Offloading the computational complexity of transfer learning with generic features.

Deep learning approaches are generally complex, requiring extensive computational resources and having high time complexity. Transfer learning is a state-of-the-art approach to reducing the requirements of high computational resources by using pre-trained models without compromising accuracy and performance. In conventional studies, pre-trained models are trained on datasets from different but similar domains with many domain-specific features. The computational requirements of transfer learning are directly dependent on the number of features that include the domain-specific and the generic features. This article investigates the prospects of reducing the computational requirements of the transfer learning models by discarding domain-specific features from a pre-trained model. The approach is applied to breast cancer detection using the dataset curated breast imaging subset of the digital database for screening mammography and various performance metrics such as precision, accuracy, recall, F1-score, and computational requirements. It is seen that discarding the domain-specific features to a specific limit provides significant performance improvements as well as minimizes the computational requirements in terms of training time (reduced by approx. 12%), processor utilization (reduced approx. 25%), and memory usage (reduced approx. 22%). The proposed transfer learning strategy increases accuracy (approx. 7%) and offloads computational complexity expeditiously.

Swarm intelligence-based packet scheduling for future intelligent networks.

Network operations involve several decision-making tasks. Some of these tasks are related to operators, such as extending the footprint or upgrading the network capacity. Other decision tasks are related to network functions, such as traffic classifications, scheduling, capacity, coverage trade-offs, and policy enforcement. These decisions are often decentralized, and each network node makes its own decisions based on the preconfigured rules or policies. To ensure effectiveness, it is essential that planning and functional decisions are in harmony. However, human intervention-based decisions are subject to high costs, delays, and mistakes. On the other hand, machine learning has been used in different fields of life to automate decision processes intelligently. Similarly, future intelligent networks are also expected to see an intense use of machine learning and artificial intelligence techniques for functional and operational automation. This article investigates the current state-of-the-art methods for packet scheduling and related decision processes. Furthermore, it proposes a machine learning-based approach for packet scheduling for agile and cost-effective networks to address various issues and challenges. The analysis of the experimental results shows that the proposed deep learning-based approach can successfully address the challenges without compromising the network performance. For example, it has been seen that with mean absolute error from 6.38 to 8.41 using the proposed deep learning model, the packet scheduling can maintain 99.95% throughput, 99.97% delay, and 99.94% jitter, which are much better as compared to the statically configured traffic profiles.

Improving scheduling performance in congested networks.

With continuously rising trends in applications of information and communication technologies in diverse sectors of life, the networks are challenged to meet the stringent performance requirements. Increasing the bandwidth is one of the most common solutions to ensure that suitable resources are available to meet performance objectives such as sustained high data rates, minimal delays, and restricted delay variations. Guaranteed throughput, minimal latency, and the lowest probability of loss of the packets can ensure the quality of services over the networks. However, the traffic volumes that networks need to handle are not fixed and it changes with time, origin, and other factors. The traffic distributions generally follow some peak intervals and most of the time traffic remains on moderate levels. The network capacity determined by peak interval demands often requires higher capacities in comparison to the capacities required during the moderate intervals. Such an approach increases the cost of the network infrastructure and results in underutilized networks in moderate intervals. Suitable methods that can increase the network utilization in peak and moderate intervals can help the operators to contain the cost of network intrastate. This article proposes a novel technique to improve the network utilization and quality of services over networks by exploiting the packet scheduling-based erlang distribution of different serving areas. The experimental results show that significant improvement can be achieved in congested networks during the peak intervals with the proposed approach both in terms of utilization and quality of service in comparison to the traditional approaches of packet scheduling in the networks. Extensive experiments have been conducted to study the effects of the erlang-based packet scheduling in terms of packet-loss, end-to-end latency, delay variance and network utilization.