Gerald Cayabyab | Technological Institute Of The Philippines (original) (raw)

Uploads

Papers by Gerald Cayabyab

Proceedings of the 2019 2nd International Conference on Information Science and Systems, 2019

Every day, almost every Filipino citizen goes to a public market to purchase different agricultur... more Every day, almost every Filipino citizen goes to a public market to purchase different agricultural products for their daily food consumption. Some merchants and dealers increase the price of their products for their own sake. Many Filipino citizens earn a minimum wage to feed their family. Certain major problems existing in the majority of our public markets cover important aspects of market operations such as location, construction, sanitation, security /safety, market fee collection, and occupancy of stalls result in the gradual but progressive deterioration of the markets. This study focuses on the analysis, design, and whole development of the mobile application, Price Watch and implementation of Exponential Smoothing algorithm. This mobile application helps Filipino citizens be aware of the prices of commodities in the public market. The mobile application allows its users to see the prices of different products in the public market and show the graph so users will easily reco...

The development of an application that can help the thesis adviser and student construct and reco... more The development of an application that can help the thesis adviser and student construct and recommend thesis titles through the use of Natural Language Processing (NLP) was the primary objective of this study. Resembling the concept of Information Retrieval under Query-Focused Summarization, words except stop words from the related literature and studies of the thesis and its title were used as a training corpus while the words except stop words of chapters one (1), two (2) and three (3) of the thesis or merely the test document acts as the query in the corpus, where it retrieved its weight from both training and test records. The result showed that out of forty-five (45) thesis titles, twentyeight (28) different title formats were constructed by the thesis advisers with the support of the developed application. The advanced application obtained the accuracy score of 1.55 or “Accurate” and quality score of 4.06 or “Good” in fifteen (15) thesis titles. 

Proceedings of the 2018 International Conference on Information Science and System, 2018

In this paper, we developed a new mobile application designed to protect your images stored on yo... more In this paper, we developed a new mobile application designed to protect your images stored on your mobile phone using Advanced Encryption Standard algorithm to secure images by encrypting it and Least Significant Bit algorithm to process the encrypted image and embed it into another image. To achieve high level of encryption, a 256 bit length key of Advance Encryption Standard is used to maximize protection and Diffie-Hellman algorithm to secure the processed key to both parties without interference from outside. In steganography, the encrypted image will be invisible into the cover image in which potential hackers do not have any idea about the original image embedded inside of the cover image, and with this even if the hacker got the image it will still need the correct key to decrypt it or else the image will be deleted The study used Rapid Application Development Model as the project development methodology, which allows the preceding phase to iterate until the application is r...

Proceedings of the 2nd International Conference on Computing and Big Data - ICCBD 2019, 2019

The International Data Encryption Algorithm (IDEA) is one of an encryption algorithm that uses a ... more The International Data Encryption Algorithm (IDEA) is one of an encryption algorithm that uses a cyclic process in producing sub keys from secret key using its key schedule but generates large weak keys. GISKOP is a modified IDEA that uses the concept of serpent key scheduling operation to address the weak keys found on the original IDEA. Randomness test was used to identify the dependence and correlations between generated sub-keys of a key scheduling operation. Statistical evaluation was done to analyze and compare key distribution and exchange operations of the modified key scheduling operation. The GISKOP key scheduling operation obtained an increase of 8% randomness using frequency test in the sub-key independence level. Also, it was able to maintain its 100% randomness under the sub-key level independence. Thus, proving that each generated sub keys are not correlated with each other. With this, many attacks on systems that implement IDEA can be mitigated. Furthermore, the find...

Cryptography is a method of storing and transmitting data in a particular form. Only those for wh... more Cryptography is a method of storing and transmitting data in a particular form. Only those for whom it is intended can read, use it, and return it back to the original data by using various techniques. The International Data Encryption Algorithm "IDEA" is a block cipher that works with 64-bit plaintext block and ciphertext blocks and it has a 128-bit input key. This paper describe the designing and implementation of a modified key schedule operation of IDEA called GISKOP. It uses the same number of rounds and output transformation that operates using 128 bit user input plaintext and a modified way of key scheduling operation of 256 bit keys. The modified algorithm uses Serpent key scheduling operation to derive the different sub keys to be used in each rounds. The algorithm was implemented to provide better security on user's password within the Document Management System to protect user's data within the cloud database. It has gone through initial testing and eval...

Security assurance in any telecommunication lines is a necessity. It is everyone's desire to ... more Security assurance in any telecommunication lines is a necessity. It is everyone's desire to maintain secrecy of any information sent thru both unsecured and secured telecommunication lines. Short Message Service (SMS) has turned into an extension and has been an important part in the life of its user. Payment, mobile banking, important reminders such as stocks and news alerts, traffic updates, weather information and business related information are being catered thru SMS. Problems of privacy and imitations are the core issues dealt in the study. In order to prolong the secrecy of any information, an implementation of an improved cryptology scheme was designed. The study used a cascaded encryption process designed for sending SMS thru any communication line. The strength of the algorithm using the framework focused on designing a secured encryption process and adapting AES (Advance Encryption Standard) encryption with two more encryption layers. It discussed impact of the frame...

International Journal of Signal Processing Systems, Dec 1, 2016

The development of an application that can help the thesis adviser and student construct and reco... more The development of an application that can help the thesis adviser and student construct and recommend thesis titles through the use of Natural Language Processing (NLP) was the primary objective of this study. Resembling the concept of Information Retrieval under Query-Focused Summarization, words except stop words from the related literature and studies of the thesis and its title were used as a training corpus while the words except stop words of chapters one (1), two (2) and three (3) of the thesis or merely the test document acts as the query in the corpus, where it retrieved its weight from both training and test records. The result showed that out of forty-five (45) thesis titles, twentyeight (28) different title formats were constructed by the thesis advisers with the support of the developed application. The advanced application obtained the accuracy score of 1.55 or "Accurate" and quality score of 4.06 or "Good" in fifteen (15) thesis titles.

Proceedings of the 2017 International Conference on Computer Science and Artificial Intelligence - CSAI 2017

In this paper, we developed a new mobile application designed to serve as a color vision enhancem... more In this paper, we developed a new mobile application designed to serve as a color vision enhancement tool for individuals with color vision deficiency, or commonly known as color blindness. A person who suffers from Color Vision Deficiency (CVD) faces many complexities in everyday life in even the simplest activities due to having a narrower color spectrum which caused them to perceive colors with similar shades and intensity. Hence, to address this problem, a color vision enhancement method using LMS Daltonization Algorithm was utilized to transform or convert the color of images into a clearer and more recognizable colors to differentiate the colors of two unrelated areas. The application was also designed for a real-time image color processing function that minimizes color discrimination by changing the color for better representation. The application also provided an assessment to identify the user's colorblindness type using D-15 Color Arrangement Test. To validate the accuracy and correctness of information, selected doctors of Optometry and CVD users evaluated the mobile application.

International Journal for Research in Applied Science and Engineering Technology

This paper feature an efficient extraction and matching approach on eye with or without contact l... more This paper feature an efficient extraction and matching approach on eye with or without contact lens to innovate authentication process. The proposed feature extraction and matching approach is develop based on FGM (Feature Group Matching) which extract the key points and descriptor of each images using the two feature extraction algorithm which are SIFT (Scale-Invariant Feature Transform) and SURF(Speeded-Up Robust Features) and to match the key points and descriptors using FLANN based matcher. The major advantages of the developed approach are the simplicity and accuracy as compared to the prior extraction and matching approaches developed for contact lens detection images. The new used approach was tested in AMD Ryzen 5 2500U with 2GHz processor, 4GB Mobile RAM, dual graphic card and GPU rendering of RX 560 x with 5GB. The experimental results obtained from IIITD-Contact lens Iris Database and publicly available images and respectively achieved better performance in terms of simplicity and accuracy as compared to the previous proposed methods and Filipino Iris Database as an added contribution to the field of contact lens.

Proceedings of the 2019 2nd International Conference on Information Science and Systems, 2019

Every day, almost every Filipino citizen goes to a public market to purchase different agricultur... more Every day, almost every Filipino citizen goes to a public market to purchase different agricultural products for their daily food consumption. Some merchants and dealers increase the price of their products for their own sake. Many Filipino citizens earn a minimum wage to feed their family. Certain major problems existing in the majority of our public markets cover important aspects of market operations such as location, construction, sanitation, security /safety, market fee collection, and occupancy of stalls result in the gradual but progressive deterioration of the markets. This study focuses on the analysis, design, and whole development of the mobile application, Price Watch and implementation of Exponential Smoothing algorithm. This mobile application helps Filipino citizens be aware of the prices of commodities in the public market. The mobile application allows its users to see the prices of different products in the public market and show the graph so users will easily reco...

The development of an application that can help the thesis adviser and student construct and reco... more The development of an application that can help the thesis adviser and student construct and recommend thesis titles through the use of Natural Language Processing (NLP) was the primary objective of this study. Resembling the concept of Information Retrieval under Query-Focused Summarization, words except stop words from the related literature and studies of the thesis and its title were used as a training corpus while the words except stop words of chapters one (1), two (2) and three (3) of the thesis or merely the test document acts as the query in the corpus, where it retrieved its weight from both training and test records. The result showed that out of forty-five (45) thesis titles, twentyeight (28) different title formats were constructed by the thesis advisers with the support of the developed application. The advanced application obtained the accuracy score of 1.55 or “Accurate” and quality score of 4.06 or “Good” in fifteen (15) thesis titles. 

Proceedings of the 2018 International Conference on Information Science and System, 2018

In this paper, we developed a new mobile application designed to protect your images stored on yo... more In this paper, we developed a new mobile application designed to protect your images stored on your mobile phone using Advanced Encryption Standard algorithm to secure images by encrypting it and Least Significant Bit algorithm to process the encrypted image and embed it into another image. To achieve high level of encryption, a 256 bit length key of Advance Encryption Standard is used to maximize protection and Diffie-Hellman algorithm to secure the processed key to both parties without interference from outside. In steganography, the encrypted image will be invisible into the cover image in which potential hackers do not have any idea about the original image embedded inside of the cover image, and with this even if the hacker got the image it will still need the correct key to decrypt it or else the image will be deleted The study used Rapid Application Development Model as the project development methodology, which allows the preceding phase to iterate until the application is r...

Proceedings of the 2nd International Conference on Computing and Big Data - ICCBD 2019, 2019

The International Data Encryption Algorithm (IDEA) is one of an encryption algorithm that uses a ... more The International Data Encryption Algorithm (IDEA) is one of an encryption algorithm that uses a cyclic process in producing sub keys from secret key using its key schedule but generates large weak keys. GISKOP is a modified IDEA that uses the concept of serpent key scheduling operation to address the weak keys found on the original IDEA. Randomness test was used to identify the dependence and correlations between generated sub-keys of a key scheduling operation. Statistical evaluation was done to analyze and compare key distribution and exchange operations of the modified key scheduling operation. The GISKOP key scheduling operation obtained an increase of 8% randomness using frequency test in the sub-key independence level. Also, it was able to maintain its 100% randomness under the sub-key level independence. Thus, proving that each generated sub keys are not correlated with each other. With this, many attacks on systems that implement IDEA can be mitigated. Furthermore, the find...

Cryptography is a method of storing and transmitting data in a particular form. Only those for wh... more Cryptography is a method of storing and transmitting data in a particular form. Only those for whom it is intended can read, use it, and return it back to the original data by using various techniques. The International Data Encryption Algorithm "IDEA" is a block cipher that works with 64-bit plaintext block and ciphertext blocks and it has a 128-bit input key. This paper describe the designing and implementation of a modified key schedule operation of IDEA called GISKOP. It uses the same number of rounds and output transformation that operates using 128 bit user input plaintext and a modified way of key scheduling operation of 256 bit keys. The modified algorithm uses Serpent key scheduling operation to derive the different sub keys to be used in each rounds. The algorithm was implemented to provide better security on user's password within the Document Management System to protect user's data within the cloud database. It has gone through initial testing and eval...

Security assurance in any telecommunication lines is a necessity. It is everyone's desire to ... more Security assurance in any telecommunication lines is a necessity. It is everyone's desire to maintain secrecy of any information sent thru both unsecured and secured telecommunication lines. Short Message Service (SMS) has turned into an extension and has been an important part in the life of its user. Payment, mobile banking, important reminders such as stocks and news alerts, traffic updates, weather information and business related information are being catered thru SMS. Problems of privacy and imitations are the core issues dealt in the study. In order to prolong the secrecy of any information, an implementation of an improved cryptology scheme was designed. The study used a cascaded encryption process designed for sending SMS thru any communication line. The strength of the algorithm using the framework focused on designing a secured encryption process and adapting AES (Advance Encryption Standard) encryption with two more encryption layers. It discussed impact of the frame...

International Journal of Signal Processing Systems, Dec 1, 2016

The development of an application that can help the thesis adviser and student construct and reco... more The development of an application that can help the thesis adviser and student construct and recommend thesis titles through the use of Natural Language Processing (NLP) was the primary objective of this study. Resembling the concept of Information Retrieval under Query-Focused Summarization, words except stop words from the related literature and studies of the thesis and its title were used as a training corpus while the words except stop words of chapters one (1), two (2) and three (3) of the thesis or merely the test document acts as the query in the corpus, where it retrieved its weight from both training and test records. The result showed that out of forty-five (45) thesis titles, twentyeight (28) different title formats were constructed by the thesis advisers with the support of the developed application. The advanced application obtained the accuracy score of 1.55 or "Accurate" and quality score of 4.06 or "Good" in fifteen (15) thesis titles.

Proceedings of the 2017 International Conference on Computer Science and Artificial Intelligence - CSAI 2017

In this paper, we developed a new mobile application designed to serve as a color vision enhancem... more In this paper, we developed a new mobile application designed to serve as a color vision enhancement tool for individuals with color vision deficiency, or commonly known as color blindness. A person who suffers from Color Vision Deficiency (CVD) faces many complexities in everyday life in even the simplest activities due to having a narrower color spectrum which caused them to perceive colors with similar shades and intensity. Hence, to address this problem, a color vision enhancement method using LMS Daltonization Algorithm was utilized to transform or convert the color of images into a clearer and more recognizable colors to differentiate the colors of two unrelated areas. The application was also designed for a real-time image color processing function that minimizes color discrimination by changing the color for better representation. The application also provided an assessment to identify the user's colorblindness type using D-15 Color Arrangement Test. To validate the accuracy and correctness of information, selected doctors of Optometry and CVD users evaluated the mobile application.

International Journal for Research in Applied Science and Engineering Technology

This paper feature an efficient extraction and matching approach on eye with or without contact l... more This paper feature an efficient extraction and matching approach on eye with or without contact lens to innovate authentication process. The proposed feature extraction and matching approach is develop based on FGM (Feature Group Matching) which extract the key points and descriptor of each images using the two feature extraction algorithm which are SIFT (Scale-Invariant Feature Transform) and SURF(Speeded-Up Robust Features) and to match the key points and descriptors using FLANN based matcher. The major advantages of the developed approach are the simplicity and accuracy as compared to the prior extraction and matching approaches developed for contact lens detection images. The new used approach was tested in AMD Ryzen 5 2500U with 2GHz processor, 4GB Mobile RAM, dual graphic card and GPU rendering of RX 560 x with 5GB. The experimental results obtained from IIITD-Contact lens Iris Database and publicly available images and respectively achieved better performance in terms of simplicity and accuracy as compared to the previous proposed methods and Filipino Iris Database as an added contribution to the field of contact lens.