Next Issue
Previous Issue

Table of Contents

Future Internet, Volume 9, Issue 4 (December 2017)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Cover Story (view full-size image) The screenshots are of a Virtual Aquarium and a toothbrush-embedded wireless sensor device that can [...] Read more.
View options order results:
result details:
Displaying articles 1-42
Export citation of selected articles as:
Open AccessArticle SCMC: An Efficient Scheme for Minimizing Energy in WSNs Using a Set Cover Approach
Future Internet 2017, 9(4), 95; https://doi.org/10.3390/fi9040095
Received: 1 November 2017 / Revised: 7 December 2017 / Accepted: 8 December 2017 / Published: 13 December 2017
PDF Full-text (2822 KB) | HTML Full-text | XML Full-text
Abstract
Energy-efficient clustering and routing are well known optimization problems in the study of Wireless Sensor Network (WSN) lifetime extension. In this paper, we propose an intelligent hybrid optimization algorithm based on a Set Cover approach to create clusters, and min-cost max-flow for routing
[...] Read more.
Energy-efficient clustering and routing are well known optimization problems in the study of Wireless Sensor Network (WSN) lifetime extension. In this paper, we propose an intelligent hybrid optimization algorithm based on a Set Cover approach to create clusters, and min-cost max-flow for routing (SCMC) to increase the lifetime of WSNs. In our method we used linear programming (LP) to model the WSN optimization problem. This model considers minimizing the energy for all nodes in each set cover (cluster), and then minimizing the routing energy between the nodes and the base station through intermediate nodes, namely cluster heads. To evaluate the performance of our scheme, extensive simulations were conducted with different scenarios. The results show that the set cover approach combined with the min-cost max-flow algorithm reduces energy consumption and increases the network’s lifetime and throughput. Full article
Figures

Figure 1

Open AccessFeature PaperArticle Approximate Networking for Universal Internet Access
Future Internet 2017, 9(4), 94; https://doi.org/10.3390/fi9040094
Received: 19 October 2017 / Revised: 27 November 2017 / Accepted: 4 December 2017 / Published: 11 December 2017
PDF Full-text (2403 KB) | HTML Full-text | XML Full-text
Abstract
Despite the best efforts of networking researchers and practitioners, an ideal Internet experience is inaccessible to an overwhelming majority of people the world over, mainly due to the lack of cost-efficient ways of provisioning high-performance, global Internet. In this paper, we argue that
[...] Read more.
Despite the best efforts of networking researchers and practitioners, an ideal Internet experience is inaccessible to an overwhelming majority of people the world over, mainly due to the lack of cost-efficient ways of provisioning high-performance, global Internet. In this paper, we argue that instead of an exclusive focus on a utopian goal of universally accessible “ideal networking” (in which we have a high throughput and quality of service as well as low latency and congestion), we should consider providing “approximate networking” through the adoption of context-appropriate trade-offs. In this regard, we propose to leverage the advances in the emerging trend of “approximate computing” that rely on relaxing the bounds of precise/exact computing to provide new opportunities for improving the area, power, and performance efficiency of systems by orders of magnitude by embracing output errors in resilient applications. Furthermore, we propose to extend the dimensions of approximate computing towards various knobs available at network layers. Approximate networking can be used to provision “Global Access to the Internet for All” (GAIA) in a pragmatically tiered fashion, in which different users around the world are provided a different context-appropriate (but still contextually functional) Internet experience. Full article
(This article belongs to the Special Issue Communications and Computing for Sustainable Development Goals)
Figures

Figure 1

Open AccessFeature PaperArticle How 5G Wireless (and Concomitant Technologies) Will Revolutionize Healthcare?
Future Internet 2017, 9(4), 93; https://doi.org/10.3390/fi9040093
Received: 5 October 2017 / Revised: 1 December 2017 / Accepted: 4 December 2017 / Published: 11 December 2017
PDF Full-text (1975 KB) | HTML Full-text | XML Full-text
Abstract
The need to have equitable access to quality healthcare is enshrined in the United Nations (UN) Sustainable Development Goals (SDGs), which defines the developmental agenda of the UN for the next 15 years. In particular, the third SDG focuses on the need to
[...] Read more.
The need to have equitable access to quality healthcare is enshrined in the United Nations (UN) Sustainable Development Goals (SDGs), which defines the developmental agenda of the UN for the next 15 years. In particular, the third SDG focuses on the need to “ensure healthy lives and promote well-being for all at all ages”. In this paper, we build the case that 5G wireless technology, along with concomitant emerging technologies (such as IoT, big data, artificial intelligence and machine learning), will transform global healthcare systems in the near future. Our optimism around 5G-enabled healthcare stems from a confluence of significant technical pushes that are already at play: apart from the availability of high-throughput low-latency wireless connectivity, other significant factors include the democratization of computing through cloud computing; the democratization of Artificial Intelligence (AI) and cognitive computing (e.g., IBM Watson); and the commoditization of data through crowdsourcing and digital exhaust. These technologies together can finally crack a dysfunctional healthcare system that has largely been impervious to technological innovations. We highlight the persistent deficiencies of the current healthcare system and then demonstrate how the 5G-enabled healthcare revolution can fix these deficiencies. We also highlight open technical research challenges, and potential pitfalls, that may hinder the development of such a 5G-enabled health revolution. Full article
(This article belongs to the Special Issue Communications and Computing for Sustainable Development Goals)
Figures

Figure 1

Open AccessArticle Social-Aware Relay Selection for Cooperative Multicast Device-to-Device Communications
Future Internet 2017, 9(4), 92; https://doi.org/10.3390/fi9040092
Received: 29 September 2017 / Revised: 27 November 2017 / Accepted: 28 November 2017 / Published: 4 December 2017
Cited by 1 | PDF Full-text (676 KB) | HTML Full-text | XML Full-text
Abstract
The increasing use of social networks such as Facebook, Twitter, and Instagram to share photos, video streaming, and music among friends has generated a huge increase in the amount of data traffic over wireless networks. This social behavior has triggered new communication paradigms
[...] Read more.
The increasing use of social networks such as Facebook, Twitter, and Instagram to share photos, video streaming, and music among friends has generated a huge increase in the amount of data traffic over wireless networks. This social behavior has triggered new communication paradigms such as device-to-device (D2D) and relaying communication schemes, which are both considered as strong drivers for the next fifth-generation (5G) cellular systems. Recently, the social-aware layer and its relationship to and influence on the physical communications layer have gained great attention as emerging focus points. We focus here on the case of relaying communications to pursue the multicast data dissemination to a group of users forming a social community through a relay node, according to the extension of the D2D mode to the case of device-to-many devices. Moreover, in our case, the source selects the device to act as the relay among different users of the multicast group by taking into account both the propagation link conditions and the relay social-trust level with the constraint of minimizing the end-to-end content delivery delay. An optimization procedure is also proposed in order to achieve the best performance. Finally, numerical results are provided to highlight the advantages of considering the impact of social level on the end-to-end delivery delay in the integrated social–physical network in comparison with the classical relay-assisted multicast communications for which the relay social-trust level is not considered. Full article
Figures

Figure 1

Open AccessArticle High-Performance Elastic Management for Cloud Containers Based on Predictive Message Scheduling
Future Internet 2017, 9(4), 87; https://doi.org/10.3390/fi9040087
Received: 2 October 2017 / Revised: 31 October 2017 / Accepted: 7 November 2017 / Published: 28 November 2017
PDF Full-text (3721 KB) | HTML Full-text | XML Full-text
Abstract
Containerized data centers can improve the computational density of IaaS layers. This intensive high-concurrency environment has high requirements for message scheduling and container processing. In the paper, an elastically scalable strategy for cloud containers based on predictive message scheduling is introduced, in order
[...] Read more.
Containerized data centers can improve the computational density of IaaS layers. This intensive high-concurrency environment has high requirements for message scheduling and container processing. In the paper, an elastically scalable strategy for cloud containers based on predictive message scheduling is introduced, in order to reduce the delay of messages and improve the response time of services and the utilization of container resources. According to the busy degree of different containers, a management strategy of multiple containers at message-granularity level is developed, which gives the containers better elasticity. The simulation results show that the proposed strategy improves service processing efficiency and reduces response latency compared with existing solutions. Full article
Figures

Figure 1

Open AccessArticle High Throughput and Acceptance Ratio Multipath Routing Algorithm in Cognitive Wireless Mesh Network
Future Internet 2017, 9(4), 91; https://doi.org/10.3390/fi9040091
Received: 9 October 2017 / Revised: 12 November 2017 / Accepted: 21 November 2017 / Published: 25 November 2017
PDF Full-text (1116 KB) | HTML Full-text | XML Full-text
Abstract
The link failure due to the secondary users exiting the licensed channels when primary users reoccupy the licensed channels is very important in cognitive wireless mesh networks (CWMNs). A multipath routing and spectrum allocation algorithm based on channel interference and reusability with Quality
[...] Read more.
The link failure due to the secondary users exiting the licensed channels when primary users reoccupy the licensed channels is very important in cognitive wireless mesh networks (CWMNs). A multipath routing and spectrum allocation algorithm based on channel interference and reusability with Quality of Service (QoS) constraints in CWMNs (MRIR) was proposed. Maximizing the throughput and the acceptance ratio of the wireless service is the objective of the MRIR. First, a primary path of resource conservation with QoS constraints was constructed, then, a resource conservation backup path based on channel interference and reusability with QoS constraints was constructed. The MRIR algorithm contains the primary path routing and spectrum allocation algorithm, and the backup path routing and spectrum allocation algorithm. The simulation results showed that the MRIR algorithm could achieve the expected goals and could achieve a higher throughput and acceptance ratio. Full article
Figures

Graphical abstract

Open AccessConference Report A Fast and Reliable Broadcast Service for LTE-Advanced Exploiting Multihop Device-to-Device Transmissions
Future Internet 2017, 9(4), 89; https://doi.org/10.3390/fi9040089
Received: 13 October 2017 / Revised: 14 November 2017 / Accepted: 21 November 2017 / Published: 25 November 2017
Cited by 3 | PDF Full-text (12982 KB) | HTML Full-text | XML Full-text
Abstract
Several applications, from the Internet of Things for smart cities to those for vehicular networks, need fast and reliable proximity-based broadcast communications, i.e., the ability to reach all peers in a geographical neighborhood around the originator of a message, as well as ubiquitous
[...] Read more.
Several applications, from the Internet of Things for smart cities to those for vehicular networks, need fast and reliable proximity-based broadcast communications, i.e., the ability to reach all peers in a geographical neighborhood around the originator of a message, as well as ubiquitous connectivity. In this paper, we point out the inherent limitations of the LTE (Long-Term Evolution) cellular network, which make it difficult, if possible at all, to engineer such a service using traditional infrastructure-based communications. We argue, instead, that network-controlled device-to-device (D2D) communications, relayed in a multihop fashion, can efficiently support this service. To substantiate the above claim, we design a proximity-based broadcast service which exploits multihop D2D. We discuss the relevant issues both at the UE (User Equipment), which has to run applications, and within the network (i.e., at the eNodeBs), where suitable resource allocation schemes have to be enforced. We evaluate the performance of a multihop D2D broadcasting using system-level simulations, and demonstrate that it is fast, reliable and economical from a resource consumption standpoint. Full article
Figures

Figure 1

Open AccessFeature PaperArticle An Ontology-Based Approach to Enable Knowledge Representation and Reasoning in Worker–Cobot Agile Manufacturing
Future Internet 2017, 9(4), 90; https://doi.org/10.3390/fi9040090
Received: 20 September 2017 / Revised: 15 November 2017 / Accepted: 20 November 2017 / Published: 24 November 2017
PDF Full-text (8315 KB) | HTML Full-text | XML Full-text
Abstract
There is no doubt that the rapid development in robotics technology has dramatically changed the interaction model between the Industrial Robot (IR) and the worker. As the current robotic technology has afforded very reliable means to guarantee the physical safety of the worker
[...] Read more.
There is no doubt that the rapid development in robotics technology has dramatically changed the interaction model between the Industrial Robot (IR) and the worker. As the current robotic technology has afforded very reliable means to guarantee the physical safety of the worker during a close proximity interaction with the IR. Therefore, new forms of cooperation between the robot and the worker can now be achieved. Collaborative/Cooperative robotics is the new branch of industrial robotics which empowers the idea of cooperative manufacturing. Cooperative manufacturing significantly depends on the existence of a collaborative/cooperative robot (cobot). A cobot is usually a Light-Weight Robot (LWR) which is capable of operating safely with the human co-worker in a shared work environment. This is in contrast with the conventional IR which can only operate in isolation from the worker workspace, due to the fact that the conventional IR can manipulate very heavy objects, which makes it so dangerous to operate in direct contact with the worker. There is a slight difference between the definition of collaboration and cooperation in robotics. In cooperative robotics, both the worker and the robot are performing tasks over the same product in the same shared workspace but not simultaneously. Collaborative robotics has a similar definition, except that the worker and the robot are performing a simultaneous task. Gathering the worker and the cobot in the same manufacturing workcell can provide an easy and cheap method to flexibly customize the production. Moreover, to adapt with the production demands in the real time of production, without the need to stop or to modify the production operations. There are many challenges and problems that can be addressed in the cooperative manufacturing field. However, one of the most important challenges in this field is the representation of the cooperative manufacturing environment and components. Thus, in order to accomplish the cooperative manufacturing concept, a proper approach is required to describe the shared environment between the worker and the cobot. The cooperative manufacturing shared environment includes the cobot, the co-worker, and other production components such as the product itself. Furthermore, the whole cooperative manufacturing system components need to communicate and share their knowledge, to reason and process the shared information, which eventually gives the control solution the capability of obtaining collective manufacturing decisions. Putting into consideration that the control solution should also provide a natural language which is human readable and in the same time can be understood by the machine (i.e., the cobot). Accordingly, a distributed control solution which combines an ontology-based Multi-Agent System (MAS) and a Business Rule Management System (BRMS) is proposed, in order to solve the mentioned challenges in the cooperative manufacturing, which are: manufacturing knowledge representation, sharing, and reasoning. Full article
Figures

Figure 1

Open AccessArticle Behavioural Verification: Preventing Report Fraud in Decentralized Advert Distribution Systems
Future Internet 2017, 9(4), 88; https://doi.org/10.3390/fi9040088
Received: 18 September 2017 / Revised: 31 October 2017 / Accepted: 16 November 2017 / Published: 20 November 2017
Cited by 1 | PDF Full-text (2354 KB) | HTML Full-text | XML Full-text
Abstract
Service commissions, which are claimed by Ad-Networks and Publishers, are susceptible to forgery as non-human operators are able to artificially create fictitious traffic on digital platforms for the purpose of committing financial fraud. This places a significant strain on Advertisers who have no
[...] Read more.
Service commissions, which are claimed by Ad-Networks and Publishers, are susceptible to forgery as non-human operators are able to artificially create fictitious traffic on digital platforms for the purpose of committing financial fraud. This places a significant strain on Advertisers who have no effective means of differentiating fabricated Ad-Reports from those which correspond to real consumer activity. To address this problem, we contribute an advert reporting system which utilizes opportunistic networking and a blockchain-inspired construction in order to identify authentic Ad-Reports by determining whether they were composed by honest or dishonest users. What constitutes a user’s honesty for our system is the manner in which they access adverts on their mobile device. Dishonest users submit multiple reports over a short period of time while honest users behave as consumers who view adverts at a balanced pace while engaging in typical social activities such as purchasing goods online, moving through space and interacting with other users. We argue that it is hard for dishonest users to fake honest behaviour and we exploit the behavioural patterns of users in order to classify Ad-Reports as real or fabricated. By determining the honesty of the user who submitted a particular report, our system offers a more secure reward-claiming model which protects against fraud while still preserving the user’s anonymity. Full article
Figures

Figure 1

Open AccessFeature PaperArticle Study of Mobility Enhancements for RPL in Convergecast Scenarios
Future Internet 2017, 9(4), 86; https://doi.org/10.3390/fi9040086
Received: 3 October 2017 / Revised: 10 November 2017 / Accepted: 14 November 2017 / Published: 17 November 2017
PDF Full-text (494 KB) | HTML Full-text | XML Full-text
Abstract
In recent years, mobility support has become an important requirement in various wireless sensor network (WSN) applications. However, due to the strict resource constraints of power, memory, and processing resources in WSNs, routing protocols are mainly designed without considering mobility. Low-Power and Lossy
[...] Read more.
In recent years, mobility support has become an important requirement in various wireless sensor network (WSN) applications. However, due to the strict resource constraints of power, memory, and processing resources in WSNs, routing protocols are mainly designed without considering mobility. Low-Power and Lossy Networks (LLNs) are a special type of WSNs that tolerate data loss. The Routing Protocol for Low-Power and Lossy Networks (RPL) is a routing protocol for LLNs that adapts IPv6 (Internet Protocol version 6) and runs on top of the IEEE (Institute of Electrical and Electronics Engineers) 802.15.4 standard. RPL supports multipoint-to-point traffic and point-to-multipoint traffic. In this paper we propose a mobility enhancement mechanism in order to improve data collection applications in highly mobile scenarios. The enhancement is based on signal strength monitoring and depth updating in order to improve the routing protocol performance in mobile scenarios. This enhancement helps routing protocols to cope better with topology changes and makes proactive decisions on updating next-hop neighbours. We integrated this mechanism into the RPL and compared it with other existing RPL mobility support enhancements. Results obtained through simulation using Cooja show that our work outperforms other existing RPL mobility supports on different performance metrics. Results also prove the efficiency of our proposal in highly mobile scenarios. Full article
Figures

Graphical abstract

Open AccessFeature PaperArticle Blockchain-Empowered Fair Computational Resource Sharing System in the D2D Network
Future Internet 2017, 9(4), 85; https://doi.org/10.3390/fi9040085
Received: 8 October 2017 / Revised: 12 November 2017 / Accepted: 14 November 2017 / Published: 17 November 2017
Cited by 2 | PDF Full-text (699 KB) | HTML Full-text | XML Full-text
Abstract
Device-to-device (D2D) communication is becoming an increasingly important technology in future networks with the climbing demand for local services. For instance, resource sharing in the D2D network features ubiquitous availability, flexibility, low latency and low cost. However, these features also bring along challenges
[...] Read more.
Device-to-device (D2D) communication is becoming an increasingly important technology in future networks with the climbing demand for local services. For instance, resource sharing in the D2D network features ubiquitous availability, flexibility, low latency and low cost. However, these features also bring along challenges when building a satisfactory resource sharing system in the D2D network. Specifically, user mobility is one of the top concerns for designing a cooperative D2D computational resource sharing system since mutual communication may not be stably available due to user mobility. A previous endeavour has demonstrated and proven how connectivity can be incorporated into cooperative task scheduling among users in the D2D network to effectively lower average task execution time. There are doubts about whether this type of task scheduling scheme, though effective, presents fairness among users. In other words, it can be unfair for users who contribute many computational resources while receiving little when in need. In this paper, we propose a novel blockchain-based credit system that can be incorporated into the connectivity-aware task scheduling scheme to enforce fairness among users in the D2D network. Users’ computational task cooperation will be recorded on the public blockchain ledger in the system as transactions, and each user’s credit balance can be easily accessible from the ledger. A supernode at the base station is responsible for scheduling cooperative computational tasks based on user mobility and user credit balance. We investigated the performance of the credit system, and simulation results showed that with a minor sacrifice of average task execution time, the level of fairness can obtain a major enhancement. Full article
Figures

Figure 1

Open AccessArticle Energy-Efficient Resource and Power Allocation for Underlay Multicast Device-to-Device Transmission
Future Internet 2017, 9(4), 84; https://doi.org/10.3390/fi9040084
Received: 20 October 2017 / Revised: 6 November 2017 / Accepted: 8 November 2017 / Published: 14 November 2017
Cited by 1 | PDF Full-text (1466 KB) | HTML Full-text | XML Full-text
Abstract
In this paper, we present an energy-efficient resource allocation and power control scheme for D2D (Device-to-Device) multicasting transmission. The objective is to maximize the overall energy-efficiency of D2D multicast clusters through effective resource allocation and power control schemes, while considering the quality of
[...] Read more.
In this paper, we present an energy-efficient resource allocation and power control scheme for D2D (Device-to-Device) multicasting transmission. The objective is to maximize the overall energy-efficiency of D2D multicast clusters through effective resource allocation and power control schemes, while considering the quality of service (QoS) requirements of both cellular users (CUs) and D2D clusters. We first build the optimization model and a heuristic resource and power allocation algorithm is then proposed to solve the energy-efficiency problem with less computational complexity. Numerical results indicate that the proposed algorithm outperforms existing schemes in terms of throughput per energy consumption. Full article
Figures

Figure 1

Open AccessArticle Request Expectation Index Based Cache Replacement Algorithm for Streaming Content Delivery over ICN
Future Internet 2017, 9(4), 83; https://doi.org/10.3390/fi9040083
Received: 2 October 2017 / Revised: 4 November 2017 / Accepted: 8 November 2017 / Published: 14 November 2017
PDF Full-text (1277 KB) | HTML Full-text | XML Full-text
Abstract
Since the content delivery unit over Information-Centric Networking (ICN) has shifted from files to the segments of a file named chunks, solely either file-level or chunk-level request probability is insufficient for ICN cache management. In this paper, a Request Expectation Index (RXI) based
[...] Read more.
Since the content delivery unit over Information-Centric Networking (ICN) has shifted from files to the segments of a file named chunks, solely either file-level or chunk-level request probability is insufficient for ICN cache management. In this paper, a Request Expectation Index (RXI) based cache replacement algorithm for streaming content delivery is proposed. In this algorithm, RXI is introduced to serve as a fine-grained and unified estimation criteria of possible future request probability for cached chunks. RXI is customized for streaming content delivery by adopting both file-level and chunk-level request probability and considering the dynamically varied request status at each route as well. Compared to prior work, the proposed algorithm evicts the chunk with the minimum expectation of future request to maintain a high cache utilization. Additionally, simulation results demonstrate that the RXI-based algorithm can remarkably enhance the streaming content delivery performance and can be deployed in complex network scenarios. The proposed results validate that, by taking fine-grained request probability and request status into consideration, the customized in-network caching algorithm can improve the ICN streaming content delivery performance by high cache utilization, fast content delivery, and lower network traffic. Full article
Figures

Figure 1

Open AccessArticle A Combinational Buffer Management Scheme in Mobile Opportunistic Network
Future Internet 2017, 9(4), 82; https://doi.org/10.3390/fi9040082
Received: 19 September 2017 / Revised: 7 November 2017 / Accepted: 8 November 2017 / Published: 14 November 2017
PDF Full-text (913 KB) | HTML Full-text | XML Full-text
Abstract
Nodes in Mobile Opportunistic Network (MON) have to cache packets to deal with the intermittent connection. The buffer management strategy obviously impacts the performance of MON, and it attracts more attention recently. Due to the limited storage capacity of nodes, traditional buffer management
[...] Read more.
Nodes in Mobile Opportunistic Network (MON) have to cache packets to deal with the intermittent connection. The buffer management strategy obviously impacts the performance of MON, and it attracts more attention recently. Due to the limited storage capacity of nodes, traditional buffer management strategies just drop messages based on the property of message, and they neglect the collaboration between neighbors, resulting in an ineffective performance improvement. Therefore, effective buffer management strategies are necessary to ensure that each node has enough buffer space to store the message when the node buffer is close to congestion. In this paper, we propose a buffer management strategy by integrating the characteristics of messages and nodes, and migrate the redundant messages to the neighbor to optimize the total utility, instead of deleting them. The simulation experiment results show that it can obviously improve the delivery ratio, the overhead ratio and the average delays, and reduce the amount of hops compared with the traditional ones. Full article
Figures

Graphical abstract

Open AccessArticle Network Intrusion Detection through Discriminative Feature Selection by Using Sparse Logistic Regression
Future Internet 2017, 9(4), 81; https://doi.org/10.3390/fi9040081
Received: 18 October 2017 / Revised: 1 November 2017 / Accepted: 6 November 2017 / Published: 10 November 2017
PDF Full-text (2873 KB) | HTML Full-text | XML Full-text
Abstract
Intrusion detection system (IDS) is a well-known and effective component of network security that provides transactions upon the network systems with security and safety. Most of earlier research has addressed difficulties such as overfitting, feature redundancy, high-dimensional features and a limited number of
[...] Read more.
Intrusion detection system (IDS) is a well-known and effective component of network security that provides transactions upon the network systems with security and safety. Most of earlier research has addressed difficulties such as overfitting, feature redundancy, high-dimensional features and a limited number of training samples but feature selection. We approach the problem of feature selection via sparse logistic regression (SPLR). In this paper, we propose a discriminative feature selection and intrusion classification based on SPLR for IDS. The SPLR is a recently developed technique for data analysis and processing via sparse regularized optimization that selects a small subset from the original feature variables to model the data for the purpose of classification. A linear SPLR model aims to select the discriminative features from the repository of datasets and learns the coefficients of the linear classifier. Compared with the feature selection approaches, like filter (ranking) and wrapper methods that separate the feature selection and classification problems, SPLR can combine feature selection and classification into a unified framework. The experiments in this correspondence demonstrate that the proposed method has better performance than most of the well-known techniques used for intrusion detection. Full article
(This article belongs to the collection Information Systems Security)
Figures

Figure 1

Back to Top