Rate Adaptation Research Articles

Dynamic long short-term memory model for enhanced product recommendations in e-commerce

Recommendation systems are pivotal for personalized user experiences, employing algorithms to predict and suggest items aligned with user preferences. Deep learning (DL) models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), excel in capturing sequential dependencies, enhancing recommendation accuracy. However, challenges persist in session-based recommendation systems, particularly with gradient descent and class imbalances. Addressing these challenges, this work introduces dynamic LSTM (D-LSTM), a novel DL-based recommendation system tailored for dynamic E-commerce environments. The primary objective is to optimize recommendation accuracy by effectively capturing temporal dependencies within user sessions. The methodology involves the integration of D-LSTM with weight matrix optimization and a Bayesian personalized ranking (BPR) adaptable learning rate optimizer to enhance learning efficiency. Experimental results demonstrate the efficacy of D-LSTM, showing significant improvements over existing models. Specifically, comparisons with the hybrid time-centric prediction (HTCP) model reveal a performance enhancement of 19.4%, 17.2%, 35.41%, and 21.99% for hit-rate (HR) and mean reciprocal rank (MRR) in 10k and 20k recommendation sets using the Tmall dataset. These findings underscore the superior performance of D-LSTM, highlighting its potential to advance personalized recommendations in dynamic E-commerce settings.

Establishment of a locally adaptive allele in multidimensional continuous space.

Local adaptation is widely seen when species adapt to spatially heterogeneous environments. Although many theoretical studies have investigated the dynamics of local adaptation using two-population models, there remains a need to extend the theoretical framework to continuous space settings, reflecting the real habitats of species. In this study, we use a multidimensional continuous space model and mathematically analyze the establishment process of local adaptation, with a specific emphasis on the relative roles of mutation and migration. First, the role of new mutations is evaluated by deriving the establishment probability of a locally adapted mutation using a branching process and a diffusion approximation. Next, the contribution of immigrants from a neighboring region with similar environmental conditions is considered. Theoretical predictions of the local adaptation rate agreed with the results of Wright-Fisher simulations in both mutation-driven and migration-driven cases. Evolutionary dynamics depend on several factors, including the strength of migration and selection, population density, habitat size, and spatial dimensions. These results offer a theoretical framework for assessing whether mutation or migration predominantly drives convergent local adaptation in spatially continuous environments in the presence of patchy regions with similar environmental conditions.

Exploring the Motives Behind the Adoption of Climate Change Adaptation Strategies among Farmers in the Czech Republic

AbstractClimate change threatens agriculture in the EU and is a primary issue discussed in the European Green Deal within the Common Agricultural Policy. Central and Eastern European countries are particularly prone to climate change effects, such as droughts and extreme weather. Therefore, agriculture in Central and Eastern Europe is expected to be increasingly affected by shifting climatic patterns. This study examines the motivation for adopting adaptation strategies derived from climate-smart agriculture among farmers in the Czech Republic. We drew particular attention to analyzing the influence of farm-level and information source variables on the adaptation behavior of Czech farmers. The dataset comprises 358 respondents who were asked about climate change adaptation through a quantitative survey. We analyzed the collected data via descriptive statistics and binary logit regression models. The analysis results reveal a high degree of awareness and a diversified usage of climate change adaptation strategies among the respondents. The close linkage between perceived profitability and the willingness to adapt to climate change requires policymakers to communicate economic benefits within this context further. Information sources, such as topic-specific journals, research institutions, and field training, positively influenced the adaptation rates among the sample. Therefore, we recommend focusing on these media channels to communicate targets set within the European Green Deal.

Delay management for heterogeneous traffic in vehicular sensor networks using packet fragmentation of low priority data

AbstractVehicular sensor networks (VSNs) are expected to revolutionize the transportation systems through automated decision‐making. These networks function on the communication between vehicles, traffic infrastructure, and people. One of the major challenges of VSNs is to deal with heterogeneous traffic due to the diverse nature of information and data generated by different types of sensors and devices within the vehicular environment. To ensure an effective operation of the network, it is crucial to offer a differentiated quality of service to each traffic class. Media access control (MAC) protocols offer an opportunity to provide differentiated channel access to the traffic of different priorities. This work is focused on offering comparison of recent MAC schemes in terms of their performance for heterogeneous traffic generated by VSNs. Two protocols FROG‐MAC and UrgMAC have been selected: FROG‐MAC is developed using a simple concept of packet fragmentation, where the packets of lower priority are fragmented to offer an early transmission opportunity to urgent traffic; on the other hand, urgMAC is designed using advanced cross‐layer techniques of two‐tiered service differentiation mechanism, adaptive data rate adjustment mechanism, urgency‐based contention window size adaptation, traffic type adaptive duty cycle, and multimedia message passing. It has been found that the FROG‐MAC outperforms urgMAC in terms of delay, energy consumption and packet delivery ratio.

FEATURES OF SOCIO-PSYCHOLOGICAL ADAPTATION IN STUDENTS WITH RATIONAL AND PRALOGICAL THINKING

The article describes the results of a study on the features of the socio-psychological adaptation of students with rational and pralogical types of thinking. The purpose of the study was to identify who has higher rates of socio-psychological adaptation, owners of rational or pralogical thinking.

AdaLo: Adaptive learning rate optimizer with loss for classification

Gradient-based algorithms are frequently used to optimize neural networks, with various methods developed to enhance their performance. Among them, the adaptive moment estimation (Adam) optimizer is well-known for its effectiveness and ease of implementation. However, it suffers from poor generalization without a learning rate scheduler. Additionally, it has the disadvantage of a large computational burden because of individual learning rate term, as known as second-order moments of gradients. In this study, we propose a novel gradient descent algorithm called AdaLo, which stands for Adaptive Learning Rate Optimizer with Loss. AdaLo addresses two problems using its adaptive learning rate (ALR). Firstly, the proposed ALR adjusts the learning rate, based on the model's training progress, specifically the loss value. Therefore AdaLo's ALR effectively replaces traditional learning rate schedulers. Secondly, the ALR is a scalar global learning rate, reducing the computational burden. In addition, the stability of the proposed method is analyzed from the perspective of the learning rate. The superiority of AdaLo was proven by non-convex functions. Simulation results indicated that the proposed optimizer outperformed the Adam, AdaBelief, and diffGrad with regard to the training error and test accuracy.

CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis

Psoriasis, being a chronic, inflammatory, lifelong skin disorder, has become a major threat to the human population. The precise and effective diagnosis of psoriasis continues to be difficult for clinicians due to its varied nature. In northern India, the prevalence of psoriasis among adult population ranges from 0.44 to 2.8%. Chronic plaque psoriasis accounts for over 90% of cases. This study utilized a dataset of 325 raw images collected from a reputable local hospital using a digital camera under uniform lighting conditions. These images were processed to generate 496 image patches (both diseased and normal), which were then normalized and resized for model training. An automated psoriasis image recognition framework was developed using four state-of-the-art deep transfer learning models: VGG16, VGG19, MobileNetV1, and ResNet-50. The convolutional layers adopted various edge, shape, and color filters to generate the feature map for psoriasis detection. Each pre-trained model was adapted with two dense layers, one dropout layer, and one output layer to classify input images. Among these models, MobileNetV1 achieved the best performance, with 94.84% sensitivity, 89.37% specificity, and 97.24% overall accuracy. Hyper-parameter tuning was performed using grid search to optimize learning rates, batch sizes, and dropout rates. The AdaGrad (Adaptive gradient)) optimizer was chosen for its adaptive learning rate capabilities, facilitating quicker convergence in model performance. Consequently, the methodology’s performance improved to 94.25% sensitivity, 96.42% specificity, and 99.13% overall accuracy. The model’s performance was also compared with non-machine learning-based diagnostic methods, yielding a Dice coefficient of 0.98. However, the model’s effectiveness is dependent upon high-quality input images, as poor image conditions may affect accuracy, and it may not generalize well across diverse demographics or psoriasis variations, highlighting the need for varied training datasets for robustness.

Forest Aboveground Biomass Estimation Based on Unmanned Aerial Vehicle-Light Detection and Ranging and Machine Learning.

Eucalyptus is a widely planted species in plantation forests because of its outstanding characteristics, such as fast growth rate and high adaptability. Accurate and rapid prediction of Eucalyptus biomass is important for plantation forest management and the prediction of carbon stock in terrestrial ecosystems. In this study, the performance of predictive biomass regression equations and machine learning algorithms, including multivariate linear stepwise regression (MLSR), support vector machine regression (SVR), and k-nearest neighbor (KNN) for constructing a predictive forest AGB model was analyzed and compared at individual tree and stand scales based on forest parameters extracted by Unmanned Aerial Vehicle-Light Detection and Ranging (UAV LiDAR) and variables screened by variable projection importance analysis to select the best prediction method. The results of the study concluded that the prediction model accuracy of the natural transformed regression equations (R2 = 0.873, RMSE = 0.312 t/ha, RRMSE = 0.0091) outperformed that of the machine learning algorithms at the individual tree scale. Among the machine learning models, the SVR prediction model accuracy was the best (R2 = 0.868, RMSE = 7.932 t/ha, RRMSE = 0.231). In this study, UAV-LiDAR-based data had great potential in predicting the AGB of Eucalyptus trees, and the tree height parameter had the strongest correlation with AGB. In summary, the combination of UAV LiDAR data and machine learning algorithms to construct a predictive forest AGB model has high accuracy and provides a solution for carbon stock assessment and forest ecosystem assessment.

An autoencoder-based confederated clustering leveraging a robust model fusion strategy for federated unsupervised learning

Concerns related to data privacy, security, and ethical considerations become more prominent as data volumes continue to grow. In contrast to centralized setups, where all data is accessible at a single location, model-based clustering approaches can be successfully employed in federated settings. However, this approach to clustering in federated settings is still relatively unexplored and requires further attention. As federated clustering deals with remote data and requires privacy and security to be maintained, it poses particular challenges as well as possibilities. While model-based clustering offers promise in federated environments, a robust model aggregation method is essential for clustering rather than the generic model aggregation method like Federated Averaging (FedAvg). In this research, we proposed an autoencoder-based clustering method by introducing a novel model aggregation method FednadamN, which is a fusion of Adam and Nadam optimization approaches in a federated learning setting. Therefore, the proposed FednadamN adopted the adaptive learning rates based on the first and second moments of gradients from Adam which offered fast convergence and robustness to noisy data. Furthermore, FednadamN also incorporated the Nesterov-accelerated gradients from Nadam to further enhance the convergence speed and stability. We have studied the performance of the proposed Autoencoder-based clustering methods on benchmark datasets and using the novel FednadamN model aggregation strategy. It shows remarkable performance gain in federated clustering in comparison to the state-of-the-art.

Reinforcement learning method based on sample regularization and adaptive learning rate for AGV path planning

Reinforcement learning method based on sample regularization and adaptive learning rate for AGV path planning

Perception and reconstruction of temperature field in forgings based on physical model and CNN model

Accurately perceiving and reconstructing the temperature field of hot-deformed large forgings is essential for intelligent forging and enhancing forging quality. In this study, the surface temperature of large forgings is measured using an infrared thermal imager. The relationship between the grayscale of infrared images and the surface temperature of large forgings is analyzed. A physical model, incorporating a convolutional neural network (CNN) model, is established to ascertain the surface temperature of large forgings. The CNN model utilizes standard convolution and multilayer perceptron modules for the backbone network and implements an adaptive learning rate. The correlation between three channel information and the surface temperature besides the grayscale is considered in the CNN model. Lastly, this study proposes a method for reconstructing the temperature field of large forgings based on the developed perception model, enabling accurate surface temperature measurement even when the large forgings are covered by oxide skin.

Intelligent Gear Decision Method for Vehicle Automatic Transmission System Based on Data Mining

The gear decision logic of automatic transmission directly affects the vehicle's dynamic, fuel economic, and comfort performance. This study employs data mining techniques to address the issues of low adaptability and low recognition rate in the intelligent gear decision of vehicle automatic transmission systems. The research further proposes the utilization of Kalman filter, Hidden Markov Models, and Long Short-Term Memory networks for condition feature recognition and time series classification. Subsequently, dynamic programming algorithms are employed to optimize intelligent gear decisions. Combining driver intent and driving environment, an intelligent gear decision method is formulated. The results indicate that, during a 430s driving segment, the intelligent gear decision method consumes only 464mL of fuel, closely resembling the economic strategy's 457mL, with a gear shift frequency of 53, significantly better than the 79 shifts in the economic strategy. Moreover, the error rate for slope condition recognition is only 0.062%. In a 200s coupled condition, the intelligent gear decision results in fuel consumption of 207mL, approximating the actual vehicle's 219mL, while power-shifting consumes 316mL, and economic shifting only 202mL. This study not only improves the accuracy of gear decisions but also effectively enhances vehicle operational efficiency, providing valuable insights for future automatic transmission systems with significant practical value.

European waste management regulations in Spanish local administrations: Compliance assessment and integration Frontiers

AbstractThis research analyzes the impact of European directives, particularly the Waste Framework Directive, on municipal waste management in Spain, with a focus on Law 7/2022 promoting circular economy principles. Through an assessment of waste management ordinances in 980 municipalities, the study found that over 60% of local ordinances have not yet fully incorporated the latest regulatory requirements, indicating significant delays in adapting to European regulations. The findings reveal notable disparities in compliance, with larger municipalities showing higher adaptation rates compared to smaller ones. Additionally, regions like Catalonia and the Balearic Islands have adopted innovative approaches, including ‘pay‐as‐you‐throw’ schemes and community composting. The study underscores the critical need for better integration of circular economy principles, enhanced monitoring, and increased public awareness to promote sustainable waste management practices. By identifying regulatory gaps, this research aims to provide practical insights for improving local waste management policies and fostering greater compliance with EU mandates.

Reconciling theories of dominance with the relative rates of adaptive substitution on sex chromosomes and autosomes.

The dominance of beneficial mutations is a key evolutionary parameter affecting the rate and genetic basis of adaptation, yet it is notoriously difficult to estimate. A leading method to infer it is to compare the relative rates of adaptive substitution for X-linked and autosomal genes, which-according to a classic model by Charlesworth et al. (1987)-is a simple function of the dominance of new beneficial mutations. Recent evidence that rates of adaptive substitution are faster for X-linked genes implies, accordingly, that beneficial mutations are usually recessive. However, this conclusion is incompatible with leading theories of dominance, which predict that beneficial mutations tend to be dominant or overdominant with respect to fitness. To address this incompatibility, we use Fisher's geometric model to predict the distribution of fitness effects of new mutations and the relative rates of positively selected substitution on the X and autosomes. Previous predictions of faster-X theory emerge as a special case of our model in which the phenotypic effects of mutations are small relative to the distance to the phenotypic optimum. But as mutational effects become large relative to the optimum, we observe an elevated tempo of positively selected substitutions on the X relative to the autosomes across a broader range of dominance conditions, including those predicted by theories of dominance. Our results imply that, contrary to previous models, dominant and overdominant beneficial mutations can plausibly generate patterns of faster-X adaptation. We discuss resulting implications for genomic studies of adaptation and inferences of dominance.

COBIRAS: Offering a Continuous Bit Rate Slide to Maximize DASH Streaming Bandwidth Utilization

Reaching close-to-optimal bandwidth utilization in dynamic adaptive streaming over HTTP (DASH) systems can, in theory, be achieved with a small discrete set of bit rate representations. This includes typical bit rate ladders used in state-of-the-art DASH systems. In practice, however, we demonstrate that bandwidth utilization, and consequently the quality of experience (QoE), can be improved by offering a continuous set of bit rate representations, i.e., a continuous bit rate slide (COBIRAS). Moreover, we find that the buffer fill behavior of different standard adaptive bit rate (ABR) algorithms is sub-optimal in terms of bandwidth utilization. To overcome this issue, we leverage COBIRAS’ flexibility to request segments with any arbitrary bit rate and propose a novel ABR algorithm MinOff , which helps maximizing bandwidth utilization by minimizing download off-phases during streaming. To avoid extensive storage requirements with COBIRAS and to demonstrate the feasibility of our approach, we design and implement a proof-of-concept DASH system for video streaming that relies on just-in-time encoding ( JITE ), which reduces storage consumption on the DASH server. Finally, we conduct a performance evaluation on our testbed and compare a state-of-the-art DASH system with few bit rate representations and our JITE DASH system, which can offer a COBIRAS, in terms of bandwidth utilization and video QoE for different ABR algorithms.

User-Perceived Capacity: Theory, Computation, and Achievable Policies

User-perceived throughput is a novel performance metric attracting a considerable amount of recent attention because it characterizes the quality of the experience in mobile multimedia services. For instance, it gives a data rate of video streaming with which a user will not experience any lag or outage in watching video clips. However, its performance limit remains open. In this paper, we are interested in the achievable upper bound of user-perceived throughput, also referred to as the user-perceived capacity, and how to achieve it in typical wireless channels. We find that the user-perceived capacity is quite limited or even zero with channel state information at the receiver (CSIR) only. When both CSIR and channel state information at the transmitter (CSIT) are available, the user-perceived throughput can be substantially improved by power or even rate adaptation. A constrained Markov decision process (CMDP)-based approach is conceived to compute the user-perceived capacity with joint power–rate adaptation. It is rigorously shown that the optimal policy obeys a threshold-based rule with time, backlog, and channel gain thresholds. With power adaptation only, the user-perceived capacity is equal to the hard-delay-constrained capacity in our previous work and achieved by joint diversity and channel inversion.

Computational modeling of cardiac electrophysiology applied to a swine model of Long QT Syndrome

Abstract Background Computational models are pivotal for understanding electrophysiological aspects of cardiac diseases. Despite pigs' increased use in research, limited in vitro porcine data impedes accurate mathematical modeling. In this context, we recently developed a novel knock-in porcine model of long QT syndrome type 8 (LQT8) [1]. Purpose To develop a novel computational model for electrophysiology and Ca2+ handing in wild-type and LQT8 swine ventricular cardiomyocytes. Methods We designed a mathematical model of wild-type swine action potential (AP) based on a wide range of cellular electrophysiological data. Using the ORd model [2] as a foundation, we re-parametrized main ionic currents using the Nelder-Mead algorithm. We then modified the model to simulate LQT8, evaluating its utility in exploring arrhythmogenic mechanisms and pharmacological approaches. For the L-type Ca Channel (LTCC), we replaced the original HH formulation with a Markov model based on [3], which was subsequently modified to account for a population of mutant p.G406R channels. Selected biomarkers for validation were AP duration at 20, 50, and 90% of repolarization, maximum upstroke velocity, AP amplitude and resting membrane potential. To assess the robustness of the model, we generated a random population of 500 models accounting for biological variability by sampling key parameters in the range [-20 to +20%] of their original values, using the Latin Hypercube Sampling. Simulations were executed using MATLAB R2023a. Numerical integration was performed utilizing the MATLAB function ode15s. Results The mathematical model accurately reproduced a wide range of experimental data, including steady-state curves of the main ionic currents, kinetic properties of LTCC, APD rate dependency, maximum upstroke velocity and Ca2+transient morphology. The model successfully simulated AP prolongation in LQT8. Also, it replicated key features of the cellular phenotype such as steeper APD rate adaptation, increased duration and amplitude of the Ca2+ transients, increased CaMKII-mediated late Na+ current, pathologically decreased upstroke velocity with increasing pacing frequency, due to a CaMKII-mediated mechanism. As a proof-of-concept, the model was utilized to investigate arrhythmogenic mechanisms and pharmacological approaches for LQT8. According to model’s prediction, early afterdepolarizations (EADs) in LQT8 can stem from three distinct mechanisms: improper kinetics of late Na+ current, improper kinetics of LTCC, and enhanced late-systolic SR Ca release. Notably, the model also predicts that full CaMKII inhibition effectively eliminates EADs for all three mechanisms, showcasing the potential efficacy of this pharmacological intervention. Conclusions A novel mathematical swine ventricular myocyte model explores arrhythmogenic mechanisms and therapeutic interventions, aiding LQT8 research and clinical translation in cardiac disorders.

Robust optimization incorporating weekly predicted anatomical CTs in IMPT of nasopharyngeal cancer.

Objective.This study proposes a robust optimization (RO) strategy utilizing virtual CTs (vCTs) predicted by an anatomical model in intensity-modulated proton therapy (IMPT) for nasopharyngeal cancer (NPC).Methods and Materials.For ten NPC patients, vCTs capturing anatomical changes at different treatment weeks were generated using a population average anatomy model. Two RO strategies of a 6 beams IMPT with 3 mm setup uncertainty (SU) and 3% range uncertainty (RU) were compared: conventional robust optimization (cRO) based on a single planning CT (pCT), and anatomical RO incorporating 2 and 3 predicted anatomies (aRO2 and aRO3). The robustness of these plans was assessed by recalculating them on weekly CTs (week 2-7) and extracting the voxel wise-minimum and maximum doses with 1 mm SU and 3% RU (voxmin\voxmax1mm3%).Results.The aRO plans demonstrated improved robustness in high-risk CTV1 and low-risk CTV 2 coverage compared to cRO plans. The weekly evaluation showed a lower plan adaptation rate for aRO3 (40%) vs. cRO (70%). The weekly nominal and voxmax1mm3%doses to OARs, especially spinal cord, are better controlled relative to their baseline doses at week 1 with aRO plans. The accumulated dose analysis showed that CTV1&2 had adequate coverage and serial organs (spinal cord and brainstem) were within their dose tolerances in the voxmin\voxmax1mm3%, respectively.Conclusion.Incorporating predicted weekly CTs from a population based average anatomy model in RO improves week-to-week target dose coverage and reduces false plan adaptations without increasing normal tissue doses. This approach enhances IMPT plan robustness, potentially facilitating reduced SU and further lowering OAR doses.

Research on Rate Adaptation of Underwater Optical Communication with Joint Control of Photoelectric Domain

As the communication distance changes, the received signal strength of an underwater optical communication system will change, and the range of its variation may not only exceed the dynamic range of the photoelectric detection device but also cause the reliability of communication to change due to the change in the received signal-to-noise ratio. In order to maintain better communication over a longer distance, this paper proposes a rate-adaptive method for underwater optical communication with joint control in the photoelectric domain. In the optical domain, the incident light’s power is adaptively adjusted by controlling the transmittance of the liquid crystal light valve to reduce saturation distortion. In the electrical domain, the constellation distribution is optimized according to the desired probability mass function, and the modulation order is adjusted in real time by estimating the received signal-to-noise ratio of the link. The simulation results show that under the forward error correction (FEC) threshold, the proposed method increases the dynamic range of the photomultiplier tube (PMT) by about 10 dB and expands the dynamic range of the system’s communication distance.

A multi-objective indirect neural adaptive processes control design for minimization of energy consumption: An experimental validation on a transesterification reactor

Nowadays, energy management environment is a very important issue that technologies have focused on in order to save costs and minimize energy waste. This objective can be achieved by means of an energy resource management approach through an appropriate optimization technique. However, energy savings can conflict with other objective functions, to solve the problem a multi-objective optimization that considers the minimization of the control energy can be adopted. In this paper, we propose to use a multi-objective indirect neural adaptive control concept for nonlinear systems with unknown dynamics. The control scheme consists of an adaptive instantaneous neural emulator and neural controller built on fully connected real-time recurrent learning networks (RTRL). The multi-objective particle swarm optimization (MOPSO) algorithm is used as a mechanism to find NE and NC adaptive learning rates that optimize the proposed objective functions: control energy minimization and closed-loop preservation. Comparative studies and experimental validation on a semi-batch reactor, used to generate cleaner biofuels, are performed to confirm the effectiveness of the proposed strategy.