Patents by Inventor Zhiping Lin
Zhiping Lin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8951193Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: GrantFiled: March 6, 2014Date of Patent: February 10, 2015Assignees: Singapore Health Services Pte Ltd., Nanyang Technological UniversityInventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Patent number: 8932220Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: GrantFiled: March 6, 2014Date of Patent: January 13, 2015Assignees: Singapore Health Services Pte Ltd., Nanyang Technological UniversityInventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Patent number: 8895805Abstract: A method for improving insect resistance of plants, in which dsRNA of insect's gene is expressed in plants by using transgenic technique, and then the interfering RNAs are formed in the plants. The interfering RNAs then enter into insects' bodies after being ingested by the insect that eats the plant, and conduct RNA interference against the target gene, thereby expression of the target gene is suppressed by RNA interference. A new plant-mediated method for improving insect resistance by suppressing the growth of insects by RNA interference mechanism.Type: GrantFiled: December 4, 2007Date of Patent: November 25, 2014Assignee: Shanghai Institutes for Biological Sciences, Chinese Academy of SciencesInventors: Xiaoya Chen, Yingbo Mao, Zhiping Lin, Lingjian Wang
-
Publication number: 20140257063Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: ApplicationFiled: March 6, 2014Publication date: September 11, 2014Applicants: NANYANG TECHNOLOGICAL UNIVERSITY, SINGAPORE HEALTH SERVICES PTE LTD.Inventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Publication number: 20140187988Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: ApplicationFiled: March 6, 2014Publication date: July 3, 2014Applicants: NANYANG TECHNOLOGICAL UNIVERSITY, SINGAPORE HEALTH SERVICES PTE LTD.Inventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Patent number: 8668644Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: GrantFiled: April 23, 2013Date of Patent: March 11, 2014Assignees: Singapore Health Services Pte Ltd., Nanyang Technological UniversityInventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Publication number: 20130237776Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.Type: ApplicationFiled: April 23, 2013Publication date: September 12, 2013Applicants: NANYANG TECHNOLOGICAL UNIVERSITY, SINGAPORE HEALTH SERVICES PTE LTD.Inventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Publication number: 20110224565Abstract: According to embodiments of the invention, there is provided a method of producing an artificial neural network capable of predicting the survivability of a patient, the method including: storing in an electronic database patient health data, the patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron of the plurality of artificial neurons is adjusted in response to respective first, second and third parameters of different seType: ApplicationFiled: March 14, 2011Publication date: September 15, 2011Applicants: SINGAPORE HEALTH SERVICES PTE LTD., NANYANG TECHNOLOGICAL UNIVERSITYInventors: Marcus Eng Hock Ong, Zhiping Lin, Wee Ser, Guangbin Huang
-
Publication number: 20100050294Abstract: A method for improving insect resistance of plants, in which dsRNA of insect's gene is expressed in plants by using transgenic technique, and then the interfering RNAs are formed in the plants. The interfering RNAs then enter into insects' bodies after being ingested by the insect that eats the plant, and conduct RNA interference against the target gene, thereby expression of the target gene is suppressed by RNA interference. A new plant-mediated method for improving insect resistance by suppressing the growth of insects by RNA interference mechanism.Type: ApplicationFiled: December 4, 2007Publication date: February 25, 2010Inventors: Xiaoya Chen, Yingbo Mao, Zhiping Lin, Lingjian Wang
-
Publication number: 20090243530Abstract: An apparatus that provides electrical power for the operation of analog motors or decoder-equipped motors, said apparatus comprising: e) a power source having variable voltage output for operating analog motors and/or fixed voltage output for operating decoder-equipped motors; f) a circuit for changing the output of the power source from variable voltage output to fixed voltage output and from a fixed voltage output to a variable voltage output; g) a means to vary the analog voltage output; and h) a switch to actuate the circuit and thus the change from a variable voltage output to a fixed voltage output and from fixed voltage output to variable voltage output.Type: ApplicationFiled: March 28, 2008Publication date: October 1, 2009Inventors: Zhiping Lin, Frank Ritota
-
Publication number: 20080023593Abstract: A method, apparatus and system for AC or DC track powered model trains which increases the number of remote control functions available to the powered engines via an on-board sound decoder module. The functions include sound functions, including bell, whistle, brakes, announcements, and the like, and any other functions programmed into the on-board sound decoder module. The invention is compatible with traditional AC, DC, and DCC systems and allows the hobbyist to use a wireless controller to operate the engines and associated functions in a remote fashion.Type: ApplicationFiled: June 15, 2007Publication date: January 31, 2008Inventors: Frank Ritota, Zhiping Lin
-
Patent number: 6218808Abstract: An apparatus and method for fast battery charging are provided. A fast battery charger applies high charging current to a battery to minimize charging time. Micropeak detection of the battery voltage prevents overcharging of the battery cells, thereby preventing degradation of battery capacity over time. Noise reduction throughout the system as well as improved detection resolution allows for micropeak detection. A linear power supply eliminates switch noise. The sampling frequency is synchronized with the power supply, eliminating error due to power supply variation. Sleeping sampling is performed to overcome noise due to operation of the CPU. Improved measurement resolution is obtained via a 10-bit analog to digital converter. A subtraction technique maintains the high measurement resolution.Type: GrantFiled: March 24, 2000Date of Patent: April 17, 2001Assignee: Model Rectifier CorporationInventor: Zhiping Lin
-
Patent number: 5999863Abstract: The present invention relates to a DC power pack integrated with a micro-controller embedded controller for setting various voltages to accommodate different trains run on a track system. Micro-controller embedded controller (MECC) contains memory for pre-stored information and variable or changing information relating to the operation of the train system and related voltage and waveform requirements. Storage of variable or changing information can be in non-volatile memory or volatile memory with battery back-up. Throttle setting, braking and acceleration are controlled with the MECC connected to a user interface for selecting a number of possible values to increase the realism of the railroad operation. The railroader is capable of setting acceleration and deceleration times. Alternate embodiments provide for uploading/downloading data and information from the present invention to update the variable information pertaining to the operation of various manufactures trains and their operation set points.Type: GrantFiled: October 31, 1997Date of Patent: December 7, 1999Assignee: Model Rectifier CorporationInventor: Zhiping Lin