arXiv subjects

Francis Palma

Publications and source records attributed to Francis Palma.

7 recordsLinked to original sources

arXiv2025

Privacy-Preserving Multi-Stage Fall Detection Framework with Semi-supervised Federated Learning and Robotic Vision Confirmation

The aging population is growing rapidly, and so is the danger of falls in older adults. A major cause of injury is falling, and detection in time can greatly save medical expenses and recovery time. However, to provide timely intervention and avoid unnecessary alarms, detection systems must be effective and reliable while addressing privacy concerns regarding the user. In this work, we propose a framework for detecting falls using several complementary systems: a semi-supervised federated learning-based fall detection system (SF2D), an indoor localization and navigation system, and a vision-based human fall recognition system. A wearable device and an edge device identify a fall scenario in the first system. On top of that, the second system uses an indoor localization technique first to localize the fall location and then navigate a robot to inspect the scenario. A vision-based detection system running on an edge device with a mounted camera on a robot is used to recognize fallen people. Each of the systems of this proposed framework achieves different accuracy rates. Specifically, the SF2D has a 0.81% failure rate equivalent to 99.19% accuracy, while the vision-based fallen people detection achieves 96.3% accuracy. However, when we combine the accuracy of these two systems with the accuracy of the navigation system (95% success rate), our proposed framework creates a highly reliable performance for fall detection, with an overall accuracy of 99.99%. Not only is the proposed framework safe for older adults, but it is also a privacy-preserving solution for detecting falls.

cs.CV↗

arXiv2025

Encoded Spatial Attribute in Multi-Tier Federated Learning

This research presents an Encoded Spatial Multi-Tier Federated Learning approach for a comprehensive evaluation of aggregated models for geospatial data. In the client tier, encoding spatial information is introduced to better predict the target outcome. The research aims to assess the performance of these models across diverse datasets and spatial attributes, highlighting variations in predictive accuracy. Using evaluation metrics such as accuracy, our research reveals insights into the complexities of spatial granularity and the challenges of capturing underlying patterns in the data. We extended the scope of federated learning (FL) by having multi-tier along with the functionality of encoding spatial attributes. Our N-tier FL approach used encoded spatial data to aggregate in different tiers. We obtained multiple models that predicted the different granularities of spatial data. Our findings underscore the need for further research to improve predictive accuracy and model generalization, with potential avenues including incorporating additional features, refining model architectures, and exploring alternative modeling approaches. Our experiments have several tiers representing different levels of spatial aspects. We obtained accuracy of 75.62% and 89.52% for the global model without having to train the model using the data constituted with the designated tier. The research also highlights the importance of the proposed approach in real-time applications.

cs.LG↗

arXiv2024

An Adaptive Indoor Localization Approach Using WiFi RSSI Fingerprinting with SLAM-Enabled Robotic Platform and Deep Neural Networks

Indoor localization plays a vital role in the era of the IoT and robotics, with WiFi technology being a prominent choice due to its ubiquity. We present a method for creating WiFi fingerprinting datasets to enhance indoor localization systems and address the gap in WiFi fingerprinting dataset creation. We used the Simultaneous Localization And Mapping (SLAM) algorithm and employed a robotic platform to construct precise maps and localize robots in indoor environments. We developed software applications to facilitate data acquisition, fingerprinting dataset collection, and accurate ground truth map building. Subsequently, we aligned the spatial information generated via the SLAM with the WiFi scans to create a comprehensive WiFi fingerprinting dataset. The created dataset was used to train a deep neural network (DNN) for indoor localization, which can prove the usefulness of grid density. We conducted experimental validation within our office environment to demonstrate the proposed method's effectiveness, including a heatmap from the dataset showcasing the spatial distribution of WiFi signal strengths for the testing access points placed within the environment. Notably, our method offers distinct advantages over existing approaches as it eliminates the need for a predefined map of the environment, requires no preparatory steps, lessens human intervention, creates a denser fingerprinting dataset, and reduces the WiFi fingerprinting dataset creation time. Our method achieves 26% more accurate localization than the other methods and can create a six times denser fingerprinting dataset in one-third of the time compared to the traditional method. In summary, using WiFi RSSI Fingerprinting data surveyed by the SLAM-Enabled Robotic Platform, we can adapt our trained DNN model to indoor localization in any dynamic environment and enhance its scalability and applicability in real-world scenarios.

cs.RO↗

arXiv2024

Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment

This paper proposes an optimization of an existing Deep Neural Network (DNN) that improves its hardware utilization and facilitates on-device training for resource-constrained edge environments. We implement efficient parameter reduction strategies on Xception that shrink the model size without sacrificing accuracy, thus decreasing memory utilization during training. We evaluate our model in two experiments: Caltech-101 image classification and PCB defect detection and compare its performance against the original Xception and lightweight models, EfficientNetV2B1 and MobileNetV2. The results of the Caltech-101 image classification show that our model has a better test accuracy (76.21%) than Xception (75.89%), uses less memory on average (847.9MB) than Xception (874.6MB), and has faster training and inference times. The lightweight models overfit with EfficientNetV2B1 having a 30.52% test accuracy and MobileNetV2 having a 58.11% test accuracy. Both lightweight models have better memory usage than our model and Xception. On the PCB defect detection, our model has the best test accuracy (90.30%), compared to Xception (88.10%), EfficientNetV2B1 (55.25%), and MobileNetV2 (50.50%). MobileNetV2 has the least average memory usage (849.4MB), followed by our model (865.8MB), then EfficientNetV2B1 (874.8MB), and Xception has the highest (893.6MB). We further experiment with pre-trained weights and observe that memory usage decreases thereby showing the benefits of transfer learning. A Pareto analysis of the models' performance shows that our optimized model architecture satisfies accuracy and low memory utilization objectives.

cs.LG↗

arXiv2023

Improving Software Requirements Prioritization through the Lens of Constraint Solving

Requirements prioritization is a critical activity during the early software development process, which produces a set of key requirements to implement. The prioritization process offers a parity among the requirements based on multiple characteristics, including end-users' preferences, cost to implement, and technical dependencies. This paper presents an interactive method to requirements prioritization that leverages the pairwise comparisons and a constraint solver. Our method employs an interactive accumulation of knowledge from the requirements analyst when the relative priority among the requirements cannot be determined based on the existing knowledge from the requirements documents. The final ranking of the requirements is produced via the constraint solver and interactive pairwise comparisons. We evaluate the proposed method using the requirements from a real healthcare project. The proposed prioritization method relying on a constraint solver outperforms state-of-the-art interactive prioritization methods in terms of effectiveness and robustness to analyst's errors.

cs.SE↗

arXiv2023

Exploring the Relationship Between Ownership and Contribution Alignment and Code Technical Debt

Software development organisations aim to stay effective and efficient amid growing system complexity. To address this, they often form small teams focused on separate components that can be independently developed, tested, and deployed. Aligning architecture with organisational structures is crucial for effective communication and collaboration, reducing code and architectural degradation. Assigning specific component responsibility to the teams primarily working on them is key to these goals. This article explores the relationship between ownership and contribution alignment and code quality degradation, measured as technical debt per line of code. It also examines how team structure changes impact their ability to manage code quality degradation. We conducted a case study in a company developing a large software system, analysing ten components managed by one team. This team was later split into two, redistributing components between the new teams. Archival data from development tools used in their daily operations was collected. Before the split, there was a statistically significant negative correlation between contribution alignment and technical debt density in four components, indicating that higher contribution alignment leads to lower technical debt density and better code quality. After the split, this negative correlation persisted in three components, while five components showed a positive correlation, suggesting that low contribution alignment might worsen code quality degradation. Our findings suggest that contribution alignment is important in controlling code quality degradation in software development organisations. Ensuring teams are responsible for components they are most familiar with and minimising dependencies between teams can help mitigate code quality degradation.

cs.SE↗

arXiv2022

Assessing the Linguistic Quality of REST APIs for IoT Applications

Internet of Things (IoT) is a growing technology that relies on connected 'things' that gather data from peer devices and send data to servers via APIs (Application Programming Interfaces). The design quality of those APIs has a direct impact on their understandability and reusability. This study focuses on the linguistic design quality of REST APIs for IoT applications and assesses their linguistic quality by performing the detection of linguistic patterns and antipatterns in REST APIs for IoT applications. Linguistic antipatterns are considered poor practices in the naming, documentation, and choice of identifiers. In contrast, linguistic patterns represent best practices to APIs design. The linguistic patterns and their corresponding antipatterns are hence contrasting pairs. We propose the SARAv2 (Semantic Analysis of REST APIs version two) approach to perform syntactic and semantic analyses of REST APIs for IoT applications. Based on the SARAv2 approach, we develop the REST-Ling tool and empirically validate the detection results of nine linguistic antipatterns. We analyse 19 REST APIs for IoT applications. Our detection results show that the linguistic antipatterns are prevalent and the REST-Ling tool can detect linguistic patterns and antipatterns in REST APIs for IoT applications with an average accuracy of over 80%. Moreover, the tool performs the detection of linguistic antipatterns on average in the order of seconds, i.e., 8.396 seconds. We found that APIs generally follow good linguistic practices, although the prevalence of poor practices exists.

cs.SE↗