• Extends the prior NLBSE tool competition work with an additional model family (SetFit). • Transforms the prototype into a reusable tool ( Beyond Balance ), providing easy-to-use access to the implemented loss-weighting strategies. • Compares the performance impact of loss-weighting across various strategies and model families. • Evaluates the generalizability of loss-weighting across two benchmark datasets from the NLBSE’24 and NLBSE’25 tool competitions. Datasets often contain heavily underrepresented classes. Class imbalance biases models toward frequent classes, reducing performance on rare but important categories; in-process strategies such as loss-weighting remain under-explored for software engineering artefacts. We investigate loss-weighting functions for code comment classification and package our methods into Beyond Balance , a reusable implementation offering multiple weighting strategies for Transformer- and Sentence-Transformer–based models. Loss weighting consistently improves F1 performance across datasets, demonstrating an effective and easily adoptable imbalance-handling technique through Beyond Balance .

The Internet of Things (IoT) enables the interconnection of new cyber-physical devices which generate significant traffic of distributed, heterogeneous and dynamic data at the network edge. Since several IoT applications demand for short response times (e.g., industrial applications, emergency management, real-time systems) and, at the same time, rely on resource-constrained devices, the adoption of traditional Data Mining techniques is neither effective nor efficient. Therefore, conventional Data Mining techniques need to be adjusted for optimizing response times, energy consumption and data traffic while still providing adequate accuracy as required by the IoT application. In this paper, new Data Mining approaches particularly tailored for the IoT scenario have been investigated, in particular with respect to the promising, emerging novel distributed computing paradigm of Edge Computing. In detail, two approximated versions of K-Means clustering algorithm, centralized and distributed, have been implemented in the EdgeCloudSim simulation framework and validated on a real system. As highlighted by the algorithm performance analysis, choosing an approximated and distributed clustering solution can provide benefits in terms of computation, communication and energy consumption, while maintaining high levels of accuracy. The management of such trade-off, obviously, has to be done in the light of the specific IoT application requirements.

A new adaptive sparse least squares support vector regression algorithm, referred to as SLSSVR has been introduced for the adaptive modeling of nonstationary systems. Using a sliding window of recent data set of size N to track t he non-stationary characteristics of the incoming data, our adaptive model is initially formulated based on least squares support vector regression with forgetting factor (without bias term). In order to obtain a sparse model in which some parameters are exactly zeros, a l1penalty was applied in parameter estimation in the dual problem. Furthermore we exploit the fact that since the associated system/kernel matrix in positive definite, the dual solution of least squares support vector machine without bias term, can be solved iteratively with guaranteed convergence. Furthermore since the models between two consecutive time steps there are (N-1) shared kernels/parameters, the online solution can be obtained efficiently using coordinate descent algorithm in the form of Gauss-Seidel algorithm with minimal number of iterations. This allows a very sparse model per time step to be obtained very efficiently, avoiding expensive matrix inversion. The real stock market dataset and simulated examples have shown that the proposed approaches can lead to superior performances in comparison with the linear recursive least algorithm and a number of online non-linear approaches in terms of modelling performance and model size.

Computing and spreading global information in large-scale distributed systems pose significant challenges when scalability, parallelism, resilience and consistency are demanded. Epidemic protocols are a robust and scalable computing and communication paradigm that can be effectively used for information dissemination and data aggregation in a fully decentralised context where each network node requires the local computation of a global synopsis function. Theoretical analysis of epidemic protocols for synchronous and static network models provide guarantees on the convergence to a global target and on the consistency among the network nodes. However, practical applications in real-world networks may require the explicit detection of both local convergence and global agreement (consensus). This work introduces the Epidemic Consensus Protocol (ECP) for the determination of consensus on the convergence of a decentralised data aggregation task. ECP adopts a heuristic method to locally detect convergence of the aggregation task and stochastic phase transitions to detect global agreement and reach consensus. The performance of ECP has been investigated by means of simulations and compared to a tree-based Three-Phase Commit protocol (3PC). Although, as expected, ECP exhibits total communication costs greater than the optimal tree-based protocol, it is shown to have better performance and scalability properties; ECP can achieve faster convergence to consensus for large system sizes and inherits the intrinsic decentralisation, fault-tolerance and robustness properties of epidemic protocols.

Mining data streams is a core element of Big Data Analytics. It represents the velocity of large datasets, which is one of the four aspects of Big Data, the other three being volume, variety and veracity. As data streams in, models are constructed using data mining techniques tailored towards continuous and fast model update. The Hoeffding Inequality has been among the most successful approaches in learning theory for data streams. In this context, it is typically used to provide a statistical bound for the number of examples needed in each step of an incremental learning process. It has been applied to both classification and clustering problems. Despite the success of the Hoeffding Tree classifier and other data stream mining methods, such models fall short of explaining how their results (i.e., classifications) are reached (black boxing). The expressiveness of decision models in data streams is an area of research that has attracted less attention, despite its paramount of practical importance. In this paper, we address this issue, adopting Hoeffding Inequality as an upper bound to build decision rules which can help decision makers with informed predictions (white boxing). We termed our novel method Hoeffding Rules with respect to the use of the Hoeffding Inequality in the method, for estimating whether an induced rule from a smaller sample would be of the same quality as a rule induced from a larger sample. The new method brings in a number of novel contributions including handling uncertainty through abstaining, dealing with continuous data through Gaussian statistical modelling, and an experimentally proven fast algorithm. We conducted a thorough experimental study using benchmark datasets, showing the efficiency and expressiveness of the proposed technique when compared with the state-of-the-art.

This work investigates the problem of feature selection in neuroimaging features from structural MRI brain images for the classification of subjects as healthy controls, suffering from Mild Cognitive Impairment or Alzheimer's Disease. A Genetic Algorithm wrapper method for feature selection is adopted in conjunction with a Support Vector Machine classifier. In very large feature sets, feature selection is found to be redundant as the accuracy is often worsened when compared to an Support Vector Machine with no feature selection. However, when just the hippocampal subfields are used, feature selection shows a significant improvement of the classification accuracy. Three-class Support Vector Machines and two-class Support Vector Machines combined with weighted voting are also compared with the former and found more useful. The highest accuracy achieved at classifying the test data was 65.5% using a genetic algorithm for feature selection with a three-class Support Vector Machine classifier.

In this paper a custom classification algorithm based on linear discriminant analysis and probability-based weights is implemented and applied to the hippocampus measurements of structural magnetic resonance images from healthy subjects and Alzheimer's Disease sufferers; and then attempts to diagnose them as accurately as possible. The classifier works by classifying each measurement of a hippocampal volume as healthy control-sized or Alzheimer's Disease-sized, these new features are then weighted and used to classify the subject as a healthy control or suffering from Alzheimer's Disease. The preliminary results obtained reach an accuracy of 85.8% and this is a similar accuracy to state-of-the-art methods such as a Naive Bayes classifier and a Support Vector Machine. An advantage of the method proposed in this paper over the aforementioned state-of-the-art classifierst is the descriptive ability of the classifications it produces. The descriptive model can be of great help to aid a doctor in the diagnosis of Alzheimer's Disease, or even further the understand of how Alzheimer's Disease affects the hippocampus.

Future extreme-scale high-performance computing systems will be required to work under frequent component failures. The MPI Forum's User Level Failure Mitigation proposal has introduced an operation, MPI_Comm_shrink, to synchronize the alive processes on the list of failed processes, so that applications can continue to execute even in the presence of failures by adopting algorithm-based fault tolerance techniques. This MPI_Comm_shrink operation requires a fault tolerant failure detection and consensus algorithm. This paper presents and compares two novel failure detection and consensus algorithms. The proposed algorithms are based on Gossip protocols and are inherently fault-tolerant and scalable. The proposed algorithms were implemented and tested using the Extreme-scale Simulator. The results show that in both algorithms the number of Gossip cycles to achieve global consensus scales logarithmically with system size. The second algorithm also shows better scalability in terms of memory and network bandwidth usage and a perfect synchronization in achieving global consensus.

This paper proposes and demonstrates Skilloscopy as an approach to the assessment of decision makers. In an increasingly sophisticated, connected, and information-rich world, decision making is becoming both more important and more difficult. At the same time, modeling decision making on computers is becoming more feasible and of interest, partly because the information input to those decisions is increasingly on record. The aims of Skilloscopy are to rate and rank decision makers in a domain relative to each other; these aims do not include an analysis of why a decision is wrong or suboptimal, nor the modeling of the underlying cognitive process of making the decisions. In the proposed method, a decision-maker is characterized by a probability distribution of its competence in choosing among quantifiable alternatives. This probability distribution is derived by classic Bayesian inference from a combination of prior belief and evidence of the decisions. Thus, decision makers' skills may be better compared, rated, and ranked. The proposed method is applied and evaluated in the game domain of chess. A large set of games by players across a broad range of the World Chess Federation (FIDE) Elo ratings has been used to infer the distribution of players' rating directly from the moves they play rather than from game outcomes. Demonstration applications address questions frequently asked by the chess community regarding the stability of the Elo rating scale, the comparison of players of different eras and/or leagues, and controversial incidents possibly involving fraud. The method of Skilloscopy may be applied in any decision domain where the value of the decision-options can be quantified.

Spatially distributed sensor nodes can be used to monitor systems and humans conditions in a wide range of application domains. A network of body sensors in a community of people generates large amounts of contextual data that requires a scalable approach for storage and processing. Cloud computing can provide a powerful, scalable storage and processing infrastructure to perform both online and offline analysis and mining of body sensor data streams. This paper presents BodyCloud, a system architecture based on Cloud Computing for the management and monitoring of body sensor data streams. It incorporates key concepts such as scalability and flexibility of resources, sensor heterogeneity, and the dynamic deployment and management of user and community applications.

K-Means is a popular clustering algorithm which adopts an iterative refinement procedure to determine data partitions and to compute their associated centres of mass, called centroids. The straightforward implementation of the algorithm is often referred to as `brute force' since it computes a proximity measure from each data point to each centroid at every iteration of the K-Means process. Efficient implementations of the K-Means algorithm have been predominantly based on multi-dimensional binary search trees (KD-Trees). A combination of an efficient data structure and geometrical constraints allow to reduce the number of distance computations required at each iteration. In this work we present a general space partitioning approach for improving the efficiency and the scalability of the K-Means algorithm. We propose to adopt approximate hierarchical clustering methods to generate binary space partitioning trees in contrast to KD-Trees. In the experimental analysis, we have tested the performance of the proposed Binary Space Partitioning K-Means (BSP-KM) when a divisive clustering algorithm is used. We have carried out extensive experimental tests to compare the proposed approach to the one based on KD-Trees (KD-KM) in a wide range of the parameters space. BSP-KM is more scalable than KDKM, while keeping the deterministic nature of the `brute force' algorithm. In particular, the proposed space partitioning approach has shown to overcome the well-known limitation of KD-Trees in high-dimensional spaces and can also be adopted to improve the efficiency of other algorithms in which KD-Trees have been used.

Systems Engineering often involves computer modelling the behaviour of proposed systems and their components. Where a component is human, fallibility must be modelled by a stochastic agent. The identification of a model of decision-making over quantifiable options is investigated using the game-domain of Chess. Bayesian methods are used to infer the distribution of players' skill levels from the moves they play rather than from their competitive results. The approach is used on large sets of games by players across a broad FIDE Elo range, and is in principle applicable to any scenario where high-value decisions are being made under pressure.

Visual exploration of scientific data in life science area is a growing research field due to the large amount of available data. The Kohonen's self organizing map (SOM) is a widely used tool for visualization of multidimensional data. In this paper we present a fast learning algorithm for SOMs that uses a simulated annealing method to adapt the learning parameters. The algorithm has been adopted in a data analysis framework for the generation of similarity maps. Such maps provide an effective tool for the visual exploration of large and multi-dimensional input spaces. The approach has been applied to data generated during the high throughput screening of molecular compounds; the generated maps allow a visual exploration of molecules with similar topological properties. The experimental analysis on real world data from the National Cancer Institute shows the speed up of the proposed SOM training process in comparison to a traditional approach. The resulting visual landscape groups molecules with similar chemical properties in densely connected regions.

In this paper, we present a Dynamic Load Balancing (DLB) policy for problems characterized by a highly irregular search tree, whereby no reliable workload prediction is available. DLB approaches based on global statistics are known to provide optimal load balancing performance, while randomized techniques provide high scalability. The proposed method combines both advantages and adopts distributed job-pools and a randomized polling policy. The method has been successfully adopted in a parallel search algorithm for sugbraph mining. The work load distribution process of the parallel application is based on a dynamic partitioning of the search space and a peer-to-peer communication framework. The effectiveness of the DLB method has been evaluated on a molecular biology dataset. The distributed application with the novel DLB method has shown good scalability and close-to linear speedup in a distributed network of workstations. Moreover, fault tolerance and dynamic resource aggregation make it suitable for largescale, multi-domain, heterogeneous environments, such as computational Grids.

In molecular biology, it is often desirable to find common properties in large numbers of drug candidates. One family of methods stems from the data mining community, where algorithms to find frequent graphs have received increasing attention over the past years. However, the computational complexity of the underlying problem and the large amount of data to be explored essentially render sequential algorithms useless. In this paper, we present a distributed approach to the frequent subgraph mining problem to discover interesting patterns in molecular compounds. This problem is characterized by a highly irregular search tree, whereby no reliable workload prediction is available. We describe the three main aspects of the proposed distributed algorithm, namely, a dynamic partitioning of the search space, a distribution process based on a peer-to-peer communication framework, and a novel receiver-initiated load balancing algorithm. The effectiveness of the distributed method has been evaluated on the well-known National Cancer Institute's HIV-screening data set, where we were able to show close-to linear speedup in a network of workstations. The proposed approach also allows for dynamic resource aggregation in a nondedicated computational environment. These features make it suitable for large-scale, multidomain, heterogeneous environments, such as computational grids

Active queue management (AQM) policies are those policies of router queue management that allow for the detection of network congestion, the notification of such occurrences to the hosts on the network borders, and the adoption of a suitable control policy. This paper proposes the adoption of a fuzzy proportional integral (FPI) controller as an active queue manager for Internet routers. The analytical design of the proposed FPI controller is carried out in analogy with a proportional integral (PI) controller, which recently has been proposed for AQM. A genetic algorithm is proposed for tuning of the FPI controller parameters with respect to optimal disturbance rejection. In the paper the FPI controller design methodology is described and the results of the comparison with random early detection (RED), tail drop, and PI controller are presented.

This paper proposes the deployment of a neural network computing environment on Active Networks. Active Networks are packet-switched computer networks in which packets can contain code fragments that are executed on the intermediate nodes. This feature allows the injection of small pieces of codes to deal with computer network problems directly into the network core, and the adoption of new computing techniques to solve networking problems. The goal of our project is the adoption of a distributed neural network for approaching tasks which are specific of the computer network environment. Dynamically reconfigurable neural networks are spread on an experimental wide area backbone of active nodes (ABone) to show the feasibility of the proposed approach.