Grace L Samson - Academia.edu (original) (raw)

Conference Presentations by Grace L Samson

The key advantages of a well-designed multidimensional database is its ability to allow as many u... more The key advantages of a well-designed multidimensional database is its ability to allow as many users as possible across an organisation to simultaneously gain access and view of the same data. Large spatial datasets evolve from scientific activities (from recent days) that tends to generate large databases which always come in a scale nearing terabyte of data size and in most cases are multidimensional. In this paper, we look at the issues pertaining to large spatial datasets; its feature (for example views), architecture, access methods and most importantly design technologies. We also looked at some ways of possibly improving the performance of some of the existing algorithms for managing large spatial datasets. The study reveals that the major challenges militating against effective management of large spatial datasets is storage utilization and computational complexity (both of which are characterised by the size of spatial big data which now tends to exceeds the capacity of commonly used spatial computing systems owing to their volume, variety and velocity). These problems fortunately can be combated by employing functional programming method or parallelization techniques.

Spatial data mining organizes by location what is interesting as such, specific features of spati... more Spatial data mining organizes by location what is interesting as such, specific features of spatial data mining (including observations that are not independent and spatial autocorrelation among the features) that preclude the use of general purpose data mining algorithms poses a serious challenge in the task of mining meaningful patterns from spatial systems. This creates the complexity that characterises complex spatial systems. Thus, the major challenge for a spatial data miner in trying to build a general complex spatial model would be; to be able to integrate the elements of these complex systems in a way that is optimally effective in any particular case. We have examined ways of creating explicit spatial model that represents an application of mining techniques capable of analysing data from a complex spatial system and then producing information that would be useful in various disciplines where spatial data form the basis of general interest.

Papers by Grace L Samson

We focused on applying parallel computing technique to the bulk loading of X-tree in other to imp... more We focused on applying parallel computing technique to the bulk loading of X-tree in other to improve the performance of DBSCAN clustering algorithm. We have given a full description of how the system can be archived. We proposed a new parallel algorithm for DBSCAN and another algorithm to extend the X-tree spatial indexing structure. Spatial database systems incorporate space in database systems, they support non-traditional data types and more complex queries, therefore in order to optimise such systems for efficient information processing and retrieval, appropriate techniques must be adopted to facilitate the construction of suitable index structures.

Spatial databases are optimized for the management of data stored based on their geometric space.... more Spatial databases are optimized for the management of data stored based on their geometric space. Researchers through high degree scalability have proposed several spatial indexing structures towards this effect. Among these indexing structures is the X-tree. The existing X-trees and its variants are designed for dynamic environment, with the capability for handling insertions and deletions. Notwithstanding, the X-tree degrades on retrieval performance as dimensionality increases and brings about poor worst-case performance than sequential scan. We propose a new X-tree packing techniques for static spatial databases which performs better in space utilization through cautious packing. This new improved structure yields two basic advantage: It reduces the space overhead of the index and produces a better response time, because the aX-tree has a higher fan-out and so the tree always ends up shorter. New model for super-node construction and effective method for optimal packing using an...

International Journal of Advanced Research in Computer Science, 2015

Time is an expensive resource and it is an asset to those who respect and use it efficiently. As ... more Time is an expensive resource and it is an asset to those who respect and use it efficiently. As regards information delivery services, there have been so much delay and loss of information packets in the process of delivery. In this study, we demonstrate the effect of a scheduling algorithm on the speed and reliability of information delivery.Anew decentralized scheduling algorithm and mail delivery and an example of manual mail delivery samples is presented to prove the effect of a proposed scheduling tool on information packets distribution. We useda set of mail information from a private mail bag as locations against some resource agents used in delivering the mail and we applied the algorithm on these locations to see its effects on the time of delivery. The time spam was studied from applying the algorithm and from manually sorting them. The comparism showed differences in the time duration. The research demonstrates the influence of scheduling algorithm on the delivery of mai...

Multimedia Tools and Applications

We present a new detection method for color-based object detection, which can improve the perform... more We present a new detection method for color-based object detection, which can improve the performance of learning procedures in terms of speed, accuracy, and efficiency, using spatial inference, and algorithm. We applied the model to human skin detection from an image; however, the method can also work for other machine learning tasks involving image pixels. We propose (1) an improved RGB/HSL human skin color threshold to tackle darker human skin color detection problem. (2), we also present a new rule-based fast algorithm (packed k-dimensional tree --- PKT) that depends on an improved spatial structure for human skin/face detection from colored 2D images. We also implemented a novel packed quad-tree (PQT) to speed up the quad-tree performance in terms of indexing. We compared the proposed system to traditional pixel-by-pixel (PBP)/pixel-wise (PW) operation, and quadtree based procedures. The results show that our proposed spatial structure performs better (with a very low false hit...

Multimedia Tools and Applications : SpringerLink, 2021

We present a new detection method for color-based object detection, which can improve the perform... more We present a new detection method for color-based object detection, which can improve the performance of learning procedures in terms of speed, accuracy, and efficiency, using spatial inference, and algorithm. We applied the model to human skin detection from an image; however, the method can also work for other machine learning tasks involving image pixels. We propose (1) an improved RGB/HSL human skin color threshold to tackle darker human skin color detection problem. (2), we also present a new rule-based fast algorithm (packed kdimensional tree-PKT) that depends on an improved spatial structure for human skin/face detection from colored 2D images. We also implemented a novel packed quad-tree (PQT) to speed up the quad-tree performance in terms of indexing. We compared the proposed system to traditional pixel-by-pixel (PBP)/pixel-wise (PW) operation, and quadtree based procedures. The results show that our proposed spatial structure performs better (with a very low false hit rate, very high precision, and accuracy rate) than most state-of-the-art models.

— This research work identifies the roles and values of USE CASES in software development, and an... more — This research work identifies the roles and values of USE CASES in software development, and analysed the concept of USE CASES critically in other to ascertain their usefulness in achieving a user's requirement when applied to a system development methodology. We examined the major considerations for deploying advanced UML modelling by considering the best approach for a programmer to get to the source code by putting the right aspect of the UML to work at the right stage of a system life cycle in an object (OO) oriented analysis and design practice. research has found out that to achieve a successful object oriented programming design and implementation, an analyst should strive to drive an OO software design from USE CASES

The technology behind information systems in today's world has been embedded in nearly every aspe... more The technology behind information systems in today's world has been embedded in nearly every aspect of our lives. Thus, the idea of securing our information systems and/or computer networks has become very paramount. Owing to the significance of computer networks in transporting the information and knowledge generated by the increased diversity and sophistication of computational machinery, it would be very imperative to engage the services of network security professionals to manage the resources that are passed through the various terminals (end points) of the these network, so as to achieve a maximum reliability of the information passed, making sure that this is achieved without creating a discrepancy between the security and usability of such network. This paper examines the various techniques involved in securely maintaining the safe states of an active computer network, its resources and the information it carries. We examined techniques of compromising an information system by breaking into the system without authorised access (Hacking), we also looked at the various phases of digital analysis of an already compromised system, and then we investigated the tools and techniques for digitally analysing a compromised system in other to bring it back to a safe state.

Information and Communication Technologies (ICT) developments have existed in Nigeria with a sign... more Information and Communication Technologies (ICT) developments have existed in Nigeria with a significant growth over the past decade. This paper looks at the role of emerging ICT on the general operations of Federal Radio Cooperation of Nigeria in achieving an objective of information decimation. This study shows that the ICT facilities have brought significant improvement to the FRCN service delivery which is important factor for growth and development in the society even though there are still some problems militating the use of ICT in the FRCN. The highest factor militating against the use of ICT is shortage of power supply followed by poor funding and lastly poor network facilities.

In this paper we considered several frameworks for data mining. These frameworks are based on dif... more In this paper we considered several frameworks for data mining. These frameworks are
based on different approaches, including inductive databases approach, the reductionist statistical
approaches, data compression approach, constructive induction approach and some others. We
considered advantages and limitations of these frameworks. We presented the view on data
mining research as continuous and never- ending development process of an adaptive DM
system towards the efficient utilization of available DM techniques for solving a current problem
impacted by the dynamically changing environment. We discussed one of the traditional
information systems frameworks and, drawing the analogy to this framework, we considered a
data mining system as the special kind of adaptive information system. We adapted the information
systems development framework for the context of data-mining systems development.

Key words: Data Mining, Information Systems, Knowledge Discovery Databases

Spatial data mining is the quantitative study of phenomena that are located in space. This paper ... more Spatial data mining is the quantitative study of phenomena that are located in space. This paper investigates methods of mining patterns of a complex spatial data set (which generally describes any kind of data where the location in space of object holds importance). We based this research on the analysis of some spatial characteristics of certain objects. We began with describing the spatial pattern of events or objects with respect to their attributes; we looked at how to describe the spatial nature/characteristics of entities in an environment with respect to their spatial and non-spatial attributes. We also looked at modelling (predictive modelling/knowledge management of complex spatial systems), querying and implementing a complex spatial database (using data structure and algorithms). Critically speaking, the presence of spatial auto-correlation and the fact that continuous data types are always present in spatial data makes it important to create methods, tools and algorithms to mine spatial patterns in a complex spatial data set. This work is particularly useful to researchers in the ¯eld of data mining as it contributes a whole lot of knowledge to di®erent application areas of data mining especially spatial data mining. It can also be useful in teaching and likewise for other study purposes.

Books by Grace L Samson

Spatial databases maintain space information which is appropriate for applications where there is... more Spatial databases maintain space information which is appropriate for applications where there is need
to monitor the position of an object or event over space. Spatial databases describe the fundamental
representation of the object of a dataset that comes from spatial or geographic entities. A spatial database
supports aspects of space and offers spatial data types in its data model and query language.
The spatial or geographic referencing attributes of the objects in a spatial database permits them to be
positioned within a two (2) dimensional or three (3) dimensional space. This chapter looks into the fundamentals
of spatial databases and describes their basic component, operations and architecture. The
study focuses on the data models, query Language, query processing, indexes and query optimization
of a spatial databases that approves spatial databases as a necessary tool for data storage and retrieval
for multidimensional data of high dimensional spaces.

International Journal of Advanced Research in Computer Science, 2015

Multimedia Tools and Applications

Multimedia Tools and Applications : SpringerLink, 2021

We present a new detection method for color-based object detection, which can improve the perform... more We present a new detection method for color-based object detection, which can improve the performance of learning procedures in terms of speed, accuracy, and efficiency, using spatial inference, and algorithm. We applied the model to human skin detection from an image; however, the method can also work for other machine learning tasks involving image pixels. We propose (1) an improved RGB/HSL human skin color threshold to tackle darker human skin color detection problem. (2), we also present a new rule-based fast algorithm (packed kdimensional tree-PKT) that depends on an improved spatial structure for human skin/face detection from colored 2D images. We also implemented a novel packed quad-tree (PQT) to speed up the quad-tree performance in terms of indexing. We compared the proposed system to traditional pixel-by-pixel (PBP)/pixel-wise (PW) operation, and quadtree based procedures. The results show that our proposed spatial structure performs better (with a very low false hit rate, very high precision, and accuracy rate) than most state-of-the-art models.

Key words: Data Mining, Information Systems, Knowledge Discovery Databases