Cognitive Networks Research Articles

Optimizing Cognitive Radio Networks with Deep Learning-Based Semantic Spectrum Sensing

Optimizing Cognitive Radio Networks with Deep Learning-Based Semantic Spectrum Sensing

Understanding the complex network of objectively assessed cognition and self-reported psychological symptoms in people with multiple sclerosis.

Literature on the intricate relationship between self-reported and objectively assessed cognitive functioning suggests a discrepancy between self-reported cognitive complaints (SCC) and actual test performance. To investigate the interplay between patient-reported outcome measures (PROMs) and objective cognitive functioning using network analysis in people with multiple sclerosis (PwMS). We collected PROMs on anxiety, depression, fatigue and SCC, and cognitive functioning across six domains (n = 703 PwMS; 71% female, mean age = 46.3 ± 11.2 years). We constructed cognitive symptom networks using Gaussian Graphical Models, in which the aforementioned variables were presented as nodes linked by regularized partial correlations. We compared global network strength between relevant subgroups. The networks primarily showed clustering of PROMs and cognitive domains into two separate modules, with weaker links connecting both modules. Global network strength was lower for PwMS with impaired information processing speed (IPS; indicating lower symptom interrelatedness) compared to those with preserved IPS (3.57 versus 4.51, p = 0.001), but not when comparing SCC subgroups (p = 0.140). Cognitive symptom networks deepen our understanding of the discrepancy between self-reported and objectively assessed cognitive functioning. Lower symptom interrelatedness in PwMS with impaired IPS might suggest a nonlinear relation between PROMs and cognitive domains, which depends on the cognitive status.

Cognitive and cortical network alterations in pediatric temporal lobe space-occupying lesions: an fMRI study

BackgroundTemporal lobe mass lesions are the most common intracranial space-occupying lesions in children, among various brain lobes. The temporal lobe is critically involved in higher cognitive functions, and surgical interventions often risk causing damage to these functions. If necessary interventions and prehabilitation can be conducted preoperatively, it might be possible to achieve a larger extent of lesion resection with minimal cognitive impairment. However, research in this area has been relatively limited in the past. Our study aims to fill this gap.MethodsWe enrolled 15 children with temporal lobe mass lesions and 15 age- and gender-matched healthy children as controls. All participants underwent cognitive assessments and functional MRI scans. The cognitive testing data and functional MRI data were then analyzed and compared between the two groups.ResultsOur findings suggest that children with temporal lobe mass lesions primarily exhibit impairments in working memory and sustained attention. Multiple brain network indices were altered in the affected children, with the most prominent change being hyperactivation of the default mode network (DMN). This hyperactivation was correlated with cognitive impairments, indicating that the overactivation of the DMN might represent an inefficient compensatory mechanism within the brain’s networks.ConclusionCompared to healthy children, those with temporal lobe mass lesions experience deficits in working memory and sustained attention, and the hyperactivation of the DMN may be the underlying network mechanism driving these cognitive impairments. Our research offers a unique and clinically valuable reference for future studies on preoperative interventions and prehabilitation in this population.

Channel-Hopping Using Reinforcement Learning for Rendezvous in Asymmetric Cognitive Radio Networks

This paper addresses the rendezvous problem in asymmetric cognitive radio networks (CRNs) by proposing a novel reinforcement learning (RL)-based channel-hopping algorithm. Traditional methods like the jump-stay (JS) algorithm, while effective, often struggle with high time-to-rendezvous (TTR) in asymmetric scenarios where secondary users (SUs) have varying channel availability. Our proposed RL-based algorithm leverages the actor-critic policy gradient method to learn optimal channel selection strategies by dynamically adapting to the environment and minimizing TTR. Extensive simulations demonstrate that the RL-based algorithm significantly reduces the expected TTR (ETTR) compared to the JS algorithm, particularly in asymmetric scenarios where M-sequence-based approaches are less effective. This suggests that RL-based approaches not only offer robustness in asymmetric environments but also provide a promising alternative in more predictable settings.

EHWPTCRN-energy harvesting using wireless power transfer for cognitive radio networks with 802.11 (DCF) MAC protocol

EHWPTCRN-energy harvesting using wireless power transfer for cognitive radio networks with 802.11 (DCF) MAC protocol

Dynamic spectrum resource allocations in wireless senor networks for improving packet transmission

Spectrum allocation has gained a lot of attention in cognitive wireless networks and research as one of the key problems for enhancing spectrum quality in the communication processes in the contemporary communication-dependent wireless environment. By effectively managing the restricted spectrum resources, adjusting to dynamic network conditions, lowering interference, and increasing energy efficiency, the study on dynamic spectrum allocation in wireless sensor networks seeks to improve packet transmission. In a variety of applications, this improves network performance, dependability, and quality of service. This is the reason we apply the dynamic source allocation to the sensor nodes in the network visualization for the packet transmission performance study in the 5G spectrum region. The primary goal of the study conducted for this article is to improve packet delivery ratios and data packet throughputs from the source to the destinations. Compared to previous research, this work has achieved 100% of its aims. In this context, certain DRL concerns are also addressed. The spectrum is allotted such that, in the event of phishing or malicious nodal assaults on the cluster groups of the wireless sensor nodal points in the WSN, efficient packet transmission will occur, beginning at the source and terminating at the sink. The simulation results demonstrate the efficacy of the approach described in the research paper and its application to data transmission.

Multiple PUE Attack Detection in Cooperative Mobile Cognitive Radio Networks

The Mobile Cognitive Radio Network (MCRN) are an alternative to spectrum scarcity. However, like any network, it comes with security issues to analyze. One of the attacks to analyze is the Primary User Emulation (PUE) attack, which leads the system to give the attacker the service as a legitimate user and use the Primary Users’ (PUs) spectrum resources. This problem has been addressed from perspectives like arrival time, position detection, cooperative scenarios, and artificial intelligence techniques (AI). Nevertheless, it has been studied with one PUE attack at once. This paper implements a countermeasure that can be applied when several attacks simultaneously exist in a cooperative network. A deep neural network (DNN) is used with other techniques to determine the PUE’s existence and communicate it with other devices in the cooperative MCRN. An algorithm to detect and share detection information is applied, and the results show that the system can detect multiple PUE attacks with coordination between the secondary users (SUs). Scenarios are implemented on software-defined radio (SDR) with a cognitive protocol to protect the PU. The probability of detection (PD) is measured for some signal-to-noise ratio (SNR) values in the presence of one PUE or more in the network, which shows high detection values above 90% for an SNR of -7dB. A database is also created with the attackers’ data and shared with all the SUs.

Short-term changes in brain networks and cognition in children with frontal lobe lesions treated solely with neurosurgical procedures

Intracranial lesions in children often have good prognoses, allowing long-term survival. Cognitive functions, crucial for life quality, need more attention. Previous research has focused on adults, with pediatric studies limited by varied lesions and complex treatments. This study aims to evaluate cognitive and brain network changes in children with frontal lobe lesions, which significantly impact cognitive function, using a before-and-after comparison. The study enrolled 20 children with frontal lesions who underwent fMRI and cognitive tests before and after surgery, with only surgical treatment initially. Brain network changes were evaluated using functional metrics, and cognitive shifts were measured through test scores. Correlations were analyzed to explore brain mechanisms behind cognitive changes. Additionally, 20 healthy children underwent the same assessments for baseline data. Preliminary evidence of cognitive recovery, notably in social cognition, was observed about three months post-surgery, potentially linked to increased functional connectivity between the right lingual gyrus and right middle temporal gyrus. Children with frontal lobe lesions have demonstrated short-term postoperative cognitive improvement and associated reorganization and repair of brain networks, though this capacity for repair may diminish over time. This underscores the importance of timely rehabilitation interventions. This study offers unique insights into cognitive neuroscience and potential rehabilitation targets.

Family Support Group to Reduce Loneliness in Caregiver of Mental Health Disorders Patients

Introduction: Caring for patients with mental health disorders causes loneliness in caregivers. Therefore, interventions are needed to reduce the level of loneliness in caregivers of patients with mental health disorders. This literature review study aims to determine the effectiveness of family support groups in reducing loneliness in caregivers of patients with mental health disorders. Methods: This study used the ScienceDirect and Google Scholar databases and were searched using the following keywords family support group AND reduce AND loneliness AND caregiver And Mental Health Disorder in filtered journals published in 2013-2023. Results: Caregivers of mental health patients experience the main psychosocial problem, namely loneliness in the process of caring for patients with mental health disorders. Loneliness in caregivers of patients with mental health disorders is caused by stigma which causes feelings of isolation, disconnection, and lack of social relationships, increased stress, and emotional tension. Family support groups can reduce the level of loneliness in caregivers of patients with mental health disorders. Conclusion: Family group support intervention creates effective coping so that the cognitive control network in processing socio-affective information becomes a reflection. This stimulates the reduction of thoughts and perceptions which have an impact on reducing feelings of loneliness. Keywords: Caregiver, Family Support Group, Loneliness, Mental Health Disorder, Reduce

Spectrum and Power Efficient Anti-jamming Approach for Cognitive Radio Networks Based on Reinforcement Learning

Background: Spectrum scarcity, spectrum efficiency, power constraints, and jamming attacks are core challenges that face wireless networks. While cognitive radio networks (CRNs) enable the sharing of licensed bands when they are unoccupied, the spectrum should be used efficiently by the secondary user (SU) to ensure a high data rate transmission. In addition, the mobility of the SUs makes power consumption a matter of concern in wireless networks. Because of the open environment, the jamming attack can easily deteriorate the performance and disrupt the connections. Objectives: We aim to enhance the performance of CRN and establish more reliable connections for the SU in the presence of smart jammer by ensuring efficient spectrum utilization and extending the network lifetime. Methods: To achieve our objectives, we propose an anti-jamming approach that adopts frequency hopping. Our approach assumes that SUs observe spectrum availability and channel gain. Then, SU learns the jammer behaviour and goes for the appropriate policy in terms of the number of data and control channels that optimize jointly spectrum efficiency and power consumption. Within, the interaction between the SU and the jammer is modelled as a zero-sum stochastic game, and we employ reinforcement learning (RL) to address this game. Results: SUs learn the optimal policy that maximizes the spectrum efficiency and minimizes the power consumption in the presence of a smart jammer. Simulation results show that the low channel gain leads the SU to select a high number of data channels. However, when the channel gain is high, the SU increases the number of control channels to guarantee a more reliable connection. Taking into account the spectrum efficiency, SUs save their energy by decreasing the number of used channels. The proposed strategy achieves better performance in comparison with myopic learning and the random strategy. Conclusion: Under a jamming attack, considering the gain of utilized channels, SUs select the appropriate number of control and data channels to ensure a reliable, efficient, and long-term connection.

Multi-agent deep reinforcement learning based multiple access for underwater cognitive acoustic sensor networks

Considering the challenges posed by the significant propagation delays inherent in underwater cognitive acoustic sensor networks, this paper explores the application of multi-agent deep reinforcement learning for the design of multiple access protocols. We deal with the problem of sharing channels and time slots among multiple sensor nodes that adopt different time-slotted MAC protocols. The multiple intelligent nodes can independently learn the strategies for accessing available idle time slots through the proposed multi-agent deep reinforcement learning (DRL) based multiple access control (MDRL-MAC) protocol. Considering the long propagation delay associated with underwater acoustic channels, we reformulate proper state, action, and reward within the DRL framework to address the multiple access challenges and optimize network throughput. To mitigate the decision deviation stemming from partial observability, the gated recurrent unit (GRU) is integrated into DRL to enhance the deep neural network’s performance. Additionally, to ensure both the maximization of network throughput and the maintenance of fairness among multiple agents, an inspiration mechanism (IM) is proposed to inspire the lazy agent to take more actions to improve its contribution to achieve multi-agent fairness. The simulation results show that the proposed protocol facilitates the convergence of network throughput to optimal levels across various system configurations and environmental conditions.

Sustainable pavement maintenance and rehabilitation planning using the quantum cognitive trust network

Selecting appropriate pavement maintenance strategies can enhance resource efficiency, reduce environmental pollution, prolong road lifespan, and improve societal sustainability. Currently, most models, which selecting pavement maintenance options, exhibit high subjectivity and low reliability. This study employs an innovative probabilistic linguistic multi-attribute decision-making model basing on the quantum cognitive theory. Therefore, the model focuses on expert decision-making groups for pavement maintenance strategies. It considers the trust networks within the decision-making process, as well as the sequential and interference effects arising from experts' belief biases and behavioral interactions. By doing so, it facilitates a more scientific selection of optimal strategies among multiple maintenance options. The proposed method has been validated through practical case studies of road segments, and its scientific validity and effectiveness have been further corroborated through sensitivity analysis.

Secrecy Capacity of SWIPT-Based Cognitive Satellite-Terrestrial Network With Artificial Noise and Noncolluding ERs

Secrecy Capacity of SWIPT-Based Cognitive Satellite-Terrestrial Network With Artificial Noise and Noncolluding ERs

Covert Communications Aided by Cooperative Jamming in Overlay Cognitive Radio Networks

Covert Communications Aided by Cooperative Jamming in Overlay Cognitive Radio Networks

Optimization of Cooperative Spectrum Sensing in Multihop Heterogeneous Cognitive Radio Networks

Optimization of Cooperative Spectrum Sensing in Multihop Heterogeneous Cognitive Radio Networks

Reliable and cost-efficient session provisioning in CRNs using spectrum sensing as a service

With the advancement of wireless communication technologies, and the growing number of wireless and IoT applications that demand various types and volumes of data, Sensing as a Service (SaaS) has emerged as a necessary enabling business model for many of those applications. Spectrum Sensing as a Service (SSaaS) has also emerged as a form of SaaS that is concerned with the monitoring of wireless spectrum to facilitate its safe reuse by cognitive radio-enabled wireless users. SSaaS was primarily motivated by the need for a low-cost, accurate, and reliable spectrum sensing service to support a plethora of heterogeneous wireless devices and applications. Under the SSaaS model, clients need to pay the service provider for the sensing service they receive. In this paper, we address the problem of allocating spectrum channels to links of a given communication session in a cognitive radio network (CRN) that utilizes SSaaS. The objective is to allocate channels such that the worst link availability among the session is maximized and the spectrum access cost is minimized. A number of multi-objective evolutionary optimization algorithms (MOEAs) were used to solve this multi-objective optimization problem. Extensive experimentation was conducted to compare between these algorithms and identify the best ones to use. We also propose a post-processing greedy algorithm to further enhance the solution obtained by a MOEA algorithm. Results show that an improvement of up to 20% can be achieved using the proposed greedy algorithm under some network settings.

A fuzzy cognitive map approach to selecting the best knowledge management strategy

Purpose Selecting an appropriate strategy can significantly influence an organization’s direction, but numerous interrelated factors make this decision complex and uncertain. Identifying these relationships and making informed decisions often involves navigating uncertainty. This paper aims to assist managers in leveraging the organization’s intellectual assets to select the most suitable knowledge management strategy. Design/methodology/approach This research proposes fuzzy cognitive maps to model and select the appropriate strategy. Given that knowledge is a company’s most valuable asset and its management is critical, the proposed method for selecting a knowledge management strategy was tested in one of Iran’s largest logistics companies. The factors influencing strategy adoption were treated as concepts in the fuzzy cognitive network, with evaluation criteria applied to three strategies: human-oriented, system-oriented and dynamic. Findings The model’s output identifies the most suitable strategy based on knowledge management principles and the specific characteristics of the target project within the organization. Compared to the most cited paper in this field, the proposed model shows a 0.15% improvement in sensitivity and a 0.22% improvement in separation degree. Originality/value This study proposes a novel method using fuzzy cognitive maps to assist organizations in selecting the best knowledge management strategy, even amidst multiple influencing factors and uncertain conditions.

Spectrum Monitoring in Cognitive Radio Networks for Reduced Data Loss, Resource Wastage, and Interference

ABSTRACTCognitive radio is a technology that allows the unlicensed users to access the licensed spectrum based on sensing information perceived by the users. Cognitive radio user generally attempts to access the unutilized band of licensed user. However, the emergence/reappearance of primary users during ongoing cognitive user's transmission creates the interference at the primary receiver and data loss at cognitive receiver. In this context, the spectrum monitoring is a vital process of the cognitive radio network during data transmission to continuously monitor the primary user's presence or absence on a licensed channel. In this manuscript, we have utilized the spectrum monitoring technique on earlier existing MAC protocol for CR network to detect the emergence/reappearance of primary users throughout the data transmission period of cognitive users. The spectrum monitoring is employed to reduce the interference at primary receiver, which is measured in terms of interference power (IP) and data loss at CU receiver. The closed form expressions of data loss and IP for the monitoring and without monitoring scenarios are provided. In addition, the probability of monitoring error's (which causes misinterpretation of channel's status by the cognitive users) impact on these performance parameters is also provided and simulated. Further, earlier MAC protocol has significant amount of bandwidth wastage in case primary user disappears or reappears during cognitive user's data transmission, which is shown mathematically and simulated as well. However, incorporation of the monitoring phenomenon even with significant amount of monitoring error has reduced bandwidth wastage, which is measured in bps. In addition, the throughput calculation of the proposed system and the effect of monitoring error on the throughput of the proposed system are also seen. As per the results, the maximum data loss and IP occurred at licensed channel's busy probability value of 0.5, which is 23.22 bps and 3.487 W, respectively, at maximum monitoring error value. However, minimum data loss and IP are achieved at licensed busy channel's probability values of zero and one. In addition, the resource wastage at licensed channel's busy probability value of 0.5 is varying from 2.322 to 23.22 bps for varying the monitoring error value from 0.1 to 1, respectively, giving highest resource wastage at maximum monitoring error value.

The human social cognitive network contains multiple regions within the amygdala.

Reasoning about someone's thoughts and intentions-i.e., forming a "theory of mind"-is a core aspect of social cognition and relies on association areas of the brain that have expanded disproportionately in the human lineage. We recently showed that these association zones comprise parallel distributed networks that, despite occupying adjacent and interdigitated regions, serve dissociable functions. One network is selectively recruited by social cognitive processes. What circuit properties differentiate these parallel networks? Here, we show that social cognitive association areas are intrinsically and selectively connected to anterior regions of the medial temporal lobe that are implicated in emotional learning and social behaviors, including the amygdala at or near the basolateral complex and medial nucleus. The results suggest that social cognitive functions emerge through coordinated activity between internal circuits of the amygdala and a broader distributed association network, and indicate the medial nucleus may play an important role in social cognition in humans.

Data Compression Using Optimized Compressive Sensing in Cognitive Radio Network

ABSTRACTIn cognitive radio networks, cooperative spectrum sensing can greatly improve detection performance and reduce test time because cognitive users work cooperatively to detect spectrum signals. However, it is important to reduce the number of measurements taken from the original signal. To overcome these challenges, this study proposes optimized compressive sensing (CS) to reduce processing time and speed up spectrum sensing. To optimize the performance of CS, the penguin optimization algorithm (POA) is used in this approach. The optimal CS matrix is selected using this algorithm. In this algorithm, mean square error (MSE) is considered an objective function. It selects the CS matrix with the minimum error as the optimal matrix. Step size optimized sparsity adaptive matching pursuit algorithm (SSOSAMP) is used to reconstruct the compressed signal using the optimized sensitivity matrix. MATLAB is used to implement this proposed approach. Simulation results show that the proposed system achieves an SNR of 27.43%, a reconstruction probability of 94.28%, and an MSE of 4.27%.