Kashif Naseer Qureshi

A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care

Recently, Artificial Intelligence (AI) has been used widely in medicine and health care sector. In machine learning, the classification or prediction is a major field of AI. Today, the study of existing predictive models based on machine learning methods is extremely active. Doctors need accurate predictions for the outcomes of their patients’ diseases. In addition, for accurate predictions, timing is another significant factor that influences treatment decisions. In this paper, existing predictive models in medicine and health care have critically reviewed. Furthermore, the most famous machine learning methods have explained, and the confusion between a statistical approach and machine learning has clarified. A review of related literature reveals that the predictions of existing predictive models differ even when the same dataset is used. Therefore, existing predictive models are essential, and current methods must be improved.

An energy efficient cyclic sleep control framework for ITU PONs

Abstract Cyclic Sleep Mode (CSM) is a widely studied and standard energy conservation technique for Passive Optical Networks (PONs). The energy savings provided by CSM increase with longer Asleep and shorter SleepAware state periods. However, this also leads to increased communication delays. Moreover, too short SleepAware time may degrade dynamic bandwidth assignment (DBA) performance and even may cause delay of urgent PLOAM messages from OLT. Neither CSM standards nor existing studies provide any detailed framework to configure CSM performance and control parameters in accordance to the target delays. Another limitation of existing studies is their assumption of a single traffic class during sleep mode analysis. They do not consider the impact of CSM on Type-1 (T1) to Type-4 (T4) traffic classes defined by International Telecommunication Union (ITU). Most of these studies also neglect the role of DBA by considering a fixed bandwidth assignment. However, upstream delays critically depend on the DBA performance and its impact should not be ignored during CSM studies. Therefore, this study presents an Efficient Cyclic Sleep (ECS) framework to configure all CSM parameters and timers with optimum values in the presence of all traffic classes and DBA scheme. The proposed scheme maximizes the energy savings even at very high traffic loads while satisfying the target average delay limit of 56xa0ms for both US and DS links. A sleep buffer approach is used to configure the Local Wake Up Indication (LWI) events and all CSM control timers at the OLT and ONU. The proposed scheme is compared with two other reported schemes. Simulation results show up to 84.1% energy savings at very low traffic loads and 43% savings at 80% network traffic load (equal to traffic arrival rate of 550Mbps per ONU). The delay variance results for both US and DS also remain under 1xa0ms.

Accurate and dynamic predictive model for better prediction in medicine and healthcare

IntroductionInformation and communication technologies (ICTs) have changed the trend into new integrated operations and methods in all fields of life. The health sector has also adopted new technologies to improve the systems and provide better services to customers. Predictive models in health care are also influenced from new technologies to predict the different disease outcomes. However, still, existing predictive models have suffered from some limitations in terms of predictive outcomes performance.Aims and objectivesIn order to improve predictive model performance, this paper proposed a predictive model by classifying the disease predictions into different categories. To achieve this model performance, this paper uses traumatic brain injury (TBI) datasets. TBI is one of the serious diseases worldwide and needs more attention due to its seriousness and serious impacts on human life.ConclusionThe proposed predictive model improves the predictive performance of TBI. The TBI data set is developed and approved by neurologists to set its features. The experiment results show that the proposed model has achieved significant results including accuracy, sensitivity, and specificity.

Cluster-based data dissemination, cluster head formation under sparse, and dense traffic conditions for vehicular ad hoc networks

Information and communication technologies have changed the way of operations in all fields. These technologies also have adopted for wireless communication and provide low cost and convenient solutions. Vehicular ad hoc networks are envisioned with their special and unique intercommunication systems to provide safety in intelligent transportation systems and support large-size networks. Due to dense and sparse traffic conditions, routing is always a challenging task to establish reliable and effective communication among vehicle nodes in the highly transportable environment. Several types of routing protocols have been proposed to handle high mobility and dynamic topologies including topology-based routing, position and geocast routing, and cluster-based routing protocols. Cluster-based routing is one of the feasible solutions for vehicular networks due to its manageable and more viable nature. In cluster-based protocols, the network is divided into many clusters and each cluster selects a cluster head for data dissemination. In this study, we investigate the current routing challenges and trend of cluster-based routing protocols. In addition, we also proposed a Cluster-based Routing for Sparse and Dense Networks to handle dynamic topologies, the high-mobility of vehicle nodes. Simulation results show a significant performance improvement of the proposed protocol.

Soft-GORA: Soft Constrained Globally Optimal Resource Allocation for Critical Links in IoT Backhaul Communication

The Internet of Things gateways with multi-radio facilities in wireless networks can simultaneously communicate using multiple available channels. This feature enhances the carrying capacity of wireless links and thus increases the overall network throughput. However, designing an efficient resource allocation strategy is a complex task due to the decisive behavior of interference. There is only a limited number of available channels; therefore, the resource allocation requires careful planning to mitigate the effect of interference. This research proposes a backtracking search-based resource allocation scheme that maps resource allocation to the constraint satisfaction problem. Some of the resource allocation constraints are applied as soft constraints which are relaxed to find a feasible solution, provided the perfect allocation of limited resources is not possible. The proposed approach has been benchmarked through simulations and the results prove the effectiveness of the proposed approach especially in dense multi-hop network deployments.

Channel quality and utilization metric for interference estimation in Wireless Mesh Networks

Abstract Wireless Mesh Networks have emerged as an architectural shift from traditional wireless networks for providing ubiquitous coverage. The mesh routers equipped with multiple 802.11 commodity network cards provide high throughput by maximizing the simultaneous transmissions on multiple channels. However, the selection of a channel is affected by various factors and it requires accurate knowledge of channel conditions. In addition, an imprecise selection of the channel requires channel reassignment, which significantly reduces the network performance. The existing schemes have suffered to gratifying the aggregate effect of interference. In this paper, we propose a Channel Quality and Utilization Metric (QUAM) that selects less interfering channels. The QUAM employs MAC specification parameters to acquire utilization awareness of various channels in the vicinity. The channel utilization helps to cater the effect of co-channel interference, whereas, to accommodate the impact of adjacent channel interference; the channels are further quantified by considering the channel quality. The proposed metric is evaluated through extensive simulations experiments. The simulation results demonstrated the validation of QUAM with a significant improvement in terms of network throughput and a decline in network delay and packet losses.