Aiming at the low efficiency of the Big data query of the internet of Things, the research based on the smart urban management platform, and on the premise of retaining the original platform data integration framework...
详细信息
ISBN:
(数字)9781728177380
ISBN:
(纸本)9781728177397
Aiming at the low efficiency of the Big data query of the internet of Things, the research based on the smart urban management platform, and on the premise of retaining the original platform data integration framework. The query model and process are redesigned and a new data improved query model is proposed by introducing hash coding, distributed index and data dictionary. Compared with the one by one comparison query method, the speed of the improved query model is increased by 10 6 times when processing millions of data, which significantly improves the query efficiency of big data. The research results can help improve the dataprocessing and analysis ability of Chongqing Liangjiang Smart Urban Management Platform in China.
Social media platforms such as Twitter are increasingly used to collect data of all kinds. During natural disasters, users may post text and image data on social media platforms to report information about infrastruct...
详细信息
ISBN:
(数字)9781728169972
ISBN:
(纸本)9781728169989
Social media platforms such as Twitter are increasingly used to collect data of all kinds. During natural disasters, users may post text and image data on social media platforms to report information about infrastructure damage, injured people, cautions and warnings. Effective processing and analysing tweets in real time can help city organisations gain situational awareness of the affected citizens and take timely operations. With the advances in deep learning techniques, recent studies have significantly improved the performance in classifying crisis-related tweets. However, deep learning models are vulnerable to adversarial examples, which may be imperceptible to the human, but can lead to model's misclassification. To process multi-modal data as well as improve the robustness of deep learning models, we propose a multi-modal adversarial training method for crisis-related tweets classification in this paper. The evaluation results clearly demonstrate the advantages of the proposed model in improving the robustness of tweet classification.
The autonomous underwater vehicle (AUV) aided mobile data collection is an effective method for reducing the energy consumption of the underwater acoustic (UWA) sensor networks. In this paper, we propose an AUV-aided ...
详细信息
ISBN:
(数字)9781728172026
ISBN:
(纸本)9781728172033
The autonomous underwater vehicle (AUV) aided mobile data collection is an effective method for reducing the energy consumption of the underwater acoustic (UWA) sensor networks. In this paper, we propose an AUV-aided path-planning scheme using cooperative transmission mechanism for a medium-scale UWA sensor network. In the proposed scheme, we analyze not only the energy consumption, but also the task duration and path-planning cost comprehensively for practical applications. We analyze four different path-planning schemes in terms of energy consumption of UWA sensor nodes and travel cost of AUV. The simulation results show that the lawn mower path-planning scheme has lower energy consumption of UWA sensor networks. But the circle path-planning scheme has lower working time and path energy consumption of AUV. Therefore, in view of different needs, we should make a comprehensive selection.
The hardware sample of multi-core data-flow recurrent architecture has been developed and tested on the digital signal processing domain. An analysis of the iterative algorithms execution results made it possible to p...
详细信息
ISBN:
(数字)9781728157610
ISBN:
(纸本)9781728157627
The hardware sample of multi-core data-flow recurrent architecture has been developed and tested on the digital signal processing domain. An analysis of the iterative algorithms execution results made it possible to propose a number of mechanisms to improve one of the components of the architecture - the Iterator. A significant problem in architecture programming is a high program redundancy produced by a significant number of special operands that are designed to control its internal resources. The Iterator component is designed to solve this issue, but its capabilities were not enough. The article presents the development results of the Iterator component. A description of the developed mechanisms to control the Iterator is provided. We demonstrate the results of the Iterator improvements using an example of the Viterbi algorithm for searching at hidden Markov models. The developed tools made it possible to nearly halve the volume of special operands and optimize the software implementation of the algorithm.
Electricity load forecasting is a prevalent research topic in recent years. In this study, we predict the electricity consumption using only previous power data (i.e., without using weather information or other featur...
详细信息
ISBN:
(数字)9781728169262
ISBN:
(纸本)9781728169279
Electricity load forecasting is a prevalent research topic in recent years. In this study, we predict the electricity consumption using only previous power data (i.e., without using weather information or other features). We survey existing univariate methods such as MLP-based, CNN-based, XGBoost-based, RF-based, and EN3-bestK. However, these existing methods do not perform well due to that the range of power values varies a lot. Therefore, we present an electricity consumption forecast system called Dynamic Weight Ensemble Model (DWEM). There are three stages in the proposed DWEM. First of all, we provide three types of data serialization in data preprocessing. Second, we train four types of models (i.e., MLP-based, CNN-based, XGBoost-based, and RF-based) for building the ensemble model later. Finally, we combine the four types of models into an ensemble model, using the proposed Two-Phase Ensemble. In the two-phase ensemble, the first phase is to ensemble the models trained using the same algorithm but different serializations, and the second phase is to ensemble the models from different algorithms. The two-phase ensemble method is designed to dynamically adjust weights based on the previous performance of the corresponding models. Moreover, we notice that properly handling missing values is an important factor in system performance. Therefore, we present a statistical method to estimate the missing values. We compare DWEM with various state-of-the-art methods. Comparison of DWEM and the state-of-the-art ensemble method, the results show that DWEM is on average about 46.95% and 44.47% better than EN3-bestK on the MAPE and MAE indicators, respectively.
Gastric cancer is predominantly caused by demographic-diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (EGC) factors from diet and lifestyle characteristics of Mi...
ISBN:
(数字)9781728148762
ISBN:
(纸本)9781728148779
Gastric cancer is predominantly caused by demographic-diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (EGC) factors from diet and lifestyle characteristics of Mizo-ethnicity using supervised machine learning algorithms. For this study, 80 cases and 160 controls are selected and a dataset containing 11 features that are core risk factors for the gastric cancer have been chosen for data mining. The learning curves show Naive Bayes, Logistic Regression and Multilayer perceptron are the best fit classification algorithms for our dataset. datamodels are constructed and evaluated using: brier score, accuracy, precision_recall curves for cases (patients) and controls (healthy individuals), and false positives. The data interpretation shows Naive Bayes has the highest classification results having an accuracy of 90%, with the lowest Brier score of 0.1, and a false positive rate of 3% as compared to other models. Logistic regression classifier shows equally good performances with setback in brier_score and false positives. This study found that extra salt, tuibur, smoking and alcohol are the non_invasive etiological factors for gastric cancer in Mizoram population as predicted by the Naive Bayes algorithm. This knowledge will be helpful for initiating early screening and to educate the public about the risk of dietary and lifestyle factors in high risk population with unique habits.
A supervised learning algorithm can be categorized into different forms and one of this is classification where the main goal is to predict the categorical class labels of structured or unstructured data. However, it ...
详细信息
ISBN:
(数字)9781728199108
ISBN:
(纸本)9781728184999
A supervised learning algorithm can be categorized into different forms and one of this is classification where the main goal is to predict the categorical class labels of structured or unstructured data. However, it requires large datasets to produce a good computer vision model. This study demonstrates the application of the supervised learning algorithm named Convolutional Neural Network (CNN) in multinomial classification of coral reef species. Through the backpropagation process of CNN, the model is able to learn the weights that yield accurate outputs. Moreover, data augmentation approach, retraining, fine tuning and optimization are used to provide better results in multi-class classification. The classification result in terms of F1 Score and Sensitivity is equal to 1.0 while validation accuracy yields 99.49 percent after nine (9) epochs applied to the various coral reef species available in the dataset used in this study.
In recent years, Human activity recognition and research related to it are in high demand owing to its application in various fields such as healthcare systems, assisted living, surveillance etc. Activity recognition ...
详细信息
ISBN:
(数字)9781728149882
ISBN:
(纸本)9781728149899
In recent years, Human activity recognition and research related to it are in high demand owing to its application in various fields such as healthcare systems, assisted living, surveillance etc. Activity recognition system in general aims at identifying activities performed by person in an environment. In this work, skeletal data-based activity recognition system is presented. Microsoft Kinect sensor is a motion capture sensor developed by Microsoft for xbox one. It has become most popular for its effortless operation and low cost. The 3D skeletal joint positions obtained from this kinect sensor are used as raw data for classification purpose. Set of statistical features are computed from these skeletal data. The dimensions of statistical features computed are reduced to eliminate correlated and redundant features among them. Principal component analysis (PCA), a technique used for finding smaller number of uncorrelated data is employed for reducing the feature dimension. The dimensionally reduced features are used as training data for training the classifier. The ability of K-nearest neighbour (KNN) classifier and Support vector machine (SVM) classifier in classifying actions are analysed. The classification method proposed is tested on most popular KARD (Kinect activity recognition dataset) dataset and various classification parameters are computed. Among the two classifiers considered, SVM classifier performed better with an average overall accuracy of 97% which is 3.44% higher than the accuracy produced by KNN classifier.
The entire world is facing the Covid19 pandemic. This pandemic has various consequences on the political, cultural, economical and social life of the community. Lockdown has affected the psychological impact on societ...
详细信息
ISBN:
(数字)9781728159706
ISBN:
(纸本)9781728159713
The entire world is facing the Covid19 pandemic. This pandemic has various consequences on the political, cultural, economical and social life of the community. Lockdown has affected the psychological impact on society. This is reflected in various social media sites. In such a phase social media analytics for twitter data can be useful for understanding public opinion. In this paper, we have applied the Latent Dirichlet Allocation Algorithm as a topic modeling algorithm. Topic modeling finds the main theme that pervades the large data set. Twitter media is considered as the most popular microblogging platform, hence data during this pandemic is extracted from twitter. Natural language processing Techniques applied as preprocessing and then topic modeling applied which has given satisfactory results in terms of perplexity as a performance measure. Topic extracted gives an idea of the impact of Covid19 on society through their opinion on twitter. This can be helpful for making future policies by policymakers.
Named Entity Recognition (NER) is an information extraction task that aims to automatically identify named entities in a given text. Named entities are special types of nouns or noun groups that refer to specific enti...
详细信息
ISBN:
(数字)9781728162515
ISBN:
(纸本)9781728162522
Named Entity Recognition (NER) is an information extraction task that aims to automatically identify named entities in a given text. Named entities are special types of nouns or noun groups that refer to specific entities including as person, location, organization, date, time, money and percentage. NER also facilitates various other Natural Language processing (NLP) related tasks such as summarization and question answering. It is a vastly studied problem especially on English texts, however number of NER studies on Turkish is very limited. Being a morphologically rich language, Turkish has an agglutinative structure and hence automated analysis and information extraction performance is generally lower than those on English. The previous studies mostly use conventional supervised learning and sequence tagging methods, such as Conditional Random Fields (CRF). Only few studies use deep neural models for NER problem on Turkish texts. In this work, we particularly focus on the recent neural model, Google BERT, and analyze its performance on Turkish texts. In addition to fully trained BERT model, we investigate the performance of different training levels from fully trained to fully pre-trained.
暂无评论