Computational Capabilities Research Articles

LightAuth: A Lightweight Sensor Nodes Authentication Framework for Smart Health System

ABSTRACTCounterfeit medical devices pose a threat to patient safety, necessitating a secure device authentication system for medical applications. Resource‐constrained sensory nodes are vulnerable to hacking, prompting the need for robust security measures. Token‐based authentication schemes, such as one‐time passwords (OTPs), smart cards, key fobs, and mobile authentication apps, along with certificate‐based authentication methods, such as client and code‐signing, employ cryptographic frameworks like elliptical curve cryptography (ECC) and physical unclonable functions (PUF). However, these methods face challenges, including block sequence issues and susceptibility to side‐channel attacks. To address these issues, we propose a framework for mutual authentication using private Ethereum. This framework integrates private Ethereum and cryptographic techniques for encrypting and decrypting data using mathematical algorithms to overcome block sequence issues and side‐channel attacks. Similarly, fog nodes are utilised to enhance local computing, storage, and networking capabilities for sensors. The framework is evaluated using metrics such as communication costs, execution costs, and computation costs based on Ethereum gas consumption. The performance of the LightAuth framework is compared with that of the Smart Contracts Against Counterfeit IoMT (SCACIoMT) framework, designed for Internet of Medical Things (IoMT) devices. The effectiveness of LightAuth is verified through formal security analysis using BAN logic.

Surrogate Modeling for Solving OPF: A Review

The optimal power flow (OPF) problem, characterized by its inherent complexity and strict constraints, has traditionally been approached using analytical techniques. OPF enhances power system sustainability by minimizing operational costs, reducing emissions, and facilitating the integration of renewable energy sources through optimized resource allocation and environmentally aligned constraints. However, the evolving nature of power grids, including the integration of distributed generation (DG), increasing uncertainties, changes in topology, and load variability, demands more frequent OPF solutions from grid operators. While conventional methods remain effective, their efficiency and accuracy degrade as computational demands increase. To address these limitations, there is growing interest in the use of data-driven surrogate models. This paper presents a critical review of such models, discussing their limitations and the solutions proposed in the literature. It introduces both Analytical Surrogate Models (ASMs) and learned surrogate models (LSMs) for OPF, providing a thorough analysis of how they can be applied to solve both DC and AC OPF problems. The review also evaluates the development of LSMs for OPF, from initial implementations addressing specific aspects of the problem to more advanced approaches capable of handling topology changes and contingencies. End-to-end and hybrid LSMs are compared based on their computational efficiency, generalization capabilities, and accuracy, and detailed insights are provided. This study includes an empirical comparison of two ASMs and LSMs applied to the IEEE standard six-bus system, demonstrating the key distinctions between these models for small-scale grids and discussing the scalability of LSMs for more complex systems. This comprehensive review aims to serve as a critical resource for OPF researchers and academics, facilitating progress in energy efficiency and providing guidance on the future direction of OPF solution methodologies.

Line-parameter identification of medium-voltage distribution systems based on deep deterministic policy gradients

Accurate line-parameter identification is an important foundation for refined the regulation, protection, and control of distribution systems. Traditional identification models provide accurate modeling, while conventional identification approaches are hindered by the high complexity and low observability of power systems. In this article, a parameter identification method based on the deep deterministic policy gradient is proposed for medium voltage distribution systems. The proposed method starts with objective function constructing, followed by power flow analysis and parameter identification modeling, where the L2 normalization theory is introduced to improve the computation efficiency. On this basis, the parameter identification framework is constructed through designing the Markov decision process of a parameter and using a training mechanism. An adaptive parameter correction method is proposed to improve the accuracy and efficiency of a deep-reinforcement-learning-based agent. The performance of the proposed modal is tested on IEEE 14-node and IEEE 33-node medium-voltage distribution systems. Case simulation results demonstrate that the proposed modal exhibits superior computational capability, while achieving fewer errors compared to traditional methods.

Synthetic translational coupling element for multiplexed signal processing and cellular control

Abstract Repurposing natural systems to develop customized functions in biological systems is one of the main thrusts of synthetic biology. Translational coupling is a common phenomenon in diverse polycistronic operons for efficient allocation of limited genetic space and cellular resources. These beneficial features of translation coupling can provide exciting opportunities for creating novel synthetic biological devices. Here, we introduce a modular synthetic translational coupling element (synTCE) and integrate this design with de novo designed riboregulators, toehold switches. A systematic exploration of sequence domain variants for synTCEs led to the identification of critical design considerations for improving the system performance. Next, this design approach was seamlessly integrated into logic computations and applied to construct multi-output transcripts with well-defined stoichiometric control. This module was further applied to signaling cascades for combined signal transduction and multi-input/multi-output synthetic devices. Further, the synTCEs can precisely manipulate the N-terminal ends of output proteins, facilitating effective protein localization and cellular population control. Therefore, the synTCEs could enhance computational capability and applicability of riboregulators for reprogramming biological systems, leading to future applications in synthetic biology, metabolic engineering and biotechnology.

Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation

Distributed Graph Neural Network (GNN) training facilitates learning on massive graphs that surpass the storage and computational capabilities of a single machine. Traditional distributed frameworks strive for performance parity with centralized training by maximally recovering cross-instance node dependencies, relying either on inter-instance communication or periodic fallback to centralized training. However, these processes create overhead and constrain the scalability of the framework. In this work, we propose a streamlined framework for distributed GNN training that eliminates these costly operations, yielding improved scalability, convergence speed, and performance over state-of-the-art approaches. Our framework (1) comprises independent trainers that asynchronously learn local models from locally-available parts of the training graph, and (2) synchronizes these local models only through periodic (time-based) model aggregation. Contrary to prevailing belief, our theoretical analysis shows that it is not essential to maximize the recovery of cross-instance node dependencies to achieve performance parity with centralized training. Instead, our framework leverages randomized assignment of nodes or super-nodes (i.e., collections of original nodes) to partition the training graph in order to enhance data uniformity and minimize discrepancies in gradient and loss function across instances. Experiments on social and e-commerce networks with up to 1.3 billion edges show that our proposed framework achieves state-of-the-art performance and 2.31x speedup compared to the fastest baseline, despite using less training data.

Efficient I/O Performance-Focused Scheduling in High-Performance Computing

High-performance computing (HPC) systems are becoming increasingly important as contemporary exascale applications with demand extensive computational and data processing capability. To optimize these systems, efficient scheduling of HPC applications is important. In particular, because I/O is a shared resource among applications and is becoming more important due to the emergence of big data, it is possible to improve performance by considering the architecture of HPC systems and scheduling jobs based on I/O resource requirements. In this paper, we propose a scheduling scheme that prioritizes HPC applications based on their I/O requirements. To accomplish this, our scheme analyzes the IOPS of scheduled applications by examining their execution history. Then, it schedules the applications at pre-configured intervals based on their expected IOPS to maximize the available IOPS across the entire system. Compared to the existing first-come first-served (FCFS) algorithm, experimental results using real-world HPC log data show that our scheme reduces total execution time by 305 h and decreases costs by USD 53 when scheduling 10,000 jobs utilizing public cloud resources.

Edge Computing for AI-Based Brain MRI Applications: A Critical Evaluation of Real-Time Classification and Segmentation

Medical imaging plays a pivotal role in diagnostic medicine with technologies like Magnetic Resonance Imagining (MRI), Computed Tomography (CT), Positron Emission Tomography (PET), and ultrasound scans being widely used to assist radiologists and medical experts in reaching concrete diagnosis. Given the recent massive uplift in the storage and processing capabilities of computers, and the publicly available big data, Artificial Intelligence (AI) has also started contributing to improving diagnostic radiology. Edge computing devices and handheld gadgets can serve as useful tools to process medical data in remote areas with limited network and computational resources. In this research, the capabilities of multiple platforms are evaluated for the real-time deployment of diagnostic tools. MRI classification and segmentation applications developed in previous studies are used for testing the performance using different hardware and software configurations. Cost–benefit analysis is carried out using a workstation with a NVIDIA Graphics Processing Unit (GPU), Jetson Xavier NX, Raspberry Pi 4B, and Android phone, using MATLAB, Python, and Android Studio. The mean computational times for the classification app on the PC, Jetson Xavier NX, and Raspberry Pi are 1.2074, 3.7627, and 3.4747 s, respectively. On the low-cost Android phone, this time is observed to be 0.1068 s using the Dynamic Range Quantized TFLite version of the baseline model, with slight degradation in accuracy. For the segmentation app, the times are 1.8241, 5.2641, 6.2162, and 3.2023 s, respectively, when using JPEG inputs. The Jetson Xavier NX and Android phone stand out as the best platforms due to their compact size, fast inference times, and affordability.

Scalable Fabrication of Neuromorphic Devices Using Inkjet Printing for the Deposition of Organic Mixed Ionic‐Electronic Conductor

AbstractRecent advancements in artificial intelligence (AI) have highlighted the critical need for energy‐efficient hardware solutions, especially in edge‐computing applications. However, traditional AI approaches are plagued by significant power consumption. In response, researchers have turned to biomimetic strategies, drawing inspiration from the ion‐mediated operating principle of biological synapses, to develop organic neuromorphic devices as promising alternatives. Organic mixed ionic‐electronic conductor (OMIEC) materials have emerged as particularly noteworthy in this field, due to their potential for enhancing neuromorphic computing capabilities. Together with device performance, it is crucial to select devices that allow fabrication via scalable techniques. This study investigates the fabrication of OMIEC‐based neuromorphic devices using inkjet printing, providing a scalable and material‐efficient approach. Employing a commercially available polymer mixed ionic‐electronic conductor (BTEM‐PPV) and a lithium salt, inkjet‐printed devices exhibit performance comparable to those fabricated via traditional spin‐coating methods. These two‐terminal neuromorphic devices demonstrate functionality analogous to literature‐known devices and demonstrate promising frequency‐dependent short‐term plasticity. Furthermore, comparative studies with previous light‐emitting electrochemical cells (LECs) and neuromorphic OMIEC devices validate the efficacy of inkjet printing as a potential fabrication technique. The findings suggest that inkjet printing is suitable for large‐scale production, offering reproducible and stable fabrication processes. By adopting the OMIEC material system, inkjet printing holds the potential for further enhancing device performance and functionality. Overall, this study underscores the viability of inkjet printing as a scalable fabrication method for OMIEC‐based neuromorphic devices, paving the way for advancements in AI hardware.

Green Computation Offloading With DRL in Multi‐Access Edge Computing

ABSTRACTIn multi‐access edge computing (MEC), computational task offloading of mobile terminals (MT) is expected to provide the green applications with the restriction of energy consumption and service latency. Nevertheless, the diverse statuses of a range of edge servers and mobile terminals, along with the fluctuating offloading routes, present a challenge in the realm of computational task offloading. In order to bolster green applications, we present an innovative computational task offloading model as our initial approach. In particular, the nascent model is constrained by energy consumption and service latency considerations: (1) Smart mobile terminals with computational capabilities could serve as carriers; (2) The diverse computational and communication capacities of edge servers have the potential to enhance the offloading process; (3) The unpredictable routing paths of mobile terminals and edge servers could result in varied information transmissions. We then propose an improved deep reinforcement learning (DRL) algorithm named PS‐DDPG with the prioritized experience replay (PER) and the stochastic weight averaging (SWA) mechanisms based on deep deterministic policy gradients (DDPG) to seek an optimal offloading mode, saving energy consumption. Next, we introduce an enhanced deep reinforcement learning (DRL) algorithm named PS‐DDPG, incorporating the prioritized experience replay (PER) and stochastic weight averaging (SWA) techniques rooted in deep deterministic policy gradients (DDPG). This approach aims to identify an efficient offloading strategy, thereby reducing energy consumption. Fortunately, algorithm is proposed for each MT, which is responsible for making decisions regarding task partition, channel allocation, and power transmission control. Our developed approach achieves the ultimate estimation of observed values and enhances memory via write operations. The replay buffer holds data from previous time slots to upgrade both the actor and critic networks, followed by a buffer reset. Comprehensive experiments validate the superior performance, including stability and convergence, of our algorithm when juxtaposed with prior studies.

Quantum Entanglement and Qubit Interactions: The Key to Quantum Supremacy

Abstract. Quantum computing operates in a fundamentally different way from classical computing by harnessing the principles of quantum mechanics to process information. Quantum supremacy is achieved when a quantum computer can solve problems that are beyond the capabilities of classical systems, including the human brain, showcasing its superior processing power. To attain quantum supremacy, quantum entanglement and qubit interactions play a pivotal role. Quantum entanglement occurs when qubits are interconnected in a manner where the state of one qubit directly influences the state of others, enabling the quantum computer to perform multiple operations simultaneously. Moreover, effective interaction between qubits is essential for the performance of complex calculations in quantum systems, highlighting the significance of coherence and error correction. Understanding the importance of coherence in preventing and rectifying errors in quantum computations is crucial. This paper aims to explore the critical aspects of quantum entanglement and qubit interactions, which are foundational to the operation of quantum computers. By delving into these key concepts, the paper aims to elucidate their significant roles in achieving quantum supremacy. The discussion will center on how quantum entanglement, which allows enhanced computational parallelism through qubit interconnection, and efficient qubit interactions vital for complex computations, contribute to surpassing the capabilities of classical computers. Comprehending these principles is crucial for advancing quantum computing technology and overcoming the challenges to unleash its full potential.

Quantum Neural Networks: A New Frontier

Abstract. In recent years, there has been remarkable progress in improving the availability of resources and refining algorithms for quantum computing. Since the late 1980s, the scientific community has been fascinated by the idea of harnessing quantum phenomena to tackle computational problems. This article provides a comprehensive exploration of the foundational theories and practical applications of quantum neural networks (QNNs), highlighting their potential to transform machine learning through unique features like quantum parallelism and entanglement. It delves into various QNN architectures, such as quantum circuits and hybrid quantum-classical models, showcasing their effectiveness in handling intricate computational tasks more efficiently than traditional neural networks. Furthermore, the article examines the current challenges and future prospects in this rapidly advancing field, emphasizing the pivotal role of QNNs in driving forward research in both quantum computing and artificial intelligence. Quantum neural networks are poised to not only enhance computational capabilities but also pave the way for groundbreaking innovations in diverse technological domains.

MOFSynth: A Computational Tool toward Synthetic Likelihood Predictions of MOFs.

In the past decade, high-throughput computational studies of materials have increased significantly mainly due to advances in computer capabilities and have attracted a great deal of interest. In the field of metal-organic frameworks (MOFs), over a million hypothetical MOFs have been designed in silico, yet only a small fraction of these have been synthesized. For validating the computational-hypothetical results and accelerating the progress in the field, there is a pressing need for distinguishing MOFs that are more likely to be synthesized for real-life applications. This study presents a comprehensive investigation into the synthesizability likelihood of MOFs, utilizing a novel computational approach based on the disparities in energy and geometry between the linker conformation within the MOF structure and its isolated, free-gas state since both of these have been proven to be critical factors influencing MOF synthesis. Our user-friendly tool streamlines synthesizability evaluation, requiring minimal expertise in computational chemistry. By deconstructing over 40,000 MOFs from databases, including QMOF, CoRE MOF, and ToBaCCo, we analyze key parameters defining the linker strain within the MOF unit cell. Our results indicate that QMOF and CoRE MOF contain more promising candidates for synthesis, while ToBaCCo exhibits a relatively poor synthesizability likelihood due to unoptimized materials. Through extensive analysis, we identify optimal linker candidates for highly synthesizable MOFs. Consistent trends in energy distribution across databases that are confirmed by high Pearson and Spearman coefficients suggest the potential for omitting optimization calculations, significantly reducing computational costs. This study underscores the importance of linker deformation and energy disparities and enhances our understanding of synthetic accessibility in MOF research, offering valuable insights for future advancements in the field.

Photodual-Responsive Anthracene-Based 2D Covalent Organic Framework for Optoelectronic Synaptic Devices.

To facilitate the development of efficient neuromorphic perception and computation, it is crucial to explore optoelectronic synaptic devices that integrate perceptual and computational capabilities. Various materials such as oxide semiconductors, conjugated organic polymers, transition metal sulfides, perovskite materials, and metal nanoparticles, along with their composites, are utilized in constructing these devices. However, optoelectronic synaptic devices based on 2D covalent organic frameworks (COFs) is rarely reported. In this study, an anthracene-based 2D COF (COF-DaTp) film is prepared using a room-temperature interface-confined strategy and utilized it as the active layer in an optoelectronic synaptic device with an Al/COF-DaTp/ITO configuration. The device demonstrated dual optoelectronic modulation, exhibiting significant optoelectronic resistive switching in response to light pulses, achieving 32 photoconductive states. Moreover, it exhibited history-dependent memristive behavior in voltage scans and electrical pulses, with a comparable diversity of 32 conductive states. The photodual-responsive properties of the COF-DaTp-based synaptic device enable it to simultaneously perform optical sensing and basic image denoising and recognition tasks, significantly enhancing recognition accuracy and reducing the number of training epochs compared to datasets without noise mitigation. This work opens the door for the application of 2D COF-based optoelectronic synaptic devices in visual computational processing.

Diffraction‐Driven Parallel Convolution Processing with Integrated Photonics

AbstractTraditional electronic processors often struggle with bandwidth limitations and high power consumption when executing extensive linear operations for deep learning tasks. Optical computing has emerged as a promising alternative, offering parallel and energy‐efficient computation capabilities. Yet, the development of high‐density optical computing architectures on integrated photonic platforms remains limited, hindered by constraints in neuron scalability and control engineering complexities. Addressing these challenges, this work presents a diffraction‐driven multi‐kernel optical convolution unit (MOCU) that enables on‐chip parallel convolution processing. By utilizing cascaded silica 1D metalines as pre‐trained large‐scale weights and employing spatial multiplexing at the output, MOCU allows simultaneous passive computation of diverse convolutions within a single unit. This architecture facilitates the construction of optical convolutional neural networks (OCNNs), enabling efficient machine vision processing with a streamlined design. To mitigate errors in MOCU‐embedded OCNNs, a lightweight electronic neural network operates concurrently to calibrate systematic deviations via a low‐rank adaptation (LoRA) algorithm, with minimal overhead. The fabricated MOCU chip demonstrates the highest independent 8‐kernel convolutions in parallel, each with a kernel size and occupying just 0.06 . This architecture effectively merges photonic and electronic technologies, offering a scalable design pathway for energy‐efficient, high‐density deep learning hardware.

Artificial intelligence and IoT driven system architecture for municipality waste management in smart cities: A review

Numerous devices, including sensors, RF ID, and other types of smart devices, have been developed as a result of the Artificial Intelligence (AI), and Internet of Things (IoT) revolution. Urban areas can become smart by monitoring and collecting data about their surroundings through the deployment of technologies with powerful computational capabilities and those that are converted into intelligent things. Waste management is among the most significant issues in smart cities, a rise in metropolitan regions and faster increases in population are the main reasons. When it comes to gathering data about waste management, intelligent services can serve as the front line. Waste management with IoT support is a common example of a service offered by smart cities. Various duties, like gathering, processing, and use of waste in appropriate facilities, are included in waste management. The present study proposed an updated waste management system architecture design after reviewing existing artificial intelligence and IoT-based waste management systems and automation in smart cities. The proposed system architecture deals with the automation of municipality trash in smarter urban areas, using IoT technology and sending notification messages based on sensor data relating to the dustbin state, such as full or empty. The notifications are sent simultaneously to the municipality office and the waste carrier vehicle driver, so that waste can be emptied on time. The proposed system architecture represents a scalable and adaptable model for municipalities that aim to transform their waste collection processes and play a key step in minimizing municipality waste in smart cities. By deploying this proposed system architecture with smart sensors and IoT devices, municipalities can monitor waste levels to ensure that bins are emptied when it is necessary. This reduces the frequency of waste collection, lowers fuel consumption, and minimizes operational costs. The Route optimization algorithms further enhance efficiency by determining the most efficient paths for waste collection trucks, so they can reduce travel time and fuel emissions.

A Review of Indoor Localization Methods Leveraging Smartphone Sensors and Spatial Context

As Location-Based Services (LBSs) rapidly develop, indoor localization technology is garnering significant attention as a critical component. Smartphones have become tools for indoor localization due to their highly integrated sensors, fast-evolving computational capabilities, and widespread user adoption. With the rapid advancement of smartphones, methods for smartphone-based indoor localization have increasingly attracted attention. Although there are reviews on indoor localization, there is still a lack of systematic reviews focused on smartphone-based indoor localization methods. In particular, existing reviews have not systematically analyzed smartphone-based indoor localization methods or considered the combination of smartphone sensor data with prior knowledge of the indoor environment to enhance localization performance. In this study, through systematic retrieval and analysis, the existing research was first categorized into three types to dissect the strengths and weaknesses based on the types of data sources integrated, i.e., single sensor data sources, multi-sensor data fusion, and the combination of spatial context with sensor data. Then, four key issues are discussed and the research gaps in this field are summarized. Finally, a comprehensive conclusion is provided. This paper offers a systematic reference for research and technological applications related to smartphone-based indoor localization methods.

Dynamics, Monitoring, and Forecasting of Tephra in the Atmosphere

AbstractExplosive volcanic eruptions inject hot mixtures of solid particles (tephra) and gasses into the atmosphere. Entraining ambient air, these mixtures can form plumes rising tens of kilometers until they spread laterally, forming umbrella clouds. While the largest clasts tend to settle in proximity to the volcano, the smallest fragments, commonly referred to as ash (≤2 mm in diameter), can be transported over long distances, forming volcanic clouds. Tephra plumes and clouds pose significant hazards to human society, affecting infrastructure, and human health through deposition on the ground or airborne suspension at low altitudes. Additionally, volcanic clouds are a threat to aviation, during both high‐risk actions such as take‐off and landing and at standard cruising altitudes. The ability to monitor and forecast tephra plumes and clouds is fundamental to mitigate the hazard associated with explosive eruptions. To that end, various monitoring techniques, ranging from ground‐based instruments to sensors on‐board satellites, and forecasting strategies, based on running numerical models to track the position of volcanic clouds, are efficiently employed. However, some limitations still exist, mainly due to the high unpredictability and variability of explosive eruptions, as well as the multiphase and complex nature of volcanic plumes. In the next decades, advances in monitoring and computational capabilities are expected to address these limitations and significantly improve the mitigation of the risk associated with tephra plumes and clouds.

Nonvolatile logic inverters based on 2D CuInP2S6 ferroelectric field effect transistors

With the capability of in-memory computing, integrated nonvolatile logic devices can mitigate the back-and-forth movement of data between storage and logic units, thus effectively enhancing computational speed and reducing power consumption. In this work, two-dimensional (2D) CuInP2S6, which reveals robust polarization within a few nanometer thicknesses, was utilized as gate dielectric for ferroelectric field effect transistor (FeFET). Device with a ReS2 channel demonstrated a high on/off ratio of current of 105, accompanied by a substantial hysteresis window of 2.8 V. Additionally, ReS2 FETs, gated with an h-BN layer, exhibited a switch ratio of 108 and minimal hysteresis of 61.6 mV at room temperature, attributed to the atomically flat heterointerface with negligible traps. Leveraging the performance of these devices enabled the creation of a nonvolatile logic inverter, wherein the ReS2/h-BN FET acts as the load transistor, and ReS2/h-BN/CIPS FeFET serves as the driving unit. This configuration stably operates with low power consumption of 0.45 μW and outstanding retention exceeding 1000 s. This work presents a viable device architecture for designing nonvolatile logic circuits applicable in in-memory computing.

Efficient and Compressed Deep Learning Model for Brain Tumour Classification With Explainable AI for Smart Healthcare and Information Communication Systems

ABSTRACTThe detection of brain tumours presents a significant challenge in the medical domain, where prompt and precise diagnosis is crucial as patient outcomes depend on it. Conventional deep neural networks perform well in carrying out various imaging tasks within the healthcare sector; however, their effectiveness often falls short of expectations in practical applications due to the substantial computational resources required and issues with reliability. In this research, an optimised and effective deep learning model founded on the DenseNet‐169 architecture is introduced for the classification of magnetic resonance imaging brain tumours, which is particularly advantageous for smart healthcare systems and information and communication technology (ICT) settings with limited computational capabilities. The model compression methodologies, including pruning and quantization, have been employed to significantly diminish the dimensions and intricacy of the model while achieving a classification accuracy of 97.07%. Furthermore, this endeavour necessitates the enhancement of the model's interpretability through the utilisation of explainable artificial intelligence methodologies such as Gradient‐weighted Class Activation Mapping (Grad‐CAM) and SHapley Additive exPlanations (SHAP), which will aid clinicians in highlighting crucial areas of the images and validating feature importance concerning the decisions rendered by the model. A comparative performance evaluation is conducted against DenseNet‐169, ResNet‐50 and various other models to delineate the superior efficacy of our model, rendering it exceptionally adept for knowledge‐driven, real‐time brain tumour diagnosis within smart healthcare and ICT systems where resources are constrained.

Video Generative AI in Digital Marketing: A SWOT Analysis on E-Commerce

Artificial Intelligence (AI) is reshaping the way various business processes are performed, most rapidly in digital marketing, due to its advanced computational capabilities. ECommerce companies are in advantageous position to adopt and reap the benefits of AI for many reasons including the readily available computational infrastructure and big data related to their users and processes. Meanwhile, big tech companies and startups are competing to create and improve generative AI models, that create high-definition videos based on inputs in the form of text, image or videos. The current research specifically aims to analyse the video outputs of various video generating AI models available for digital marketing purposes in ecommerce businesses and to rationally analyse how those video generative AI models benefit or affect e-commerce companies. To meet the research objectives, mixed methodologies of experimentation and content analysis were deployed. It was observed that the video outputs from the tested models were not yet suitable for digital marketing and appeared underdeveloped. Additionally, the SWOT analysis revealed advantages like low costs, alongside concerns such as intellectual property issues.