Search

With the rapid development of wireless technology and Mobile communication technology worldwide, Mobile Learning represents a new learning trend in the field of higher education, and has gradually become the development trend and research hotspot of independent learning and lifelong learning. Based on modern wireless network mobile communication terminal technology, this paper proposes a Granott model-driven mobile learning system. Firstly, the Granott model is studied and analyzed, and the ubiquitous computing with physical integration and spontaneous interoperation is used to control the Android mobile terminal, which greatly improves the interactivity of M-Learning. Then JSON is selected to optimize the data transmission format in Ajax, and j Query is used to parse JSON data. Ajax + JSON + j Query can shield the complexity of DOM parsing XML files, greatly shorten the data transmission time and improve the efficiency of Granott model. Finally, the Fast kernel density estimation (Fast KDE) algorithm is introduced to compress the data transmitted by Ajax + JSON + j Query, so as to obtain a reasonable number of training samples. Through experiments and relevant data analysis, the proposed mobile learning system based on modern wireless network mobile communication terminal technology, optimized by JSON and Fast KDE algorithm, driven by Granott model, can efficiently complete the learning task, and improve the ubiquity, interactivity, timeliness of mobile learning. [ABSTRACT FROM AUTHOR]

One of the networking technologies is called a wireless sensor network, and what it does is link sensor nodes by using wireless communication as the channel of connection. A haphazard and random distribution of nodes is carried out throughout the deployment process within the network area. As a result, the distances between the nodes do not remain constant. The nodes have a high sensing capacity, but their range of perception and battery life are also severely limited. The wireless data may be sensed by all of the nodes inside their respective sensing regions. Consequently, there are a variety of new applications that make use of WSN applications, particularly in surveillance monitoring applications such as those used in hospitals, buildings, forests, and airspace monitoring. The transmission of the data to the appropriate server or data centre that is linked with the cloud or the internet is experiencing greater difficulties as a result of the growing amount of monitoring data. This indicates that a significant quantity of data is lost as a result of the fact that wireless transmission is affected by environmental factors such as precipitation, humidity, and wind storms. It is vital to create and execute an innovative routing protocol to deliver greater throughput and raise the overall Quality of Service of the WSN applications in order to solve the difficulties that have been outlined above. This study paper presents a metaheuristic algorithm based optimal routing protocol for WSN application, which boosts the overall quality of service of any surveillance monitoring applications. To achieve this goal, the protocol was designed for wireless sensor networks. It does so in an effective manner, resulting in decreased delay and energy consumption as well as enhanced throughput and PDR. Based on the findings of the experiments, it has been hypothesised that the proposed metaheuristic algorithm-based routing protocol is capable of performing better routing for any type of surveillance monitoring and remote monitoring, as well as successfully transmitting any type of data, including numerical, video, and image data. [ABSTRACT FROM AUTHOR]

A large number of interconnected smart devices or objects interact with the physical environment known as the Internet of Things (IoT). These networks efficiently perform complex tasks with a high level of intelligence without human intervention and require run-time processing and computation. Edge computing is introduced where devices are placed at the edge between the data source and the cloud. These devices can provide more powerful computational and storage capabilities to IoT users. With various benefits, one of the significant requirements is secure and trustworthy data communication. Various trust management schemes are introduced to guarantee the trustworthiness and isolation of the malicious nodes and give preference to the most trustworthy ones. The existing schemes selected trustworthy nodes again and again from the path without considering the load factor which leads them to be more vulnerable for the Denial of Services (DoS) attacks. In this paper, we propose a Link-based Penalized Trust Management scheme to provide trust management and consider load factors for the selection of most trustworthy nodes and provide a preemptive measure to secure the network from DoS attacks based on its link's association. Simulation results indicate the better performance of the proposed scheme as compared with existing schemes. [ABSTRACT FROM AUTHOR]

In 5G, users can easily enjoy services by accessing the edge devices (EDs) deployed around the base stations. Generally, due to the uneven distribution and mobility of users, one ED is required to serve multiple users simultaneously, that results in the ED overload, seriously affecting the quality of experience (QoE) of the users. By responding to users' requests, service migration realizes the cross edge device migrations, that dynamically provides services for mobile users, which effectively improves the resource utilization rate of edge servers and the QoE of users. However, during the service migrations, malicious users may deploy pseudo base stations, gateways and other devices to illegally eavesdrop or tamper with user service data, that causes user information loss or disclosure. To prevent these security issues, a fountain-coding based cooperative jamming strategy is proposed in this paper. Specifically, the fountain coding technology is introduced to construct a three-node transmission model, including an original node, a target node and a malicious node, to realize the secure data transmission process in service migration. Besides, a group of relay nodes are employed to carry out cooperative jamming, that deteriorate the illegal eavesdropping quality of malicious nodes on service data. Then secrecy rate and outage probability are utilized to evaluate the security and reliability of the whole service migration. Finally, the theoretical analysis is shown by simulation results. [ABSTRACT FROM AUTHOR]

In path-constrained multi-hop sensor networks (M-WSNs), maximizing data collection with minimal energy consumption is critical, especially for delay-sensitive applications. Because a mobile element (ME) moving at a constant speed along a constrained-path must receive data from sensor nodes (SNs) within a given time bound. This issue can be addressed by efficiently scheduling the SNs' data transmission. The shortest path data transmission (SPT) or its variations are a simple and energy-efficient technique for scheduling data transmission from SNs. Although this method considerably minimizes total energy spent, it does not enhance data collection efficiency due to uneven data forwarding load. To solve this issue, this paper proposes a novel efficient heuristic method. The proposed method first computes a set of discrete sub-paths on a given path based on the start and end distance points of nearby SNs, the speed of ME, and the given time delay. Then, for each sub-path and SN-communication model, a network flow graph is used to schedule and optimize SN data transmission to ME. Finally, a sub-path is chosen among those which return maximum data with minimum energy consumption. The network flow graphs are created by considering two distinct SN-communication models: (1) energy-unrestricted SN-model and (2) energy-restricted SN-model. Finally, the simulation reports demonstrate the proposed method's efficacy over baseline schemes in terms of data collected, energy usage efficiency, and success-delivery ratio. [ABSTRACT FROM AUTHOR]

Vehicular ad-hoc network (VANET) plays a vital role in emerging Intelligent Transportation System (ITS). VANET's deal with the group of network that are designed in ad-hoc model in which various moving devices and other stationary linking objects that are connected over a wireless manner which interchange effective data to each other. Since, the communication between the VANET and other communication devices take place in open channel, there exist many threats caused by the intruder. Moreover, most of the existing authentication schemes suffer from computational and communicational overhead. In order to provide efficient lightweight authentication with enhanced privacy. In this paper, a novel lightweight authentication protocol named as Lightweight Authentication Protocol with Enhanced Privacy (LAPEP) has been proposed to provide efficient end to end security in VANET. The proposed protocol employs Elliptic Curve Cryptography (ECC) along with Bilinear pairing for efficient generation of keys and provides secured multiparty key exchange. Moreover, the security analysis of the proposed scheme is carried out by Burrows Abadi Needham (BAN) logic. The advantages of the proposed system are reduction of computation overhead and provide resistance to various security attacks during data transmission. Moreover, the proposed system enhances the Quality of Service (QoS) namely latency, overhead, delivery ratio, loss ratio and delay rate. The implementation of the proposed protocol is carried out in NS3 simulator. The simulation result proves that the proposed protocol improves the computational cost by 42.85%, communication cost by 35.82%, message end to end delay by 30.65%, signing time by 25.45% and verification time by 32.45%. [ABSTRACT FROM AUTHOR]

Vocal learning has found its proliferation in recent years due to the advancement in wireless networking. Vocal art encompasses profound cultural values and aesthetic preferences, making wireless platforms, e.g. Wi-Fi and ZigBee, essential for the enhancement of online vocal learning. ZigBee, as a wireless platform, has more recently been used quite frequently for online vocal learning and music. This paper aims to design an efficient wireless-enabled platform by using the lightweight features of ZigBee to support online vocal learning and expressions. The platform enables data transmission, storage, analysis, and playback of vocal learning sounds through the ZigBee network. It is built on a cloud platform, utilizing Docker virtualization technology to deploy a Hadoop distributed cluster, effectively simulating a distributed environment. The platform incorporates a model for recognizing musical sound and noise signals, empowering the online learning control platform to detect various characteristics of vocal music tones. Vocal music learning is enhanced by extracting endpoint fusion spectrum features and employing a tone adjustment and dynamic detection model. The proposed method improves anti-interference capability, online learning control, vocal tone recognition, and emotional expression accuracy. Simulation results demonstrate its effectiveness in vocal music, online learning control, and tone recognition, leading to more precise vocal music pronunciation and intonation registration. [ABSTRACT FROM AUTHOR]

Considering that one of the goals of the future network generations is to provide ubiquitous communication in the most diverse scenarios to achieve high connection coverage, it is foreseen that the use of unmanned aerial vehicles as flying base stations (UAV-BSs) can potentially extend the network and communication range. UAVs as flying base station can bring the potential to assist user devices and vehicles by carrying communication resources that can accommodate clients that were not previously planned by the ground infrastructure design due to flash crowd events, sudden natural disasters, or any other event that let to an overloaded environment. Allocating UAVs as flying base station still poses significant challenges in their deployment and the effectiveness of information transmission through UAVs as flying base station in the context of wireless communication since it is necessary to deal with both wireless communication capability and interference in the presence of terrestrial infrastructures already present. Besides, it is essential to understand how communication resources affect network performance. This paper studies the feasibility of using UAVs as flying base station in the assistance of wireless communication in a scenario where there is a sudden demand for data transmission due to possible congestion of local infrastructure. We show how the number of communication resources provided by the UAV-BS, the interference caused by the presence of multiple next generation node Bs (gNBs), and the UAV as flying base station positioning affect the network performance. We also highlight the need for a better next generation node B (gNB) and UAVs placement criteria since the received signal power prevents the user equipments (UEs) from using most of the available resources. [ABSTRACT FROM AUTHOR]

The demand for wireless connectivity has grown tremendously over the last few decades. A new perspective of wireless communication will soon be positioned worldwide. In the years beyond, the millimeter-wave spectrum for the mobile communication infrastructure has improved spectral efficiency. The problem of the technical challenges may be detected, identified, and resolved in different designs as traditional solutions involve the software tricks that prevent the modes of operation that trigger the trouble. In this research, we carry out the proposed Millimetre assisted wave technologies using 6G federated learning and high-performance computing for 6G assisted wireless communication systems for voice data optimization. Millimeter-wave technology is a specific part of the radio frequency spectrum, between 24 and 100 GHz. The outcome of this proposed technique will be voice data optimization in the 6G cellular networks for next-generation networks to improve the 6G assisted networks federated learning from existing cellular network technology generation, established on the tool of Flight stack or Autopilot. The observational results express to assess the performance of the device, we acquire theMillimetre assisted wave technologies and federated learning and high-performance computing at various data transmission rates and modulations, including real-time data transfer up to 96 Gbit/s at 420 GHz, with a low bit error rate and good signal-to-noise ratio. With 18 dBm emitted power at 0.4 THz, this method creates and transmits a signal with a 160 Gbits per second net rate across a 15 m distance. This monolithic dual-DFB PIC-based THz generating technique represents an important advancement toward completely integrated, economically viable, and energy-efficient THz transmitters. [ABSTRACT FROM AUTHOR]

Software-defined vehicular networks (SDVN) is a promising technology for wireless data transmissions between vehicles. SDVN inherits software-defined networking principles and aims to improve the typical performance of safety and non-safety applications of vehicular adhoc networks. Consequently, enhancing the performance of Intelligent Transportation System (ITS). However, the performance of these ITS applications largely depends on the computational capability of the controller node, which involves creating or destroying a data path from the source vehicle to the destination vehicle and generating flow rules for the requests coming from the data plane elements. As a result, SDVN often suffers from the problems of overburdening the controller node with route requests under heavy traffic generation at vehicles and single-point controller failure. To counter these problems, solutions based on multiple controllers are proposed. In fact, the load-balancing problem remains an important issue. So, routing of data with multiple controllers and load-balancing, both topics in SDVN, go hand in hand. In this paper, we survey this state-of-the-art that discusses the above-mentioned challenges, starting with the SDVN preliminaries. We scrutinize the existing routing methodologies and also discuss load-balancing techniques. Furthermore, we provide real-time applications and services of SDVN, discuss trending research, potential future research directions, and the real-life applicability of SDVN that have not been addressed previously. [ABSTRACT FROM AUTHOR]

Metal oxide arrester (MOA) is an electric power equipment used to limit overvoltage and cooperate insulation between generator substation and direct current converter station. In the actual operation of MOA, due to the abnormal leakage current will produce various faults, the significant increasing of its resistive component will cause thermal effect, and even explosion, so as to lose the protection for the MOA. Particularly, in the transition from preventive maintenance to state maintenance, the importance of its safe operation or fault diagnosis is undoubted. Since the 1990s, fault diagnosis of MOA in operation has been very popular, and it is still popular today. After decades of unremitting efforts, we have accumulated rich experience in fault diagnosis of MOA, and also explored some new fault diagnosis methods and means. With the rise of wireless network technology, its network construction, maintenance, and other aspects have incomparable advantages of wired. Therefore, adopting wireless online monitoring to track MOA status can greatly improve the flexibility, real-time, and accuracy of fault diagnosis, and reduce the error and cost of wired data transmission. In this study, the monitoring module can realize the real-time transmission of MOA operation characteristics to the control terminal through wireless networks, judge the running status and insulation performance of the MOA by the change of the basic component of the resistance current, and then diagnose the fault of the MOA by the proposed weighted k-nearest neighbors algorithm. The simulation results show that the proposed method has very high precision and accuracy in fault diagnosis of MOA, as well as high recall and F1. [ABSTRACT FROM AUTHOR]

Cooperative Non-Orthogonal Multiple Access (Cooperative NOMA) is a communication technique used in wireless networks to enhance spectral efficiency and overall system performance. Non-Orthogonal Multiple Access is a multiple access scheme that allows multiple users to share the same time-frequency resources by allocating different power levels to each user. This paper presents a comprehensive performance validation of NOMA empowered by optimal relay selection and deep learning-based power allocation techniques. To achieve effective data transmission to far users, the optimal relay selection process employs the Maximum Energy Harvested Relay (MEHR) selection approach, which intelligently selects relays based on their energy harvesting capabilities. Furthermore, an enhanced Deep Convolutional Optimized Neural Network (DCOnN) is utilized for optimal power allocation among users in a cooperative NOMA system. To efficiently optimize the power allocation process with the DCOnN model, the Grey Wolf (GW) optimization is utilized to fine-tune the network weights. The presented approach significantly increases the energy efficiency in cooperative NOMA networks. The combination of optimal relay selection and deep learning-based power allocation enhances outage probability performance, ensuring better coverage and communication reliability while reducing the bit error rate for users in challenging channel conditions. Finally, the integration of optimal relay selection using DCOnN with GW optimization and cooperative cognitive NOMA provides a powerful framework to achieve superior communication performance in wireless networks. The proposed scheme achieves higher performance in terms of energy efficiency (519.257 Bits/J/Hz) and CPU time (0.012 seconds). The experimental results proved that the proposed performance is enhanced than the different existing schemes. [ABSTRACT FROM AUTHOR]

In recent years, wireless sensor networks (WSNs), as the underlying basic interface of the Internet of Things, have developed rapidly, and the performance requirements of WSNs are constantly improved in various application environments. However, in the practical application, the traditional wireless sensor network has the problem of uneven and limited energy consumption. To solve this problem, a non-uniform clustering algorithm based on node classification and multi-level data transmission (NCMLT) is proposed in this paper. The algorithm divides the nodes into S1 and S2 levels according to the distance from the base station, and transmits data in chain and cluster structures respectively, effectively combining the advantages of the two structures. In the stage of cluster head election, the threshold formula of low energy adaptive clustering hierarchy (LEACH) is improved, and the remaining energy of nodes and other factors are added into the candidate cluster head election function. When clustering, considering the rationality of the competitive radius, the distance and energy factors are adjusted to form non-uniform clustering, which reduces the energy cost of the network. Based on the greedy algorithm, the chain structure is constructed according to the defined chain head election formula, and the optimal chain node is selected by calculating the relay value of the cluster chain as the relay node for data transmission between the cluster head that is closer to the base station and the base station, and the data transmission distance between the nodes is optimized by means of hierarchical multi-hop. Through simulation experiments, compared with the energy-efficient uneven clustering algorithm (EEUC) and the uneven clustering routing algorithm based on ant colony optimization (URACO), the network lifetime of NCMLT algorithm is increased by 47.43% and 5.02%, respectively, which proves that NCMLT algorithm can effectively balance node energy consumption and extend network lifetime. [ABSTRACT FROM AUTHOR]

On-demand routing protocols discover routes through network-wide searches. Route requests are broadcast to a large number of nodes, and route replies may contain long routes. In this paper, we address the route discovery problem and aim to reduce route discovery overhead. We propose using data packets to discover routes. A source sets a boolean variable in a data packet to be true when it has only one route to the destination. This variable is a new form of a route request. The nodes forwarding the data packet send route replies containing cached routes. To prevent nodes from sending duplicate routes to the source, we define a forward list and a backward list in the data packet. The node sending a route reply records route diverging and converging information about the route in the route reply. Subsequent nodes use the information in the data packet to decide whether to send a route reply. Our algorithm reduces route discovery latency and discovers routes shorter than or having the same length as the active data path. Due to these shorter routes, it reduces the total size of route requests and route replies significantly. Routing overhead increases slowly as mobility or network load increases. Our algorithm is independent of node movement. It improves packet delivery ratio by 15% and reduces latency by 54% for the 100-node networks at node mean speed of 20 m/s. [ABSTRACT FROM AUTHOR]

Device-to-Device (D2D) communication stands as a pivotal technology revolutionizing conventional base station-to-device (B2D) communication paradigms. It facilitates direct data exchange among Internet of Things (IoT) devices without intermediaries such as servers or cloud services. However, the direct link between devices poses significant security risks, such as data leaks and unauthorized access. In this paper, a novel Secure data Transmission using Crystals Kyber (STUCK) technique has been proposed to secure device-to-device communication efficiently. STUCK encompasses four pivotal phases: token generation, device discovery, link configuration, and secure data transmission, ensuring robust protection against potential security breaches. Leveraging the Crystals Kyber cryptographic technique, STUCK adeptly manages key operations, encrypts and decrypts data, thus ensuring the integrity of data transmission across devices. Experimental validation conducted in MATLAB validates the efficacy of the proposed system, revealing noteworthy performance metrics encompassing processing time, communication overhead, and encryption duration. Comparative analysis demonstrates superior performance of STUCK, showcasing processing time increases of 23.07%, 44.23%, and 65.38% compared to existing techniques such as B-IoMV, LMECC, and QSAP, respectively. [ABSTRACT FROM AUTHOR]

To deal with the problem of complex changes of topology in UAVs (Unmanned Aerial Vehicles) network and the increasing need of data transmission, the combination of self-organizing and SDN (Software Defined Network) is a usefull paradigm. However, the control node's position in SDN will influence the transmission of command between controller and relay nodes, thus determining the quality of communication. In this context, we present a network construction, named SDN-FANET (Flying Ad-Hoc Network). We formulate the problem as a classical network center location model. To solve this problem, we propose a particle swarm algorithm based on the graph theory. Simulation results show the algorithm performs better in terms of accuracy and stability, compared with several benchmarks. Particularly, with the initial particle position optimized, the proposed algorithm converges faster. [ABSTRACT FROM AUTHOR]

In-Game theory Applications, the 6G-assisted federated learning in continuous monitoring applications with wireless sensor networks (WSN) is a significant concern. With increased applications comes the increased demand for advanced resource allocation and energy management systems. WSN can be determined as a self-configured, infrastructure-less wireless network monitoring physical or other surrounding conditions. In this study, the proposed system is concentrated on applying game theory to 6G-assisted federated learning for continuous monitoring in wireless sensor networks. The techniques imposed by the dual sink, such as Static and dynamic moving nodes approaches, are applied to the tentative node selection based on aggregated data transmission techniques. Based on the Static nodes and trusted nodes, the Aggregated data transmission is achieved high-level data transmission by combining individual-level data, i.e., the aggregate of the output data. This technique is performed with the wireless sensor network (WSN) platform with a future 6G network coordinating with the tool of NS4-Programmable Data Plane simulation. The proposed system simplifies the development of a behavioral model and bridges the gap between simulation and deployment. Finally, the combination of game theory with 6G-assisted federated learning for continuous monitoring applications in WSN solves problems and identifies several future directions. The outcome analysis of the proposed system is to design the wireless sensor network to yield a high network lifetime of more than 20 h and low power (less than 0.2 kJ energy) consumption for efficient communication in the future 6G cellular network. [ABSTRACT FROM AUTHOR]

With the advancement of ICT technology today, we can equip every single object with tiny and inexpensive radio modules; hence, they can interact and cooperate to perform complex tasks that have not been possible previously. During recent years several practical IoT-based applications have been proposed by deploying this improvement. With the expansion of IoT-based systems, many challenges began to emerge in this area. Energy optimization has been considered, as one of the most important problems in this domain, and data transmission has been identified as the primary accused. To tackle this problem, clustering has been suggested as a promising solution for reducing transmission distance and consequently energy consumption. The non-deterministic polynomial-time hard problem nature of clustering; alongside a variety of considerable parameters, limitations, and their contradiction, have made this problem more complex. As a result, various approaches have been proposed during recent years, each of which considered some parameters and real-world constraints. Here we present an efficient improvement on the existing energy-aware distributed unequal clustering protocol (EADUC). Our solution deploys a well-known swarm intelligence algorithm (SI), named Biogeography-based optimization (BBO) in a distributed manner to achieve heterogeneous load balancing. Our proposed work reflected a variety of real-world limitations such as energy, time, communication radius, and buffer size that have not been considered in many previous works simultaneously. Our simulations show approximately a 26% drop in the total number of dead nodes and a 1.59 % drop in energy consumption in comparison to the existing EADUC algorithm. [ABSTRACT FROM AUTHOR]

With the continuous maturity and adoption of mobile devices enabled by wireless communication technology, people are more apt to record their sport exercise data or healthcare data through various lightweight and smart devices, e.g., mobile phones and smart watches. Meanwhile, massive sport data or healthcare data keep being produced with time, which forms a main source of big healthcare data. Deep mining and analysis of such healthcare data are of positive significance for accurately recognizing the real-time health condition of mobile users and further recommend appropriate sport items to them. However, traditional centralized healthcare data mining and recommendation approaches require mobile users to transmit their health data collected by mobile devices to a remote cloud platform, which often involves heavy data transmissions from mobile devices to cloud platform. As a consequence, the transmission cost is high and the time delay is long. Moreover, long-distance data transmissions are prone to disclose user privacy. Considering these limitations, we bring forth a novel time-efficient and privacy-preserving healthcare data integration and mining approach for sport item recommendation, based on edge-cloud collaboration mechanism. At last, we design a group of simulation experiments to validate the effectiveness and efficiency of our approach. Experimental comparisons indicate a good balance between different evaluation metrics. [ABSTRACT FROM AUTHOR]

A wireless sensor network (WSN) is made up of many sensor nodes with insufficient energy, storage, and processing capabilities. Data gathering and transmission to the base station are two of the main responsibilities of the sensor nodes (BS). As a result, the network lifespan becomes the key factor in the successful design of data collection strategies in WSN. In this study, we provide the Enriched energy optimized LEACH (EE-OLEACH) protocol for data transfer. Through a combination of efficient optimum clustering and an optimal route selection mechanism, it provides a means for energy-efficient routing in WSN. The Homogeneous Hunter-Wolf optimization (HHWO) is used for clustering, and a cluster head is chosen for each cluster to reduce energy loss among sensor nodes and maximize efficiency in their use of available resources. Nodes with the highest residual energy may receive the most energy-efficient routing. In order to send the data to BS, the nodes with the greatest residual energy are chosen. The pheromone-profound Ant optimization (PPAO) method was then used to reduce energy consumption throughout the path-selection process. It contributes to a higher packet delivery ratio while reducing power consumption. According to the experimental findings, the proposed EE-OLEACH performs better than the current Protocol in terms of packet delivery ratio, end-to-end latency, and energy usage. In this paper, we compare the performance of the existing hierarchical routing protocols under varying conditions (packet size, starting energy level, etc.) and demonstrate how the optimal CH selection based on a suggested algorithm improves both network lifetime and energy consumption. The Simulation results shows that the EE-OLEACH enhances energy efficiency by 30%, delay by 35%, node survived by 45%, network lifetime by 56%, packet delivery ratio by 47% and throughput by 38% when compared with other existing protocols. The results clearly show that the suggested EE-OLEACH extends the lifespan of the network and reduce the energy consumption. [ABSTRACT FROM AUTHOR]

Underwater Wireless Sensor Networks (UWSNs) are the type of WSNs that transmit the data through water medium and monitor the oceanic conditions, water contents, under-sea habitations, underwater beings and military objects. Unlike air medium, water channel creates stronger communication barriers. In addition, the malicious data injection and other network attacks create security problems during data communication. Protecting the vulnerable UWSN channel is not an easy task under critical water conditions. Many research works proposed in the literature used cryptography principles and intelligent intrusion detection systems to secure the network activities from malicious nodes. However, the need for Machine Learning (ML) and Deep Learning (DL) associated Medium Access Control (MAC) principles is expected for handling the barriers in uncertain UWSN. In this regard, this article proposes a new Intrusion detection system with Integrated Secure MAC principles and Long Short-Term Memory (LSTM) architectures for organizing real-time neighbor monitoring tasks. The proposed system implements Generative Adversarial Network (GAN) driven UWSN channel assessment models and Secure LSTM-MAC principles to protect the data communication. In this regard, the proposed model creates the Intrusion Detection System (IDS) using trained distributed agents. These agents run in each legitimate sensor node contain novel LSTM-MAC engine, intrusion dataset, rule-based monitoring techniques, Secure Hashing Algorithm-3 (SHA-3), Two Fish algorithm and packet filtering tools. The proposed LSTM and agent-based model drives adaptive MAC channel operations to avoid malicious traffics in to legitimate nodes. In addition, this work implements neighbor-based packet monitoring, signal jamming and alert messaging procedures to build reliable security services against different types of attacks. The experiments and the observations reveal the performance of proposed techniques is proved to be 5% to 10% higher than existing techniques in various aspects measured with different metrics. [ABSTRACT FROM AUTHOR]