Response Body

{
  "relations": [
    {
      "type": "memberOf",
      "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
      "score": 0.353495,
      "arguments": [
        {
          "text": "Patients",
          "entities": [
            {
              "type": "Person",
              "text": "Patients"
            }
          ]
        },
        {
          "text": "Classify Liver Cancer",
          "entities": [
            {
              "type": "Organization",
              "text": "Classify Liver Cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "educatedAt",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.284405,
      "arguments": [
        {
          "text": "Tom Wenska",
          "entities": [
            {
              "type": "Person",
              "text": "Tom Wenska2"
            }
          ]
        },
        {
          "text": "University of Hawaii",
          "entities": [
            {
              "type": "Organization",
              "text": "University of Hawaii"
            }
          ]
        }
      ]
    },
    {
      "type": "partOf",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.463644,
      "arguments": [
        {
          "text": "University of Hawaii",
          "entities": [
            {
              "type": "Organization",
              "text": "University of Hawaii"
            }
          ]
        },
        {
          "text": "Cancer Research Center",
          "entities": [
            {
              "type": "Organization",
              "text": "Cancer Research Center"
            }
          ]
        }
      ]
    },
    {
      "type": "basedIn",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.695919,
      "arguments": [
        {
          "text": "University of Hawaii",
          "entities": [
            {
              "type": "Organization",
              "text": "University of Hawaii"
            }
          ]
        },
        {
          "text": "Manoa",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "Manoa"
            }
          ]
        }
      ]
    },
    {
      "type": "locatedAt",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.539062,
      "arguments": [
        {
          "text": "Manoa",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "Manoa"
            }
          ]
        },
        {
          "text": "USA",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "USA"
            }
          ]
        }
      ]
    },
    {
      "type": "agentOf",
      "sentence": "We vectorize the output of the wavelet and construct a new matrix by replacing each column of the original data matrix with the vectorized form of the wavelet coefficients.",
      "score": 0.55659,
      "arguments": [
        {
          "text": "We",
          "entities": [
            {
              "type": "Organization",
              "text": "We"
            }
          ]
        },
        {
          "text": "replacing",
          "entities": [
            {
              "type": "EventPersonnel",
              "text": "replacing"
            }
          ]
        }
      ]
    },
    {
      "type": "agentOf",
      "sentence": "We vectorize the output of the wavelet and construct a new matrix by replacing each column of the original data matrix with the vectorized form of the wavelet coefficients.",
      "score": 0.581557,
      "arguments": [
        {
          "text": "matrix",
          "entities": [
            {
              "type": "Person",
              "text": "matrix"
            }
          ]
        },
        {
          "text": "replacing",
          "entities": [
            {
              "type": "EventPersonnel",
              "text": "replacing"
            }
          ]
        }
      ]
    },
    {
      "type": "hasAttribute",
      "sentence": "It is shown that the expansion and compression of data leads to a better neural network model to classify the liver cancer patients.",
      "score": 0.90168,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "liver cancer",
          "entities": [
            {
              "type": "HealthCondition",
              "text": "liver cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "residesIn",
      "sentence": "In Section IIA, the survival time analysis is used to classify the patients.",
      "score": 0.378734,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "Section IIA",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "Section IIA"
            }
          ]
        }
      ]
    },
    {
      "type": "residesIn",
      "sentence": "In Section IIC, a neural network model is trained to classify the patients.",
      "score": 0.355952,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "Section IIC",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "Section IIC"
            }
          ]
        }
      ]
    },
    {
      "type": "agentOf",
      "sentence": "We describe how the parameters of the neural network model are optimized.",
      "score": 0.964451,
      "arguments": [
        {
          "text": "We",
          "entities": [
            {
              "type": "Organization",
              "text": "We"
            }
          ]
        },
        {
          "text": "describe",
          "entities": [
            {
              "type": "EventCommunication",
              "text": "describe"
            }
          ]
        }
      ]
    },
    {
      "type": "productOf",
      "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
      "score": 0.717205,
      "arguments": [
        {
          "text": "Data\nExpansion",
          "entities": [
            {
              "type": "Product",
              "text": "Data\nExpansion"
            }
          ]
        },
        {
          "text": "Classify Liver Cancer",
          "entities": [
            {
              "type": "Organization",
              "text": "Classify Liver Cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "basedIn",
      "sentence": "In Section II-D, we show the numerical results obtained through simulation evaluations.",
      "score": 0.55049,
      "arguments": [
        {
          "text": "we",
          "entities": [
            {
              "type": "Organization",
              "text": "We"
            }
          ]
        },
        {
          "text": "Section II-D",
          "entities": [
            {
              "type": "GeopoliticalEntity",
              "text": "Section II-D"
            }
          ]
        }
      ]
    },
    {
      "type": "hasAttribute",
      "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
      "score": 0.605721,
      "arguments": [
        {
          "text": "We",
          "entities": [
            {
              "type": "Person",
              "text": "We"
            }
          ]
        },
        {
          "text": "liver cancer",
          "entities": [
            {
              "type": "HealthCondition",
              "text": "liver cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "hasAttribute",
      "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
      "score": 0.898158,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "liver cancer",
          "entities": [
            {
              "type": "HealthCondition",
              "text": "liver cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "memberOf",
      "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
      "score": 0.25856,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "groups",
          "entities": [
            {
              "type": "Organization",
              "text": "groups"
            }
          ]
        }
      ]
    },
    {
      "type": "hasAttribute",
      "sentence": "Then the data is used to train a neural network model that enables us to classify cancer patients into two different classes of high-risk and low-risk patients.",
      "score": 0.922835,
      "arguments": [
        {
          "text": "patients",
          "entities": [
            {
              "type": "Person",
              "text": "patients"
            }
          ]
        },
        {
          "text": "cancer",
          "entities": [
            {
              "type": "HealthCondition",
              "text": "liver cancer"
            }
          ]
        }
      ]
    },
    {
      "type": "employedBy",
      "sentence": "Neural network models are not computationally effective for big data sets.",
      "score": 0.533977,
      "arguments": [
        {
          "text": "models",
          "entities": [
            {
              "type": "Person",
              "text": "authors"
            }
          ]
        },
        {
          "text": "network",
          "entities": [
            {
              "type": "Organization",
              "text": "Neural Network Model"
            }
          ]
        }
      ]
    },
    {
      "type": "employedBy",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.738014,
      "arguments": [
        {
          "text": "Gordon Okimoto",
          "entities": [
            {
              "type": "Person",
              "text": "Gordon Okimoto2\nAbstract"
            }
          ]
        },
        {
          "text": "USA azeinalz@nd.edu\n2",
          "entities": [
            {
              "type": "Organization",
              "text": "USA azeinalz@nd.edu\n2"
            }
          ]
        }
      ]
    },
    {
      "type": "employedBy",
      "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
      "score": 0.528551,
      "arguments": [
        {
          "text": "Tom Wenska",
          "entities": [
            {
              "type": "Person",
              "text": "Tom Wenska2"
            }
          ]
        },
        {
          "text": "Cancer Research Center",
          "entities": [
            {
              "type": "Organization",
              "text": "Cancer Research Center"
            }
          ]
        }
      ]
    }
  ],
  "language": "en"
}