Search

The ubiquity of mobile devices and their advanced features have increased the use of crowdsourcing in many areas, such as the mobility in the smart cities. With the advent of high-quality sensors on smartphones, online communities can easily collect and share information. These information are of great importance for the institutions, which must analyze the facts by facilitating the data collecting on crimes and criminals, for example. This paper proposes an approach to develop a crowdsensing framework allowing a wider collaboration between the citizens and the authorities. In addition, this framework takes advantage of an objectivity analysis to ensure the participants? credibility and the information reliability, as law enforcement is often affected by unreliable and poor quality data. In addition, the proposed framework ensures the protection of users' private data through a de-identification process. Experimental results show that the proposed framework is an interesting tool to improve the quality of crowdsensing information in a government context.

Purpose The pervasiveness of mobile devices has led to the permanent use of their new features by the crowd to perform different tasks. The purpose of this paper is to exploit this massive consumption of new information technologies supported by the concept of crowdsourcing in a governmental context to access citizens as a source of ideas and support. The aim is to find out how crowdsourcing combined with the new technologies can constitute a great force to enhance the performance of the suspect investigation process. Design/methodology/approach This paper provides a structured view of a suspect investigation framework, especially based on the image processing techniques, including the automatic face analysis. This crowdsourcing framework is mainly based on the personal description as an identification technique to facilitate the suspect investigation and the use of MongoDB as a document-oriented database to store the information. Findings The case study demonstrates that the proposed framework provides satisfying results in each step of the identification process. The experimental results show how the combination between the crowdsourcing concept and the mobile devices pervasiveness has fruitfully strengthened the identification process with the use of automatic face analysis techniques. Originality/value A review of the literature has shown that previous work has focused mainly on the presentation of forensic techniques that can be used in the investigation process steps. However, this paper implements a complete framework whose whole strength is based on the crowdsourcing concept as a new paradigm used by institutions to solve many organizational problems.

As social networking has spread, people started sharing their personal opinions and thoughts widely via these online platforms. The resulting vast valuable data represent a rich source for companies to deduct their products’ reputation from both social media and crowds’ judgments. To exploit this wealth of data, a framework was proposed to collect opinions and rating scores respectively from social media and crowdsourcing platform to perform sentiment analysis, provide insights about a product and give consumers’ tendencies. During the analysis process, a consumer category (strict) is excluded from the process of reaching a majority consensus. To overcome this, a fuzzy clustering is used to compute consumers’ credibility. The key novelty of our approach is the new layer of validity check using a crowdsourcing component that ensures that the results obtained from social media are supported by opinions extracted directly from real-life consumers. Finally, experiments are carried out to validate this model (Twitter and Facebook were used as data sources). The obtained results show that this approach is more efficient and accurate than existing solutions thanks to our two-layer validity check design.

Cancer is a major problem worldwide. It is a deadly disease that affects our lives and will continue to affect it. For example, breast cancer, the most common cancer, is the second leading cause of cancer. Its incidence has increased considerably in recent years. Machine learning applications to cancer have also received a great deal of attention in clinical decision support. It is important to detect cancer as early as possible, health professionals need a reliable forecasting methodology to diagnose cancer and distinguish its different stages. The classification is a mining function that assigns elements of a collection to groups or target classes. This paper presents an adaptive online learning (OL) framework for supporting the clinical breast cancer diagnosis. Unlike traditional data mining, which trains a particular model from a defined set of medical data, the framework offers adaptive predictive models that can be updated continuously according to new data sequences and newly discovered features. The framework is based on a two-phase approach to classifying breast cancer using supervised learning. The first phase consists of selecting relevant features to develop predictive models using the association rules. The second is to define the predictive model using decision tree algorithm C5.0 to classify benign and malignant mass tumors contained in breast mammography images whose characteristics are archived in a database. This work can be generalized and applied to the classification of cancers other than breast cancer.

Many factors explain traffic accidents, such as the type of the accident site, its environment, the driver's behavior, and other uncertain complex factors. As a result, the occurrence of road accidents is non-linear, so it is necessary to explore the correlation between data from many aspects to minimize the risk. After data preprocessing following a classification using the datamining tools, relevant information can be deduced about the causes of the high-frequency accidents. Depending on the results obtained, we can verify the accuracy of the extracted information, and this can help predict new situations with similar data in the future. The aim is to choose the most accurate extraction process, by analyzing the characteristics of the data and their relationship with the analysis and the extraction process. In this paper, we propose a decision-making system for the traffic accident data analysis in order to extract information relevant to the prevention of the road risk. This system is based on appropriate datamining techniques for collecting, pre-processing and exploring accident data to categorize road accidents and identify the most problematic sites.

PurposeThe purpose of this paper is to bring together the textual and multimedia opinions, since the use of social data has become the new trend that enables to gather the product reputation traded in social media. Integrating a product reputation process into the companies' strategy will bring several benefits such as helping in decision-making regarding the current and the new generation of the product by understanding the customers’ needs. However, image-centric sentiment analysis has received much less attention than text-based sentiment detection.Design/methodology/approachIn this work, the authors propose a multimedia content-based product reputation framework that helps in detecting opinions from social media. Thus, in this case, the analysis of a certain publication is made by combining their textual and multimedia parts.FindingsTo test the effectiveness of the proposed framework, a case study based on YouTube videos has been established, as it brings together the image, the audio and the video processing at the same time.Originality/valueThe key novelty is the implication of multimedia content in addition of the textual one with the goal of gathering opinions about a certain product. The multimedia analysis brings together facial sentiment detection, printed text analysis, opinion detection from speeches and textual opinion analysis.

The invasion of new technologies in people’s life has allowed a great interactive collaboration between citizens and law enforcement agencies. The appearance of crowdsourcing has become a new source of research and development especially in the suspect investigation domain that needs the combination of human intelligence and the technical tools to lead the investigation towards the greatest results. The objective of this paper is to exploit the pervasiveness of image processing techniques (face detection and recognition) to design a crowdsourcing framework that may be chiefly used by government authorities to identify a suspect. This framework is primarily based on the surveillance video analysis and the sketch generation tools supported by the intelligence of the crowd.

Crowdsourcing consists of tools and methods that harness the potential of the crowd (intelligence and sense of creativity). It is increasingly used in different fields especially in some extreme emergency cases that require broad collaboration of all citizens. This collaboration will be unsuccessful or at least a heavy work without the ubiquity of new information technologies and the emergence of smartphones and mobile devices. They become more and more powerful mainly with the ‘anytime and anywhere’ Internet access. The contribution of this paper is twofold: we introduce a framework that can be widely used by government organizations to stimulate the crowd participation in a missing child case and we also reveal the importance of crowdsourcing in an e-government context to cope with society's changes.

International audience; There is an ongoing interest in examining users' experiences made available through social media. Unfortunately these experiences like reviews on products and/or services are sometimes conflicting and thus, do not help develop a concise opinion on these products and/or services. This paper presents a multi-stage approach that extracts and consolidates reviews after addressing specific issues such as user multi-identity and user limited credibility. A system along with a set of experiments demonstrate the feasibility of the approach.

The increasing number of people using social media to express their personal experiences has led to an emerging interest in supporting social media analysis for marketing, opinion analysis and understanding community cohesion. Social customer relationship management (SCRM) systems have become an interesting research area. Generally analysis needs to be done on large volumes of data (Big Data) in an efficient and timely manner. In this research, we propose a social intelligence framework that can extract and consolidate the reviews expressed via social media to help enterprises to know more about the customers' opinion toward the target products. This goal can be achieved by analyzing the reviewers' knowledge and authority and their opinion, sentiment (SentiGem) toward the target products, after filtering the extracted tweets from Twitter using Twitter4J. Additionally we present an architecture based on Map/Reduce analysis using Hadoop.

Air pollution is considered a major health problem in urban areas. Small sensor technology integrated with smart phones can be widely used to collect air quality information in real time using mobile applications. By applying the concept of crowdsensing, citizens and authorities can be aware of exposure to pollution during their daily activities in urban areas. This paper describes an on-road air quality monitoring and control approach based on the crowdsensing paradigm. In addition to collecting air pollution data, we are exploring the possibility of using this technology to effectively detect critical situations and redistribute all information through a proactive decision support framework. This information can be combined with sensed air quality parameters for displaying, on an interactive map, the detected pollutants' concentrations using sensors attached to smart phones. The proposed framework provides users with real-time traffic and air quality information, traffic recommendations and notifications, and environmental conditions. Moreover, the authorities can use this system to improve urban mobility and traffic regulation. Such behavior and movements related to geographic information can provide a better understanding of the dynamics of a road network. In this work, we propose to combine the benefits of the crowdsensing paradigm with both machine learning and Big Data tools. An artificial neural networks model and the A* algorithm are used for air quality prediction and the least polluted path finding. All data processing tasks are performed over a Hadoop-based framework.