International Journal of Computer and Applications

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Network Simulator NS2

Congestion control in wireless sensor networks by hybrid multi-objective optimization algorithm

Ensuring a seamless connection during the mobility of various User Equipments (UEs) will be one of the major challenges facing the practical implementation of the Fifth Generation (5G) networks and beyond. Several key determinants will significantly contribute to numerous mobility challenges. One of the most important determinants is the use of millimeter waves (mm-waves) as it is characterized by high path loss. The inclusion of various types of small coverage Base Stations (BSs), such as Picocell, Femtocell and drone-based BSs is another challenge. Other issues include the use of Dual Connectivity (DC), Carrier Aggregation (CA), the massive growth of mobiles connections, network diversity, the emergence of connected drones (as BS or UE), ultra-dense network, inefficient optimization processes, central optimization operations, partial optimization, complex relation in optimization operations, and the use of inefficient handover decision algorithms. The relationship between these processes and diverse wireless technologies can cause growing concerns in relation to handover associated with mobility. The risk becomes critical with high mobility speed scenarios. Therefore, mobility issues and their determinants must be efficiently addressed. This paper aims to provide an overview of mobility management in 5G networks. The work examines key factors that will significantly contribute to the increase of mobility issues. Furthermore, the innovative, advanced, efficient, and smart handover techniques that have been introduced in 5G networks are discussed. The study also highlights the main challenges facing UEs’ mobility as well as future research directions on mobility management in 5G networks and beyond.

/pdf/key-challenges-drivers-and-solutions-for-mobility-management-37q1948lki.pdf

Key Challenges, Drivers and Solutions for Mobility Management in 5G Networks: A Survey

Several sensor nodes in the wireless network collect the data rigorously which aids in many of the applications. The network with high and the consistent data load is the only requirement of the wireless sensor networks. Due to the limited sources of the network and the high data loads, networks may be affected by congestion. Congestion is a highly objectionable issue which leads to information loss and the deprived performance of the wireless sensor networks. In this paper, an adaptive cuckoo search based optimal rate adjustment (ACSRO) for the congestion avoidance and control is proposed. The rate adjustment regulates the share rate of the node to mitigate the congestion. The performance of the proposed rate optimization approach is evaluated using the evaluation metrics such as throughput, delay, normalized packet loss, normalized queue size, and congestion level. The results of the proposed rate optimization show that the congestion is compacted and the performance of the WSN is improved.

ACSRO: Adaptive cuckoo search based rate adjustment for optimized congestion avoidance and control in wireless sensor networks


 Routing in mobile ad hoc networks (MANETs) is a hectic challenge due to the dynamic nature of the network. The provisional communication links are assured due to the infrastructure-independent capability of MANET, but with no proper centralized monitoring process, which makes routing in MANETs with respect to the security and trust a major issue. Thus, the paper introduces Advanced Encryption Standard-enabled Trust-based Secure Routing protocol based on the proposed Dolphin Cat Optimizer (AES-TDCO), which is an energy and trust-aware routing protocol. The proposed Dolphin Cat Optimizer is engaged in the optimal route selection based on the modeled objective function based on the trust factors, recent trust, historical trust, direct and indirect trust in addition to delay, distance and link lifetime. The Dolphin Cat Optimizer is the integration of Dolphin Echolocation and Cat Swarm Optimization algorithm that inherits the faster global convergence. The simulation using 75 nodes revealed that the proposed routing protocol acquired the maximal throughput, minimal delay, minimal packet drop and detection rate of 0.6531, 0.0107, 0.3267 and 0.9898 in the absence of network attacks and 0.7693, 0.0112, 0.3605 and 0.9961 in the presence of the network attacks.

Trust-Based Secure Routing in Mobile Ad Hoc Network Using Hybrid Optimization Algorithm

E‐TDGO: An encrypted trust‐based dolphin glowworm optimization for secure routing in mobile ad hoc network

Ocular artifact always contaminates the original EEG signal. EEG bandwidth is generally up to 64 Hz. Ocular artifacts are introduced due to of eye blinks and eyeball rolling in the EEG signal. The band of original EEG and ocular artifacts are in the same region and are overlapped. The Present method uses wavelet ICA technique for artifact suppression. Haar family of wavelets is used. Static segmentation of EEG signal is carried out. This technique removes the ocular artifacts significantly by preserving the neural activity of interest. Performance parameters like PSNR, standard deviation and power spectral density are considered for analysis. Results show that ocular artifacts are greatly suppressed.

Removal of ocular artifacts from multichannel EEG signal using wavelet enhanced ICA

In current trends, the central target of interest for multimedia applications is to meet the stringent quality of service (QoS) requirements for traffic flow over contention based MAC protocol of IEEE 802.11 WLAN. To achieve this objective, our paper proposes a connection admission control (CAC) policy, which attempts to maintain the flow of incoming traffic in the wireless network so as to effectively coordinate the medium in the midst of the challenging traffic sources so that wireless network operates in an optimum way, thereby sustaining the QoS requirements with better channel utilization. In this proposal, majority of the available bandwidth is allocated to real time sources (RT) (voice) and the remaining small portion is reserved for non real time (NRT) data traffic to meet the statistical QoS requirements, such as low delay and high throughput, for both the traffics (RT and NRT) over WLAN.

Uttam D. Kolekar

Papers

ACSRO: Adaptive cuckoo search based rate adjustment for optimized congestion avoidance and control in wireless sensor networks

Trust-Based Secure Routing in Mobile Ad Hoc Network Using Hybrid Optimization Algorithm

E‐TDGO: An encrypted trust‐based dolphin glowworm optimization for secure routing in mobile ad hoc network

Removal of ocular artifacts from multichannel EEG signal using wavelet enhanced ICA

Performance Analysis of Real and Non Real Time Traffic over WLAN Using Connection Admission Control Policy