Dynamic algorithm selection for multi-sensor image registration

A session-based communication network is a store-and-forward message (or packet) switching network in which each session (conversation from logon until logoff) is assigned to a single communication route (or path) until its termination. Examples of such networks are TYMNET and SNA. A route selection algorithm can be either static or dynamic. A static selection is based on given route selection tables which are usually provided to the system by the system generation process. A dynamic selection uses dynamically changing information of the network for determining an optimal route for the new session to be assigned to. This paper develops both static and dynamic route selection algorithms which may be used in a session-based communication network. Route selection algorithms will be classified into several classes depending on the network work-load information available for making decisions. It will be shown that very simple algorithms give good robustness with good response time.

The current increase in the Internet traffic along with the global crisis have accelerated the roll-out of the next generation 5G network and key enabling technologies. In this context, addressing the end-to-end Quality of Service (QoS) provisioning in order to guarantee a sustainable service delivery to the end-users became of paramount importance. Some of the enabling technologies that could play a key role in this regard are Software Defined Network (SDN) and Machine Learning (ML). This paper proposes REDO, a Reinforcement lEarning-based Dynamic rOuting algorithm selection method that decides on the conventional routing algorithm to be applied on the traffic flows within a SDN environment. REDO will dynamically select the most appropriate routing algorithm from a set of centralized routing algorithms (MHA, WSP, SWP, MIRA) that maximizes the reward function from the network. The proposed REDO solution is implemented and evaluated using an experimental setup based on Mininet, Floodlight controller and Open vSwitch switches. The results show that REDO outperforms other state-of-the-art solutions.

Feature selection is an important pre-processing step in many fields, such as data mining, machine learning and pattern recognition. This paper focuses on dynamically updating a subset of features with new samples arriving and provides a hypergraph model to deal with dynamic feature selection problem. Firstly, we discuss the relationship between feature selection of information system and minimum vertex cover of hypergraph, and feature selection is converted to a minimum vertex cover problem based on this relationship. Then, an algorithm for generating induced hypergraph from information system is presented, the induced hypergraph can be divided into two part: the original induced hypergraph and the added hypergraph with new samples arriving. Finally, a novel dynamic feature selection algorithm based on minimum vertex cover of hypergraph is proposed, and this algorithm only needs a small amount of computation. Experiments show that the proposed method is feasible and highly effective.

A dynamic predictor selection algorithm for predicting stock market movement

With the increasing complexity of networked cooperative detection environment, new targets appear and leave in the detection area, and the mobility of targets is increasing. The emergence of sensors makes the sensors in the sensor network have certain motion characteristics. These uncertainties increase the complexity of the problem. At the same time, the dynamic selection of sensor resources needs to consider the needs of different priority tasks, platform survival risk, sensor cost and other factors. In view of these problems to be solved, based on the qualitative synthesis theory of predictive control and stochastic dynamic programming optimization theory, the dynamic sensor selection decision theory and method based on multi-step forward decision are explored. This paper studies the dynamic sensor strategy based on multi-step forward decision scheduling, and carries out the research on the optimization decomposition method of sensor selection under different structural characteristics, the dynamic optimization method of sensor selection under complex and uncertain environment, and the multi-objective optimization method of dynamic sensor selection under heterogeneous targets, so as to explore a new way of dynamic sensor selection algorithm design and performance analysis under networked collaborative tracking A new way. The research of dynamic target tracking algorithm in mobile sensor networks has important theoretical and engineering significance to improve the resource efficient utilization and the overall target tracking performance of sensor networks.

In this paper, we investigate a fifth generation cellular vehicle-to-everything based platoon system and propose low-complexity dynamic manager selection and resource allocation algorithms in the finite block length regime, to meet the ultra reliable and low latency communication requirements of intra-platoon safety-related data transmission. A closed-form expression for the platoon manager index is derived, based on which a low-complexity dynamic platoon manager selection algorithm is proposed, enabling a significant communication performance enhancement over the conventional head vehicle platoon manager algorithm. This is also the first work to investigate the impact of finite block length on platoon communication. The optimal finite block length coding rate under automatic repeat request retransmission is obtained. A subchannel multiplexing criterion is proposed and closed-form expressions for the optimal transmission powers of the platoon manager and its subchannel multiplexing partner are derived. Based on the theoretical findings, a joint resource allocation and coding rate optimization algorithm is proposed, achieving a near-optimal performance in terms of groupcast latency with a significant complexity reduction over exhaustive search.

Merit-guided dynamic feature selection filter for data streams

A dynamic overproduce-and-choose strategy for the selection of classifier ensembles

Electrocardiography (ECG) is one of the simplest and fastest methods for examining the cardiovascular system. Despite its widespread use in assessing cardiac health, collecting ECG data can be a challenge, often requiring the attachment of multiple sensors to the body or the use of specialized equipment. To overcome these limitations, many research has been conducted to find alternative approaches. One promising avenue is the use of photoplethysmography (PPG) data, which has a high correlation with ECG data and can be easily collected in real-time through wearable devices. Consequently, there has been growing interest in using PPG data to generate ECG data for real-time cardiac analysis. In this study, we propose a diffusion-based PPG-to-ECG translation with dynamic region of interest (ROI) selection, using the diffusion model success in various domains, including image, video, audio, and time-series data. Our proposed methodology addresses a key limitation of traditional diffusion models, which struggle to accurately generate the QRS complex which is an essential component of ECG data. We enhance the model performance by selectively adding noise to the ROI, focusing on the most critical segments. Instead of relying on hyperparameters for ROI selection, we develop a dynamic ROI selection algorithm. Furthermore, instead of using a standard U-Net architecture commonly used in image processing, we propose using a diffusion model suitable for time-series data, DiffWave, enabling more precise and detailed extraction of signal characteristics. To validate the performance of our model, we use a benchmark comprising five bio-signal datasets. Experimental results show that, compared with the baseline RDDM, our method reduced the average RMSE from 0.533 to 0.212 and FD from 129.88 to 14.28 across five benchmark datasets.

Existing feature selection methods mainly target single-label learning and multi-label learning, and only a few algorithms are optimized for label distribution learning. In label distribution learning, the associated labels of each sample have different levels of importance. Therefore, multi-label feature selection algorithms cannot be directly applied to label distribution learning. Discretizing label distribution data into multi-label data will cause part of the supervision information to be lost. In most practical applications of label distribution learning, the feature space is undefined, and the features are in the form of flow features. To solve this problem, this paper applies fuzzy rough set theory and applies the flow feature framework to propose a dynamic label distribution feature selection algorithm that handles flow features. Experimental results show that the proposed method is more effective than six state-of-the-art feature selection algorithms on 12 datasets with respect to six representative evaluation metrics.

Server selection is an important problem in replicated server systems distributed over the Internet. In this paper, we study two server selection algorithms under a server-based framework we have developed. These algorithms utilize server load and network performance information collected through a shared passive measurement mechanism to determine the appropriate server for processing a client request. The performance of these algorithms is studied using simulations. Comparison with two naive server selection algorithms is also made. The initial simulation results show that our dynamic server selection algorithms have superior performance over the two naive ones, and as a result, demonstrate the importance of dynamic server selection mechanisms in a replicated server system.

The growth of self-installed femtocells in residential and office environments triggers harmful femto-to-femto interference levels. In order to overcome this problem, we suggested that operators mutually share their licensed spectrum allowing femtocells to exploit also the frequency resources of other operators. By assuming mutual arrangements among operators, we proposed algorithms enabling femtocells to dynamically select the best operating channel among those available from every operator just based on local interference measurements. In such a way the interference between femtocells belonging to the same operator can be considerably reduced. In this paper we describe and evaluate performance of the proposed dynamic frequency selection algorithms in terms of outage probability and average throughput per femtocell. In our analysis we examine various scenarios in which we consider different number of available frequency channels. Results show that in a multi-operator environments the proposed approach allows to improve QoS in femtocell networks.

Aiming at improving the predictive ability of corporate financial distress, a method integrating decision tree and genetic algorithms is put forward to realize dynamic selection of financial ratios in the process of modeling. It uses genetic algorithms to optimize financial ratio set, so the ultimate decision tree model for financial distress prediction has a good balance between accuracy and generalization. Empirical study shows that this model's prediction accuracy for training samples and validation samples are respectively 94.67% and 93.75%. This indicates that the proposed method for financial distress prediction can dynamically optimize the financial ratio set and effectively avoid the over-fitting problem of decision tree to improve the generalization ability

In this paper we investigate the suitability of different types of Dynamic Classifier Selection approaches for the task of multimodal music mood classification. The dynamic selection methods evaluated were: KNORA-UNION, KNORAELIMINATE, Dynamic Ensemble Selection Performance, Overall Local Accuracy, Local Class Accuracy, Multiple Classifier Behaviour, A Priori and A Posteriori. The experiments were performed using the Brazilian Music Mood Database, which is a multimodal database, containing the audio signal itself, beyond their visual representation (i.e. spectrogram) and the lyrics. The obtained results have shown that the use of dynamic classifier selection methods can improve the classification results for the task at hand.

Underwater Acoustic Networks (UANs) play a critical role in marine monitoring and exploration. The integration of mobile nodes can extend the monitoring range and enhance network flexibility and real-time performance. UANs that combine both fixed and mobile nodes typically employ geographic routing protocols and dynamic communication techniques. However, in geographic routing protocols, the uncertainty of the next-hop node leads to several challenges, including access conflicts in the underwater acoustic medium, data collisions, and resource allocation difficulties. Non-Orthogonal Multiple Access (NOMA) technology allows for more users to access the network under limited frequency spectrum, thereby improving network performance. However, due to the complexity of underwater acoustic channels, existing NOMA solutions are difficult to be directly applied in marine environments. Moreover, many existing NOMA techniques rely on centralized control and require real-time global network information, which is challenging to be implemented in UANs. Currently, research on physical-layer and network-layer integrated Medium Access Control (MAC) protocols to address resource allocation and data collision issues remains limited. To address these challenges, this paper proposes the GNC-MAC protocol, compatible with geographic routing protocols and NOMA access techniques. First, we propose a dynamic programming-based grouping algorithm to address the user grouping problem in the uplink of underwater NOMA. Next, to tackle the resource allocation issue, we transform it into a problem of maximizing the sum of the system data transmission rates, and design a distributed dynamic power selection algorithm considering node constraints to improve system throughput. Finally, considering six dynamic factors, including channel quality, energy status, link stability, queue load, node mobility, and interruption probability, we design an adaptive backoff algorithm in the GNC-MAC protocol to optimize next-hop selection in geographic routing protocols and reduce packet collisions. The simulation results indicate that the overall performance of GNC-MAC outperforms existing advanced protocols and offers higher reliability.