scispace - formally typeset
Search or ask a question
Author

Javier Diaz-Cely

Bio: Javier Diaz-Cely is an academic researcher from ICESI University. The author has contributed to research in topics: Deep learning & Market segmentation. The author has an hindex of 2, co-authored 6 publications receiving 14 citations.

Papers
More filters
Book ChapterDOI
25 Apr 2019
TL;DR: The experimental results showed that color representation in the CIE-L*a*b* color space gave reasonably good results compared to the RGB color format originally used during training, support the idea that the features learned can be transferred to new models with images using different color channels, and opens up new research questions as to the transferability of image representation in convolutional neural networks.
Abstract: Image classification is one of the most important tasks in computer vision, since it can be used to retrieve, store, organize, and analyze digital images. In recent years, deep learning convolutional neural networks have been successfully used to classify images surpassing previous state of the art performances. Moreover, using transfer learning techniques, very complex models have been successfully utilized for other tasks different from the original task for which they were trained for. Here, the influence of the color representation of the input images was tested when using a transfer learning technique in three different well-known convolutional models. The experimental results showed that color representation in the CIE-L*a*b* color space gave reasonably good results compared to the RGB color format originally used during training. These results support the idea that the features learned can be transferred to new models with images using different color channels such as the CIE-L*a*b* space, and opens up new research questions as to the transferability of image representation in convolutional neural networks.

15 citations

Journal ArticleDOI
TL;DR: In this article, a workflow composed of several machine learning models incorporating Transformers as an attention mechanism and BERT-based data augmentation capable of predicting product classes from Amazon product reviews and Twitter message corpora, and then characterizing the obtained geographic clusters based on their aggregated scores.
Abstract: In data analysis, context information plays a significant role in enhancing the quality of the insight obtained. Furthermore, spatial analysis helps understand spatial relationships among entities. Nevertheless, findings of a comprehensive literature review show that the characterization of geographic areas based on user generated content, such as text messages, has not been sufficiently explored. This paper focuses on investigating how to combine and exploit geographic information with user generated text content to detect geographic clusters of textual events, and infer relationships between each cluster and a fixed set of retail product categories, which we consider as an insightful way to perform spatial market segmentation. We propose a workflow composed of several machine learning models incorporating Transformers as an attention mechanism and BERT-based data augmentation capable of predicting product classes from Amazon product reviews and Twitter message corpora, and then characterizing the obtained geographic clusters based on their aggregated scores. The output of our system is an effective visualization of the geographic areas with their corresponding relevance score against a fixed set of categories. We trained a product document classifier achieving an F1-Score of 86% in the test set for product reviews, and of 76% in the test set for tweets; and validated our approach by manually annotating a subset of Twitter data with respect to ten product categories. Our approach provides practitioners with a mechanism to combine location context, a Transformer encoder, and transfer learning to derive insights from geo-spatial and text data; and researchers with opportunities to continue advancing the field.

8 citations

Journal ArticleDOI
TL;DR: This paper presents the results of a systematic literature review (SLR), in which a total of 168 location-based and business oriented analytics solutions that were published between 2014 and 2019 are characterized and provides business and data analytics practitioners with a comprehensive catalog of location- based data analytics approaches that could be applied to improve value generation along their businesses’ value chains.
Abstract: Context information has become a significant asset to optimize the value obtained from information systems. Location is an important type of context information that refers to the place in which an event occurs. In business environments, the implementation of location-based analytics systems to aid decision making processes is of paramount importance for business development. However, after an exhaustive literature review, we found that researchers and practitioners still lack a comprehensive characterization of location-based data analytics systems that have been effectively applied to business processes. This paper presents the results of a systematic literature review (SLR), in which we characterized a total of 168 location-based and business oriented analytics solutions that were published between 2014 and 2019. To conduct this SLR we defined three characterization dimensions: business aspects , through which we identified value chain business processes or activities that may be benefited with the proposed solution; data source , which allowed us to report on the data used in each of the studies; and data analytics , through which we report on the analytics techniques and validation strategies implemented by the studied approaches. The contribution of our SLR is twofold. First, it provides business and data analytics practitioners with a comprehensive catalog of location-based data analytics approaches that could be applied to improve value generation, at different levels, along their businesses’ value chains. And second, it provides researchers with a complete landscape of recent advancements and open challenges in the field.

6 citations

Book ChapterDOI
01 Jan 2019
TL;DR: In this article, the authors describe the importance of music design for background instrumental music and the effect on task performance and emotional states of participants during a complex task scenario using a complicated web-interface.
Abstract: The authors describe the importance of music design for background instrumental music and the effect on task performance. Three instrumental music conditions that differ in tempo, articulation, mode, and musical meter were tested using a complex task scenario. The task was performed using a complicated web-interface that required users to focus their attention and perform several specific interactions for successfully finishing the task. All the interactions with the interface were recorded. Moreover, a mixed assessment of the emotional state, perceived task performance, and music perception was asked to participants upon task completion. Experimental results revealed that music design has complex effects on task performance and emotion. Also, the results revealed important trends that can help design music environments to control frustration when confronted to complex and cognitively demanding tasks.

2 citations

Book ChapterDOI
26 Jul 2019
TL;DR: Preliminary results support the idea that technology-enhanced training is a feasible alternative to motivate and guide owners to implement separation training with their dogs.
Abstract: Separation anxiety in dogs is a common condition that is manifested by destructive behavior when dogs are left alone. The most successful treatment for canine separation-related problems requires dog’s behavior modification via a time consuming training. Moreover, this type of training needs a high commitment from the dog’s owner. Here, a canine wearable interface connected to a mobile application was designed to monitor and guide a training program aiming at behavior modification in dogs. The objective was to design a system that enhances user engagement while monitoring dog’s biometrical signals. Preliminary testing of the system revealed significant behavior changes. Significant decrease in dog’s overall destructive behavior was recorded. Specifically, when using the technology-enhanced vest, dogs were quieter and reduced their anxious movements. These preliminary results support the idea that technology-enhanced training is a feasible alternative to motivate and guide owners to implement separation training with their dogs.

1 citations


Cited by
More filters
Journal Article
TL;DR: Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS* is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches.
Abstract: The problem of hyper-local place ranking. Given a user location and query string (e.g., “Indian restaurant"), hyper-local ranking provides a list of top-k points of interest influenced by previously logged directional queries (e.g., map direction searches from point A to point B).This paper proposes LARS*, a location-aware recommender system that uses their location-based ratings to show recommendations. Traditional recommender systems do not have spatial properties of users nor items; LARS*, next, supports a taxonomy of three novel classes of location-based ratings, namely, spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS* exploits user rating locations through user partitioning, a technique that influences recommendations with ratings spatially close to querying users in a manner that maximizes system scalability while not sacrificing recommendation quality. LARS* exploits item locations using travel penalty, a technique that favors recommendation candidates closer in travel distance to querying users in a way that avoids exhaustive access to all spatial items. LARS* can apply these techniques separately, or together, depending on the type of location-based rating available. Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS* is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches. Our proposed location-aware recommender system, tackles a problem untouched by traditional recommender systems by dealing with three types of location-based ratings: spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS* employs user partitioning and travel penalty techniques to support spatial ratings and spatial items, respectively.

42 citations

Journal ArticleDOI
TL;DR: In this article, the authors examined the effect of background music on experiential value, cognitive value, and purchase intention of high and low-involvement consumers among both students and non-student samples.
Abstract: Background music adds a multi-sensory element to marketing and e-commerce. Applying interactive sensory-enabling technologies (SETs) to online shopping websites is an area of interest of sensory marketing. This research examines interactive background music in ecommerce and investigates how online consumer involvement moderates the effects of interactive music. Single-factor experiments with three conditions (interactive music, static background music, and control) were conducted to investigate its impact on experiential value, cognitive value, and purchase intention of high- and low-involvement consumers among both students (Study 1, N = 251) and non-student samples (Study 2, N = 218). Different music genres were applied to stimuli of the two studies to demonstrate generalizability of the findings. Results find that interactive music enhances the experiential value of e-commerce for low-involvement consumers. By contrast, high-involvement consumers show greater purchase intention under the interactive music condition due to a heightened level of perceived cognitive value. Involvement is an effective predictor of elaboration and purchase intention under the interactive music condition, but not under the other two conditions. The contribution is twofold: 1) it shows the impact of music as an interactive SET and, 2) demonstrates the moderating role of consumer involvement in the context of multi-sensory integration in e-commerce. Theoretical and practical implications are discussed along with limitations and directions for future research.

33 citations

Journal ArticleDOI
TL;DR: In this article, a workflow composed of several machine learning models incorporating Transformers as an attention mechanism and BERT-based data augmentation capable of predicting product classes from Amazon product reviews and Twitter message corpora, and then characterizing the obtained geographic clusters based on their aggregated scores.
Abstract: In data analysis, context information plays a significant role in enhancing the quality of the insight obtained. Furthermore, spatial analysis helps understand spatial relationships among entities. Nevertheless, findings of a comprehensive literature review show that the characterization of geographic areas based on user generated content, such as text messages, has not been sufficiently explored. This paper focuses on investigating how to combine and exploit geographic information with user generated text content to detect geographic clusters of textual events, and infer relationships between each cluster and a fixed set of retail product categories, which we consider as an insightful way to perform spatial market segmentation. We propose a workflow composed of several machine learning models incorporating Transformers as an attention mechanism and BERT-based data augmentation capable of predicting product classes from Amazon product reviews and Twitter message corpora, and then characterizing the obtained geographic clusters based on their aggregated scores. The output of our system is an effective visualization of the geographic areas with their corresponding relevance score against a fixed set of categories. We trained a product document classifier achieving an F1-Score of 86% in the test set for product reviews, and of 76% in the test set for tweets; and validated our approach by manually annotating a subset of Twitter data with respect to ten product categories. Our approach provides practitioners with a mechanism to combine location context, a Transformer encoder, and transfer learning to derive insights from geo-spatial and text data; and researchers with opportunities to continue advancing the field.

8 citations

Journal ArticleDOI
TL;DR: In this paper , an ensemble of convolutional neural networks (CNN) trained with normalized images using different color adjustment techniques was proposed to detect breast cancer. But, the proposed method is not suitable for the detection of breast cancer in women.

7 citations