Responsive and intelligent service recommendation method based on deep learning in cloud service.

The rapid expansion of the cloud service market is inseparable from its widely acclaimed service model. The rapid increase in the number of cloud services has resulted in the phenomenon of service overload. Service recommendations based on services' function attributes are important because they can help users filter services with specific functions, such as the function of guessing hobbies on shopping websites and daily recommendation functions in the listening app. Nowadays, cloud service market has a large number of services, which have similar functions, but the quality of service (QoS) is very different. Although the recommendation based on services' function attributes satisfies users' basic demands, it ignores the impact of the QoS on the user experience. To further improve users' satisfaction with service recommendations, researchers try to recommend services based on services' non-functional attributes. There is sparsity of the QoS matrix in the real world, which brings obstacles to service recommendation; hence, the prediction of the QoS becomes a solution to overcome this obstacle. Scholars have tried to use collaborative filtering (CF) methods and matrix factorization (MF) methods to predict the QoS, but these methods face two challenges. The first challenge is the sparsity of data; the sparsity makes it difficult for CF to accurately determine whether users are similar, and the gap between the hidden matrices obtained by MF decomposition is large; the second challenge is the cold start of recommendation when new users (or services) participate in the recommendation; its historical record is vacant, making accurately predicting the QoS value be more difficult. To solve the aforementioned problems, this study mainly does the following work: 1) we organized the QoS matrix into a service call record, which contains user characteristic information and current QoS. 2) We proposed a QoS prediction method based on GRU-GAN. 3) We used the time series data for quality predictions and compared some QoS prediction methods, such as CF and MF. The results showed that the prediction results based on GRU-GAN are far superior to other prediction methods under the same data density. We aim to help the engineering community promote their findings, shape the technological revolution, improve multidisciplinary collaborations, and collectively create a better future.

A Reverse Modification Method for Binary Code and Data.

This paper reveals the hidden dangers of reverse data modifications on distributed software with network synchronization, during the era of 5G, which may occur in more important domains, such as telemedicine and automatic driving. We used pseudo-codes to formally elaborate the distributed software architectures and design patterns. It is necessary to deal with three challenges for the modification of binary code and data in the distributed software architectures: (1) the base virtual addresses of software objects are changed frequently for safety; (2) prior knowledge of the reverse is not considered; (3) system memory values of some target objects are changed with extreme speed. For this purpose, a novel reverse modification method for binary code and data is proposed. According to the knowledge-based rules, our method can manipulate physical data, sight data, animation data, etc., while the game synchronization mechanism cannot detect the changes. The implementation details of our method are presented using high-level programming languages (C++) and low-level programming languages (assembly), based on multiple snippets, so that readers can understand both the overall distributed software developments and the corresponding reverse processes. In particular, two network games are used for the demonstrations in this paper. The demonstration results show that our proposed methodology is efficient (as proved by formulas and practices) to manipulate the codes and data of distributed software using a synchronization mechanism.

A resource scheduling method for reliable and trusted distributed composite services in cloud environment based on deep reinforcement learning.

With the vigorous development of Internet technology, applications are increasingly migrating to the cloud. Cloud, a distributed network environment, has been widely extended to many fields such as digital finance, supply chain management, and biomedicine. In order to meet the needs of the rapid development of the modern biomedical industry, the biological cloud platform is an inevitable choice for the integration and analysis of medical information. It improves the work efficiency of the biological information system and also realizes reliable and credible intelligent processing of biological resources. Cloud services in bioinformatics are mainly for the processing of biological data, such as the analysis and processing of genes, the testing and detection of human tissues and organs, and the storage and transportation of vaccines. Biomedical companies form a data chain on the cloud, and they provide services and transfer data to each other to create composite services. Therefore, our motivation is to improve process efficiency of biological cloud services. Users' business requirements have become complicated and diversified, which puts forward higher requirements for service scheduling strategies in cloud computing platforms. In addition, deep reinforcement learning shows strong perception and continuous decision-making capabilities in automatic control problems, which provides a new idea and method for solving the service scheduling and resource allocation problems in the cloud computing field. Therefore, this paper designs a composite service scheduling model under the containers instance mode which hybrids reservation and on-demand. The containers in the cluster are divided into two instance modes: reservation and on-demand. A composite service is described as a three-level structure: a composite service consists of multiple services, and a service consists of multiple service instances, where the service instance is the minimum scheduling unit. In addition, an improved Deep Q-Network (DQN) algorithm is proposed and applied to the scheduling algorithm of composite services. The experimental results show that applying our improved DQN algorithm to the composite services scheduling problem in the container cloud environment can effectively reduce the completion time of the composite services. Meanwhile, the method improves Quality of Service (QoS) and resource utilization in the container cloud environment.

Hardness Prediction of Laser Powder Bed Fusion Product Based on Melt Pool Radiation Intensity.

The quality stability and batch consistency of laser powder bed fusion products are key issues that must be solved in additive manufacturing. The melt pool radiation intensity data of laser powder bed fusion contain a significant amount of forming process information, and studies have shown that the analysis of melt pool radiation intensity using data-driven methods can achieve online quality judgment; however, there are still speed and accuracy problems. In this study, we propose a data-driven model for hardness predictions of laser powder bed fusion products based on process parameters fused with power spectrum features of melt pool intensity data, which quickly and accurately predicts the microhardness of laser powder bed fusion specimens and can make constructive guidance for closed-loop feedback quality regulation in practical production. The effects of three integrated learning models, Random Forest, XGBoost and LightGBM, are also compared. The results indicate that random forest has the highest prediction accuracy in this dataset; however, it has the limitation of slow training and prediction speeds. The LightGBM algorithm has the fastest training and prediction speeds, about 1.4% and 4.4% of the random forest, respectively; however, the prediction accuracy is lower than that of random forest and XGBoost. XGBoost has the best overall comparative performance with adequate training and prediction speeds, about 23.7% and 37.9% of the random forest, respectively, while ensuring a specified prediction accuracy, which is suitable for application in engineering practices.

Optimal Planning and Management of Land Use in River Source Region: A Case Study of Songhua River Basin, China.

Adjusting land use is a practical way to protect the ecosystem, but protecting water resources by optimizing land use is indirect and complex. The vegetation, soil, and rock affected by land use are important components of forming the water cycle and obtaining clean water sources. The focus of this study is to discuss how to optimize the demands and spatial patterns of different land use types to strengthen ecological and water resources protection more effectively. This study can also provide feasible watershed planning and policy suggestions for managers, which is conducive to the integrity of the river ecosystem and the sustainability of water resources. A watershed-scale land use planning framework integrating a hydrological model and a land use model is established. After quantifying the water retention value of land use types through a hydrological model, a multi-objective land use demands optimization model under various development scenarios is constructed. Moreover, a regional study was completed in the source area of the Songhua River in Northeast China to verify the feasibility of the framework. The results show that the method can be used to optimize land use requirements and obtain future land use maps. The water retention capacity of forestland is strong, about 2500-3000 m3/ha, and there are differences among different forest types. Planning with a single objective of economic development will expand the area of cities and cultivated land, and occupy forests, while multi-objective planning considering ecological and water source protection tends to occupy cultivated land. In the management of river headwaters, it is necessary to establish important forest reserves and strengthen the maintenance of restoration forests. Blindly expanding forest area is not an effective way to protect river headwaters. In conclusion, multi-objective land use planning can effectively balance economic development and water resources protection, and find the limits of urban expansion and key areas of ecological barriers.

A Comprehensive Review of Artificial Intelligence in Prevention and Treatment of COVID-19 Pandemic.

The unprecedented outbreak of the Corona Virus Disease 2019 (COVID-19) pandemic has seriously affected numerous countries in the world from various aspects such as education, economy, social security, public health, etc. Most governments have made great efforts to control the spread of COVID-19, e.g., locking down hard-hit cities and advocating masks for the population. However, some countries and regions have relatively poor medical conditions in terms of insufficient medical equipment, hospital capacity overload, personnel shortage, and other problems, resulting in the large-scale spread of the epidemic. With the unique advantages of Artificial Intelligence (AI), it plays an extremely important role in medical imaging, clinical data, drug development, epidemic prediction, and telemedicine. Therefore, AI is a powerful tool that can help humans solve complex problems, especially in the fight against COVID-19. This study aims to analyze past research results and interpret the role of Artificial Intelligence in the prevention and treatment of COVID-19 from five aspects. In this paper, we also discuss the future development directions in different fields and prove the validity of the models through experiments, which will help researchers develop more efficient models to control the spread of COVID-19.

Rhizosphere enzyme activities and microorganisms drive the transformation of organic and inorganic carbon in saline-alkali soil region.

Western Jilin Province is one of the world's three major saline-alkali land distribution areas, and is also an important area of global climate change and carbon cycle research. Rhizosphere soil microorganisms and enzymes are the most active components in soil, which are closely related to soil carbon cycle and can reflect soil organic carbon (SOC) dynamics sensitively. Soil inorganic carbon (SIC) is the main existing form of soil carbon pool in arid saline-alkali land, and its quantity distribution affects the pattern of soil carbon accumulation and storage. Previous studies mostly focus on SOC, and pay little attention to SIC. Illumina Miseq high-throughput sequencing technology was used to reveal the changes of community structure in three maize fields (M1, M2 and M3) and three rice fields (R1, R2 and R3), which were affected by different levels of salinization during soil development. It is a new research topic of soil carbon cycle in saline-alkali soil region to investigate the effects of soil microorganisms and soil enzymes on the transformation of SOC and SIC in the rhizosphere. The results showed that the root-soil-microorganism interaction was changed by saline-alkali stress. The activities of catalase, invertase, amylase and ß-glucosidase decreased with increasing salinity. At the phylum level, most bacterial abundance decreases with increasing salinity. However, the relative abundance of Proteobacteria and Firmicutes in maize field and Firmicutes, Proteobacteria and Nitrospirae in rice field increased sharply under saline-alkali stress. The results of redundancy analysis showed that the differences of rhizosphere soil between the three maize and three rice fields were mainly affected by ESP, pH and soil salt content. In saline-alkali soil region, ß-glucosidase activity and amylase were significantly positively correlated with SOC content in maize fields, while catalase and ß-glucosidase were significantly positively correlated with SOC content in rice fields. Actinobacteria, Bacteroidetes and Verrucomicrobia had significant positive effects on SOC content of maize and rice fields. Proteobacteria, Gemmatimonadetes and Nitrospirae were positively correlated with SIC content. These enzymes and microorganisms are beneficial to soil carbon sequestration in saline-alkali soils.

Apathy Classification Based on Doppler Radar Image for the Elderly Person.

Apathy is a disease characterized by diminished motivation not attributable to a diminished level of consciousness, cognitive impairment, or emotional distress. It is a serious problem facing the elderly in today's society. The diagnosis of apathy needs to be done at a clinic, which is particularly inconvenient and difficult for elderly patients. In this work, we examine the possibility of using doppler radar imaging for the classification of apathy in the elderly. We recruited 178 elderly participants to help create a dataset by having them fill out a questionnaire and submit to doppler radar imaging while performing a walking action. We selected walking because it is one of the most common actions in daily life and potentially contains a variety of useful health information. We used radar imaging rather than an RGB camera due to the greater privacy protection it affords. Seven machine learning models, including our proposed one, which uses a neural network, were applied to apathy classification using the walking doppler radar images of the elderly. Before classification, we perform a simple image pre-processing for feature extraction. This pre-processing separates every walking doppler radar image into four parts on the vertical and horizontal axes and the number of feature points is then counted in every separated part after binarization to create eight features. In this binarization, the optimized threshold is obtained by experimentally sliding the threshold. We found that our proposed neural network achieved an accuracy of more than 75% in apathy classification. This accuracy is not as high as that of other object classification methods in current use, but as an initial research in this area, it demonstrates the potential of apathy classification using doppler radar images for the elderly. We will examine ways of increasing the accuracy in future work.

On the Logical Design of a Prototypical Data Lake System for Biological Resources.

Biological resources are multifarious encompassing organisms, genetic materials, populations, or any other biotic components of ecosystems, and fine-grained data management and processing of these diverse types of resources proposes a tremendous challenge for both researchers and practitioners. Before the conceptualization of data lakes, former big data management platforms in the research fields of computational biology and biomedicine could not deal with many practical data management tasks very well. As an effective complement to those previous systems, data lakes were devised to store voluminous, varied, and diversely structured or unstructured data in their native formats, for the sake of various analyses like reporting, modeling, data exploration, knowledge discovery, data visualization, advanced analysis, and machine learning. Due to their intrinsic traits, data lakes are thought to be ideal technologies for processing of hybrid biological resources in the format of text, image, audio, video, and structured tabular data. This paper proposes a method for constructing a practical data lake system for processing multimodal biological data using a prototype system named ProtoDLS, especially from the explainability point of view, which is indispensable to the rigor, transparency, persuasiveness, and trustworthiness of the applications in the field. ProtoDLS adopts a horizontal pipeline to ensure the intra-component explainability factors from data acquisition to data presentation, and a vertical pipeline to ensure the inner-component explainability factors including mathematics, algorithm, execution time, memory consumption, network latency, security, and sampling size. The dual mechanism can ensure the explainability guarantees on the entirety of the data lake system. ProtoDLS proves that a single point of explainability cannot thoroughly expound the cause and effect of the matter from an overall perspective, and adopting a systematic, dynamic, and multisided way of thinking and a system-oriented analysis method is critical when designing a data processing system for biological resources.

70ProPred: a predictor for discovering sigma70 promoters based on combining multiple features.

BACKGROUND: Promoter is an important sequence regulation element, which is in charge of gene transcription initiation. In prokaryotes, σ70 promoters regulate the transcription of most genes. The promoter recognition has been a crucial part of gene structure recognition. It's also the core issue of constructing gene transcriptional regulation network. With the successfully completion of genome sequencing from an increasing number of microbe species, the accurate identification of σ70 promoter regions in DNA sequence is not easy. RESULTS: In order to improve the prediction accuracy of sigma70 promoters in prokaryote, a promoter recognition model 70ProPred was established. In this work, two sequence-based features, including position-specific trinucleotide propensity based on single-stranded characteristic (PSTNPss) and electron-ion potential values for trinucleotides (PseEIIP), were assessed to build the best prediction model. It was found that 79 features of PSTNPSS combined with 64 features of PseEIIP obtained the best performance for sigma70 promoter identification, with a promising accuracy and the Matthews correlation coefficient (MCC) at 95.56% and 0.90, respectively. CONCLUSION: The jackknife tests showed that 70ProPred outperforms the existing sigma70 promoter prediction approaches in terms of accuracy and stability. Additionally, this approach can also be extended to predict promoters of other species. In order to facilitate experimental biologists, an online web server for the proposed method was established, which is freely available at http://server.malab.cn/70ProPred/ .

HPSLPred: An Ensemble Multi-Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source.

Predicting the subcellular localization of proteins is an important and challenging problem. Traditional experimental approaches are often expensive and time-consuming. Consequently, a growing number of research efforts employ a series of machine learning approaches to predict the subcellular location of proteins. There are two main challenges among the state-of-the-art prediction methods. First, most of the existing techniques are designed to deal with multi-class rather than multi-label classification, which ignores connections between multiple labels. In reality, multiple locations of particular proteins imply that there are vital and unique biological significances that deserve special focus and cannot be ignored. Second, techniques for handling imbalanced data in multi-label classification problems are necessary, but never employed. For solving these two issues, we have developed an ensemble multi-label classifier called HPSLPred, which can be applied for multi-label classification with an imbalanced protein source. For convenience, a user-friendly webserver has been established at http://server.malab.cn/HPSLPred.

Event Coverage Detection and Event Source Determination in Underwater Wireless Sensor Networks.

With the advent of the Internet of Underwater Things, smart things are deployed in the ocean space and establish underwater wireless sensor networks for the monitoring of vast and dynamic underwater environments. When events are found to have possibly occurred, accurate event coverage should be detected, and potential event sources should be determined for the enactment of prompt and proper responses. To address this challenge, a technique that detects event coverage and determines event sources is developed in this article. Specifically, the occurrence of possible events corresponds to a set of neighboring sensor nodes whose sensory data may deviate from a normal sensing range in a collective fashion. An appropriate sensor node is selected as the relay node for gathering and routing sensory data to sink node(s). When sensory data are collected at sink node(s), the event coverage is detected and represented as a weighted graph, where the vertices in this graph correspond to sensor nodes and the weight specified upon the edges reflects the extent of sensory data deviating from a normal sensing range. Event sources are determined, which correspond to the barycenters in this graph. The results of the experiments show that our technique is more energy efficient, especially when the network topology is relatively steady.