spatial

social media

Media Sosial dan GIS Untuk Pengumpulan dan Analisis Data Ruang

Oleh Shahabuddin Amerudin Pengenalan  Dalam era digital ini, media sosial telah berkembang menjadi platform yang bukan sahaja digunakan untuk berinteraksi secara sosial, tetapi juga sebagai sumber data yang kaya untuk pelbagai analisis. Integrasi media sosial dengan Sistem Maklumat Geografi (GIS) membuka peluang besar dalam pelbagai sektor seperti pemantauan bencana, keselamatan, dan analisis alam sekitar. Dengan ciri geotag yang disertakan dalam kebanyakan platform media sosial seperti Twitter, Instagram, dan Facebook, data dapat dianalisis secara spatial untuk menghasilkan pemahaman yang lebih mendalam mengenai corak dan tren di lapangan. Pemanfaatan GIS dan Media Sosial dalam Pengumpulan Data Ruang  Penggunaan data geotag daripada media […]

Media Sosial dan GIS Untuk Pengumpulan dan Analisis Data Ruang Read More »

spatial computing

Spatial Computing: The Next AI-Driven Business Revolution

By Shahabuddin Amerudin Spatial computing is rapidly emerging as a revolutionary force in the business world, merging cutting-edge technologies like artificial intelligence (AI), extended reality (XR), and computer vision to create immersive, interactive environments that bridge the physical and digital realms. This advanced form of computing enables businesses to visualize, simulate, and interact with data in unprecedented ways, enhancing everything from operations and decision-making to customer experiences. The Paradigm Shift in Human-Computer Interaction Spatial computing represents a significant departure from traditional human-computer interactions. Instead of relying on 2D screens and interfaces, spatial computing introduces a 3D-centric approach where virtual and

Spatial Computing: The Next AI-Driven Business Revolution Read More »

© 2025 Justine Blanford

Spatial-Temporal Analysis Framework for Health and Disease Mapping and Modelling

By Shahabuddin Amerudin Abstract The study of spatial-temporal dynamics in health and disease mapping is crucial for understanding the spread and control of diseases. This review examines a comprehensive framework that integrates various scales of temporal and spatial data to enhance health and disease modeling. The framework leverages granular to broad/noisy data types, transitioning from local observations to global predictive models. This multidimensional approach is essential for developing effective public health strategies and interventions. Introduction The integration of spatial and temporal dimensions in health and disease mapping provides a more nuanced understanding of epidemiological patterns (Blanford, 2025). The spatial-temporal analysis

Spatial-Temporal Analysis Framework for Health and Disease Mapping and Modelling Read More »

Predicting Property Investment Opportunities in an Emerging Urban Neighborhood

By Shahabuddin Amerudin Introduction You are a real estate investor looking to identify promising property investment opportunities in an emerging urban neighborhood. To make informed decisions on whether to invest in land, shops, or houses, you need to predict their potential future value and assess their investment viability. This scenario explores how to predict property investment opportunities in such a dynamic urban environment. Defining the Objective The objective is to predict the future value and investment potential of properties in the urban neighborhood over the next five years. This includes forecasting property values and assessing the expected return on investment

Predicting Property Investment Opportunities in an Emerging Urban Neighborhood Read More »

Predicting House Demand with Spatial Considerations in a Growing Suburb

By Shahabuddin Amerudin Introduction As a real estate developer planning to invest in a growing suburban area, you recognize that housing demand is not solely influenced by time-related factors but also by spatial considerations. To make precise predictions about where and when houses will be in demand, you need to incorporate both temporal and spatial elements into your forecasting. Defining the Objective The objective remains to forecast the demand for houses in the suburban area over the next five years, but now with a spatial dimension. You want to estimate the number of new homes that potential buyers are likely

Predicting House Demand with Spatial Considerations in a Growing Suburb Read More »

Navigating the Expansive Horizon of Spatial Data Science

By Shahabuddin Amerudin Abstract In recent times, the realm of spatial data science has witnessed an unprecedented surge, propelled by the exponential growth of spatial data and its potential applications across diverse domains. This review article delves into the multifaceted world of spatial data science, spanning its foundational principles, practical applications, inherent challenges, and the evolving research trends that are shaping its trajectory. By exploring the intricate interplay of spatial data, complexities, and novel methodologies, this review aims to provide a holistic understanding of this dynamic and interdisciplinary field. Unveiling the Essence of Spatial Data Science The advent of the

Navigating the Expansive Horizon of Spatial Data Science Read More »

Unveiling Spatial Relationships: Predictive Applications of Regression Analysis

By Shahabuddin Amerudin Introduction In the realm of data analysis, regression analysis stands as a powerful tool that facilitates the exploration, understanding, and prediction of spatial relationships. By unraveling the intricate connections between variables, it provides insights into the factors driving observed spatial patterns. In this article, we delve into the fascinating world of regression analysis, focusing on its predictive applications through two distinct examples: the prediction of human deaths and the analysis of grave demand. Regression analysis forms the cornerstone of modern statistical analysis, enabling us to move beyond mere correlation and into the realm of causation. As we

Unveiling Spatial Relationships: Predictive Applications of Regression Analysis Read More »

Spatial Analysis Techniques for Unveiling Geographic Patterns and Interactions

By Shahabuddin Amerudin Introduction Spatial analysis is a critical discipline within geography and various other fields that deal with spatial data. It involves the examination of geographic patterns, relationships, and dependencies among data points in a given space. This exploration is crucial for understanding the underlying mechanisms driving spatial phenomena and for making informed decisions in urban planning, environmental management, economics, and various other domains. In this article, we delve into several key techniques of spatial analysis, each offering unique insights into the complex interplay between geographical elements. By exploring methods such as autocorrelation, spatial interpolation, spatial regression, spatial interaction,

Spatial Analysis Techniques for Unveiling Geographic Patterns and Interactions Read More »

Revisiting the Relevance of Key Skills for GIS Software Developers in the Current Technological Landscape: A Review of Justin Holman’s 2012 Spatial Career Guide

Suggestion for Citation: Amerudin, S. (2023). Revisiting the Relevance of Key Skills for GIS Software Developers in the Current Technological Landscape: A Review of Justin Holman’s 2012 Spatial Career Guide. [Online] Available at: https://people.utm.my/shahabuddin/?p=6350 (Accessed: 12 April 2023).

Revisiting the Relevance of Key Skills for GIS Software Developers in the Current Technological Landscape: A Review of Justin Holman’s 2012 Spatial Career Guide Read More »

Spatial Career Guide – 5 Key Skills for Future GIS Software Developers – A Short Review

Suggestion for Citation: Amerudin, S. (2023). Spatial Career Guide – 5 Key Skills for Future GIS Software Developers – A Short Review. [Online] Available at: https://people.utm.my/shahabuddin/?p=6339 (Accessed: 12 April 2023).

Spatial Career Guide – 5 Key Skills for Future GIS Software Developers – A Short Review Read More »

Geographically Weighted Regression (GWR)

Geographically Weighted Regression (GWR) is a spatial statistical method used for predicting outcomes based on geographical data. To conduct prediction using GWR, you can follow these steps: Note: It is essential to validate the GWR results with independent validation data and assess the model performance using appropriate validation metrics. Geographically Weighted Regression (GWR) is a powerful statistical tool for predicting outcomes based on geographical data. Its ability to account for spatial heterogeneity in the relationships between independent and dependent variables makes it an attractive alternative to traditional regression methods such as Ordinary Least Squares (OLS). The quality of GWR results

Geographically Weighted Regression (GWR) Read More »

The Green Building Index (GBI) Certification 

Introduction Green Building Index (GBI) is a rating system that evaluates the environmental performance of buildings in Malaysia. Developed by the Malaysia Green Building Confederation (MGBC), the system aims to promote sustainable building practices and reduce the environmental impact of buildings. GBI assesses buildings based on nine categories: energy efficiency, indoor environment quality, materials and resources, site and surrounding, water efficiency, innovation, environmental management, land use and ecology, and emissions and effluents. Each category is assigned a certain number of points, and buildings must achieve a minimum number of points in each category in order to be certified. One of

The Green Building Index (GBI) Certification  Read More »

Spatial vs Geospatial [2]

Mike Goodchild believes that we should make a distinction between spatial and geospatial believing that if spatial is special then geospatial is even more special! The way he sees it is that geospatial is a subset of something much larger that encompases any spatiotemporal frame, any spatial resoultion, non-Cartesian spaces and metrics and so on.  Spatial represents the big picture while geospatial carves out its own area of interest at on on the earth’s surface  He goes on to suggest that any theory of geospatial (geographic information) should be developed quite separetely from a theory of spatial (spatial information) with the proviso

Spatial vs Geospatial [2] Read More »

Spatial vs Geospatial [1]

Often my students ask about the difference(s) between spatial and geospatial. These two words appear very frequently in remote sensing and GIS literature. The word spatial originated from Latin ‘spatium’, which means space. Spatial means ‘pertaining to space’ or ‘having to do with space, relating to space and the position, size, shape, etc.’ (Oxford Dictionary), which refers to features or phenomena distributed in three-dimensional space (any space, not only the Earth’s surface) and, thus, having physical, measurable dimensions. In GIS, ‘spatial’ is also referred to as ‘based on location on map’. Geographic(al) means ‘pertaining to geography (the study of the

Spatial vs Geospatial [1] Read More »

Scroll to Top