Search

This study introduces an innovative approach to predict late delivery risks, aiming to strengthen supply chain resilience through smart, data-driven strategies. The approach combines clustering using the Elbow method and multiclassification, incorporating advanced deep learning models like Neural Network(NN), Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), and Bidirectional Long Short-Term Memory (Bi-LSTM). The findings highlight the effectiveness of the (CNN-LSTM) model in producing more accurate results, ultimately improving supply chain resilience, boosting customer satisfaction, and enabling proactive risk management.

Determining appropriate weights and biases for feed-forward neural networks is a critical task. Despite the prevalence of gradient-based methods for training, these approaches suffer from sensitivity to initial values and susceptibility to local optima. To address these challenges, we introduce a novel two-level clustering-based differential evolution approach, C2L-DE, to identify the initial seed for a gradient-based algorithm. In the initial phase, clustering is employed to detect some regions in the search space. Population updates are then executed based on the information available within each region. A new central point is proposed in the subsequent phase, leveraging cluster centres for incorporation into the population. Our C2L-DE algorithm is compared against several recent DE-based neural network training algorithms, and is shown to yield favourable performance.

In this paper, we consider an Internet-of-Things network supported by several satellites and multiple cache-assisted unmanned aerial vehicles (UAVs). We propose an optimisation problem with the aim of minimising the total network latency. To reduce the complexity of the original problem, it is divided into three sub-problems, namely, clustering ground users associated with UAVs, cache placement in UAVs (to support the network in avoiding backhaul congestion), and power allocation for satellites and UAVs. A non-cooperative game is designed to obtain the solution to the clustering problem; a genetic algorithm, which is powerful in the scenario of many variables, is employed to obtain the optimal solution to the high-complexity caching problem; and a quick estimation technique is used for power allocation. The total network latency is then minimised by using alternating optimisation technique. Numerical results prove the efficiency of our methods compared to other traditional ones. © 2023 IEEE.

Human Activity Recognition (HAR) plays a significant role in recent years due to its applications in various fields including health care and well-being. Traditional centralized methods reach very high recognition rates, but they incur privacy and scalability issues. Federated learning (FL) is a leading distributed machine learning (ML) paradigm, to train a global model collaboratively on distributed data in a privacy-preserving manner. However, for HAR scenarios, the existing action recognition system mainly focuses on a unified model, i.e. it does not provide users with personalized recognition of activities. Furthermore, the heterogeneity of data across user devices can lead to degraded performance of traditional FL models in the smart applications such as personalized health care. To this end, we propose a novel federated learning model that tries to cope with a statistically heterogeneous federated learning environment by introducing a group-personalized FL (GP-FL) solution. The proposed GP-FL algorithm builds several global ML models, each one trained iteratively on a dynamic group of clients with homogeneous class probability estimations. The performance of the proposed FL scheme is studied and evaluated on real-world HAR data. The evaluation results demonstrate that our approach has advantages in terms of model performance and convergence speed with respect to two baseline FL algorithms used for comparison. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Chillers are responsible for almost half of the total energy demand in buildings. Hence, the obligation of control systems of multi-chiller due to changes indoor environments is one of the most significant parts of a smart building. Such a controller is described as a nonlinear and multi-objective algorithm, and its fabrication is crucial to achieving the optimal balance between indoor thermal comfort and running a minimum number of chillers. This work proposes deep clustering of cooperative multi-agent reinforcement learning (DCCMARL) as well-suited to such system control, which supports centralized control by learning of agents. In MARL, since the learning of agents is based on discrete sets of actions and stats, this drawback significantly affects the model of agents for representing their actions with efficient performance. This drawback becomes considerably worse when increasing the number of agents, due to the increased complexity of solving MARL, which makes modeling policy very challenging. Therefore, the DCCMARL of multi-objective reinforcement learning is leveraging powerful frameworks of a hybrid clustering algorithm to deal with complexity and uncertainty, which is a critical factor that influences to the achievement of high levels of a performance action. The results showed that the ability of agents to manipulate the behavior of the smart building could improve indoor thermal conditions, as well as save energy up to 44.5% compared to conventional methods. It seems reasonable to conclude that agents' performance is influenced by what type of model structure.

In this preliminary work, we present an approach for the augmentation of clustering with natural language explanations. In clustering there are 2 main challenges: a) choice of a proper, reasonable number of clusters, and b) cluster analysis and profiling. There is a plethora of technics for a) but not so much for b), which is in general a laborious task of explaining obtained clusters. We propose a method that aids experts in cluster analysis by providing an iterative, human-in-the-loop methodology of generating cluster explanations. In an illustrative example, we show how the process of clustering on a set of objective variables could be facilitated with textual metadata. In our case, images of products from online fashion store are used for clustering. Then, product descriptions are used for profiling clusters. © 2022 Copyright for this paper by its authors., This paper is funded from the XPM (ExplainablePredictive Maintenance) project funded by the National Science Center, Poland under CHIST-ERAprogramme Grant Agreement No. 857925 (NCNUMO-2020/02/Y/ST6/00070).The work of Szymon Bobek has been additionallysupported by a HuLCKA grant from the PriorityResearch Area (Digiworld) under the Strategic Programme Excellence Initiative at the JagiellonianUniversity (U1U/P06/NO/02.16).The work of Samaneh Jamshidi was supportedby CHIST-ERA grant CHIST-ERA-19-XAI-012funded by Swedish Research Council.

Federated Learning (FL) provides a promising solution for preserving privacy in learning shared models on distributed devices without sharing local data on a central server. However, most existing work shows that FL incurs high communication costs. To address this challenge, we propose a clustering-based federated solution, entitled Federated Learning via Clustering Optimization (FedCO), which optimizes model aggregation and reduces communication costs. In order to reduce the communication costs, we first divide the participating workers into groups based on the similarity of their model parameters and then select only one representative, the best performing worker, from each group to communicate with the central server. Then, in each successive round, we apply the Silhouette validation technique to check whether each representative is still made tight with its current cluster. If not, the representative is either moved into a more appropriate cluster or forms a cluster singleton. Finally, we use split optimization to update and improve the whole clustering solution. The updated clustering is used to select new cluster representatives. In that way, the proposed FedCO approach updates clusters by repeatedly evaluating and splitting clusters if doing so is necessary to improve the workers’ partitioning. The potential of the proposed method is demonstrated on publicly available datasets and LEAF datasets under the IID and Non-IID data distribution settings. The experimental results indicate that our proposed FedCO approach is superior to the state-of-the-art FL approaches, i.e., FedAvg, FedProx, and CMFL, in reducing communication costs and achieving a better accuracy in both the IID and Non-IID cases. © 2022 by the authors., open access

Wireless Sensor Networks (WSNs) have been around for over a decade and have been used in many important applications. Energy and reliability are two of the major problems with these kinds of applications. Reliable data delivery is an important issue in WSNs because it is a key part of how well data are sent. At the same time, energy consumption in battery-based sensors is another challenge. Therefore, efficient clustering and routing are techniques that can be used to save sensors energy and guarantee reliable message delivery. With this in mind, this paper develops an energy-efficient and reliable clustering protocol (ERCP) for WSNs. First, an efficient clustering technique is proposed for sensor nodes’ energy savings considering different clustering parameters, including the link quality metric, the energy, the distance to neighbors, the distance to the sink node, and the cluster load metric. The proposed routing protocol works based on the concept of a reliable inter-cluster routing technique that saves energy. The routing decisions are made based on different parameters, such as the energy balance metric, the distance to the sink node, and the wireless link quality. Many experiments and analyses are examined to determine how well the ERCP performs. The experiment results showed that the ECRP protocol performs much better than some of the recent algorithms in both homogeneous and heterogeneous networks. © 2022 by the authors., open access

We study cluster assignment in multi-agent networks. We consider homogeneous diffusive networks, and focus on design of the graph that ensures the system will converge to a prescribed cluster configuration, i.e., specifying the number of clusters and agents within each cluster. Leveraging recent results from cluster synthesis, we show that it is possible to design an oriented graph such that the action of the automorphism group of the graph has orbits of predetermined sizes, guaranteeing that the network will converge to the prescribed cluster configuration. We provide upper and lower bounds on the number of edges that are needed to construct these graphs along with a constructive approach for generating these graphs. We support our analysis with some numerical examples., QC 20230510

Considering the unavailability of labeled data sets in remote sensing change detection, this letter presents a novel and low complexity unsupervised change detection method based on the combination of similarity and dissimilarity measures: mutual information (MI), disjoint information (DI), and local dissimilarity map (LDM). MI and DI are calculated on sliding windows with a step of 1 pixel for each pair of channels of both images. The resulting scalar values, weighted by q and m coefficients, are multiplied by the values of the center pixels of the windows weighted by p to remove the textures on images. The changes are detected using, respectively, the grayscale LDM and color LDM. A sliding window is then used on the color LDM and each pixel is characterized by a two-parameter Weibull distribution. Binarized change maps can be obtained by using a k-means clustering on the model parameters. Experiments on optical aerial image data set show that the proposed method produces comparable, even better results, to the state-of-the-art methods in terms of recall, precision, and F-measure.

Prediction of solar power generation is important in order to optimize energy exchanges in future micro-grids that integrate a large amount of photovoltaics. However, an accurate prediction is difficult due to the uncertainty of weather phenomena that impact produced power. In this paper, we evaluate the impact of different clustering methods on the forecast accuracy for predicting hourly ahead solar power when using machine learning based prediction approaches trained on weather and generated power features. In particular, we compare clustering methods using clearness index and K-means clustering, where we use both euclidian distance and dynamic time-warping. For evaluating prediction accuracy, we develop and compare different prediction models for each of the clusters using production data from a swedish SmartGrid. We demonstrate that proper tuning of thresholds for the clearness index improves prediction accuracy by 20.19% but results in worse performance than using K-means with all weather features as input to the clustering.

We study the mapping of software source code to architectural modules. Background: To evaluate techniques for performing automatic mapping of code-to-architecture, a ground truth mapping, often provided by an expert, is needed. From this ground truth, techniques use an initial set of mapped source code as a starting point. The size and composition of this set affect the techniques’ performance, and to make comparisons, random sizes and compositions are used. However, while randomness will give a baseline for comparison, it is not likely that a human expert would compose an initial set on random to map source code. We are interested in letting an expert create an initial set based on their experience with the system and study how this affects how a technique performs. Also, previous research has shown that when comparing an automatic mapping with the ground truth mappings, human experts often accept the automated mappings and, if not, point to the need for refactoring the source code. We want to study this phenomenon further. Audience: Researchers and developers of tools in the area of architecture conformance. The system expert can gain valuable insights into where the source code needs to be refactored. Aim: We hypothesize that an initial set assigned by an expert performs better than a random initial set of similar size and that an expert will agree upon or find opportunities for refactoring in a majority of cases where the automatic mapping and expert mapping disagrees. Method: The initial set will be extracted from an interview with the expert. Then the performance (precision and recall f1 score) will be compared to mappings starting from random initial sets and using an automatic technique. We will also use our tool to find the cases where the automatic and human mapping disagrees and then let the expert review these cases. Results: We expect to find a difference when performance is compared. We expect the expert review to reveal source code that should be rema

This paper considers the uplink of user-centric cellfree massive MIMO (multiple-input multiple-output) systems. We utilize the user-centric dynamic cooperation clustering (DCC) framework and derive the achievable spectral efficiency with two-layer decoding that is divided between the access points and the central processing unit (CPU). This decoding method is also known as large-scale fading decoding (LSFD). The fronthaul signaling load is analyzed and a nearly optimal second-layer decoding scheme at the CPU is proposed to reduce the fronthaul requirements compared to the optimal scheme.We also revisit the joint optimization of LSFD weights and uplink power control and show that the corresponding max-min fair optimization problem can be solved optimally via an efficient fixed-point algorithm. We provide simulations that bring new insights into the cell-free massive MIMO implementation., Part of proceedings: ISBN 978-3-8007-5688-9QC 20220615

The human mental search (HMS) algorithm is a relatively recent population-based metaheuristic algorithm, which has shown competitive performance in solving complex optimisation problems. It is based on three main operators: mental search, grouping, and movement. In the original HMS algorithm, a clustering algorithm is used to group the current population in order to identify a promising region in search space, while candidate solutions then move towards the best candidate solution in the promising region. In this paper, we propose a novel HMS algorithm, HMS-OS, which is based on clustering in both objective and search space, where clustering in objective space finds a set of best candidate solutions whose centroid is then also used in updating the population. For further improvement, HMS-OS benefits from an adaptive selection of the number of mental processes in the mental search operator. Experimental results on CEC-2017 benchmark functions with dimensionalities of 50 and 100, and in comparison to other optimisation algorithms, indicate that HMS-OS yields excellent performance, superior to those of other methods., Conference code: 176593; Cited By :1; Export Date: 8 June 2022; Conference Paper; Funding text 1: This research is funded within the SFEDU development program (PRIORITY 2030).