Customized multi-period stochastic assignment problem for social engagement and opportunistic IoT

Fadda, Edoardo; Perboli, Guido; Tadei, Roberto

doi:10.1016/j.cor.2018.01.010

Cited by 29 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will have two objectives. First, we want to consider the problem in a stochastic optimization settings, as for example in [ 11 ]. Second, we want to test the approach on other case studies, by also exploiting knowledge management methodologies (e.g., [ 6 ]).…”

Section: Discussionmentioning

confidence: 99%

A Novel Big Data Analytics Approach for Supporting Cyber Attack Detection via Non-linear Analytic Prediction of IP Addresses

Cuzzocrea

Mumolo

Fadda

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Computer network systems are often subject to several types of attacks. For example the distributed Denial of Service (DDoS) attack introduces an excessive traffic load to a web server to make it unusable. A popular method for detecting attacks is to use the sequence of source IP addresses to detect possible anomalies. With the aim of predicting the next IP address, the Probability Density Function of the IP address sequence is estimated. Prediction of source IP address in the future access to the server is meant to detect anomalous requests. In other words, during an access to the server, only predicted IP addresses are permitted and all others are blocked. The approaches used to estimate the Probability Density Function of IP addresses range from the sequence of IP addresses seen previously and stored in a database to address clustering, normally used by combining the K-Means algorithm. Instead, in this paper we consider the sequence of IP addresses as a numerical sequence and develop the nonlinear analysis of the numerical sequence. We used nonlinear analysis based on Volterra’s Kerners and Hammerstein’s models. The experiments carried out with datasets of source IP address sequences show that the prediction errors obtained with Hammerstein models are smaller than those obtained both with the Volterra Kernels and with the sequence clustering by means of the K-Means algorithm.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Big Data Analytics Approach for Supporting Cyber Attack Detection via Non-linear Analytic Prediction of IP Addresses

Cuzzocrea

Mumolo

Fadda

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kortoci et al [27] leverage the fog networking paradigm and devise a protocol that offloads data sampled by storage-constrained sensors to mobile gateways. Fadda et al [28] consider task assignment with the goal to minimize costs while covering all sensors in a certain area. However, none of these solutions explicitly considers incentives for user participation in data collection, as addressed in this work.…”

Section: Related Workmentioning

confidence: 99%

Incentivizing Opportunistic Data Collection for Time-Sensitive IoT Applications

Kortoçi

Mehrabi

Joe‐Wong

et al. 2021

2021 18th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)

View full text Add to dashboard Cite

Urban environments are the most prevalent application scenario for the Internet of Things (IoT). In this context, effective data collection and forwarding to a cloud (or edge) server are particularly important. This work leverages opportunistic data collection based on the mobile crowd sourcing (MCS) paradigm for time-sensitive IoT applications. Specifically, it introduces an incentive mechanism for the crowd to collect data that are valuable to data consumers in terms of regions of interest and time constraints. The proposed approach successfully incorporates the willingness of the crowd to participate in the data collection as part of the related incentives. It also ensures collection of valuable data via selective user incentivization. Accordingly, a weighted social welfare maximization problem is defined for users to decide which sensors to visit subject to deadline constraints. Following the NP-hardness of the problem, an online heuristic algorithm is proposed for sensors to dynamically incentivize mobile users with a low message and time complexity. The proposed solution is shown to be effective for time-sensitive quality data collection through extensive simulations on realistic mobility traces. It significantly increases the overall social welfare as well as the amount of collected data compared to other approaches.

show abstract

“…The most famous are Modalyzer, 2 Chronology 3 and the Android Activity Recognition. 4 Modalyzer can detect if the user is traveling by bus or by car, but it needs the maximum possible GPS sampling frequency. Chronology is a feature included in Google Maps.…”

Section: Literature Reviewmentioning

confidence: 99%

“…that enable the user to travel from its origin to its destination without sensible time variations. Sustainability is a key target for the smart cities ( [4], [13]- [15])…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smartphone Data Classification Technique for Detecting the Usage of Public or Private Transportation Modes

et al. 2020

Self Cite

View full text Add to dashboard Cite

One of the main endeavors of smart cities is the organization and subsidization of public transportation. To achieve this, it is important to obtain information about the way in which people move. This once-difficult problem can now be addressed by using smartphones. This paper introduces a machine learning-based framework that is able to ascertain the usage of a public or a private transportation mode by analyzing a little amount of data sampled by a user's smartphone. The presented method exhibits a good accuracy and a limited battery consumption. A public anonymized dataset based on real measurements is also provided along with this study. To the best of our knowledge, this is the first dataset of this kind that is offered to the public. INDEX TERMS Mobility, transportation mode detection, smart city.

show abstract

Customized multi-period stochastic assignment problem for social engagement and opportunistic IoT

Cited by 29 publications

References 12 publications

A Novel Big Data Analytics Approach for Supporting Cyber Attack Detection via Non-linear Analytic Prediction of IP Addresses

A Novel Big Data Analytics Approach for Supporting Cyber Attack Detection via Non-linear Analytic Prediction of IP Addresses

Incentivizing Opportunistic Data Collection for Time-Sensitive IoT Applications

Smartphone Data Classification Technique for Detecting the Usage of Public or Private Transportation Modes

Contact Info

Product

Resources

About