Nenad Kojić

Adaptive Content-Based Image Retrieval with Relevance Feedback

Retrieval of images, based on similarities between feature vectors of querying image and those from database, is considered. The searching procedure was performed through the two basic steps: an objective one, based on the Euclidean distances and a subjective one based on the users relevance feedback. Images recognized from user as the best matched to a query are labeled and used for updating the query feature vector through a RBF (radial basis function) neural network. The searching process is repeated from such subjectively refined feature vectors. In practice, several iterative steps are sufficient, as confirmed by intensive simulations

Neural network for finding optimal path in packet-switched network

Neural networks are very good candidates for solving different ill-defined problems, due to their high computational speed and the possibility of working with uncertain data. Among others, they represent an efficient tool for solving constrained optimization problems. Under appropriate assumptions, routing in packet-switched networks may be considered as an optimization problem, more precisely, as a shortest-path problem, where the Hopfield type neural network exhibits very good performance. An efficient neural network shortest-path algorithm, inspired by the Hopfield network, is suggested. The routing algorithm suggested is designed to find the shortest path but also it takes into account packet-loss avoidance. The applicability of the proposed model is demonstrated through computer simulations for different full-connected networks with both symmetrical and non-symmetrical links.

A Neural Networks-Based Hybrid Routing Protocol for Wireless Mesh Networks

The networking infrastructure of wireless mesh networks (WMNs) is decentralized and relatively simple, but they can display reliable functioning performance while having good redundancy. WMNs provide Internet access for fixed and mobile wireless devices. Both in urban and rural areas they provide users with high-bandwidth networks over a specific coverage area. The main problems affecting these networks are changes in network topology and link quality. In order to provide regular functioning, the routing protocol has the main influence in WMN implementations. In this paper we suggest a new routing protocol for WMN, based on good results of a proactive and reactive routing protocol, and for that reason it can be classified as a hybrid routing protocol. The proposed solution should avoid flooding and creating the new routing metric. We suggest the use of artificial logic—i.e., neural networks (NNs). This protocol is based on mobile agent technologies controlled by a Hopfield neural network. In addition to this, our new routing metric is based on multicriteria optimization in order to minimize delay and blocking probability (rejected packets or their retransmission). The routing protocol observes real network parameters and real network environments. As a result of artificial logic intelligence, the proposed routing protocol should maximize usage of network resources and optimize network performance.

Neural network for optimization of routing in communication networks

The efficient neural network algorithm for optimization of routing in communication networks is suggested. As it was known from literature different optimization and ill-defined problems may be resolved using appropriately designed neural networks, due to their high computational speed and the possibility of working with uncertain data. Under some assumptions the routing in packet-switched communication networks may be considered as optimization problem, more precisely, as a shortest-path problem. The Hopfield-type neural network is a very efficient tool for solving such problems. The suggested routing algorithm is designed to find the optimal path, meaning, the shortest path (if possible), but taking into account the traffic conditions: the incoming traffic flow, routers occupancy, and link capacities, avoiding the packet loss due to the input buffer overflow. The applicability of the proposed model is demonstrated through computer simulations in different traffic conditions and for different full-connected networks with both symmetrical and non-symmetrical links.

Optimal Routing in Packet Switching Network by using Neural Network

The routing in packet switching network is considered as a shortest-path (SP) problem. The new routing algorithm, initially inspired by the Hopfield neural network, is designed to find the optimal link between source and destination node taking into account not only the shortest path but also several in-node constraints, including link bandwidth, incoming flow and flow statistics, addressed to avoiding the packet loss. The applicability of the proposed algorithm is demonstrated through computer simulations for different network architectures and traffic conditions

Minor Component Analysis (MCA) Applied to Image Classification in CBIR Systems

A content-based image retrieval system with query image classification prior to retrieving procedure is proposed. Query image is compared to representative patterns of image classes, not to all images from database, accelerating thus initial retrieving step. Such procedure is possible when images from database are grouped into classes with similar content. Classification is performed using minor component (MC) analysis. Since it is expectable that MCs mainly depend on image details, not on an image background, this approach seems to be more efficient than classic CBIR. Minor components may be calculated by using single-layer neural network. The efficiency of proposed system is tested over images from Corel dataset

Packet routing in wireless mesh networks

Wireless mesh networks (WMN) represent a type of mobile ad-hoc networks. These networks are very important in providing the Internet access to fixed and mobile terminal equipment. The main problem in WMNs (regarding to mesh routers and mesh clients) is a routing protocol, especially because it has to enable the access to network for both mesh and conventional clients. Access to Internet for wireless mesh networks is done via special mesh routers, the gateways. Several gateways may exist in a network. The main role of a routing protocol is to find way to establish connection between an end user and one of the gateways, as fast as possible, considering links status. This path should be optimized from the traffic distribution and path distance point. This paper presents one type of packet routing in wireless mesh networks based on Hopfield neural network. Artificial intelligence is used for path optimization. Distribution of local routing information and routing table updates is realized by mobile agents. In this way, network should have a simple way of routing information delivery and thus for effective user traffic support.

Routing in Optical Networks by Using Neural Network

Routing in optical, especially wavelength division multiplexing networks, is very hard task. This paper defines a new routing algorithm, based on Hopfield neural network. It is improvement of previous research, now applied to optical communications

The influence of the feature vector content on the CBIR system efficiency

The influence of the feature vector (FV) content on the CBIR (content-based image retrieval) system efficiency was considered. By using two different FVs and applying three different learning methods, it was shown that the efficiency of retrieving depends on both the FV content and the learning method, independently.

The use of unlabeled data in image retrieval with relevance feedback

This paper describes a content-based image retrieval (CBIR) system which makes use of both labeled images, annotated by the user, and unlabeled images available in the database. The system initially retrieves images objectively closest to the query image. The user then subjectively labels retrieved images as relevant or irrelevant. Although such relevance feedback from the user is an effective way of bridging the semantic gap between objective and subjective similarity, it is also very time consuming, requiring huge human effort. Often, the number of labeled images is very small. In an inductive approach the labeled set of images is used for training a CBIR system while the large set of unlabeled images remains unused. In this paper we exploit the transductive support vector machine (SVM) algorithm as a way of taking advantage of unlabeled data in CBIR. Our findings are compared to the results of an inductive SVM. We draw some conclusions as to when the use of unlabeled data might be helpful. The considered systems are tested over images from the Corel 1K dataset.