Authors - Omar Munoz, Adolfo Ruelas, Pedro F. Rosales-Escobedo, Jorge E. Ibarra-Esquer, Ruben A. Reyes-Zamora, C. Aguilar-Avelar Abstract - The increasing demand for electricity and the integration of smart grid technologies have highlighted the need for advanced energy monitoring solutions. Non-Intrusive Load Monitoring (NILM) is essential for breaking down total energy consumption into individual appliance-level data, enabling more efficient and sustainable energy management. This work introduces the development and deployment of an IoT-enabled NILM system tailored for residential spaces, leveraging deep learning techniques to enhance classification accuracy. The system integrates a smart meter for real-time event detection and utilizes WaveNet, a deep neural network originally designed for speech processing, to classify appliance ON/OFF events based on electrical parameters. A comparative analysis with 1D-Convolutional Neural Networks (1D-CNN) and Long Short-Term Memory (LSTM) demonstrates that theWaveNet model can also achieve high classification accuracy, reaching 98.84%. The system’s performance was validated using real-world residential data, showcasing its practicality and scalability for real-time energy monitoring. These findings contribute to advancing NILM research by demonstrating the potential of deep learning models in smart energy applications.
Authors - Pedro Filipe Oliveira, Paulo Matos Abstract - This paper proposes the implementation and evaluation of an intelligent environment system designed to enhance the management of comfort preferences at a campus residence setting. With the growing importance of personalized comfort in shared living spaces, the integration of smart technologies offers promising solutions to cater to individual needs while optimizing energy efficiency. Leveraging sensors, actuators, and machine learning algorithms, the proposed system aims to dynamically adapt environmental conditions such as temperature, lighting, and ventilation based on occupants’ preferences. Through a combination of user-centric design, data analytics, and automation, the intelligent environment offers a seamless and intuitive interface for residents to interact with and customize their living environment. Furthermore, the paper discusses the practical challenges and opportunities associated with deploying such a system in a campus residence, including privacy concerns, user acceptance, and scalability. The effectiveness of the proposed solution is evaluated through energy consumption analysis, and feedback mechanisms, highlighting its potential to enhance comfort, well-being, and sustainability in residential settings. Ultimately, this research contributes to the advancement of smart living technologies and informs the design of future intelligent environments tailored to the needs of campus residences and similar shared living spaces.
Authors - Telmo Sampaio, Pedro Filipe Oliveira, Paulo Matos Abstract - This paper proposes the implementation and evaluation of an intelligent environment system designed to enhance the management of comfort preferences in a residence setting on campus. With the growing importance of personalized comfort in shared living spaces, the integration of smart technologies offers promising solutions to meet individual needs while optimizing energy efficiency. Leveraging sensors, actuators, and machine learning algorithms, the proposed system aims to dynamically adapt environmental conditions such as temperature, lighting, and ventilation based on occupants’ preferences. Through a combination of user-centric design, data analytics, and automation, the intelligent environment offers a seamless and intuitive interface for residents to interact with and customize their living environment. Furthermore, the paper discusses the practical challenges and opportunities associated with deploying such a system in a campus residence, including privacy concerns, user acceptance, and scalability. The effectiveness of the proposed solution is evaluated through energy consumption analysis, and feedback mechanisms, highlighting its potential to enhance comfort, well-being, and sustainability in residential settings. Ultimately, this research contributes to the advancement of smart living technologies and informs the design of future intelligent environments tailored to the needs of campus residences and similar shared living spaces.
Authors - Kunihiko Takamatsu, Sayaka Matsumoto, Nobuko Miyairi, Kin-Leong Pey, Alison Elizabeth Lloyd, Roy Tan, Eng Hong Ong, Jingwen Mu, Fiona Rebecca Sutherland, Mun Heng Tsoi, Sin Yi Yap, Hidekazu Iwamoto, Tokuro Matsuo, Noriko Ito, Tsunenori Inakura, Shotaro Imai, Nobuhiko Seki, Ford Lumban Gaol, Takafumi Kirimura, Taion Kunisaki, Kenya Bannaka, Ikuhiro Noda, Ryosuke Kozaki, Aoi Kishida, Katsuhiko Murakami, Yasuo Nakata, Masao Mori Abstract - Contemporary higher education institutions face increasingly complex challenges—including hybrid teaching, governance reform, and digital transformation—that traditional divisions between academic and administrative roles struggle to address. In this context, new hybrid faculty roles are needed to support organizational learning and innovation across institutional boundaries. This study explores how Abduction-Driven Management Faculty can contribute to expanding Knowledge Networks in Higher Education through the Eduinformatics framework. Contemporary higher education faces multifaceted challenges requiring interdisciplinary approaches. Eduinformatics, integrating educational principles with informatics methodologies, offers a structured framework for addressing these complexities. The research examines knowledge creation through the Knowledge Network Tag Model, where "tags" function as catalysts connecting seemingly unrelated knowledge components. Abduction, as a creative inference process, complements this model by generating explanatory hypotheses from observed phenomena. Post-pandemic transformations have high-lighted the need for hybrid faculty roles that transcend traditional administrative-academic boundaries. The study presents innovative positions like "Professor for Institute Management" that enable boundary-spanning activities. By engaging in international forums and creating environments for "designed serendipity," management faculty can foster abductive reasoning and institutional innovation. This approach, structured through frameworks like ABDU-M, enhances universities' capacity to adapt to rapidly changing educational landscapes by identifying patterns and generating hypotheses from complex educational data.
Authors - Natalia Martinez–Rojas Abstract - Achieving sustainability and productivity in agriculture, particularly in water-scarce regions, relies on the optimal allocation of water resources. In this paper a fuzzy logic defining model is proposed to maximize water resources allocation. Based on environmental data, crop water requirements, and soil moisture levels, this model updates irrigation schedules. This approach can increase the efficiency of water use, decrease the waste and be generally more sustainable. The model uses a rule-based fuzzy inference system to assess irrigation needs in real time, adapting to changing weather and soil conditions. Refining fuzzy logic-based modelling to evaluate scenarios and design policies, the study is an extension of previous efforts that moved away from prescriptive decision-making methods. The results show potential water savings without compromising crop yields, highlighting the practical relevance of this methodology.
Authors - Michael Efren Sutanto, Tanty Oktavia, Mohammad Ichsan Abstract - This study aims to detail the extent of development and implementation of generative AI technology for project management support in the financial services sector, focusing on the impacts of the practical underdevelopment gap phenomena towards realization of benefits in key project tasks of risk management, budget and resource allocation, and product or deliverables quality management. Utilizing qualitative methodologies, five semi-structured interviews were conducted with various financial project experts to uncover experiences and sentiments towards generative driven project management AI support tools in project practice. The analysis of findings discovered notable practical impacts were realized in specific subtopics of the project management areas studied, namely project tasks of risk identification and budgeting estimations. Generative AI project tools are conventionally applied as comparison and visualization tools, aiding in project team awareness throughout planning and improving efficiency through automated generation of general risk registers and preliminary budget and resource requirement documents. The findings further validate the necessity of human subjectivity as the driving factor of the practical implementation and academic research gap of project management generative AI.
Authors - Santhi Bharath Punati, Venkata Akhil Kumar Gummadi, Sandeep Kanta, Praveen Damacharla Abstract - The rise of global e-commerce demands accurate sentiment analysis across multiple languages to enhance customer experience and decision-making. However, existing sentiment analysis models struggle with multilingual and code-mixed data, leading to inconsistencies in customer sentiment interpretation. This research presents an advanced deep learning framework that integrates Multilingual BERT (mBERT) embeddings with an Attention-Augmented Gated Recurrent Unit (GRU) network to improve sentiment classification across diverse linguistic contexts. A dataset of 13,000 customer reviews spanning English, Hindi, Hinglish, German, and Spanish was processed using mBERT for contextual embedding, addressing tokenization and syntactic variability challenges. The proposed hybrid model leverages transformer-based contextual understanding with the sequence modeling capabilities of GRU, while the attention mechanism enhances key sentiment features. Experimental evaluations demonstrate the superiority of our model, achieving 93.45% test accuracy and a test loss of 0.0974, outperforming conventional architectures such as LSTM, BiLSTM, and BiLSTM-GRU. The results confirm the model’s effectiveness in maintaining contextual integrity and sentiment accuracy across multilingual datasets. This framework offers a scalable and adaptable solution for e-commerce platforms, enabling businesses to derive precise sentiment insights from global customer reviews. By addressing challenges in multilingual sentiment analysis, our approach facilitates personalized customer engagement, improved product recommendations, and strategic business decisions. Future research may explore expanding sentiment analysis to low-resource languages and real-time feedback systems, further strengthening the inclusivity and intelligence of e-commerce analytics.
Authors - Janset Shawash, Mattia Thibault, Juho Hamari Abstract - This paper explores Spatial Augmented Reality (SAR) implementation for cultural heritage interpretation, focusing on built heritage and interactive storytelling. Using Finland's Finlayson Factory as a case study, we investigate how SAR bridges digital narratives with physical historical contexts. We propose a workflow for transforming virtual narratives into spatial experiences through Research through Design that covers narrative analysis, spatial selection, conceptual translation, and evaluation. Our approach emphasizes accessibility, intuitive interactions, collaborative engagement, and immersive storytelling. Practical considerations including budget planning and operational integration are addressed to assess feasibility. This concept contributes insights for museums adopting interactive technologies to enhance visitor engagement with historical content.
