Adaptive Marine Intelligence and Sensing Architecture (AMISA) is a new framework that enables the enhancement of Autonomous Underwater Vehicle (AUV) capabilities with Artificial Intelligence (AI) and the Internet of Things (IoT). In response to the increasing requirement for real-time monitoring of marine ecosystems and sustainable ocean management, the proposed work is built for autonomous prediction, observation, and analysis of marine ecosystems through real-time data acquisition and adaptive decision-making processes. It has some cutting-edge components, such as Predictive Environment Mapping (PEM), which mines both historical and real-time data to adaptively detect and selectively focus on regions that might undergo ecological changes, and Dynamic Sensor Orchestration (DSO) is an energy-saving mechanism that selectively activates sensors in ecologically critical areas. Multi-tier AI Processing (MTAP) introduces an efficient hierarchical model structure for preliminary event detection and high-level anomaly analysis, tailoring data processing to diverse underwater conditions. Here, Energy-Conscious Path Optimization (ECPO) uses reinforcement learning to adaptively manage the route planning of the AUV to conduct optimal energy usage and to cover high-priority areas. The Smart Cloud Connectivity Protocol (SCCP) allows efficient data transmission by prioritizing essential findings and supports real-time alerts. Lastly, the Continuous Adaptive Learning (CAL) module enables the AUV to autonomously evolve by incremental updates of AI models with new data.

Bones collaborate with muscles and joints to sustain and maintain our freedom of mobility. The proper musculoskeletal activity of bone protects and strengthens the brain, heart, and lung function. When a bone is subjected to a force greater than its structural capacity, it fractures. Bone fractures should be detected with the appropriate type and should be treated early to avoid acute neurovascular complications. The manual detection of bone fracture may lead to highly delayed complications like malunion, Joint stiffness, Contractures, Myositis ossificans, and Avascular necrosis. A proper classification system must be integrated with deep learning technology to classify bone fractures accurately. This motivates me to propose a Systematized Attention Gate UNet (SAG-UNet) that classifies the type of bone fracture with high accuracy. The main contribution of this research is two-fold. The first contribution focuses on dataset preprocessing through feature extraction using unsupervised learning by adapting the Growing Neural Gas (GNG) method. The second contribution deals with refining the supervised learning Attention UNet model that classifies the ten types of bone fracture. The attention gate of the Attention UNet model is refined and applied to the upsampling decoding layer of Attention UNet. The KAGGLE Bone Break Classification dataset was processed to extract only the essential features using GNG extraction. The quantized significant feature RGB X-ray image was divided into 900 training and 230 testing images in the ratio of 80:20. The training images are fitted with the existing CNN models like DenseNet, VGG, AlexNet, MobileNet, EfficientNet, Inception, Xception, UNet and Attention UNet to choose the best CNN model. Experiment results portray that Attention UNet offers the classification of bone fractures with an accuracy of 89% when testing bone break images. Now, the Attention UNet was chosen to refine the Attention gate of the Decoding upsampling layer that occurs after the encoding layer. The Attention Gate of the proposed SAG-UNet forms the gating coefficient from the input feature map and gate signal. The gating coefficient is then processed with batch normalization that centers the aligned features in the active region, thereby leaving the focus on the unaligned weights of feature maps. Then, the ReLU activation function is applied to introduce the nonlinearity in the aligned features, thereby learning the complex representation in the feature vector. Then, dropout is used to exclude the error noise in the aligned weights of the feature map. Then, 1 × 1 linear convolution transformation was done to form the vector concatenation-based attention feature map. This vector has been applied to the sigmoid activation to create the attention coefficient feature map with weights assigned as ‘1’ for the aligned features. The attention coefficient feature map was grid resampled using trilinear interpolation to form the spatial attention weight map, which is passed to the skip connection of the next decoding layer. The implementation results reveal that the proposed SAG-UNet deep learning model classifies the bone fracture types with a high accuracy of 98.78% compared to the existing deep learning models.

Technological developments in medical image processing have created a state-of-the-art framework for accurately identifying and classifying brain tumors. To improve the accuracy of brain tumor segmentation, this study introduced VisioFlow FusionNet, a robust neural network architecture that combines the best features of DeepVisioSeg and SegFlowNet. The proposed system uses deep learning to identify the cancer site from medical images and provides doctors with valuable information for diagnosis and treatment planning. This combination provides a synergistic effect that improves segmentation performance and addresses challenges encountered across various tumor shapes and sizes. In parallel, robust brain tumor classification is achieved using NeuraClassNet, a classification component optimized with a dedicated catfish optimizer. NeuraClassNet’s convergence and generalization capabilities are powered by the Cat Fish optimizer, which draws inspiration from the adaptive properties of aquatic predators. By complementing a comprehensive diagnostic pipeline, this classification module helps clinicians accurately classify brain tumors based on various morphological and histological features. The proposed framework outperforms current approaches regarding segmentation accuracy (99.2%) and loss (2%) without overfitting.

The Internet of Underwater Things (IoUT) is an emerging revolution in underwater monitoring and communication, offering real-time detection of objects and data collection in harsh aquatic conditions. Severe communication problems, including signal attenuation, high latency, limited bandwidth, and noise/interference vulnerability, reduce underwater network performance and impede IoUT deployment. The proposed work introduces three new techniques to tackle these problems. The first work introduces the Sequential Memory Fusion Network (SMFN) for predicting environmental changes using historical and real-time data and predicting factors such as signal degradation and noise levels. In the second work, the Adaptive Condition-Based Binary Phase-Shift Keying system (ACB-BPSK) dynamically switches between modulation schemes of high-noise and low-noise modes with the help of real-time feedback to achieve signal robustness and optimized data rates. ACB-EBPSK handles adaptation in modulation techniques according to environmental conditions for enhancing wireless communication’s reliability and efficiency. The third contribution is an Energy-Efficient Reinforcement Learning (EERL) framework for routing decisions, which learns from network feedback, packet loss, and congestion-allows inserting energy into the routing policy and prolonging the lifetime of battery-operated devices considering the dynamic natures of network conditions. The developed techniques’ advantages include increased communication reliability, higher data transmission rates, and prolonged network lifetime.

Underwater aquatic systems play a crucial role in maintaining ecological balance and supporting marine biodiversity. However, due to low visibility, color distortion, and scattering effects caused by light absorption, efficient monitoring and detecting objects in such environments remain challenging. Deep learning-based image processing techniques have revolutionized underwater exploration by providing robust solutions for enhancing image quality, extracting meaningful features, and enabling precise classification. Integrating advanced image enhancement methods with deep learning architectures facilitates accurate detection and monitoring of aquatic species, objects, and anomalies. This study introduces a novel approach that synergistically combines the Multiscale Retinex (MSR) and Dark Channel Prior (DCP) approaches for underwater image enhancement in the form of the Dark Retinex Fusion (DRF) model. The DRF model is further integrated with a YOLO-based Transformer framework, leveraging attention mechanisms to enhance feature extraction and classification. The proposed DRF-YOLO-based Transformer framework effectively reduces haze, enhances contrast, and balances colors for an underwater environment. It incorporates advanced spatial precision features in the YOLO backbone and applies the attention module from the Transformer model that captures the long-range dependencies for better contextual understanding. The model was tested on underwater object datasets, achieving an accuracy of 98% and a loss of 0.2, outperforming traditional methods. Additionally, the framework demonstrated resilience to overfitting and local minima, maintaining consistent performance under varying conditions.

As with IoT devices, cloud computation increases its applicability to other areas that use the information and puts it in a commonplace that is necessary for computing and analysis. These devices need the cloud to store and retrieve data since they are unable to store and process data on their own. Cloud computing offers a variety of services to consumers, including IaaS, PaaS, and SaaS. The usage of cloud resources for data storage that may be accessible by all users associated with cloud computing is a key disadvantage of cloud computing. Without disclosing the data’s contents, the usage of Public Key Encryptions with Keyword Search (PEKS) secures publicly encrypted keys against third-party search capabilities that are not trustworthy. PEKs provide a security risk every time Interior Keywords Guessing Attacks (IKGA) are discovered in the system since an unauthorized service estimates the keywords in the trapdoor. This issue can be resolved using various methodologies such as the Certificateless Fleshed Public Key Authenticated Encryption of Keyword Search (CL-HPAEKS), which also uses Altered Elliptic Curve Cryptography (MECC), and the Mutation Centred Flower Pollinations Algorithm (CM-FPA), which uses optimization in keys to be improving the algorithm’s performance. The system’s security is achieved by adding a Message Fragments 5 (MD5) scramble mechanism. The proposed system achieves system security of 96%, and it takes less time to implement than earlier encryption methods.

This paper describes the concepts behind and implementation of the multimedia art work Alan01 / AlanOnline, which wakes up the 1952 criminally convicted Alan Turing as a piece of code within the art work- thus fulfilling Turing's own vision of preserving human consciousness in a computer. The work's context is described within the development of associative storytelling structures built up by interactive user feedback via an image and video retrieval system. The input to the retrieval system is generated by Alan01 / AlanOnline via their respective sketch interfaces, the output of the retrieval system being fed back to Alan01 / AlanOnline for further processing and presentation to the user within the context of the overall artistic experience. This paper, in addition to presenting the productions and image retrieval system, also presents the installation and online production user reception and some of the issues and observations made during the development of the systems. Categories and Subject Descriptors

Well acceptance of relevance feedback and collaborative systems has given the users to express their preferences in terms of multiple query examples. The technology devised to utilize these user preferences, is expected to mine the semantic knowledge embedded within these query examples. In this paper, we propose a video mining framework based on dynamic learning from queries, using a statistical model for topic prerogative feature selection. The proposed method is specifically designed for multiple query example scenarios. The effectiveness of the proposed framework has been established with an extensive experimentation on TRECVid2007 data collection. The results reveal that our approach achieves a performance that is in par with the best results for this corpus without the requirement of any textual data.

In this paper, a novel method of representing symbolic images in a symbolic image database (SID) invariant to image transformations that is useful for exact match retrieval is presented. The relative spatial relationships existing among the components present in an image are perceived with respect to the direction of reference and preserved by a set of triples. A distinct and unique key is computed for each distinct triple. The mean and standard deviation of the set of keys computed for a symbolic image are stored along with the total number of keys as the representatives of the corresponding image. The proposed exact match retrieval scheme is based on a modified binary search technique and, thus, requires O (logn) search time in the worst case, where n is the total number of symbolic images in the SID. An extensive experimentation on a large database of 22,630 symbolic images is conducted to corroborate the superiority of the model. The effectiveness of the proposed representation scheme is tested with standard testbed images