Search

Alzheimer's disease (AD) is a major global health concern that affects millions of people globally. This study investigates the technical challenges in AD analysis and provides a thorough analysis of AD, emphasizing the disease's worldwide effects as well as the predicted increase. It explores the technological difficulties associated with AD analysis, concentrating on the shift in automated clinical diagnosis using MRI data from conventional machine learning to deep learning techniques. This study advances our knowledge of the effects of AD and provides new developments in deep learning for precise diagnosis, providing insightful information for both clinical and future research. The research introduces an innovative deep learning model, leveraging YOLOv5 and variants of YOLOv8, to classify AD images into four (NC, EMCI, LMCI, AD) categories. This study evaluates the performance of YOLOv5 which achieved high accuracy (97%) in multi‐class classification (classes 0 to 3) with precision, recall, and F1‐score reported for each class. YOLOv8 (Small) and YOLOv8 (Medium) models are also assessed for Alzheimer's disease diagnosis, demonstrating accuracy of 97% and 98%, respectively. Precision, recall, and F1‐score metrics provide detailed insights into the models' effectiveness across different classes. Comparative analysis against a transfer learning model reveals YOLOv5, YOLOv8 (Small), and YOLOv8 (Medium) consistently outperforming across six binary classifications related to cognitive impairment. These models show improved sensitivity and accuracy compared to baseline architectures from [32]. In AD/NC classification, YOLOv8 (Medium) achieves 98.43% accuracy and 97.45% sensitivity, for EMCI/LMCI classification, YOLOv8 (Medium) also excels with 92.12% accuracy and 90.12% sensitivity. The results highlight the effectiveness of YOLOv5 and YOLOv8 variants in neuroimaging tasks, showcasing their potential in clinical applications for cognitive impairment classification. The proposed models showcase superior performance, achieving high accuracy, sensitivity, and F1‐scores, surpassing baseline architectures and previous methods. Comparative analyses highlight the robustness and effectiveness of the proposed models in AD classification tasks, providing valuable insights for future research and clinical applications. [ABSTRACT FROM AUTHOR]

Cloud computing revolutionizes data management by offering centralized repositories or services accessible over the Internet. These services, hosted by a single provider or distributed across multiple entities, facilitate seamless access for users and applications. Additionally, cloud technology enables federated search capabilities, allowing organizations to amalgamate data from diverse sources and perform comprehensive searches. However, such integration often leads to challenges in data quality and duplication due to structural disparities among datasets, including variations in metadata. This research presents a novel provenance‐based search model designed to enhance data quality within cloud environments. The model expands the traditional concept of a single canonical URL by incorporating provenance data, thus providing users with diverse search options. Leveraging this model, the study conducts inferential analyses to improve data accuracy and identify duplicate entries effectively. To verify the proposed model, two research paper datasets from Kaggle and DBLP repositories are utilized, and the model effectively identifies duplicates, even with partial queries. Tests demonstrate the system's ability to remove duplicates based on title or author, in both single and distributed dataset scenarios. Traditional search engines struggle with duplicate content, resulting in biased results or inefficient crawling. In contrast, this research uses provenance data to improve search capabilities, overcoming these limitations. [ABSTRACT FROM AUTHOR]

Federated learning has emerged as a promising approach for collaborative model training across distributed devices. Federated learning faces challenges such as Non-Independent and Identically Distributed (non-IID) data and communication challenges. This study aims to provide in-depth knowledge in the federated learning environment by identifying the most used techniques for overcoming non-IID data challenges and techniques that provide communication-efficient solutions in federated learning. The study highlights the most used non-IID data types, learning models, and datasets in federated learning. A systematic mapping study was performed using six digital libraries, and 193 studies were identified and analyzed after the inclusion and exclusion criteria were applied. We identified that enhancing the aggregation method and clustering are the most widely used techniques for non-IID data problems (used in 18% and 16% of the selected studies), and a quantization technique was the most common technique in studies that provide communication-efficient solutions in federated learning (used in 27% and 15% of the selected studies). Additionally, our work shows that label distribution skew is the most used case to simulate a non-IID environment, specifically, the quantity label imbalance. The supervised learning model CNN model is the most commonly used learning model, and the image datasets MNIST and Cifar-10 are the most widely used datasets when evaluating the proposed approaches. Furthermore, we believe the research community needs to consider the client's limited resources and the importance of their updates when addressing non-IID and communication challenges to prevent the loss of valuable and unique information. The outcome of this systematic study will benefit federated learning users, researchers, and providers. [ABSTRACT FROM AUTHOR]

Space Information Network (SIN) has significant benefits of providing communication anywhere at any time. This feature offers an innovative way for conventional wireless customers to access enhanced internet services by using SIN. However, SIN's characteristics, such as naked links and maximum signal latency, make it difficult to design efficient security and routing protocols, etc. Similarly, existing SIN authentication techniques can't satisfy all of the essentials for secure communication, such as privacy leaks or rising authentication latency. The article aims to develop a novel blockchain-based access authentication mechanism for SIN. The proposed scheme uses a blockchain application, which has offered anonymity to mobile users while considering the satellites' limited processing capacity. The proposed scheme uses a blockchain application, which offers anonymity to mobile users while considering the satellites' limited processing capacity. The SIN gains the likelihood of far greater computational capacity devices as technology evolves. Since authenticating in SIN, the technique comprises three entities: low Earth orbit, mobile user, and network control centre. The proposed mutual authentication mechanism avoids the requirement of a ground station, resulting in less latency and overhead during mobile user authentication. Finally, the new blockchain-based authentication approach is being evaluated with AVISPA, a formal security tool. The simulation and performance study results illustrate that the proposed technique delivers efficient security characteristics such as low authentication latency, minimal signal overhead and less computational cost with group authentication. [ABSTRACT FROM AUTHOR]

Osteosarcoma is one of the most widespread causes of bone cancer globally and has a high mortality rate. Early diagnosis may increase the chances of treatment and survival however the process is time-consuming (reliability and complexity involved to extract the hand-crafted features) and largely depends on pathologists' experience. Convolutional Neural Network (CNN--an end-to-end model) is known to be an alternative to overcome the aforesaid problems. Therefore, this work proposes a compact CNN architecture that has been rigorously explored on a Small Osteosarcoma histology Image Dataaseet (a high-class imbalanced dataset). Though, during training, class-imbalanced data can negatively affect the performance of CNN. Therefore, an oversampling technique has been proposed to overcome the aforesaid issue and improve generalization performance. In this process, a hierarchical CNN model is designed, in which the former model is non-regularized (due to dense architecture) and the later one is regularized, specifically designed for small histopathology images. Moreover, the regularized model is integrated with CNN's basic architecture to reduce overfitting. Experimental results demonstrate that oversamplingmight be an effective way to address the imbalanced class problem during training. The training and testing accuracies of the non-regularized CNN model are 98% & 78% with an imbalanced dataset and 96%& 81% with a balanced dataset, respectively. The regularized CNNmodel training and testing accuracies are 84% & 75% for an imbalanced dataset and 87% & 86% for a balanced dataset. [ABSTRACT FROM AUTHOR]

The rapid advancement of the Internet and digital payments has transformed the landscape of financial transactions, leading to both technological progress and an alarming rise in cybercrime. This study addresses the critical issue of financial fraud detection in the era of digital payments, focusing on enhancing operational risk frameworks to mitigate the increasing threats. The objective is to improve the predictive performance of fraud detection systems using machine learning techniques. The methodology involves a comprehensive data preprocessing and model creation process, including one‐hot encoding, feature selection, sampling, standardization, and tokenization. Six machine learning models are employed for fraud detection, and their hyperparameters are optimized. Evaluation metrics such as accuracy, precision, recall, and F1‐score are used to assess model performance. Results reveal that XGBoost and Random Forest outperform other models, achieving a balance between false positives and false negatives. The study meets the requirements for fraud detection systems, ensuring accuracy, scalability, adaptability, and explainability. This paper provides valuable insights into the efficacy of machine learning models for financial fraud detection and emphasizes the importance of striking a balance between false positives and false negatives. [ABSTRACT FROM AUTHOR]

Internet of things grew swiftly and many services, software, sensors-embedded electronic devices and related protocols were developed and still in progress with full swing. Internet of things enabling physically existing things to see, hear, think and perform a notable task by allowing them to talk to each other and share useful information while making decision and caring-on/out their important tasks. Internet of things is greatly promoted by wireless sensor network as it becomes a perpetual layer for it. Wireless sensor network works as a base-stone for most of the Internet of things applications. There are severe general and specific threats and technical challenges to Internet of things–based sensor networks which must overcome to ensure adaptation and diffusion of it. Most of the limitations of wireless sensor networks are due to its resource constraint objects nature. The specified open research challenges in Internet of things–based sensor network are power consumption, network lifespan, network throughput, routing and network security. To overcome aforementioned problems, this work aimed to prolong network lifetime, improve throughput, decrease packet latency/packet loss and further improvise in encountering malicious nodes. To further tune the network lifetime in terms of energy, wireless harvesting energy is suggested in proposed three-layer cluster-based wireless sensor network routing protocol. The proposed mechanism is a three-tier clustering technique with implanted security mechanism to encounter malicious activities of sensor nodes and to slant them into blacklist. It is a centred-based clustering protocol, where selection of cluster head and grid head is carried out by sink node based on the value of its cost function. Moreover, hardware-based link quality estimators are used to check link effectiveness and to further improve routing efficiency. At the end, excessive experiments have been carried out to check efficacy of the proposed protocol. It outperforms most of its counterpart protocols such as fuzzy logic–based unequal clustering and ant colony optimization–based routing hybrid, Artificial Bee Colony-SD, enhanced three-layer hybrid clustering mechanism and energy aware multi-hop routing in terms of network lifetime, network throughput, average energy consumption and packet latency. [ABSTRACT FROM AUTHOR]

In video surveillance, person tracking is considered as challenging task. Numerous computer vision, machine and deep learning–based techniques have been developed in recent years. Majority of these techniques are based on frontal view images/video sequences. The advancement of convolutional neural network reforms the way of object tracking. The network layers of convolutional neural network models trained on a number of images or video sequences improve speed and accuracy of object tracking. In this work, the generalization performance of existing pre-trained deep learning models have investigated for overhead view person detection and tracking, under different experimental conditions. The object tracking method Generic Object Tracking Using Regression Networks (GOTURN) which has been yielding outstanding tracking results in recent years is explored for person tracking using overhead views. This work mainly focused on overhead view person tracking using Faster region convolutional neural network (Faster-RCNN) in combination with GOTURN architecture. In this way, the person is first identified in overhead view video sequences and then tracked using a GOTURN tracking algorithm. Faster-RCNN detection model achieved the true detection rate ranging from 90% to 93% with a minimum false detection rate up to 0.5%. The GOTURN tracking algorithm achieved similar results with the success rate ranging from 90% to 94%. Finally, the discussion is made on output results along with future direction. [ABSTRACT FROM AUTHOR]

Cloud computing is a recent tendency in IT that moves computing and data away from desktop and hand-held devices into large scale processing hubs and data centers respectively. It has been proposed as an effective solution for data outsourcing and on demand computing to control the rising cost of IT setups and management in enterprises. However, with Cloud platforms user’s data is moved into remotely located storages such that users lose control over their data. This unique feature of the Cloud is facing many security and privacy challenges which need to be clearly understood and resolved. One of the important concerns that needs to be addressed is to provide the proof of data integrity, i.e., correctness of the user’s data stored in the Cloud storage. The data in Clouds is physically not accessible to the users. Therefore, a mechanism is required where users can check if the integrity of their valuable data is maintained or compromised. For this purpose some methods are proposed like mirroring, checksumming and using third party auditors amongst others. However, these methods use extra storage space by maintaining multiple copies of data or the presence of a third party verifier is required. In this paper, we address the problem of proving data integrity in Cloud computing by proposing a scheme through which users are able to check the integrity of their data stored in Clouds. In addition, users can track the violation of data integrity if occurred. For this purpose, we utilize a relatively new concept in the Cloud computing called “Data Provenance”. Our scheme is capable to reduce the need of any third party services, additional hardware support and the replication of data items on client side for integrity checking. [ABSTRACT FROM AUTHOR]

In this article, to monitor the fields with square and circular geometries, three energy-efficient routing protocols are proposed for underwater wireless sensor networks. First one is sparsity-aware energy-efficient clustering, second one is circular sparsity-aware energy-efficient clustering, and the third one is circular depth–based sparsity-aware energy-efficient clustering routing protocol. All three protocols are proposed to minimize the energy consumption of sparse regions, whereas sparsity search algorithm is proposed to find sparse regions and density search algorithm is used to find dense regions of the network field. Moreover, clustering is performed in dense regions to minimize redundant transmissions of a data packet, while sink mobility is exploited to collect data from sensor nodes with an objective of minimum energy consumption. A depth threshold ( d th ) value is also used to minimize number of hops between source and destination for less energy consumption. Simulation results show that our schemes perform better than their counter-part schemes (depth-based routing and energy-efficient depth-based routing) in terms of energy efficiency. [ABSTRACT FROM AUTHOR]

Islamophobia is a sentiment against the Muslim community; recently, atrocities towards Muslim communities witnessed this sentiment globally. This research investigates the correlation between how news stories covered by mainstream news channels impede the hate speech/Islamophobic sentiment. To examine the objective mentioned above, we shortlisted thirteen mainstream news channels and the ten most widely reported Islamophobic incidents across the globe for experimentation. Transcripts of the news stories are scraped along with their comments, likes, dislikes, and recommended videos as the users' responses. We used a word embedding technique for sentiment analysis, e.g ., Islamophobic or not, three textual variables, video titles, video transcripts, and comments. This sentiment analysis helped to compute metric variables. The I-score represents the extent of portrayals of Muslims in a particular news story. The next step is to calculate the canonical correlation between video transcripts and their respective responses, explaining the relationship between news portrayal and hate speech. This study provides empirical evidence of how news stories can promote Islamophobic sentiments and eventually atrocities towards Muslim communities. It also provides the implicit impact of reporting news stories that may impact hate speech and crime against specific communities., Competing Interests: Muhammad Asif is an Academic Editor for PeerJ Computer Science., (© 2022 Ali et al.)