Cold Start Research Articles

UPGCN: User Perception-Guided Graph Convolutional Network for Multimodal Recommendation

To tackle the challenges of cold start and data sparsity in recommendation systems, an increasing number of researchers are integrating item features, resulting in the emergence of multimodal recommendation systems. Although graph convolutional network-based approaches have achieved significant success, they still face two limitations: (1) Users have different preferences for various types of features, but existing methods often treat these preferences equally or fail to specifically address this issue. (2) They do not effectively distinguish the similarity between different modality item features, overlook the unique characteristics of each type, and fail to fully exploit their complementarity. To solve these issues, we propose the user perception-guided graph convolutional network for multimodal recommendation (UPGCN). This model consists of two main parts: the user perception-guided representation enhancement module (UPEM) and the multimodal two-step enhanced fusion method, which are designed to capture user preferences for different modalities to enhance user representation. At the same time, by distinguishing the similarity between different modalities, the model filters out noise and fully leverages their complementarity to achieve more accurate item representations. We performed comprehensive experiments on the proposed model, and the results indicate that it outperforms other baseline models in recommendation performance, strongly demonstrating its effectiveness.

Towards GPU-enabled serverless cloud edge platforms for accelerating HEVC video coding

Multimedia streaming has become integral to modern living, reshaping entertainment consumption, information access, and global engagement. The ascent of cloud computing, particularly serverless architectures, plays a pivotal role in this transformation, offering dynamic resource allocation, parallel execution, and automatic scaling-especially beneficial in HTTP Adaptive Streaming (HAS) applications. This study presents an event-driven serverless cloud edge platform with graphics processing units (GPUs), managed by Knative, tailored for video encoding. Two implementations of the High Efficiency Video Coding (HEVC) codec have been encapsulated in the functions: HEVC NVENC (Nvidia Encoder), that uses GPU acceleration, and x265 that only uses CPUs. Experiments focused on measuring the impact of replica requested resources on cold start, scalability and resource consumption with different allocated resources on slim and fat virtual machines (VMs). The best results are obtained when four slim replicas of the functions are deployed on a fat VM with a 8.4% reduction in encoding time for x265 and a 15.2% improvement for HEVC NVENC compared with other deployment scenarios. Comparatively, HEVC NVENC encoding is 8.3 times faster than x265. In multiresolution scenarios, GPU encoding drastically reduces segment encoding time by a factor of 12.4 between non-GPU and GPU-accelerated. These findings are important for live streaming applications where low latency is critical at all stages of the streaming process.

Study on the redistribution mechanism and secondary purge strategy of proton exchange membrane fuel cells

Effective control of membrane water content is essential for increasing the space for ice formation during the cold start stage and enhancing the success rate of start-up. Shutdown purge can effectively lower the membrane water content following fuel cell operation. However, during the cooling and standing process after purge, the rapid change in saturated vapor pressure can result in the redistribution of membrane dissolved water, leading to an increase in its content and a reduction in the success rate of cold start. Therefore, this study establishes a multidimensional, multiphase simulation model to comprehensively and thoroughly analyze the redistribution mechanism after purging and investigates the relationship between membrane water content and cold start. This is achieved by identifying the maximum membrane water content boundary during the cold start process and ultimately improving the success rate of cold start through a secondary purge strategy. The research results indicate that the membrane water content of the fuel cell increases from 2.31 to 8.31 after redistribution. During the cold start stage, the cold start success of the fuel cell under different environmental temperatures exhibits relatively specific boundary conditions, with the cold start process being closely related to the load current density and initial membrane water content. After implementing the secondary purging strategy, the membrane water content of the fuel cell decreases again, displaying favorable cold start characteristics in the cold start stage and successfully starting at −10 °C. This study can provide a reliable basis for the development of purging strategies during shutdown and offer a theoretical foundation for the boundary identification process of cold start.

Natural Language Processing and Machine Learning-Based Solution of Cold Start Problem Using Collaborative Filtering Approach

In today’s digital era, the abundance of online services presents users with a daunting array of choices, spanning from streaming platforms to e-commerce websites, leading to decision fatigue. Recommendation algorithms play a pivotal role in aiding users in navigating this plethora of options, among which collaborative filtering (CF) stands out as a prevalent technique. However, CF encounters several challenges, including scalability issues, privacy implications, and the well-known cold start problem. This study endeavors to mitigate the cold start problem by harnessing the capabilities of natural language processing (NLP) applied to user-generated reviews. A unique methodology is introduced, integrating both supervised and unsupervised NLP approaches facilitated by sci-kit learn, utilizing benchmark datasets across diverse domains. This study offers scientific contributions through its novel approach, ensuring rigor, precision, scalability, and real-world relevance. It tackles the cold start problem in recommendation systems by combining natural language processing (NLP) with machine learning and collaborative filtering techniques, addressing data sparsity effectively. This study emphasizes reproducibility and accuracy while proposing an advanced solution that improves personalization in recommendation models. The proposed NLP-based strategy enhances the quality of user-generated content, consequently refining the accuracy of Collaborative Filtering-Based Recommender Systems (CFBRSs). The authors conducted experiments to test the performance of the proposed approach on benchmark datasets like MovieLens, Jester, Book-Crossing, Last.fm, Amazon Product Reviews, Yelp, Netflix Prize, Goodreads, IMDb (Internet movie Database) Data, CiteULike, Epinions, and Etsy to measure global accuracy, global loss, F-1 Score, and AUC (area under curve) values. Assessment through various techniques such as random forest, Naïve Bayes, and Logistic Regression on heterogeneous benchmark datasets indicates that random forest is the most effective method, achieving an accuracy rate exceeding 90%. Further, the proposed approach received a global accuracy above 95%, a global loss of 1.50%, an F-1 Score of 0.78, and an AUC value of 92%. Furthermore, the experiments conducted on distributed and global differential privacy (GDP) further optimize the system’s efficacy.

Reducing the Cost of Cold Start Time in Serverless Function Executions Using Granularity Trees

Reducing the Cost of Cold Start Time in Serverless Function Executions Using Granularity Trees

A framework for generating recommendations based on trust in an informal e-learning environment

Rapid advancement in information technology promotes the growth of new online learning communities in an e-learning environment that overloads information and data sharing. When a new learner asks a question, how a system recommends the answer is the problem of the learner’s cold start. In this article, our contributions are: (i) We proposed a Trust-aware Deep Neural Recommendation (TDNR) framework that addresses learner cold-start issues in informal e-learning by modeling complex nonlinear relationships. (ii) We utilized latent Dirichlet allocation for tag modeling, assigning tag categories to newly posted questions and ranking experts related to specific tags for active questioners based on hub and authority scores. (iii) We enhanced recommendation accuracy in the TDNR model by introducing a degree of trust between questioners and responders. (iv) We incorporated the questioner-responder relational graph, derived from structural preference information, into our proposed model. We evaluated the proposed model on the Stack Overflow dataset using mean absolute precision (MAP), root mean squared error (RMSE), and F-measure metrics. Our significant findings are that TDNR is a hybrid approach that provides more accurate recommendations compared to rating-based and social-trust-based approaches, the proposed model can facilitate the formation of informal e-learning communities, and experiments show that TDNR outperforms the competing methods by an improved margin. The model’s robustness, demonstrated by superior MAE, RMSE, and F-measure metrics, makes it a reliable solution for addressing information overload and user sparsity in Stack Overflow. By accurately modeling complex relationships and incorporating trust degrees, TDNR provides more relevant and personalized recommendations, even in cold-start scenarios. This enhances user experience by facilitating the formation of supportive learning communities and ensuring new learners receive accurate recommendations.

IBCFaiCDR: Auxiliary data-driven item-based collaborative filtering in cross-domain RSs to address user cold start problem

The adoption of Recommender Systems (RSs) in various services is imperative in the present era. One of the inherent challenge faced by RSs is the user cold start problem (UCS) and it occurs when there is a lack of enough data available for a new user, which restricts the capacity to provide accurate recommendations. Researchers have conducted investigations into the utilization of auxiliary data like social network data, review text, demographic information etc., to augment the RSs ability to learn and understand the user's preferences, with the aim of solving this issue. The provided information is inadequate due to the restricted level of user engagement within the specified domain. The researchers utilize a Cross-Domain RS (CDR) that incorporates information from multiple domains to provide personalized suggestions to users. Item Based Collaborative Filtering (IBCF), which utilizes item-item similarity, is commonly used when dealing with sparse data. The suggested collaborative filtering technique employs IBCF which uses the item similarity obtained with item features. These features are generated by the proposed approach IBCFaiCDR's model, trained on source domain data such as product images and reviews. The efficacy of the proposed approach is assessed using a large dataset from Amazon, consisting of user interactions across many categories. The results on target domain, evaluated using MAE and RMSE, indicate that the inclusion of auxiliary information (image + text) enhances the RS performance for new users.

Exploring the Efficiency of Hybrid Recommender Systems Implemented with TensorFlow Framework

In recent years, the field of recommendation systems has seen significant advancement with the introduction of hybrid approaches. These systems combine the strengths of multiple recommendation techniques to provide more accurate and diverse recommendations to users. In this research, we propose and evaluate the effectiveness of a hybrid recommender system that utilizes TensorFlow, an open-source machine learning framework, to implement the system. The proposed system combines both collaborative and content-based methods to remove the cold start problem and make personalized recommendations that can recommend similar movies to the users based on features extracted by the model. The results of our experiments demonstrate that the proposed hybrid system outperforms traditional singular methods and can be effectively implemented using TensorFlow. This research provides insights into the potential of TensorFlow for building efficient hybrid recommendation systems and the benefits of combining multiple recommendation techniques.

Ozone-Catalytic Treatment of Automotive Exhaust

In the paper, an original design of an ozone-catalytic device, in which the process of ozone formation occurs directly inside the catalyst monolith of the honeycomb structure, is proposed for solving the problem of exhaust gases purification at the "cold start" of an automobile engine. For the considered device, various regimes of operation were examined, and the equations allowing us to calculate the concentrations of ozone depending on time were obtained. The developed mathematical model shows a significant decrease in ozone concentration after the "cold start" is over and the temperature of the exhaust gases increases, because of changes in the balance of various chemical reactions. Thus, the ozone concentration is maximum during a cold start, precisely when the lower temperatures do not allow other reactions than those of oxidation of toxic gases with ozone, and decreases by the time the catalytic unit warms up, when effective neutralization of toxic impurities becomes possible without the participation of ozone. The results of the mathematical modeling were confirmed by testing this device for purifying exhaust gases of a YaMZ-238M2 engine. The test results show that the use of ozone-catalytic reactions significantly increases the efficiency of neutralizing toxic impurities under cold start conditions, compared to the case when only catalytic reactions with oxygen without the participation of ozone are used.

Investigation of Engine Exhaust Heat Recovery Systems Utilizing Thermal Battery Technology

Over 50% of an engine’s energy dissipates via the exhaust and cooling systems, leading to considerable energy loss. Effectively harnessing the waste heat generated by the engine is a critical avenue for enhancing energy efficiency. Traditional exhaust heat recovery systems are limited to real-time recovery of exhaust heat primarily for engine warm-up and fail to fully optimize exhaust heat utilization. This paper introduces a novel exhaust heat recovery system leveraging thermal battery technology, which utilizes phase change materials for both heat storage and reutilization. This innovation significantly minimizes the engine’s cold start duration and provides necessary heating for the cabin during start-up. Dynamic models and thermal management system models were constructed. Parameter optimization and calculations for essential components were conducted, and the fidelity of the simulation model was confirmed through experiments conducted under idle warm-up conditions. Four distinct operational modes for engine warm-up are proposed, and strategies for transitioning between these heating modes are established. A simulation analysis was performed across four varying operational scenarios: WLTC, NEDC, 40 km/h, and 80 km/h. The results indicated that the thermal battery-based exhaust heat recovery system notably reduces warm-up time and fuel consumption. In comparison to the cold start mode, the constant speed condition at 40 km/h showcased the most significant reduction in warm-up time, achieving an impressive 22.52% saving; the highest cumulative fuel consumption reduction was observed at a constant speed of 80 km/h, totaling 24.7%. This study offers theoretical foundations for further exploration of thermal management systems in new energy vehicles that incorporate heat storage and reutilization strategies utilizing thermal batteries.

Cold Start Latency in Serverless Computing: A Systematic Review, Taxonomy, and Future Directions

Recently, academics and the corporate sector have paid attention to serverless computing, which enables dynamic scalability and an economic model. In serverless computing, users only pay for the time they actually use resources, enabling zero scaling to optimise cost and resource utilisation. However, this approach also introduces the serverless cold start problem. Researchers have developed various solutions to address the cold start problem, yet it remains an unresolved research area. In this article, we propose a systematic literature review on clod start latency in serverless computing. Furthermore, we create a detailed taxonomy of approaches to cold start latency, which we use to investigate existing techniques for reducing the cold start time and frequency. We have classified the current studies on cold start latency into several categories such as caching and application-level optimisation-based solutions, as well as Artificial Intelligence (AI)/Machine Learning (ML)-based solutions. Moreover, we have analyzed the impact of cold start latency on quality of service, explored current cold start latency mitigation methods, datasets, and implementation platforms, and classified them into categories based on their common characteristics and features. Finally, we outline the open challenges and highlight the possible future directions.

Deep learning approaches to address cold start and long tail challenges in recommendation systems: a systematic review

Deep learning approaches to address cold start and long tail challenges in recommendation systems: a systematic review

Residential wood heat in the US: Results of a survey investigating user behavior and operation of wood heating appliances

Wood is used as a source of primary and secondary heat by millions of people in the US, but many wood stoves emit levels of particulate matter that negatively impact human health and the environment. Modern wood stoves are designed to pass emissions testing required by regulatory bodies and manufacturers may be hindered in their ability to design for the variability of real-world use. User behavior can strongly impact wood heater emissions, and learning about how they are used in real life could inform the future design of cleaner-burning wood heaters. In this study a survey was performed to investigate the habits, needs, and challenges surrounding residential wood heating in the US. Common user characteristics and behaviors are investigated in categories covering heating technology, fuel use and preference, user behavior, and operation. The data collected from 210 completed survey responses can be used to support and refute anecdotal understandings of wood stove use. Results from this study cover wood heater ages and the presence or lack of catalysts. Fuel provenance, type, seasoning, and storage practices are discussed, along with the ways that respondents learned how to use their stoves and their operational practices including reloading, cold start behavior, and use of air controls. The information presented in this paper can be used to inform industry and regulatory groups as to how people use their wood heaters and highlights areas for potential future research.

Integrated sentiment analysis with BERT for enhanced hybrid recommendation systems

Recommendation systems play a crucial role in assisting users by providing personalized suggestions based on their preferences. However, these systems often face challenges such as data sparsity, cold start user issues, and overlooking the critical aspect of user sentiment. To address these limitations, this study integrates sentiment analysis into recommendation systems using a dataset from Yelp, focusing on two domains: restaurants and hotels. We conduct preprocessing tasks to facilitate sentiment analysis and leverage the power of BERT, achieving an accuracy rate of 90% for the restaurant domain and 87% for the hotel domain. We then incorporate the sentiment analysis component into collaborative filtering, utilizing model-based deep matrix factorization, and significantly reduce the root mean square error (RMSE) to 0.1 for the restaurant domain and 0.1186 for the hotel domain. Additionally, we integrate sentiment analysis into content-based recommendation using clustering, resulting in improved recommendations with a higher silhouette score of 0.533 for the restaurant domain and 0.42 for the hotel domain. To further enhance system performance, we propose a novel approach that combines these sentiment-aware components using NMF with DecisionTreeRegressor, achieving an even lower RMSE of 0.02 for the restaurant domain and 0.01 for the hotel domain. This integration of sentiment analysis into the recommendation system demonstrates its effectiveness in improving accuracy and personalization, providing users with more meaningful and relevant recommendations based on their sentiments. However, challenges such as data sparsity, cold start problems for new users, and other limitations remain, warranting further research to mitigate these challenges for a more robust recommendation system.

Drug–target prediction through self supervised learning with dual task ensemble approach

Drug–Target interaction (DTI) prediction, a transformative approach in pharmaceutical research, seeks novel therapeutic applications for computational method based virtual screening, existing drugs to address untreated diseases and discovery of existing drugs side effects. The proposed model predict DTI through Heterogeneous biological network by combining drug, genes and disease related knowledge. For the purpose of embedding extraction Self-supervised learning (SSL) has been used which, trains models through pretext tasks, eliminating the need for manual annotations. The pretext tasks are related to either structural based information or similarity based information. To mitigate GNN vulnerability to non-robustness, ensemble learning can be incorporated into GNNs, harnessing multiple models to enhance robustness. This paper introduces a Graph neural network based architecture consisting of task based module and ensemble module for link prediction of DTI. The ensemble module of dual task combinations, both in cold start and warm start scenarios achieve very good performance as it provide 0.960 in cold start and 0.970 in warm start mean AUCROC score with less deviation.

Magnetic Induction Heating-Driven Rapid Cold Start of Ammonia Decomposition for Hydrogen Production.

The advantages of ammonia as a hydrogen carrier have led to proposals for on-site hydrogen production through its decomposition. Rapid cold start of ammonia decomposition is crucial for applications such as ammonia-powered vehicles, but conventional heating methods are challenged by the high decomposition temperature of ammonia. In this study, we successfully achieved the rapid cold start of ammonia decomposition using Co nanoparticle catalysts driven by magnetic induction heating, demonstrating excellent catalytic performance and stability. The magnetic induction heating-driven ammonia decomposition system was integrated with a hydrogen fuel cell, proving its ability to achieve the cold start of ammonia decomposition within 10 s, as demonstrated by comparative experiments using 75% H2-25% N2 from a gas cylinder as the control. This study provides a deeper understanding of hysteresis heating catalysis, promoting the practical use of ammonia as a hydrogen carrier for rapid hydrogen production in the energy industry.

IPSRM: An intent perceived sequential recommendation model

Objectives:Sequential recommendation aims to recommend items that are relevant to users’ interests based on their existing interaction sequences. Current models lack in capturing users’ latent intentions and do not sufficiently consider sequence information during the modeling of users and items. Additionally, noise in user interaction sequences can affect the model’s optimization process. Methods:This paper introduces an intent perceived sequential recommendation model (IPSRM). IPSRM employs the generalized expectation–maximization (EM) framework, alternating between learning sequence representations and optimizing the model to better capture the underlying intentions of user interactions. Specifically, IPSRM maps unlabeled behavioral sequences into frequency domain filtering and random Gaussian distribution space. These mappings reduce the impact of noise and improve the learning of user behavior representations. Through clustering process, IPSRM captures users’ potential interaction intentions and incorporates them as one of the supervisions into the contrastive self-supervised learning process to guide the optimization process. Results:Experimental results on four standard datasets demonstrate the superiority of IPSRM. Comparative experiments also verify that IPSRM exhibits strong robustness under cold start and noisy interaction conditions. Conclusions:Capturing latent user intentions, integrating intention-based supervision into model optimization, and mitigating noise in sequential modeling significantly enhance the performance of sequential recommendation systems.

A self-supervised assisted label-efficient method for online remaining useful life prediction

Remaining Useful Life (RUL) prediction is crucial for safe and efficient production in industrial equipment. Conventional methods struggle in online environments, facing challenges like data distribution differences across working conditions, model cold start problem under new equipment, and lack of labels in online scenarios. To address these challenges, we propose a novel framework for online RUL prediction that leverages knowledge from self-supervised tasks via metric learning. First, a label-efficient self-supervised learning method incorporating soft triplet loss is proposed to transfer degradation knowledge. Second, we develop a two-stage method to distinguish different degradation stages of the equipment for better alignment of data distribution. Third, we introduce a pseudo-label dynamic self-updating strategy and a sample entropy-based data replay strategy, fine-tuning the offline model with newly acquired data. Our method outperforms state-of-the-art unsupervised approaches, reducing RMSE and MAPE by 16.02% and 8.40%, respectively, and achieves performance comparable to supervised methods.

Experimental study on the cerium oxide nanoparticles doped in diesel fuel improving the cold start performance of diesel engines at high-altitude and low-temperature environments

CeO2 nanoparticles are effective fuel additives that enhance fuel spray, atomization, and combustion characteristics due to their high catalytic activity and excellent thermal properties. When added to fuel, CeO2 nanoparticles significantly improve in-cylinder combustion, and engine performance, and reduce pollutant emissions under normal engine operating conditions. Diesel engines encounter persistent challenges during cold starts at low temperatures and high altitudes. However, there is limited research on the effects of CeO2 nanoparticles on ignition and combustion at low temperatures and cold start performance. This study aims to evaluate the impact of CeO2 nanoparticles doping in diesel fuel on the cold start performance of diesel engines in high-altitude and low-temperature environments. Diesel fuel doped with CeO2 nanoparticles at various concentrations was prepared using magnetic stirring and ultrasonication. The cold start performance of the test engine was assessed in an environmental chamber. This work investigated and evaluated the improvements of CeO2 nanoparticles on cold start performance from three perspectives: general low-temperature conditions, high-altitude environments, and extreme low-temperature scenarios with diethyl ether premixing. Experimental results indicate that incorporating CeO2 nanoparticles expanded the critical temperature required for a successful cold start from 0 °C to −5 °C. At high altitudes, the addition of CeO2 nanoparticles effectively increased the proportion of efficient combustion, evidenced by single peak and parent peak patterns during cold starts. CeO2 nanoparticles facilitated the transition from low-temperature to high-temperature reactions, promoting fuel ignition during the first injection cycle and reducing speed fluctuations during cold starts with diethyl ether premixing at −40 °C. Furthermore, adding CeO2 nanoparticles prevented detonation and rapid pressure surges during cold starts. Overall, doping diesel fuel with CeO2 nanoparticles proves to be an effective method for enhancing cold start performance in diesel engines. This study offers a novel approach for improving diesel engine cold start performance in high-altitude and low-temperature conditions.

Quantitative analysis of failure performance uncertainty based on multiscale mechanical analysis of PEMFCs’ C/C composite bipolar plates

In order to quantify the failure performance of PEMFCs’ C/C composite bipolar plates (BPs) under considering the uncertainty in multiscale sizes and loads, the failure probability function (FPF) of BPs at cold start is estimated. A three-stage multiscale simulation method is proposed for mechanical behavior analysis of multi-component heterogeneous composites. And the efficient estimation of FPF for C/C composite BPs is achieved via the proposed multiscale simulation method and decoupling sparse integration method, in which the unified density weight is constructed to decouple the double-loop framework of analyzing FPF, thereby reducing the computational complexity. Results indicate that the dangerous positions of BPs are around the gas flow channels and bolt holes. And the dangerous components are the carbon matrix and the interface between the matrix and fiber. The radius of elliptical fibers affects the distribution of failure factors on microscopic components, thereby affecting the variation of failure probability with fiber sizes significantly. The distribution parameter of composite layer thickness in BPs has a significant effect on structural safety, and the FPF result can be used to effectively guide the design of structure. Therefore, the proposed method is of great significance for guiding the rapid parameter design of composite BPs.