Information & Communications Technology

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 98
  • Item
    Exploration of a socio-cultural anthropological approach to humanistic marketing in the French toy sector.
    (Dublin Business School, 2022-01) Darnis, Celia; Gary Bernie
    In today's capitalist Western society, the field of marketing has become synonymous with manipulation. Indeed, with the development of new technologies and the use of user data as new indicators, marketers now have the power to venture into our deepest desires and turn them into needs (The Social Dilemma, 2020). However, if this data is used to more easily give us what we really need, what is the problem? The problem lies in determining whether this is likely to be the case or whether it is just induced by all the stimuli around us. So, in a society with many societal and environmental issues, having such power cannot be left without theoretical reflection. Marketing professionals are therefore increasingly called upon to adopt an ethical approach, taking into account real human needs. This is where the field of anthropology, a science that studies the human being in all its aspects, comes into play. This essay aims to provide further insights into the alliance between the field of socio-cultural anthropology and marketing. To do so, the French toy sector has been defined as the context of study, as the vulnerability of the target market, children, may represent the ideal context to demonstrate the usefulness of the alliance of these two fields. The researcher then decided to conduct individual semi-structured interviews with 6 mothers aged between 25 and 45, with children aged between 2 and 12. In this way, she will be able to gather the point of view of these mothers on their child's relationship with toys in a digitalized era, and then analyze whether the market is in line with the desires and needs of the respondents, the first decision-maker in the purchase. To support this qualitative data, an online questionnaire was also distributed to the same target group. The results revealed that mothers' feelings about the technologies used by their children were mainly negative, and that permission to use them was motivated more by a need to stay out of society than a desire on the part of respondents. Thus, the researcher felt that an anthropological approach would be relevant to the design and marketing of new products in this sector, which would meet both the needs of mothers, which are those of safety, and the needs of children, which are those of psychomotor development, entertainment and education. However, for this alliance to be successful, the different philosophies of the two fields will need to be brought together so that this approach is not just another quest for profit, but a fruitful lever for goodwill and profitability.
  • Item
    Emotion Recognition from visual Big-Data using Convolutional Neural Network (CNN)
    (Dublin Business School, 2022) Kurmi, Vinay Ramasare; Ezenwa Nwankire, Charles
    Human species has been using their facial expressions and facial muscles in order to effectively communicate for millions of years now. Expression and emotions have been captured and stored into many forms since then like paintings, pictures, videos etc. Research is also being conducted in various forms in order to successfully identify the emotion of a person with help of technologies and methods such as knowledge based techniques, statistical methods and hybrid approaches. Recently artificial intelligence has proven its effectiveness in classifying or predicting the human emotion based on accumulated data in form of audio, video, text etc... This research proposes to design a system to classify the real-time emotions from numerous facial expressions and its features while using techniques such as Convolution Neural Network(CNN) algorithm. Along with CNN, this research also proposes to utilize various other tools and technologies such as OpenCV library, Tensorflow, Keras, Python, Visual Studio Code, etc.
  • Item
    Contact Tracing using Graph Algorithms and exploring graph analytics in a Graph Database (Neo4j)
    (Dublin Business School, 2022) Narvekar, Sharvari Devdas; Hoare, Terri
    The SARS-COVID-19 epidemic is still spreading rapidly globally. Contact Tracing has played an important role during this emergency in identifying the people most likely to be high spreaders of the virus. Graph Data Science has recently come to the forefront in analysing connected data on a knowledge graph. It included various types of algorithms supporting graph analytics and machine learning workflows. Using GDS we can execute these algorithms we find the optimized result in Neo4j platform This research explores the use of graph data science in the context of contact tracing. Common real-world scenarios are explored using Neo4j, the leading graph database management system. Graph Data Science algorithms including PageRank, betweenness centrality, Louvain community detection, label propagation, shortest path algorithms are explored, and results visualised. Results prove to be insightful.
  • Item
    Forecasting the price of AWS On-spot instances using Deep Neural Network Architectures
    (Dublin Business School, 2022) Jaishankar, Ranjith Kumar; Azizi, Shahram
    Among the cloud computing services, the concept of On-spot instance is the most popular which has been introduced by Amazon AWS, in order to utilize their spare capacity. On-spot instance follows the auction-based cloud model, where the price on-spot changes with time. In general analysis, it has been found that AWS On-spot instances are 30-40% cheaper than regular instances. The concept of dynamic pricing for AWS on-spot instance makes it complicated for some users, to bid for an optimal price. In order to help the users for selecting the optimal price with AWS On-spot instances, this research is predicted using the 4 different deep learning architectures which includes CNN, RNN, LSTM and Bi-LSTM for price prediction. To select the best performing model MSE, RMSE and MAE score has been calculated for each model over the test data. The better outcomes is achieved using Bi-LSTM model in terms of performance. In order to implement the concept of ON-spot price prediction, a web-portal using python flask has been developed which provides the predicted price of On-spot instance based on user input such as Region, Operating system, instance type, Time stamp etc.
  • Item
    Deep Learning in Games to Improve Autonomous Driving
    (Dublin Business School, 2022) Borghi, Rafael; Afzal, Shazia
    Autonomous Driving is a lively research area in Artificial Intelligence that aims to automatize procedures for self-driving vehicles. Machine Learning has overcome human performance in some simulators with the development of techniques like Deep Reinforcement Learning and Convolutional Neural Networks, as they have been applied with great success to a variety of applications, such as video games. The objective of this work is to demonstrate established Deep Learning techniques used in videogame simulators to show proficiency in Autonomous Driving. In this research, concepts of Autonomous Driving, Video Games and Deep Learning are presented. For that, a simulator is used to enable the use of Machine Learning. Also, a technique related to Deep Learning is evaluated and chosen for the demonstration of conduct vehicles automation in the videogame simulator. Variables related to the agent and the environment (such as distance, steer variation, among others) are taken into consideration.