Collection Of Raw Data Research Articles

Malayalam Question Answering System Using Deep Learning Approaches

ABSTRACT Question Answering (QA) systems attempt to retrieve precise answers to questions posed in natural language by the users. It is a sophisticated form of Information Retrieval (IR) that uses a predefined collection of raw data in natural language. Malayalam is an official language in India, that is not only morphologically rich and agglutinative in nature but is also resource constrained. These aspects of the language make QA in Malayalam very challenging. This paper proposes a deep learning based QA system for Malayalam using techniques such as Long Short-Term Memory Networks (LSTM), Gated Recurrent Unit (GRU), and Memory Network models. Facebook bAbI dataset consisting of 20 tasks with the questions having multiple supporting facts, inductive and deductive reasoning, coreference, etc. have been used to train and test the system. It was observed that the Memory Network model achieved the best average accuracy (80%) among the three models implemented, in retrieving exact answers in Malayalam. This work is unique because all the reported work on Malayalam QA is rule-based, capable of extracting answers to factoid questions only. The proposed system which uses deep learning approaches is scalable and thus capable of enhancing the ongoing research in Malayalam QA along with the development of the Malayalam QA corpus.

Development of a New Wearable 3D Sensor Node and Innovative Open Classification System for Dairy Cows' Behavior.

Simple SummaryIn order to keep dairy cows under satisfactory health and welfare conditions, it is very important to monitor the animals in their living environment. With the support of technology, and, in particular, with the installation of sensors on neck-collars, cow behavior can be adequately monitored, and different behavioral patterns can be classified. In this study, an open and customizable device has been developed to classify the behaviors of dairy cows. The device communicates with a mobile application via Bluetooth to acquire raw data from behavioral observations and via an ad hoc radio channel to send the data from the device to the gateway. After observing 32 cows on 3 farms for a total of 108 h, several machine learning algorithms were trained to classify their behaviors. The decision tree algorithm was found to be the best compromise between complexity and accuracy to classify standing, lying, eating, and ruminating. The open nature of the system enables the addition of other functions (e.g., localization) and the integration with other information sources, e.g., climatic sensors, to provide a more complete picture of cow health and welfare in the barn.Monitoring dairy cattle behavior can improve the detection of health and welfare issues for early interventions. Often commercial sensors do not provide researchers with sufficient raw and open data; therefore, the aim of this study was to develop an open and customizable system to classify cattle behaviors. A 3D accelerometer device and host-board (i.e., sensor node) were embedded in a case and fixed on a dairy cow collar. It was developed to work in two modes: (1) acquisition mode, where a mobile application supported the raw data collection during observations; and (2) operating mode, where data was processed and sent to a gateway and on the cloud. Accelerations were sampled at 25 Hz and behaviors were classified in 10-min windows. Several algorithms were trained with the 108 h of behavioral data acquired from 32 cows on 3 farms, and after evaluating their computational/memory complexity and accuracy, the Decision Tree algorithm was selected. This model detected standing, lying, eating, and ruminating with an average accuracy of 85.12%. The open nature of this system enables for the addition of other functions (e.g., real-time localization of cows) and the integration with other information sources, e.g., microenvironment and air quality sensors, thereby enhancing data processing potential.

Attributes for Discrete Choice Experiment on Pharmacy-based Alcohol Brief Intervention Service in Thailand

Purpose: The alcohol brief intervention (ABI) service provided by community pharmacists was not conducted in Thailand. A discrete choice experiment (DCE) is a widely accepted approach to elicit stated preferences in the health economics. This study aims to identify important attributes and levels from both client and community pharmacists' points of view. The step involved in conducting a DCE is to develop the attributes and levels for the model. Attributes relevant to a new community pharmacy-based ABI service were used to determine clients' preferences for receiving this service by a DCE. Methods: The method includes five steps: 1) literature review and researcher observation, 2) raw data collection, 3) attribute selection, 4) attributes and wording confirmation, and 5) researchers' conclusions These steps involved a semi-structured interview given to 20 clients. After conducting the interviews, the data was triangulated to obtain one DCE choice from each client. An iterative constant comparative approach during the data collection and analysis. The selected attribute was derived from a focus group discussion among seven community pharmacists. Results: The five steps resulted in five attributes: modes of consultation, screening methods, a continuation of a conversation, a counseling session, and cost of service. According to the methodological triangulation, eight of ten key informants have opinions congruous with one DCE choice set. Conclusion: The attributes and levels of a Thai community pharmacy-based service for a DCE were derived from both client and community pharmacists' views using five steps. The attributes and levels were suitably used in a subsequent DCE.

Large Bradbury–Nielsen Gate Optimized for Electrospray Time of Flight Spectroscopy

A large, , low-cost Bradbury–Nielsen gate (BNG) was developed and optimized to reduce diagnostic noise and high-energy ion impingement damage to electrospray thrusters during time-of-flight spectroscopy (TOFS). This new BNG increased diagnostic ion transparency by 633%, significantly increased the signal-to-noise ratio in the raw data collection, and reduced thruster damage due to high-energy ionic bombardment during ion diversion. By deflecting the thruster’s ionic plume, as opposed to the conventional method of reflection, the BNG can be operated at 50–75% lower cyclic voltages, thus reducing high-frequency noise induced by the required high-voltage, high-frequency gate operation. The BNG reduces high-energy ion impingement on the thruster’s extraction surface by up to 98.9%. This significant reduction in return current allows for unaltered measurements of performance and enables repeated diagnostic use without deleterious effects during long test campaigns.

Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals.

As failures of rolling bearings lead to major failures in rotating machines, recent vibration-based rolling bearing fault diagnosis techniques are focused on obtaining useful fault features from the huge collection of raw data. However, too many features reduce the classification accuracy and increase the computation time. This paper proposes an effective feature selection technique based on intrinsic dimension estimation of compressively sampled vibration signals. First, compressive sampling (CS) is used to get compressed measurements from the collected raw vibration signals. Then, a global dimension estimator, the geodesic minimal spanning tree (GMST), is employed to compute the minimal number of features needed to represent efficiently the compressively sampled signals. Finally, a feature selection process, combining the stochastic proximity embedding (SPE) and the neighbourhood component analysis (NCA), is used to select fewer features for bearing fault diagnosis. With regression analysis-based predictive modelling technique and the multinomial logistic regression (MLR) classifier, the selected features are assessed in two case studies of rolling bearings vibration signals under different working loads. The experimental results demonstrate that the proposed method can successfully select fewer features, with which the MLR-based trained model achieves high classification accuracy and significantly reduced computation times compared to published research.

An improved routing protocol for raw data collection in multihop wireless sensor networks

Wireless sensor networks (WSNs) are an effective and efficient method for collecting data from a target area, and prolonging the lifetime of WSNs has been a focus of scientific research due to the limited energy of sensor nodes. However, traditional studies of WSNs are based on the assumption that WSNs collect aggregated data with redundant sensor nodes in an ideal radio environment. These assumptions may not be acceptable in practical applications. To address this problem, this paper introduces a novel application scenario for WSNs in which raw data are collected by a multihop network without redundant sensor nodes, and a new hybrid tree-based and cluster-based routing protocol for raw data collection (HTC-RDC) is proposed to prolong the lifetime of WSNs that can work in novel application scenarios. The experimental results demonstrate that the proposed HTC-RDC enables the WSNs to achieve their expected functions and prolongs the network lifetime by an average of 11.4% compared to the existing protocols in the explored application scenario.

Design of mathematical model for the prediction of rainfall

There are several soft computing methods in use to predict rainfall. Mainly two features were included to increase rainfall prediction: (1) using data pre-processing procedure and (2) using a modular approach. The projected pre-processing approach incorporated Moving Average (MA) and Singular Spectrum Analysis (SSA). The method of modular was poised of Support Vectors Regression l (SVR) models or the Rough Set Technique (RST). In the development for forecasting of rainfall, the RST was initially applied for the data- preprocessing. Modular models used to pre-process the preparation data into three distinct subsets (level-1, level-2, and level-3) from the scales of the trained data, and lastly, two SVRs were used in the level-2 and level-3 subsets. In contrast, Artificial Neural Network (ANN) or SVR was concerned with predicting and was useful in training the data. Each day’s rate of downpour proof, the level-1 subset tended to be modelled by the ANN because it was overwhelming in the training data. ANN is beneficial for huge-scale samples training because of its corresponding information processing configuration. This work explores the use of hybridization technique of RST and time series, where RST helps to find the essential attribute from the collection of raw meteorological data set then analyzing the important characteristic using time series and various classifiers. There are several prediction techniques available to predict based on meteorological data set to suitably predict a meteorological phenomenon. In this work, our objective is to find the most frequent meteorological phenomena which affects our state most. Purposefully, we consider the RST to predict the most significant meteorological phenomena by using the RST and predict the rainfall per day basis. Hybrid soft computing techniques and RST are used in the present work. We validate our claim using the Chi-square test.

From Data Analysis to Intent-Based Recommendation: An Industrial Case Study in the Video Domain

This work presents a comprehensive study, from an industrial perspective, of the process between the collection of raw data, and the generation of next-item recommendation, in the domain of Video-on-Demand (VoD). Most research papers focus their efforts on analyzing recommender systems on already-processed datasets, but they do not face the same challenges that occur naturally in industry, e.g., processing raw interactions logs to create datasets for testing. This paper describes the whole process between data collection and recommendation, including cleaning, processing, feature engineering, session inferring, and all the challenges that a dataset provided by an industrial player in the domain posed. Then, a comparison on the new dataset of several intent-based recommendation techniques in the next-item recommendation task follows, studying the impact of different factors like the session length, and the number of previous sessions available for a user. The results show that taking advantage of the sequential data available in the dataset benefits recommendation quality, since deep learning algorithms for session-aware recommendation are consistently the most accurate recommenders. Lastly, a summary of the different challenges in the VoD domain is proposed, discussing on the best algorithmic solutions found, and proposing future research directions to be conducted based on the results obtained.

Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor.

Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes are frequently employed for this purpose, which are now compacted into smart devices, e.g., smartphones. Since the use of smartphones is so widespread now-a-days, activity data acquisition for the HAR systems is a pressing need. In this article, we have conducted the smartphone sensor-based raw data collection, namely H-Activity, using an Android-OS-based application for accelerometer, gyroscope, and linear acceleration. Furthermore, a hybrid deep learning model is proposed, coupling convolutional neural network and long-short term memory network (CNN-LSTM), empowered by the self-attention algorithm to enhance the predictive capabilities of the system. In addition to our collected dataset (H-Activity), the model has been evaluated with some benchmark datasets, e.g., MHEALTH, and UCI-HAR to demonstrate the comparative performance of our model. When compared to other models, the proposed model has an accuracy of 99.93% using our collected H-Activity data, and 98.76% and 93.11% using data from MHEALTH and UCI-HAR databases respectively, indicating its efficacy in recognizing human activity recognition. We hope that our developed model could be applicable in the clinical settings and collected data could be useful for further research.

Kolaborasi Pemerintah dan Masyarakat Sipil Merespon Covid-19 di Daerah Istimewa Yogyakarta Melalui Pendekatan Crisis Visualizations

This research discusses the collaboration of the Yogyakarta Special Region government (DIY) and civil society in responding to Covid-19. This study analyzes the collaboration between the two by applying the crisis visualizations approach. Crisis visualization is a concept that describes visual crisis information, which aims to assist the public in mitigating risks and emergencies, as well as helping institutions and authorities in overcoming threats. In creating a visualization of the Covid-19 crisis, there are six techniques or forms, namely: crisis information in the form of temporal and geospatial visualizations (crisis maps); forecast trends and influences; the nature of the crisis; risk mitigation guidelines; visualization of risk, vulnerability and equity information; and measure the multi-effect impact of the crisis. The collaboration between the DIY government and civil society will be reviewed from the six techniques or forms of visualizing the Covid-19 crisis. This study uses a qualitative method. Data collection using interview techniques, literature study, and from internet sources. This study found that the collaboration between DIY government and civil society in crisis visualization does not occur directly. This research found that the making of visual crisis communication was managed only by the government. Community involvement occurs in the collection of raw data in the field to be conveyed to the government. This study found that the collaboration with civil society was built on the educational aspect, informal coordination which tended to be bottom-up approach, and promotion through the mass media.

Dynamics of the global trade Asiatic Softshell Turtle (Amyda cartilaginea Boddaert 1770): Shifting trends in commerce and consequences for sustainability

Biodiverse countries such as Indonesia provide the exotic Asiatic Softshell Turtle (Amyda cartilaginea Boddaert 1770) for the wildlife trade. Deciding which trade model is detrimental to species survival in the wild can be a major challenge for Management Authorities (MA) in implementing CITES. The consequences for conservation, long-term use, and livelihoods are uncertain. The study used the CITES (Convention on International Trade in Endangered Species of Wild Fauna and Flora) trade database. The collection of raw data is based on trade reports for the species of freshwater turtles (testudinidae) for the period 2011 to 2021, export countries from Indonesia, export destinations for all countries and sources of harvested turtles from the wild. This research aims to study the freshwater turtle trading trends over the decade, compare total quotas to actual harvest, and recognize how the precautionary principle is applied in harvesting A. cartilaginea. Harvesting and trading are following the quota regulated under the Indonesian government. However, conservation efforts were less emphasized, so it is feared that there will be a population decline and even extinction in the future, while the population in the wild cannot be ascertained. The larger the harvest quota set and the shorter the harvest period, the larger the natural population that must be available.

Data-Independent Acquisition-Based Mass Spectrometry (DIA-MS) for Quantitative Analysis of Intact N-Linked Glycopeptides.

N-linked protein glycosylation is a key regulator in various biological functions. Previous studies have shown that aberrant glycosylation is associated with many diseases. Therefore, it is essential to elucidate protein modifications of glycosylation by quantitatively profiling intact N-linked glycopeptides. Data-independent acquisition (DIA) mass spectrometry (MS) is a cost-effective, flexible, and high-throughput method for global proteomics. However, substantial challenges are still present in the quantitative analysis of intact glycopeptides with high accuracy at high throughput. In this study, we have established a novel integrated platform for the DIA analysis of intact glycopeptides isolated from complex samples. The established analysis platform utilizes a well-designed DIA-MS method for raw data collection, a spectral library constructed specifically for intact glycopeptide quantification providing accurate results by the inclusion of Y ions for quantification and filtering of quantified intact glycopeptides with low-quality MS2 spectra automatically using a set of criteria. Intact glycopeptides isolated from human serum were used to evaluate the performance of the integrated platform. By utilizing 100 isolation windows for DIA data acquisition, a well-constructed human serum spectral library containing 1123 nonredundant intact glycopeptides with Y ions, and automated data inspection, 620 intact glycopeptides were quantified with high confidence from DIA-MS. In summary, our integrated platform can serve as a reliable quantitative tool for characterizing intact glycopeptides isolated from complex biological samples to assist our understanding of biological functions of N-linked glycosylation.

Variation of Harmonics to Noise Ratio from the Age Range of 9-18 Years Old in both the Genders.

Voice is the perception of physical complexity of the laryngeal tone modified by a resonating cavity. The voice parameters are the vital signs of an individual to project their personality and gender. The basic acoustical parameters of voice are: Fundamental frequency, Intensity, Jitter, Shimmer and Harmonics to noise ratio (HNR) and among these parameters HNR is the most significant. The voice component represents the periodic and aperiodic signals and predominantly aperiodic signals. There are many research work have been documented on acoustical analysis of voice with narrowed age range at different zonals in India. The motive of the study was mainly focused on the ratio between periodic and aperiodic components of voice and its changes from pre pubertal to post pubertal stages in both the genders. Due to the paucity of literature on changes in HNR in developing children, the present study was conducted to find out how do the changes in HNR occur in both the genders. Observational study design with convenient sampling method was used for the collection of raw data. A total of 198 subjects comprising of group I males (n = 99) and group II females (n = 99). These groups were further subdivided into 9 sub groups in males (n = 99) and females (n = 99) based on the age range. Sustained phonation of /a/ was used as a stimulus for voice sample. The data was analyzed using PRAAT software. The over mean Harmonic to Noise Ratio was found to be higher in males compared to the females. When age wise comparison was done, a significant difference in the Harmonic to Noise Ratio was found in males with no significant changes noticed in females. The transition in the Harmonic to Noise Ratio in males was seen to start at the age of 14-15years.

Computer Vision: A Timely Opportunity

Different approaches to the study of computer vision have been taken into consideration. It begins with the collection of raw data and advances to methodologies and ideas that combine digital images, pattern recognition, machine learning, and computer graphics to produce new products, as well as new products themselves. In order to get crucial information, students can analyze images and videos to interpret events or descriptions, as well as discern patterns in the landscape, using computer vision. It makes use of a multi-spectrum application domain strategy in conjunction with a large amount of data in order to achieve its goals. In recent years, technological developments in computer vision have paved the way for the creation of novel agricultural applications. Precision yield forecasts for fruit and vegetable crops are particularly critical for improving harvesting, marketing, and logistics planning and execution. When a bridge is under stress or has a high volume of traffic, the geographical and temporal information provided by cars on the bridge reflects this. It is proposed to design a methodology for information gathering and dissemination by utilizing computer vision technology, which recognizes various items tracking and picture calibration via a quick regional neural convolution network, and a quick regional neural convolution network (Faster R-CNN). When dealing with small fish populations, it can be difficult to objectively assess the differences in behavior between individuals. The behavior of fish in aquaculture tanks has been studied with the use of a computer vision system that has been built in order to quantify these types of observations. Contained traffic load data is essential for bridge statistical analysis, security evaluation, and maintenance planning. This is particularly true for heavy trucks. From retail to agriculture, and across all industries, computer vision is having a big impact on organizations of all sizes and in all sectors. When a human eye is required to assess the situation, the significance of this becomes even more apparent. This paper provides information about computer vision technology, including short algorithms, issues, opportunities, and applications for computer vision in a range of fields in the year 2021, as well as information on computer vision in general. Information about computer vision applications in many fields is also included for the year 2021.

Sociodemographic characteristics of missing data in digital phenotyping

The ubiquity of smartphones, with their increasingly sophisticated array of sensors, presents an unprecedented opportunity for researchers to collect longitudinal, diverse, temporally-dense data about human behavior while minimizing participant burden. Researchers increasingly make use of smartphones for “digital phenotyping,” the collection and analysis of raw phone sensor and log data to study the lived experiences of subjects in their natural environments using their own devices. While digital phenotyping has shown promise in fields such as psychiatry and neuroscience, there are fundamental gaps in our knowledge about data collection and non-collection (i.e., missing data) in smartphone-based digital phenotyping. In this meta-study using individual-level data from six different studies, we examined accelerometer and GPS sensor data of 211 participants, amounting to 29,500 person-days of observation, using Bayesian hierarchical negative binomial regression with study- and user-level random intercepts. Sensitivity analyses including alternative model specification and stratified models were conducted. We found that iOS users had lower GPS non-collection than Android users. For GPS data, rates of non-collection did not differ by race/ethnicity, education, age, or gender. For accelerometer data, Black participants had higher rates of non-collection, but rates did not differ by sex, education, or age. For both sensors, non-collection increased by 0.5% to 0.9% per week. These results demonstrate the feasibility of using smartphone-based digital phenotyping across diverse populations, for extended periods of time, and within diverse cohorts. As smartphones become increasingly embedded in everyday life, the insights of this study will help guide the design, planning, and analysis of digital phenotyping studies.

ECHR-OD: On building an integrated open repository of legal documents for machine learning applications

This paper presents an exhaustive and unified repository of judgments documents, called ECHR-OD, based on the European Court of Human Rights. The need of such a repository is explained through the prism of the researcher, the data scientist, the citizen, and the legal practitioner. Contrarily to many open data repositories, the full creation process of ECHR-OD, from the collection of raw data to the feature transformation, is provided by means of a collection of fully automated and open-source scripts. It ensures reproducibility and a high level of confidence in the processed data, which is one of the most important issues in data governance nowadays. The experimental evaluation was performed to study the problem of predicting the outcome of a case, and to establish baseline results of popular machine learning algorithms. The obtained results are consistently good across the binary datasets with an accuracy comprised between 75.86% and 98.32%, having the average accuracy equals to 96.45%, which is 14pp higher than the best known result with similar methods. We achieved a F1-Score of 82% which is aligned with the recent result using BERT. We show that in a multilabel setting, the features available prior to a judgment are good predictors of the outcome, opening the road to practical applications.

Smartphone-based indoor localization techniques: State-of-the-art and classification

Smartphone is now undeniably essential and a very functional tool for everyone. As the need for more powerful computations, faster communications, and more sophisticated location-based services, the number of powerful embedded sensors also becomes indispensable in smartphones. Leveraging the huge collection of raw data coming from these commodity sensors gives birth to a myriad of mobile applications that are mostly centered on the users’ location. This survey explores the sensing capabilities of different smartphone sensors and how they become more functional in the context of wireless-based localization. It identifies the different techniques toward efficient indoor localization using the modalities inherent in smartphones. A taxonomy based on the notable approaches used in the system such as mapping, path loss prediction, and dead reckoning is also defined. The strengths and weaknesses of each system and identify and compare the technologies used are highlighted. Finally, open issues and challenges for future works are presented.

The UMA-SAR Dataset: Multimodal data collection from a ground vehicle during outdoor disaster response training exercises

This article presents a collection of multimodal raw data captured from a manned all-terrain vehicle in the course of two realistic outdoor search and rescue (SAR) exercises for actual emergency responders conducted in Málaga (Spain) in 2018 and 2019: the UMA-SAR dataset. The sensor suite, applicable to unmanned ground vehicles (UGVs), consisted of overlapping visible light (RGB) and thermal infrared (TIR) forward-looking monocular cameras, a Velodyne HDL-32 three-dimensional (3D) lidar, as well as an inertial measurement unit (IMU) and two global positioning system (GPS) receivers as ground truth. Our mission was to collect a wide range of data from the SAR domain, including persons, vehicles, debris, and SAR activity on unstructured terrain. In particular, four data sequences were collected following closed-loop routes during the exercises, with a total path length of 5.2 km and a total time of 77 min. In addition, we provide three more sequences of the empty site for comparison purposes (an extra 4.9 km and 46 min). Furthermore, the data is offered both in human-readable format and as rosbag files, and two specific software tools are provided for extracting and adapting this dataset to the users’ preference. The review of previously published disaster robotics repositories indicates that this dataset can contribute to fill a gap regarding visual and thermal datasets and can serve as a research tool for cross-cutting areas such as multispectral image fusion, machine learning for scene understanding, person and object detection, and localization and mapping in unstructured environments. The full dataset is publicly available at: www.uma.es/robotics-and-mechatronics/sar-datasets.

Application of Fuzzy Clustering Maximum Tree Algorithm in Teaching Quality Evaluation

The evaluation process of school teaching quality is more complicated. The traditional schemes mainly based on manual evaluation or expert evaluation. Due to the strong subjectivity, there is a big deviation between the evaluation results and the real results. To this end, a teaching quality evaluation program based on the largest tree of fuzzy clustering is proposed. After raw data collection, preprocessing, and data mining, accurate and objective evaluation results are finally obtained. Taking the original evaluation data set as the object, construct the fuzzy clustering maximum tree model, and obtain the importance matrix of the data set and the similarity coefficient between the input data variables. With the help of the fuzzy clustering maximum tree model, the importance of each factor in the evaluation of teaching quality can be objectively evaluated. Application examples also verify the superiority of the proposed evaluation algorithm.

IoT Enabled Clustering of Traffic Data - A Review

The administration of the traffic control system is a great concern in the metropolitan cities. The traffic control system has become much busier in recent years, traffic congestion is one of the reasons for these key challenges in smart cities. Traditional traffic management systems are not suitable for solving the problem, the mechanism of the congestion control mechanism is needed. This is how there is an intelligent control system. This research document proposes an intelligent system of traffic control based on IOT. This improves the high degree of scalability, replacing the previous traffic signage system with traffic signal control data in real time. To solve these safety protocol concerns, we implement IOT systems based on privacy with intelligence, which analyze the traffic data in real time for the control of traffic signals. We approach the man's data security attack in the center (MITM). And here, the algorithm of the support vector machine (SVM) will be used here for the classification of data on the edge and will be implemented by RASPBERRY PI3 and Scikit to implement the collection of raw traffic data. The sensors are used to distinguish positive or bad data from. The traffic data pattern of the terminal devices based on IOT. The edge router and the fog router will also be used to store traffic information in the cloud and to decide the level of traffic.