Fuzzy c-means (FCM) and possibilistic c-means (PCM) are two commonly used fuzzy clustering algorithms for extracting land use land cover (LULC) information from satellite images. However, these algorithms use only spectral or grey-level information of pixels for clustering and ignore their spatial correlation. Different variants of the FCM algorithm have emerged recently that utilize local spatial information in addition to spectral information for clustering. Such algorithms are seen to generate clustering outputs that are more enhanced than the classical spectral-based FCM algorithm. Nonetheless, the scope of integrating spatial contextual information with the conventional PCM algorithm, which has several advantages over the FCM algorithm for supervised classification, has not been explored much. This study proposed integrating local spatial information with the PCM algorithm using simpler but proven approaches from available FCM-based local spatial information algorithms. The three new PCM-based local spatial information algorithms: Possibilistic c-means with spatial constraints (PCM-S), possibilistic local information c-means (PLICM), and adaptive possibilistic local information c-means (ADPLICM) algorithms, were developed corresponding to the available fuzzy c-means with spatial constraints (FCM-S), fuzzy local information c-means (FLICM), and adaptive fuzzy local information c-means (ADFLICM) algorithms. Experiments were conducted to analyze and compare the FCM and PCM classifier variants for supervised LULC classifications in soft (fuzzy) mode. The quantitative assessment of the soft classification results from fuzzy error matrix (FERM) and root mean square error (RMSE) suggested that the new PCM-based local spatial information classifiers produced higher accuracies than the PCM, FCM, or its local spatial variants, in the presence of untrained classes and noise. The promising results from PCM-based local spatial information classifiers suggest that the PCM algorithm, which is known to be naturally robust to noise, when integrated with local spatial information, has the potential to result in more efficient classifiers capable of better handling ambiguities caused by spectral confusions in landscapes.

No abstract

<p><strong>Abstract.</strong> GIS and machine learning (ML) are powerful ICT tools in retail industry which helps the sellers understand their markets. For the consumers, however, there always lies an ambiguity with respect to the quality and quantity of the product to be purchased, vis-à-vis the price paid for it. Most retail businesses today adopt “Discount Pricing Strategies” or “Offers” to make new customers and increase sales. Owing to several establishments selling the same product and offering a variety of offers, the process of identifying the shops where the consumer can get the best value for his money, requires a lot of manual effort. A prototype has been developed in this study to allow the consumers to locate such prospective shops based on advertisements in newspapers. This solution has a two-pronged approach. First, all the offers advertised in the newspaper are pre-processed and text extraction is performed using a ML algorithm named Tesseract OCR. Second the location of shops is collected and stored in a geodatabase. Finally, the advertisement is matched to the respective geo-located shop based on its name and location. Further based on the location of the consumer and his purchase choice, shops offering discounts are shown on a web based map. This prototype provides the consumer, a platform for geo-discovery of establishments of interest through the clutter of unrelated endorsements, by the use of Open Source GIS, Python programming and ML techniques.</p>