Predictive maintenance involves collecting data from machines and using algorithms to analyze the machine’s condition or determine if the machine requires maintenance or repairs. This work presents a clustering-based algorithm for predictive maintenance that detects potential faults and gradual deterioration for IoT-based buses. It demonstrates that predictive maintenance enhances cost and time efficiency and improves user safety by enabling preemptive maintenance actions. While the predictive models implemented in this article focus on the cooling and engine torque systems, the methodology proposed is flexible and can be extended to other subsystems. To mitigate the problem of insufficient data, this work also generates synthetic datasets to simulate normal buses and buses with potential faults. Experiments on synthetic datasets simulating 78 buses deliver high-quality clusters with silhouette scores as high as 0.99 (cooling system) and 0.88 (engine system). Furthermore, the clusters identify the faulty components with an accuracy of 100%, that is, all the buses with potential faults were detected successfully. Predictive maintenance frameworks usually require large volumes of labeled data and suffer from imbalance issues; however, the proposed methodology in this article delivers highly accurate results even in the absence of large volumes of labeled data while being robust against imbalanced cases. Overall, this work contributes to predictive maintenance by presenting an efficient and practical solution that ensures the reliability and safety of transportation systems.

Federated Learning (FL) enables collaborative training of Machine Learning (ML) models while maintaining user data privacy. However, leaked model updates can reveal private training data. Existing solutions using additive secret sharing introduce intermediary servers, increasing complexity and communication overhead, and often lack privacy guarantees. We propose AddShare+, which enhances efficiency and scalability by creating additive shares for a subset of model weight parameters and using the Elliptic Curve Integrated Encryption Scheme (ECIES) for faster, lighter model encryption. By sampling and splitting a percentage of local weight parameters, AddShare+ reduces computation and communication costs while maintaining model accuracy. We implemented and evaluated AddShare+ on multiple datasets, comparing it with baseline approaches including FedAvg, SCOTCH, FedShare, and AddShare. Results demonstrate that AddShare+ maintains accuracy while significantly reducing running time per round. Notably, sharing as low as 25% of model weights decreases bandwidth demands by over 5x while preserving accuracy within 0.05 % of the full model. Our empirical results demonstrate significant reductions in running time per round with strong privacy guarantees, highlighting the potential of lightweight partial sharing solutions for privacy-preserving FL in resource-constrained environments, paving the way for more efficient and secure collaborative learning systems.

This paper introduces the Subspace Rotation Algorithm (SRA) for training the Restricted Hopfield Network (RHN) as an auto-associative memory. SRA is a gradient-free subspace tracking method based on Singular Value Decomposition (SVD) to update the weight matrix. Despite having slightly worse time complexity than Back-propagation (BP) theoretically, in practice, SRA completes training faster since it requires fewer iterations to converge. Comparative analysis with BP for training RHN reveals that SRA consistently reaches the optimal solution, whereas BP fails to achieve comparable performance if the weight initialization is not within the appropriate basin of attraction. Experiments involving the memorization of 10, 50, and 100 patterns from the MNIST dataset show that RHN trained with SRA exhibits better robustness to noisy and corrupted patterns compared to RHN trained with BP. These findings suggest that SRA offers a more reliable and effective method for training RHNs in applications needing high tolerance to input distortions.

Environmental sustainability is crucial for ensuring the long-term health and well-being of our planet and its in-habitants. Precise navigation of autonomous and semi-autonomous vehicles in agricultural usage, therefore, becomes a crucial com-ponent in ensuring such sustainability. It is no surprise that the use of visible light communication (VLC) in navigation is steadily expanding, driven primarily by its remarkable precision in indoor environments. VLC has significant potential as a su-perior alternative to traditional navigation systems, including the global positioning system (GPS), particularly in dynamic outdoor environments. However, despite its indoor success, addressing the challenges posed by ambient light remains critical, particularly in outdoor scenarios where natural lighting conditions vary substan-tially. This article investigates the complex relationship between ambient light and outdoor VLC technology. The study aims to quantify the impact of ambient light on the receiving power level at varying distances in outdoor VLC systems by employing advanced simulation and modelling techniques. It provides a detailed analysis of the effects of sunlight, offering valuable insights for optimizing the positioning of light transmitters and receivers to enhance performance and reliability in real-world applications. The results discussed have significant implications for advancing outdoor VLC technology. They provide a pathway for creating more resilient and efficient navigation systems that function seamlessly across various environmental conditions.

Agriculture and Agri-Food Canada, in its unwavering commitment to sustainable agriculture, has launched a program to reduce nitrous oxide (N 2 O) emissions from fertilizer utilization in farming practices. This initiative is a response to the pressing environmental and climate challenges we face. To achieve our goal, we must delve into the mechanism of N 2 O emission by measuring and predicting the flux of N 2 O. This study proposes a novel architecture for neural network models, namely the agriculture-informed neural network (AINN) model, consisting of recurrent neural networks and a process-based ecosystem model, the Dynamic Land Ecosystem Model (DLEM), to predict N 2 O emissions from farming. During the 2021 and 2022 growing seasons, field data on the flux of N 2 O, soil temperature, and soil moisture were collected. However, the amount of nitrate in the soil was missing since collecting accurate data on nitrate quantities from the soil was challenging. Therefore, assumptions about the nitrate quantity in the soil were made when training and testing AINN with the data collected from the 2021 and 2022 growing seasons. In 2024, from January to April, an indoor experiment under controlled conditions was successfully executed to collect data on nitrate quantity in the soil. This experiment demonstrated that nitrate quantity is an essential factor for predicting the emission of N 2 O. To demonstrate the versatility of the AINN across various neural networks, we conduct a comprehensive comparison with four state-of-the-art models: multilayer perceptron, convolutional neural network, long short-term memory, and Transformer. Our experiment and simulation results unequivocally demonstrate that the performance of AINN is superior to single neural network models. The DLEM component of the AINN acts as a regularizer, facilitating the training process of the AINN. This mathematical formulation transforms the problem of N 2 O emission into a constrained optimization issue, minimizing the explicit objective function and satisfying the constraints of the parameters fed into the DLEM in the AINN. The empirical results show that by incorporating information from the agricultural field, the AINN significantly reduces the generalization error compared to the corresponding neural network, underscoring its potential to revolutionize the field of neural network modeling.

Input cost reductions and yield optimization can be done using yield precision maps created by machine learning models to address the increase in food demand predicted by 2050. However, without taking into account the spatial structure of the data, the precision map’s accuracy evaluation assessment runs the risk of being overly optimistic. In the current work, a corn yield prediction study was conducted, and the predictive abilities of two vegetation indices (VIs) and five spectral bands for a single image acquisition date were evaluated. We also examined the impacts of image spatial and spectral resolution on model performance. We used a Canadian smart farm’s yield data, multispectral (MS) and red-green-blue (RGB) imagery captured by unmanned aerial vehicles (UAVs), and we trained deep neural networks (DNN), random forest (RF), and linear regression (LR) models using standard cross-validation and spatial cross-validation approaches. We found that multi-band datasets led to better performance than single-VI datasets. MS imagery led to generally better performance than RGB imagery. High spatial resolution imagery led to better performance than lower spatial resolution imagery. RF was the best performing model while LR was the worst. The choice of RF’s hyperparameters had more of an impact on performance when the number of features was small and less of an impact when the number of features was large or when the input dataset had a lot of spatial structure.

As the global population grows rapidly, ensuring food security has become a challenge. Climate change on the other hand has led to increased frequency and intensity of weather conditions, posing significant risks to agriculture production. An accurate yield prediction system plays a crucial role in addressing the challenge by enabling effective resource allocation, optimizing agriculture practices, and reducing risk. By accurately estimating end-of-season yield in advance, farmers can take timely proactive measures for risk mitigation and yield improvement. Current approaches suffer from imprecision, an incapacity to capture intricate nonlinear connections and the challenge of accounting for spatial-temporal variations. The current work proposes an end-to-end framework using 3 dimensional CNN models and compares different strategies to improve prediction performance. The data was collected from farms located in Ottawa, Ontario, where predominantly corn (measured in bushels per acre, bu/ac) is cultivated from the 2021 growing season divided into Early, Mid, and Later stages. Two CNN models (a) 2D CNN and (b) 3D CNN were tested, where the widely used 2D CNN model was used as a baseline. The findings demonstrated that the 3D CNN model, which also incorporates temporal features(crop changes over time), outperformed the 2D CNN model, which exclusively focuses on spatial characteristics. Overall, the 3D CNN model with stacked Early and growing season images was able to achieve a Mean Absolute Percentage Error of 15.18% and a Root Mean Square Error of 17.63 bu/ac.

In recent years, big data produced by the Internet of Things has enabled new kinds of useful applications. One such application is monitoring a fleet of vehicles in real time to predict their remaining useful life. The consensus self-organized models (COSMO) approach is an example of a predictive maintenance system. The present work proposes a novel Internet of Things based architecture for predictive maintenance that consists of three primary nodes: the vehicle node, the server leader node, and the root node, which enable on-board vehicle data processing, heavy-duty data processing, and fleet administration, respectively. A minimally viable prototype of the proposed architecture was implemented and deployed to a local bus garage in Gatineau, Canada. The present work proposes improved consensus self-organized models (ICOSMO), a fleet-wide unsupervised dynamic sensor selection algorithm. To analyze the performance of ICOSMO, a fleet simulation was implemented. The J1939 data gathered from a hybrid bus was used to generate synthetic data in the simulations. Simulation results that compared the performance of the COSMO and ICOSMO approaches revealed that in general ICOSMO improves the average area under the curve of COSMO by approximately 1.5% when using the Cosine distance and 0.6% when using Hellinger distance.

Identifying anomalous samples from highly complex and unstructured data is a crucial but challenging task in a variety of intelligent systems. In this paper, we present a novel deep anomaly detection framework named AnoDM (standing for Anomaly detection based on unsupervised Disentangled representation learning and Manifold learning). The disentanglement learning is currently implemented by β-VAE for automatically discovering interpretable factorized latent representations in a completely unsupervised manner. The manifold learning is realized by t-SNE for projecting the latent representations to a 2D map. We define a new anomaly score function by combining β-VAE's reconstruction error in the raw feature space and local density estimation in the t-SNE space. AnoDM was evaluated on both image and time-series data and achieved better results than models that use just one of the two measures and other deep learning methods.

In many real-world applications, the characteristics of data collected by activity logs, sensors and mobile devices change over time. This behavior is known as concept drift. In complex environments, which produce high dimensional data streams, machine learning tasks become cumbersome, as models become outdated very quickly. In our study, we assess hundreds of combinations of data characteristics and methods on network traffic data. Specifically, we focus on seven conventional machine learning and deep learning methods and compare their generalization power in the presence of concept drift. Our results show that Convolutional Neural Networks (CNNs) outperform conventional methods, even when compared to an idealized upper bound on their performance created in a piecewise manner by selecting the best method and its best configuration at each point in time, thus mimicking the output of a perfect meta-learning architecture. In the context of sequential data subject to concept drift, our results appear to defy the usually accepted ”No Free Lunch Theorem (NFL)”, which stipulates that no method dominates all the others in every situation. While this is by no means a rejection of the NFL Theorem, which captures a much more complex phenomenon, it is nonetheless a surprising result worth further investigations. As a matter of fact, our results show that, when data availability is limited, a meta-learning approach is preferable to CNNs, as it requires less data for training.

Following a series of deep learning breakthroughs in the area of image segmentation, multiple objects in an image input can be finely sub-categorized. Although Convolutional Neural Networks (CNNs) are known for their state-of-the-art performance in image classification, they present drawbacks when used to analyze different data types, such as time series. In this paper, we propose the Sequential Mask Convolutional Neural Network (SMCNN), a method that overcomes such drawbacks, and leverages CNNs for sequential data analysis. Our method transforms sequential data into an image representation by means of a specialized filter that produces flexible shape forms, and detects multiple types of outliers simultaneously. We evaluate the effectiveness of our method on data containing a variety of anomaly types combined with different concept drifts. The solution shows to significantly outperform prior endeavors and to provide high generalization capabilities on a wide array of data characteristics. We attribute its success to its ability to pinpoint the exact location of patterns and anomalies in parallel and to the invariance of CNNs, which allows them to adapt seamlessly to concept drifts.

Many industrial applications, from domains such as telecommunication, web and sales, require to perform complex analytics across several data processing systems. The performance of such analytics is usually expressed in workflows, and it is a task that is both labor-intensive and time-consuming. At the same time, with increasing amounts of data to be analysed, the optimization of analytics workflows becomes crucial for satisfying business objectives. This paper focuses on workflow optimization with respect to time efficiency, over multiple execution engines, such as a traditional DBMS, a MapReduce engine, and a scripting engine. This configuration is emerging as a common paradigm used to combine analysis of unstructured and structured data. We propose a novel optimization technique as part of our system called PAW (Platform for Analytics Workflows). This technique creates alternative workflow structures and their execution plans based on equivalent combinations and orders of operators. The technique employs an exhaustive and a heuristic algorithm to search efficiently the space of equivalent workflow structures and select the one with the optimal execution plan. We present a thorough experimental study and we showcase the efficiency of the proposed optimization technique in a fully fledged multi-engine system, applied on three real-world applications and their data, as well as on a synthetic benchmark.

Under the tuple-level uncertainty paradigm, we introduce a novel graphical model, Generator-Recognizer Network (GRN), as a model for probabilistic databases. The GRN modeling framework extends existing graphical models of probabilistic databases and is capable of representing a much wider range of dependence structures.

Under the tuple-level uncertainty paradigm, we formalize the use of a novel graphical model, Generator-Recognizer Network (GRN), as a model of probabilistic databases. The GRN modeling framework is capable of representing a much wider range of tuple dependency structure. We show that a GRN representation of a probabilistic database may undergo transitions induced by imposing constraints or evaluating queries. We formalize procedures for these two types of transitions such that the resulting graphical models after transitions remain as GRNs. This formalism makes GRN a self-contained modeling framework and a closed representation system for probabilistic databases - a property that is lacking in most existing models. In addition, we show that exploiting the transitional mechanisms allows a systematic approach to constructing GRNs for arbitrary probabilistic data at arbitrary stages. Advantages of GRNs in query evaluation are also demonstrated.

This is a demonstration of data coordination in a peer data management system through the employment of distributed triggers. The latter express in a declarative manner individual security and consistency requirements of peers, that cannot be ensured by default in the P2P environment. Peers achieve to handle in a transparent way data changes that come from local and remote actions and events. The distributed triggers are implemented as an extension of the active functionality of a centralized commercial DBMS. The language and execution semantics of distributed triggers are integrated in the kernel of the DBMS such that the latter handles transparently and simultaneously both centralized and distributed triggers. Moreover, the management of distributed triggers is associated with a set of peer acquaintance and termination protocols which are incorporated in the centralized DBMS.

We consider the problem of update processing in a peer-to-peer (P2P) database network where each peer consists of an independently created relational database. We assume that peers store related data, but data has heterogeneity wrt instances and schemas. The differences in schema and data vocabulary are bridged by value correspondences called mapping tables. Peers build an overlay network called acquaintance network, in which each peer may get acquainted with any other peer that stores related data. In this setting, the updates are free to initiate in any peer and are executed over other peers which are acquainted directly or indirectly with the updates initiator. The execution of an update is achieved by translating, through mapping tables, the update into a set of updates that are executed against the acquainted peers. We consider both the soundness and completeness of update translation. When updates are generated and propagated in the network initiated from a peer, a tree is built dynamically called Update Dependency Tree (UDT). The UDT depicts the relationships among the component updates generated from the initial update. We also discuss the issues of the update propagation when a peer is temporarily unavailable or offline. Our propagation mechanism keeps track of a peer when the peer is not available for a certain period of time and once the peer comes back online the system propagates the updates destined to the returning peer to keep it's database synchronized. Moreover, conflict detection and resolution strategies have been proposed for such a dynamic P2P database network. We have implemented and experimentally tested a prototype of our update processing mechanism on a small P2P database network. We show the results of our experiments.

The need for data sharing across heterogeneous data sources is growing. Peer Database Management Systems (PDBMSs) offer one data sharing approach, which favors a direct and dynamic node-to-node model of communication with no centralized control. Moreover, Service Oriented Architectures (SOA) using Web service technologies allow users to leverage existing assets towards the goal of building new architectures and integrating existing systems that can be componentized. We propose an Open Service Architecture for PDBMSs (OSAP). This architecture offers the main services of a PDBMS as Web services that are invoked via the communication network using a set of well-defined interfaces. This approach provides power and flexibility in terms of development and usage of the system. We have implemented this architecture within the Hyperion PDBMS infrastructure. We provide an analysis of the implementation of the OSAP architecture in terms of its characteristics. We also conduct a performance comparison with both the original Hyperion architecture, and a much simpler architecture that hides all the internal functionalities offered by a PDBMS as private processes that can be used by other peers only through one single web service which acts as peer manager.

We describe a mechanism based on distributed Event-Condition-Action (ECA) rules that supports data coordination in a multidatabase setting. The proposed mechanism includes an ECA rule language and a rule execution engine that transforms rules when they are first posted, and then coordinates their execution. Like traditional ECA rules, our ECA rule language has three parts: an event language, a condition language, and an action language. The event language provides a set of operators with a formal semantics for a multidatabase environment, and which allows a wide variety of composite events. The condition language provides Boolean algebra operators that take as operands either composite or simple conditions. The action language provides a conjunction of simple or composite actions. The execution model partitions rules to more easily manageable forms, distributes them to relevant databases, monitors their execution and composes their evaluations. The mechanism has been designed in a manner that minimizes the number of messages that need to be exchanged over the network. We have also conducted an experimental evaluation to compare the implementation with a naïve centralized execution model. The paper also presents a prototype implementation as well as experimental results on its performance. This work is part of an on-going project intended to develop data coordination techniques for data sharing settings.

Metadata comes into forefront as a savior of multimedia search and management. However, the existence of the diverse set of metadata standards and the different vocabularies used by these standards has made that task especially challenging in recent days. In this paper, we propose a framework for managing multimedia content by effectively dealing with the heterogeneous multimedia metadata in a transparent fashion. The cornerstone of our approach is to leverage the existing metadata standards and provide schema and data level mapping among them. The proposed framework also allows adding new tags/vocabularies with the given metadata vocabularies, defining equivalency relationship among those vocabularies, and separately managing the metadata vocabularies outside of the actual media files. We have developed a prototype of the framework and evaluated its performance in terms of some basic query execution times