Dimensionality reduction via preserving local information

Sparse multi-view image clustering with complete similarity information

PurposeBig Data has become crucial for fulfilling the vision of smart cities; however, there are several challenges associated with its use. This study aims to provide a holistic view of challenges of using Big Data in smart cities and the solutions to deal with them by systematically selecting, reviewing and synthesizing the literature in this area.Design/methodology/approachA systematic literature review was conducted by following a rigorous search protocol that identified a total of 310 peer-reviewed academic research papers. These papers were subsequently filtered and finally 38 relevant papers were selected.FindingsA number of major challenges (human dynamics, privacy, security, volume, velocity, variety, veracity and value) associated with Big Data in a smart city and the respective solutions to address them were identified. This study primarily contributes in providing the process of effectively managing Big Data in smart cities.Practical implicationsThe study provides valuable information to the Big Data practitioners by illustrating the process of effective management of Big Data in smart cities. This study further provides the directions to the future researchers.Originality/valueThe study is original and is based on the existing literature and its interpretation.

For classifying images with various appearances, graph embedding based subspace learning has difficulty in taking a comprehensive consideration of both local geometrical structure and between-class discriminative information. In addition, when no sufficient training samples exist, using only the simple weight graph corresponding to labeled samples, the embedding subspace may not be accurately modeled. We present a semisupervised graph embedding algorithm by combining graph embedding and sparse representation. This algorithm can effectively learn a compact and semantic subspace by using a locally connected graph, which can model the geometrical structure and essential correlation of subclusters within a class and can fully utilize both labeled and unlabeled samples. Moreover, using L2,1-norm, the proposed algorithm can preserve the sparse representation property of images from the original space in the lower dimensional projected space. Our experiments demonstrate that the proposed algorithm has better performance than the alternatives reported in recent literature.

Cartoon-Texture decomposition with patch-wise decorrelation

Electrochemical performance of manganese hexacyanoferrate cathode material in aqueous Zn-ion battery

A community detection method based on local similarity and degree clustering information

Recently, the notion of a smart city, which includes smart well‐being, smart transit, and smart society, has attracted much attention due to its impact on people's quality of living. Data in smart cities are characterized by variety, velocity, volume, value, and veracity that are the well‐known characteristics of big data. The fast pace expanding of IoT devices and sensors in smart cities generates a huge volume of data that can help decision‐makers and managers in city management. The aim of this article is to wholly and systematically review big data handling approaches in smart cities, in which we analyze research efforts published between 2013 and February 2021, where these techniques are categorized based on their algorithms and architectures. Further, the main ideas, evaluation techniques, tools, evaluation metrics, algorithm types, advantages, and disadvantages are explored. Additionally, essential evaluation factors are introduced in which scalability and availability by 16%, time by 15% and accuracy by 11% are more in focus, and finally, some of the challenges, open issues, and future trends that are valuable for further research are suggested in big data handling approaches in smart cities.

Smart cities collect lots of data from sources like traffic systems and sensors. This data is vital for improving services such as transport management, public safety, energy saving, and citizen involvement. However, keeping people’s privacy secure by making data anonymous can make the data less useful. Anonymization methods include mix-zones, pseudonymization, and data masking. Existing systems often evaluate the usefulness of data after it’s processed, but usually can not adjust to changes in real-time or work well across different fields. It also does not typically consider fairness for individuals or integrate well with privacy-preserving data methods on devices, which are crucial for city services needing quick responses. This paper presents a new system to assess anonymized data in smart cities in real-time. The system includes four main components: 1. A real-time tool that continuously monitors how anonymization affects data quality across various areas. 2. A utility model that adjusts usefulness scores based on the needs of different smart city services. 3. A module that detects and addresses unfair differences in data usefulness caused by anonymization. 4. A data combination layer that operates well on devices, allowing on-site decision-making while complying with privacy regulations like GDPR. The framework is tested with multiple real-world transportation datasets, anonymized in different ways, and applied to tasks like traffic prediction, anomaly detection, and location-based services. The results demonstrate that the framework provides accurate data usefulness estimation with minimal computing effort, and it offers fair, situation-specific trade-offs in usefulness in real-time. This work connects privacy and usefulness, offering a scalable solution for responsibly using anonymized data in smart city environments. The framework is validated on both transportation and smart energy datasets, demonstrating consistent improvements in privacy–utility–fairness balance and confirming its generality across smart-city domains.

In this work, a solution for the distributed storage of data in Smart Cities is presented. An Edge-Fog-Cloud architecture that partitions the data through the Sharding technique proposes a hierarchical model that manipulates IoT data generated by Smart Cities. The problem is related to the approaches used to promote an integrated environment. Related works tend to use cloud-focused approaches that generate high latency rates, and those that use Fog Computing only use the layer as middleware, not exploring greater possibilities for use. In this context, this work presents the DASTData model that aims to enable lower latency rates, more data security, fault tolerance, high availability, and concurrent queries to promote a better experience in data management and availability in smart cities. In addition, our contribution to the literature is related to the proposition of an architecture focused on enabling the traceability of users who have mobile behavior in the city, providing the ability to analyze patterns and occurrences through the consolidation of data from one or more individuals. In the results obtained through the tests carried out in this work, we observed that in queries DASTData is up to 73% more efficient.

The explosive data growth in smart city is making domain big data a hot topic for knowledge extraction. Non-taxonomic relations refer to any relations between concept pairs except the is-a relation, which is an important part of Knowledge Graph. In this paper, toward big data in smart city, we present a multi-phase correlation search framework to automatically extract non-taxonomic relations from domain documents. Different kinds of semantic information are used to improve the performance of the system. First, inspired by the works of network representation; we propose a Semantic Graph-Based method to combine structure information of semantic graph and context information of terms together for non-taxonomic relationships identification. Second, different semantic types of verb sets are extracted based on the dependency syntactic information, which are ranked to act as non-taxonomic relationship labels. Extensive experiments demonstrate the efficiency of the proposed framework. The F1 value reaches 81.4% for identification of non-taxonomic relationships. The total precision of the non-taxonomic relationship labels extraction is 73.4%, and 87.8% non-taxonomic relations can be provided with “good” labels. We hope this article can provide a useful way for domain big data knowledge extraction in smart city.

Internet of Things (IoT) and Big Data have played a significant role in the development and sustainability of Smart Cities. They are the backbones of Smart Cities' efforts to connect human resources, social capital, and ICT infrastructure to address public challenges, achieve sustainable development and improve people's standard of life. It helps Smart Cities improve public services, such as water management, healthcare, education, security issues, transportation, energy usage, and other community to achieve a better life. Big Data helps to analyze, store and back-ups a massive amount of data generated in smart cities in seconds day by day. For this matter, different analytical tools are employed, such as data analytics, machine learning, statistics, and data mining. Even though there are many benefits offered to smart cities; the Smart Cities encounters challenges that need to be addressed. Many of these challenges focus on security and privacy, infrastructures and operational and handling massive data. This paper describes the overview of IoT, Big Data, and Smart Cities. The Applications of IoT and Smart Cities were also discussed; the features of Smart Cities and Big Data; Different challenges of IoT, Big Data, and Smart Cities are described. Also, the proposed research work has presented the relationship between IoT and Big Data to Smart Cities; the role of IoT and Big Data in smart cities was identified; finally, the future directions for IoT and Big Data regarding Smart Cities are discussed.

In the Fishervoice (FSH) based framework, the mean supervectors of the speaker models are divided into several subvectors by mixture index. However, this division strategy cannot capture local acoustic class structure information among similar acoustic classes or discriminative information between different acoustic classes. In order to verify whether or not local structure information can help improve system performance, we develop five different speaker supervector segmentation methods. Experiments on NIST SRE08 prove that clustering similar acoustic classes together improves the system performance. In particular, the proposed method of equal size clustering achieves 5.1% relative decrease on EER compared to FSH1.

PurposeThe purpose of this paper is to propose a distributed deep learning architecture for smart cities in big data systems.Design/methodology/approachWe have proposed an architectural multilayer to describe the distributed deep learning for smart cities in big data systems. The components of our system are Smart city layer, big data layer, and deep learning layer. The Smart city layer responsible for the question of Smart city components, its Internet of things, sensors and effectors, and its integration in the system, big data layer concerns data characteristics 10, and its distribution over the system. The deep learning layer is the model of our system. It is responsible for data analysis.FindingsWe apply our proposed architecture in a Smart environment and Smart energy. 10; In a Smart environment, we study the Toluene forecasting in Madrid Smart city. For Smart energy, we study wind energy foresting in Australia. Our proposed architecture can reduce the time of execution and improve the deep learning model, such as Long Term Short Memory10;.Research limitations/implicationsThis research needs the application of other deep learning models, such as convolution neuronal network and autoencoder.Practical implicationsFindings of the research will be helpful in Smart city architecture. It can provide a clear view into a Smart city, data storage, and data analysis. The 10; Toluene forecasting in a Smart environment can help the decision-maker to ensure environmental safety. The Smart energy of our proposed model can give a clear prediction of power generation.Originality/valueThe findings of this study are expected to contribute valuable information to decision-makers for a better understanding of the key to Smart city architecture. Its relation with data storage, processing, and data analysis.

PurposeThe Covid-19 pandemic has profoundly affected urban communities, generating the need for an immediate response from local governance. The availability of urban data platforms in some smart cities helped the relevant actors to develop various solutions in an innovative and highly contextual way. The purpose of this paper is to explore the role of data platforms in smart cities in the context of the Covid-19 crisis.Design/methodology/approachA total of 85 studies were identified using the Clarivate Analytics Web of Science electronic library. After applying exclusion and inclusion criteria, 61 publications were considered appropriate and reasonable for the research, being read in-depth. Finally, only 52 studies presented relevant information for the topic and were synthesized following the defined research questions. During the research, the authors included in the paper other interesting references found in selected articles and important information regarding the role of data in the fight against Covid-19 in smart cities available on the Internet and social media, with the intention to capture both academic and practical perspectives.FindingsThe authors' main conclusion suggests that based on their previous expertise in collecting, processing and analyzing data from multiple sources, some smart cities quickly adapted their data platforms for an efficient response against Covid-19. The results highlight the importance of open data, data sharing, innovative thinking, the collaboration between public and private stakeholders, and the participation of citizens, especially in these difficult times.Practical implicationsThe city managers and data operators can use the presented case studies and findings to identify relevant data-driven smart solutions in the fight against Covid-19 or another crisis.Social implicationsThe performance of smart cities is a social concern since the population of urban communities is continuously growing. By reviewing the adoption of information technologies-based solutions to improve the quality of citizens' life, the paper emphasizes their potential in societies in which information technology is embedded, especially during a major crisis.Originality/valueThis research re-emphasizes the importance of collecting data in smart cities, the role of the diversity of their sources and the necessity of citizens, companies and government synergetic involvement, especially in a pandemic context. The existence of smart solutions to process and extract information and knowledge from large data sets was essential for many actors involved in smart cities, helping them in the decision-making process. Based on previous expertise, some smart cities quickly adapted their data platforms for an efficient response against Covid-19. The paper analyzes also these success cases that can be considered models to be adopted by other municipalities in similar circumstances.

New sensors and devices are being incorporated in modern buildings and cities to facilitate the understanding of its dynamics and improve its efficiency. With this in mind, the combination of information technology and sensors capable of capturing and sharing energy data with other devices can help solve power consumption problems. However, large volumes of these data are collected and stored uninterrupted, becoming a challenge to analyze it to confirm trends, identify hidden patterns, and outliers to aid in decision-making. As an alternative to address the issue, this paper presents an interactive visual analytics system to understand energy data coming from a smart building or city. This system provides ways to analyze the data at different levels of time granularities for the identification of energy trends, patterns, and data outliers. Moreover, it combines different algorithms that allow fulfilling predictive analysis. An analysis with domain experts demonstrates the feasibility and advantages of using the system to monitor energy data.