MethodsX最新文献

{"title":"Quantum-enhanced LSTM for predictive maintenance in industrial IoT systems","authors":"Sudharson K , Varsha S , Santhiya R , Rajalakshmi D","doi":"10.1016/j.mex.2025.103653","DOIUrl":"10.1016/j.mex.2025.103653","url":null,"abstract":"<div><div>An innovative solution for predictive maintenance in IIoT systems combining quantum computing with the proficiency of LSTM neural networks is proposed by us. Our concept is guided by a hybrid quantum-classical architecture to facilitate quantum computing to exploit high-dimensional industrial sensor measurements while preserving crucial temporal relationships through particular quantum channels. Through the combination of the representational ingenuity of quantum circuits, along with the sequence-based modelling of classical LSTMs, QE-LSTM is uniquely positioned to handle complicated time series coming out of industrial sensors. At the heart of our methodology are the following unique elements:<ul><li><span>•</span><span><div>A collaborative framework integrating quantum and classical technologies allowing for the quantum computer to manage the complex analysis of high dimensional sensor data in the industry.</div></span></li><li><span>•</span><span><div>Quantum channel designs were aimed at minimizing temporal dependencies in temporal series industrial measurements, thereby maximizing the quality of sequential analysis.</div></span></li><li><span>•</span><span><div><div>Under ODS hindcasting, QE-LSTM improved F1 by 4–5 percentage points on SECOM and reduced RMSE and NASA Score on C-MAPSS; trends were consistent on IMMD (<span><span>Table 1</span></span>, <span><span>Table 2</span></span>).</div><div><span><span><p><span>Table 1</span>. <!-->Performance comparison across datasets.</p></span></span><div><table><thead><tr><th>Dataset</th><th>Model</th><th>Accuracy</th><th>Precision</th><th>Recall</th><th>F1</th><th>AUC</th></tr></thead><tbody><tr><td>SECOM</td><td>LSTM</td><td>0.864</td><td>0.842</td><td>0.809</td><td>0.825</td><td>0.902</td></tr><tr><td></td><td>CNN-LSTM</td><td>0.878</td><td>0.862</td><td>0.824</td><td>0.842</td><td>0.914</td></tr><tr><td></td><td><strong>QE-LSTM (sim)</strong></td><td><strong>0.904</strong></td><td><strong>0.892</strong></td><td><strong>0.861</strong></td><td><strong>0.876</strong></td><td><strong>0.938</strong></td></tr><tr><td></td><td><strong>QE-LSTM (hardware)</strong></td><td>0.896</td><td>0.881</td><td>0.850</td><td>0.865</td><td>0.930</td></tr><tr><td>IMMD</td><td>LSTM</td><td>0.906</td><td>0.883</td><td>0.862</td><td>0.872</td><td>0.943</td></tr><tr><td></td><td>CNN-LSTM</td><td>0.913</td><td>0.891</td><td>0.869</td><td>0.880</td><td>0.949</td></tr><tr><td></td><td><strong>QE-LSTM (sim)</strong></td><td><strong>0.928</strong></td><td><strong>0.908</strong></td><td><strong>0.888</strong></td><td><strong>0.898</strong></td><td><strong>0.960</strong></td></tr></tbody></table></div><div><div>QE-LSTM (sim) vs LSTM F1 deltas: SECOM <strong>+5.1 pp</strong>, IMMD <strong>+2.6 pp</strong>; paired <em>t</em>-test <em>p</em> < 0.01.</div></div></div><div><span><span><p><span>Table 2</span>. <!-->RUL prediction performance metrics.</p></span></span><div><table><thead><tr><th>Metric</th><th>Classical LS","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103653"},"PeriodicalIF":1.9,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AAB-FusionNet: A real-time object detection model for UAV edge computing platforms","authors":"Chi Kien Ha,&nbsp;Hoanh Nguyen,&nbsp;Long Ho Le","doi":"10.1016/j.mex.2025.103654","DOIUrl":"10.1016/j.mex.2025.103654","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) often operate under stringent resource constraints while requiring real-time object detection, which can lead to failures in cluttered backgrounds or when targets are small or partially occluded. To address these challenges, we introduce AAB-FusionNet, a real-time detection model specifically designed for UAV edge computing platforms. At its core is the Adaptive Attention Block (AAB), which employs an Adaptive Saliency-based Attention (ASA) mechanism to highlight the most discriminative tokens while a lightweight MBConv sub-layer refines local spatial features. This saliency-driven framework ensures the network remains focused on critical cues despite complex aerial imagery. To further boost performance, AAB-FusionNet utilizes a Multi-layer Feature Fusion Network that integrates three key components: Attentive Inverted Bottleneck Aggregation (AIBA) to restore significant details at multiple scales, DySample for preserving spatial fidelity during feature alignment, and the Dual-Attention Noise Mitigation (DNM) module to suppress environmental noise through complementary channel and spatial attention. Experiments on diverse aerial datasets confirm that AAB-FusionNet achieves robust detection, especially for small or partially occluded objects, while offering real-time inference on low-power hardware. Overall, AAB-FusionNet effectively balances accuracy, computational efficiency, and adaptability, making it ideally suited for UAV scenarios demanding fast, reliable object detection and robust and consistent performance.<ul><li><span>•</span><span><div>Incorporates an Adaptive Saliency-based Attention mechanism to emphasize critical visual cues.</div></span></li><li><span>•</span><span><div>Introduces a Multi-layer Feature Fusion Network for detail restoration, feature alignment, and noise mitigation.</div></span></li><li><span>•</span><span><div>Demonstrates real-time, high-accuracy detection on low-power UAV platforms, particularly for small or occluded targets.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103654"},"PeriodicalIF":1.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The AI-DRM protocol to enhance the lifetime of wireless sensor network","authors":"Santosh Anand,&nbsp;Anantha Narayanan V","doi":"10.1016/j.mex.2025.103649","DOIUrl":"10.1016/j.mex.2025.103649","url":null,"abstract":"<div><div>Energy is a major research challenge in wireless sensor networks since it is placed in an area that is inaccessible to humans. In the current study, nodes send data to their neighboring nodes at any distance using the same energy level. Smaller distances require less energy to transmit to adjacent nodes, creating a strong research gap. High-distance transmissions require more energy. The node must tailor its transmission energy to distance, not fixed energy. The best transmission power for communication is determined via the neural network-based machine learning technique, which is based on the propagation model and network properties, such as the node density, residual energy, and energy harvesting rate. In this work, sensor nodes transmit information to their neighboring nodes via the multiple linear regression model for dynamic radio tuning with the FRIIS propagation model, and the simulation records the node's energy consumption. Compared with the four recent best current methods that increase the W.S.N. lifetime, the proposed protocol is better and uses less power. The proposed AI-DRM protocol has sufficient residual energy to transmit the packet until 1403 rounds, which is higher than those of two recent energy-efficient protocols, the ARORA and the EACHS-B2SPNN protocols.<ul><li><span>1.</span><span><div>The AI-based dynamic transmission power protocol tunes the sensor nodes using a propagation model.</div></span></li><li><span>2.</span><span><div>Prediction of lifetime of WSN</div></span></li><li><span>3.</span><span><div>Effective utilization of all sensor nodes<span><span>¹</span></span></div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103649"},"PeriodicalIF":1.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hypercomplex neural networks: Exploring quaternion, octonion, and beyond in deep learning","authors":"Raghavendra M Devadas ,&nbsp;Vani Hiremani ,&nbsp;Preethi ,&nbsp;Sowmya T ,&nbsp;Sapna R ,&nbsp;Praveen Gujjar","doi":"10.1016/j.mex.2025.103644","DOIUrl":"10.1016/j.mex.2025.103644","url":null,"abstract":"<div><div>Hypercomplex Neural Networks (HNNs) represent the next frontier in deep learning, building on the mathematical theory of quaternions, octonions, and higher-dimensional algebras to generalize conventional neural architectures. This review synthesizes cutting-edge methods with their theoretical bases, architectural advancements, and primary applications, tracing the development of hypercomplex mathematics and its implementation in computational models. We distil key advances in quaternion and octonion networks, highlighting their ability to provide compact representations and computational efficiency. Particular attention is given to the unique challenge of non-associativity in octonions—where the order in which numbers are multiplied affects the result—requiring careful design of network operations. The article also discusses training complexity, interpretability, and the lack of standardized frameworks, alongside comparative performance with real- and complex-valued networks. Future directions include scalable algorithm construction, lightweight architectures through tensor decompositions, and integration with quantum-inspired systems using higher-order algebras. By presenting a systematic synthesis of current literature and linking these advances to practical applications, this review aims to equip researchers and practitioners with a clear understanding of the strengths, limitations, and potential of HNNs for advancing multidimensional data modelling.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103644"},"PeriodicalIF":1.9,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A modified Gompertz model and its MATLAB implementation for microbial growth performance assessment","authors":"Loyal Murphy,&nbsp;Q․Peter He,&nbsp;Jin Wang","doi":"10.1016/j.mex.2025.103642","DOIUrl":"10.1016/j.mex.2025.103642","url":null,"abstract":"<div><div>To systematically assess the growth performance of different methanotrophs, microalgae and their cocultures, this work presents an improved four-parameter Zwietering modification of the Gompertz model (4Z model) to extract biologically relevant information using batch growth data. The 4Z model was based on the three-parameter Zwietering modification of the original Gompertz model, with a constant term added to address the discrepancy between model predictions and measurements for the initial period of growth data. The 4Z model provided excellent fits to the batch growth data of different monocultures and cocultures. However, the parameters in the 4Z model are different from the commonly used maximum growth rate and delay time, making interpretation of the results challenging. To facilitate the assessment of different strains, we follow the two-step procedure to extract biologically significant parameters:</div><div>1. Estimate the four parameters in the 4Z model using the whole batch growth trajectory.</div><div>2. Use the 4Z model prediction of early-stage growth data to estimate the biologically significant parameters in the commonly used exponential growth model.</div><div>The estimated biologically significant parameters (maximum growth rate, delay time, and carrying capacity) enabled an unbiased assessment of different strains.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103642"},"PeriodicalIF":1.9,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145154426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining established methods for value chain and power analyses: Towards a comprehensive next-generation understanding of value chain governance","authors":"Kendisha Soekardjo Hintz ,&nbsp;La Thi Tham ,&nbsp;Felister Mombo ,&nbsp;Eckhard Auch ,&nbsp;Jürgen Pretzsch ,&nbsp;Lukas Giessen","doi":"10.1016/j.mex.2025.103637","DOIUrl":"10.1016/j.mex.2025.103637","url":null,"abstract":"<div><div>Methods to analyze power in value chain governance often focus on multinational firms, which may not apply well to natural resource-based chains in domestic markets. Value chain analyses imply the complexity and power imbalances among the (in)direct actors in a value chain. However, quantifying the added value alone cannot fully capture the nuances of power among value chain actors. To cover the methodological gap, we propose complementing value chain analysis with actor-centered power and institutional power frameworks. The appropriation of profit and labor is framed as the key issue area to ensure coherence. Besides mapping the value chain and calculating the added value per value chain actor, the value network is mapped, and the power capabilities of the actors are quantified. The expected output identifies actors’ power in monetary and non-monetary terms, revealing how they utilize (in)formal institutional settings to their (dis)advantage. This multistage mixed-methods methodology permits the derivation of recommendations on how to achieve a more equitable value chain.<ul><li><span>•</span><span><div>The methodology consists of three stages: value chain analysis, actor-centered power and institutional power analyses, and synthesis</div></span></li><li><span>•</span><span><div>The appropriation of profit and labor are the common issue area in both approaches</div></span></li><li><span>•</span><span><div>The paper provides a step-by-step protocol for researchers to collect data</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103637"},"PeriodicalIF":1.9,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145117664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of an algae extract-based culture medium for Paenibacillus larvae without animal-derived components","authors":"Štěpán Ryba,&nbsp;Adéla Píchová,&nbsp;Petr Mráz,&nbsp;Irena Hoštičková,&nbsp;Michaela Horčičková","doi":"10.1016/j.mex.2025.103638","DOIUrl":"10.1016/j.mex.2025.103638","url":null,"abstract":"<div><div>The cultivation of <em>Paenibacillus larvae</em>, the etiological agent of American foulbrood, traditionally relies on media containing animal-derived nutrients. In response to ethical and practical concerns associated with such components, we developed and validated a new culture medium based on an algae extract. The formulation includes <em>Chlorella</em> as the principal nutrient source and is supplemented with uric acid and L-tyrosine to support spore germination under conditions resembling the honeybee larval gut. The method includes optimized procedures for dissolving sparingly soluble components and minimizing nutrient degradation. Performance of the new medium was comparable to that of MYPGP and other conventional media in supporting spore germination and vegetative growth of <em>P. larvae</em>.</div><div>• Eliminates the need for animal-derived components through the use of microalgal nutrients</div><div>• Supports robust germination and colony development of <em>P. Larvae</em></div><div>• Provides an ethical and cost-efficient medium suitable for diagnostic and research applications</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103638"},"PeriodicalIF":1.9,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145154425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unmasking digital deceptions: An integrative review of deepfake detection, multimedia forensics, and cybersecurity challenges","authors":"Sonam Singh ,&nbsp;Amol Dhumane","doi":"10.1016/j.mex.2025.103632","DOIUrl":"10.1016/j.mex.2025.103632","url":null,"abstract":"<div><div>Deepfakes, which are driven by developments in generative AI, seriously jeopardize public trust, cybersecurity, and the veracity of information. This study offers a comprehensive analysis of the most recent methods for creating and detecting deepfakes in image, video, and audio modalities. With a focus on their advantages and disadvantages in cross-dataset and real-world scenarios, we compile the latest developments in transformer-based detection models, multimodal biometric defenses, and Generative Adversarial Networks (GANs). We provide implementation-level information such as pseudocode workflows, hyperparameter settings, and preprocessing pipelines for popular detection frameworks to improve reproducibility. We also examine the implications of cybersecurity, including identity theft and biometric spoofing, as well as policy-oriented solutions that incorporate federated learning, explainable AI, and ethical protections. By enriching technical insights with interdisciplinary perspectives, this review charts a roadmap for building robust, scalable, and trustworthy deepfake detection systems.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103632"},"PeriodicalIF":1.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145154427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Provably lightweight and secure IoHT scheme with post-quantum cryptography and fog computing: A comprehensive scheme for healthcare system","authors":"Enas W. Abood ,&nbsp;Ali A. Yassin ,&nbsp;Zaid Ameen Abduljabbar ,&nbsp;Vincent Omollo Nyangaresi ,&nbsp;Ali Hasan Ali","doi":"10.1016/j.mex.2025.103631","DOIUrl":"10.1016/j.mex.2025.103631","url":null,"abstract":"<div><div>Quantum computers threaten the security of commonly used public-key cryptosystems, such as Rivest-Shamir-Adleman (RSA) and Elliptic Curve Cryptography (ECC). This is because these quantum computers efficiently solve factorization and discrete logarithm problems, which are the basis for RSA and ECC. This compromises confidentiality, integrity, and authenticity in security systems deployed in various applications, such as Internet-of-Healthcare Things (IoHT). Post-quantum cryptography, while a potential solution, introduces computational overheads that can slow service delivery. This poses serious concerns in IoHT safety critical systems as it directly impacts patient safety and healthcare systems. This paper aims to design a post-quantum resistance scheme for IoHTs. Our scheme is based on ECC, Counter mode (CTR), and Key Encapsulation Mechanism (KEM). To guarantee the safety and storage of electronic records for the network entities and support scalability, blockchain and InterPlanetary File System (IPFS) were employed. To achieve improved levels of security and more effective control when accessing specific data and resources, we apply Role-Based Access Control (RBAC). In addition, we deploy Symmetric Searchable Encryption (SSE) for efficient and secure data search. The scheme's security was formally verified using the Scyther tool, and Burrows–Abadi–Needham (BAN) logic. In addition, informal security analysis shows that our proposed scheme offers mutual authentication, confidentiality, integrity, and other security requirements. In addition, it withstands well-known threats and some of the recent threats, such as phishing, quantum, and 51% attacks. Moreover, a comparative analysis was conducted with other related protocols to show the efficiency of the proposed scheme in the IoHT environment. The results indicate that the computation overhead was reduced by 90%, while communication cost and latency were relatively low. On the other hand, throughput was greatly increased while energy consumption was very low.</div><div>The proposed scheme is a low complexity solution for IoHT environments to address existing threats and maintain data integrity.</div><div>Blockchain and IPFS ensure secure, scalable e-record storage for network entities.</div><div>Achieving secure, effective access control with RBAC and enhancing data searchability with SSE.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103631"},"PeriodicalIF":1.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145154424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High performance GPU implementation of KNN algorithm: A review","authors":"Pooja Bidye,&nbsp;Pradnya Borkar,&nbsp;Nitin Rakesh","doi":"10.1016/j.mex.2025.103633","DOIUrl":"10.1016/j.mex.2025.103633","url":null,"abstract":"<div><div>With large volumes of complex data generated by different applications, Machine Learning (ML) algorithms alone may not yield significant performance benefits on a single or multi-core CPU. Applying optimization techniques to these ML algorithms in a High-Performance Computing (HPC) environment can give considerable speedups for high-dimensional datasets. One of the most widely used classification algorithms, with applications in various domains, is the K-Nearest Neighbor (KNN). Despite its simplicity, KNN poses several challenges while handling high-dimensional data. However, the algorithm’s inherent nature presents an opportunity for parallelization. This paper reviews the optimization techniques employed by several researchers to accelerate the KNN algorithm on a GPU platform. The study reveals that techniques such as coalesced-memory access, tiling with shared memory, chunking, data segmentation, and pivot-based partitioning significantly contribute towards speeding up the KNN algorithm to leverage the GPU capabilities. The algorithms reviewed have performed exceptionally well on high-dimensional data with speedups up to 750x for a dual-GPU platform and up to 1840x for a multi-GPU platform. This study serves as a valuable resource for researchers examining KNN acceleration in high-performance computing environments and its applications in various fields.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103633"},"PeriodicalIF":1.9,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145117663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}