point in the global model carries a weight, and the weight of any three-dimensional point represents the possibility that the three-dimensional point is a noise point or a target object; after projecting the current frame point cloud into the global model, projecting a number of rays between the projected current frame point cloud and the point cloud acquisition device to determine the target three-dimensional point in the global model passed by the ray; reducing the weight of the target three-dimensional point; if the reduced weight of the target three-dimensional point meets the noise deletion condition, delete the target three-dimensional point. Accurately delete noise points.

The invention discloses a book recommendation method and device for colleges and universities and a storage medium, and belongs to the technical field of education management, and the method comprises the following steps: obtaining information of students before entering a school, inputting the information into a pre-trained machine learning model, and obtaining initial book interest vectors of the students; generating a cumulative borrowing vector of students in school, and obtaining a cumulative borrowing vector of graduated students; similarity comparison is carried out, and a plurality of graduated students with the highest similarity are determined; performing weighted summation on the corresponding actual book interest vectors to obtain predicted book interest vectors of the school students after borrowing; performing weighted summation on the initial book interest vector and the predicted book interest vector to obtain a real-time book interest vector; and recommending the books to the students. According to the invention, book recommendation can be carried out based on the school book borrowing data sparsity condition, the characteristics of a college book system are met, and the real-time recommendation result is accurate.

The invention provides application of a traditional Chinese medicine composition in preparation of medicines for preventing and / or treating influenza A and related diseases thereof. The traditional Chinese medicine composition comprises the following components or is prepared from the following raw material medicines in parts by weight: 20-40 parts of gypsum, 10-30 parts of wild buckwheat rhizome, 10-30 parts of herba houttuyniae, 3-15 parts of roasted herba ephedrae, 3-15 parts of fried semen armeniacae amarae, 3-15 parts of bulbus fritillariae cirrhosae, 5-25 parts of herba ardisiae japonicae, 3-15 parts of folium eriobotryae, 3-15 parts of fried fructus perillae and 3-15 parts of roasted radix glycyrrhizae. The traditional Chinese medicine composition disclosed by the invention has a relatively good inhibition effect on influenza A viruses, is low in toxicity and high in safety, also has a good anti-influenza A virus infection effect, and can provide a basis for clinically treating pulmonary infection caused by the influenza A viruses.

The invention provides an elastic composite material and a preparation method thereof and a pants product, the elastic composite material comprises a first non-woven fabric, a second non-woven fabric and an adhesive elastic band arranged between the first non-woven fabric and the second non-woven fabric, the adhesive elastic band is an SEBS copolymer or contains an SEBS copolymer, and the adhesive elastic band is made of a thermoplastic elastomer. Wherein the adhesive elastic band imparts elasticity to the elastic composite material. The hot melt adhesive property and elasticity of the SEBS copolymer are combined, the inner layer non-woven fabric and the outer layer non-woven fabric of the waistline assembly are bonded together through online melting of the SEBS copolymer, stretchability and viscidity are provided at the same time, existing waistline rubber band and glue bonding is replaced, only the waistline non-woven fabric and the SEBS material are used for compounding, and in addition, the waistline elastic partition design is adopted, so that the elasticity of the waistline assembly is greatly improved. And the advantages of cost saving, air permeability, softness, wearing comfort improvement and the like are brought.

The invention discloses a main arch ring design method for rapid construction of a large-span cast-in-cantilever arch bridge. The main arch ring design method comprises the following steps: establishing a macroscopic finite element model according to arch bridge information; a local finite element model is established for the steel-concrete main arch ring, load simulation is conducted on the steel-concrete main arch ring, and arch ring information is determined; obtaining an anti-overturning coefficient of the arch bridge according to the macroscopic finite element model, and obtaining an anti-seismic property value of the arch bridge by utilizing anti-seismic simulation; acquiring disease early warning information according to the load simulation and the anti-seismic simulation, and implementing a disease early warning strategy; load simulation is conducted according to the steel-concrete main arch ring structure through the finite element model, stiffening connection steel plate information and steel hole information of the optimal arch ring strategy are obtained, the load bearing capacity, the anti-seismic performance and the anti-overturning performance of the arch bridge are improved, the self weight of the main arch ring is effectively reduced, arch ring steel bars are connected through the stiffening connection steel plates, and the safety of the arch bridge is improved. Factory-like rapid and high-precision installation of the bottom face is achieved, and the working efficiency and the engineering safety can be greatly improved through whole-section hoisting.

The invention relates to the field of sensor communication, in particular to an intelligent sensor communication method. The method comprises the following steps: acquiring a physical quantity signal in an environment by using an intelligent sensor, generating a corresponding time domain signal, and converting the time domain signal into a frequency domain signal; based on the frequency domain signal, using a dynamic frequency hopping and power consumption perception optimization algorithm to select an optimal frequency; based on the optimal frequency, performing data block coding by using a nonlinear multi-level frequency coding algorithm; and evaluating the path state and the channel performance by using a path optimization selection algorithm, and calculating to obtain the optimal transmission path of each data block. The problems of frequency band overlapping and interference in sensor data acquisition are solved; the problems of fluctuation and inconsistency of sensor signals caused by changes of environmental conditions, reduction of signal reliability due to interference among different frequency channels, signal distortion due to frequency band interference among different data blocks, and fluctuation of channel quality and bandwidth of different paths along with time are solved.

The invention discloses an electromagnetic wave rain attenuation model selection method based on a confidence interval upper bound, and belongs to the technical field of electromagnetic wave propagation loss. According to the method, an improved confidence interval upper bound reinforcement learning algorithm is adopted, an action space is defined as a plurality of different rain attenuation models, and the system can dynamically select an optimal model from a plurality of candidate models by inputting rainfall rate information; the reward function is based on an absolute error between a unit distance electromagnetic wave rain attenuation value predicted by each model and an actual observation value, the smaller the error is, the higher the reward is, otherwise, the lower the reward is. Through continuous iterative training, the method can adaptively select the rain attenuation model with the highest prediction precision in different environments, thereby improving the accuracy of electromagnetic wave propagation prediction.

The invention relates to the technical field of autoclave forming dies, and discloses a bullet train protection plate autoclave forming die which comprises a chassis and a bottom plate which are integrated, the bottom face of the chassis is of a grid structure, the top of the chassis is connected with the bottom plate through a supporting structure so that the bottom plate can be communicated with the outside, and a protection plate material containing groove is formed in the top face of the bottom plate. A plurality of through holes are formed in the side face of the chassis so that the through holes in the side face can communicate with the grid structure. Uniform distribution of heat is facilitated, stress concentration is reduced, the heating performance and the heat dissipation performance are improved, and sufficient heat stability and heat conduction coefficient are achieved, so that the production cost is reduced; through combination of a grid structure and a protection plate mold containing groove, the self weight is reduced so as to reduce the production and transportation cost, meanwhile, the strength and rigidity are kept, material use is optimized, reinforcing ribs are combined on the edge of the mold, stability and durability are improved, and fatigue and deformation risks are reduced; the net rack design facilitates heat dissipation, heat stability is improved, forming precision is ensured, and product defects are reduced.

The automatic compensating and avoiding device of the construction hoist comprises a mounting bracket, a hoist body is arranged on the mounting bracket, and the hoist body is connected with the mounting bracket in a matched mode; a traction device is arranged on the mounting bracket and is fixedly connected with the elevator body; a plurality of wind direction and wind speed detection sensors are arranged outside the mounting bracket; the elevator body is provided with a data analysis processor which is electrically connected with the wind direction detection sensor and is used for analyzing and processing detection data; a driving controller is arranged on one side of the data analysis processor, the driving controller is electrically connected with the data analysis processor, the driving controller is electrically connected with the traction device and the anti-falling safety device, and whether an output result analyzed by the data analysis processor belongs to a non-Gaussian turbulence excitation state or not is judged through the controller. And if yes, the operation state of the construction hoist is adjusted through the traction device and the anti-falling safety device. The invention aims to solve the problem of safe operation of the construction hoist during buffeting under the excitation of canyon wind non-Gaussian turbulent flow.

The invention relates to the field of food processing, and discloses a composite cream and a preparation method thereof, the composite cream comprises base oil, an emulsifier and a thickener; the base material oil comprises diglyceride and animal oil, and the weight ratio of the diglyceride to the animal oil is 1: (0.2-3); the diglyceride is a mixture of C12: 0, C14: 0, C16: 0, C18: 0 and C18: 1. The compound fat cream emulsion disclosed by the invention has excellent whipping performance and water-retaining property, has a finer taste and can meet the taste preference of people.

The invention relates to the field of medicines, in particular to a GLP-1 analogue fusion protein and application thereof. The GLP-1 analogue fusion protein is obtained by fusing GLP-1 at N ends of a heavy chain constant region and a light chain constant region of IgG4. A research result shows that the GLP-1 analogue fusion protein has an obvious effect of reducing the body weight of a mouse, the volume and the weight of the liver of the mouse are reduced, and the NAS score and the liver fatty degeneration are obviously improved. Therefore, the traditional Chinese medicine composition can be applied to medicines or products for slimming or treating fatty liver.