Abstract: An illegal call detection apparatus comprises a data collecting unit, a preprocessing unit, and a learning unit. The data collecting unit collects, from at least one of a subscriber terminal or a call exchanger, a raw packet generated by the subscriber terminal using a VoIP service, and collects, from the billing server, CDR data related to the raw packet. The preprocessing unit generates learning data by using service usage information extracted from the CDR data and service detailed information extracted from the raw packet, and generates a training image by converting the training data into an image according to a predetermined imaging rule. The learning unit extracts at least one or more features from the training image, and learns whether the training image is related to an illegal call by using the features, through an illegal call detection model.

Abstract: An illegal call detection apparatus comprises a data collecting unit, a preprocessing unit, and a learning unit. The data collecting unit collects, from at least one of a subscriber terminal or a call exchanger, a raw packet generated by the subscriber terminal using a VoIP service, and collects, from the billing server, CDR data related to the raw packet. The preprocessing unit generates learning data by using service usage information extracted from the CDR data and service detailed information extracted from the raw packet, and generates a training image by converting the training data into an image according to a predetermined imaging rule. The learning unit extracts at least one or more features from the training image, and learns whether the training image is related to an illegal call by using the features, through an illegal call detection model.

Abstract: A method of compressing sequence data in a text-based format, the method involving parsing text of the sequence data into a plurality of fields, identifying encoding algorithms that achieve greatest compression gains with respect to the plurality of fields based on collected statistics, and generating a bitstream, compressed from the sequence data, by encoding the sequence data using the identified encoding algorithms.

Abstract: Provided are methods and apparatuses for compressing genetic information, the methods and apparatuses obtaining read information about reads and alignment information about positions of the reads that are aligned to a reference sequence, and generating a compressed file comprising information about an address of a block corresponding to the aligned reads. Also, a method and apparatus for decompressing genetic information obtains a compressed file with respect to the genetic information, determines an address of a block corresponding to input gene search information, from the compressed file, and selectively decompresses genetic information corresponding to the determined address.

Abstract: An efficient and accurate method of identifying a target biomolecule in a sample by using target molecule-probe binding frequencies is disclosed.

Abstract: Provided are a method and apparatus for analyzing genetic information to acquire expression data of a subject with respect to gene expression patterns of genes included in a gene network and determine a genetic abnormality of the gene network included in the expression data of the subject by using a representative expression pattern estimated from a group of normal people.

Abstract: A method and apparatus for analyzing personalized multi-omics data are disclosed. The method includes acquiring a plurality of biological data groups from an individual's gene sample, estimating indices indicating a degree of genetic abnormalities for the biological data groups, and generating a combined index by merging the estimated indices.

Abstract: A method of recovering a nucleic acid sequence using a probe map includes: aligning a probe onto a target sequence based on a result in which the probe is hybridized to the target sequence; determining a representative value representing each aligned position of the probe; and recovering a base sequence of the target sequence by using a probe map to which the determined representative values and base sequence information of the probe are mapped.

Abstract: A method and apparatus for analyzing information about a gene network in which genes included in a genome of an individual are classified into a plurality of subgroups based on functional correlations between the genes is acquired, and subgroups corresponding to an action of at least one drug to be used are visualized.

Abstract: A method and apparatus for analyzing genetic information of abnormal tissue, the method and apparatus involving obtaining a first set of sequence data that includes one or more pieces of sequence data that are aligned in one or more single nucleotide polymorphism (SNP) sites from genetic samples of abnormal tissue; obtaining a second set of sequence data that includes one or more pieces of sequence data that are aligned in one or more SNP sites from genetic samples of normal tissue; analyzing, by a processing unit, a distribution of alleles in corresponding portions of the first set of sequence data and the second set of sequence data; and determining a contamination rate of a sample of a tissue by using a result of the analyzing.

Abstract: A method and apparatus for searching compressed nucleic acid sequences are disclosed. In the method, a reference sequence is compared with a subject sequence to be encoded, the subject sequence is compressed, an index is created with respect to the reference sequence and the compressed subject sequence, a position corresponding to a query is searched for in the compressed subject sequence using the index, a character found at the position within the compressed sequence is converted into a sequence, and the sequence is output as the response to the query.

Abstract: A method of compressing sequence data in a text-based format, the method involving parsing text of the sequence data into a plurality of fields, identifying encoding algorithms that achieve greatest compression gains with respect to the plurality of fields based on collected statistics, and generating a bitstream, compressed from the sequence data, by encoding the sequence data using the identified encoding algorithms.

Abstract: An efficient and accurate method of identifying a target biomolecule in a sample by using target molecule-probe binding frequencies is disclosed.

Abstract: A method and apparatus for monitoring a code to detect intrusion code is used to monitor target code to determine whether the target code is a resident code in a system or an intrusion code into the system. A first code pattern is extracted from the target code and a second code pattern is loaded from a storage unit, and a distance between the first code pattern and the second code pattern is calculated. The calculated distance is compared to a threshold to determine whether the target code is an intrusion code.

Abstract: A method of recovering a nucleic acid sequence using a probe map includes: aligning a probe onto a target sequence based on a result in which the probe is hybridized to the target sequence; determining a representative value representing each aligned position of the probe; and recovering a base sequence of the target sequence by using a probe map to which the determined representative values and base sequence information of the probe are mapped.

Abstract: A kit and method for predicting the sensitivity of gastric cancer patient to an anti-cancer agent are disclosed.

Abstract: A method and apparatus for searching compressed nucleic acid sequences are disclosed. In the method, a reference sequence is compared with a subject sequence to be encoded, the subject sequence is compressed, an index is created with respect to the reference sequence and the compressed subject sequence, a position corresponding to a query is searched for in the compressed subject sequence using the index, a character found at the position within the compressed sequence is converted into a sequence, and the sequence is output as the response to the query.

Abstract: Provided is a multiple single nucleotide polymorphism (SNP) for colorectal cancer diagnosis, a microarray and a kit including a polynucleotide having the SNP, and a method of diagnosing colorectal cancer using the SNP. Early diagnosis of incidence or possibility of colorectal cancer can be effectively performed by using the method.

Abstract: A method of designing probes for detecting a target sequence and a method of detecting the target sequence using the probes are provided. The method of designing probes for detecting target sequence includes: selecting an anchoring location in the target sequence; selecting a first probe designing region; selecting a matched probe; and selecting a mismatched probe.

Abstract: Provided is a polynucleotide for diagnosis or treatment of breast cancer, including at least 10 contiguous nucleotides of a nucleotide sequence selected from the group consisting of nucleotide sequences of SEQ ID No: 1 to SEQ ID No: 5 and comprising a nucleotide at 101st position of the nucleotide sequence, or a complementary polynucleotide thereof.