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]

In this paper, a smart home energy management system is proposed to improve the efficiency of the electricity infrastructure of residential buildings. To solve the scheduling problem of a smart building, we propose bacterial foraging ant colony optimization (HB-ACO). The primary objective of scheduling is to shift load from on-peak hours to off-peak hours to reduce electricity cost and peak-to-average ratio. A comparison of these algorithms is also presented in terms of performance parameters, electricity cost, reduction of PAR, and user comfort in terms of waiting time. The proposed techniques are evaluated using two pricing schemes: (1) time of use and (2) critical peak pricing. Moreover, coordination among home appliances is presented for real-time scheduling. We represent this as a knapsack problem and solve it through ant colony optimization algorithm. The HB-ACO shows better performance than ACO and BFA in reducing electricity cost, PAR, and increased user comfort, which is evident from the simulation results. [ABSTRACT FROM AUTHOR]

Background subtraction, being the most cited algorithm for foreground detection, encounters the major problem of proper threshold value at run time. For effective value of the threshold at run time in background subtraction algorithm, the primary component of the foreground detection process, motion is used, in the proposed algorithm. For the said purpose, the smooth histogram peaks and valley of the motion were analyzed, which reflects the high and slow motion areas of the moving object(s) in the given frame and generates the threshold value at run time by exploiting the values of peaks and valley. This proposed algorithm was tested using four recommended video sequences, including indoor and outdoor shoots, and were compared with five high ranked algorithms. Based on the values of standard performance measures, the proposed algorithm achieved an average of more than 12.30% higher accuracy results. [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]

Routing protocols plays a key role in coherent use of resources in Internet of Things (IoT). The more efficient routing scheme is, the more efficiently will nodes communicate with each other. In this paper, we present presents an efficient cluster based routing protocol for IoT. The protocol aims at increasing lifetime and stability of networks. The paper introduces a new routing scheme Modified-Percentage LEACH Protocol based on existing protocol namely Percentage LEACH. Extra amount of energy wastage is alleviated by reducing communication between Cluster Heads (CHs) and sink. Thus, it increases the lifetime of sensor nodes in IoT communication networks. It is achieved by introducing threshold calculation on each CH, which is used as basic criteria for CH election and selection. The protocol also takes into account distance parameter of nodes from sink. This protocol helps plummeting energy wastage which results in more lifetime and high throughput. The depicted protocol is compared with its parent protocol and simulation results shows high throughput and outperforms its parent protocols. [ABSTRACT FROM AUTHOR]

Abstract Textual content of citations has been widely applied to access the impact of research outputs, observe knowledge transfer across domains and generate summaries of research articles. These applications, however, experience the problem of correct identification of citational context windows, and alternately use text in a fixed-size window around the citation instance. Citation contexts might contain terms not referenced by the target citation. When application requirement is only the reference terms, this observation ought to be taken into account. This paper tries to find out whether the reference terms of a target citation can be represented as topics derived from its citation contexts or not. We, specifically, consider cases where complete statements are referred to by a citation and cases where there are no explicit reference terms. Evaluation results show that in a majority of cases, reference terms of a citation can be replaced with topics generated from its contexts. [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]

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]

Diabetic retinopathy (DR) is widely recognized as a leading cause of blindness among individuals with diabetes worldwide. Therefore, early diagnosis of DR plays a crucial role in preserving patients' vision and halting the progression of the disease to advanced stages. However, manual diagnosis of DR in clinical practice is time-consuming and susceptible to human error, especially during the early stages when the lesions associated with DR are often minute and challenging to identify. Furthermore, with the projected surge in the number of diabetic patients and a concurrent shortage of ophthalmologists, there will be insufficient healthcare professionals available to examine all individuals at risk. The application of machine- and deep learning-based techniques has proven effective in diagnosing medical images, including those related to DR. In this review, we surveyed and analyzed 55 DR grading studies published between 2018 and 2022 extracted from four academic digital libraries: Scopus, Web of Science, Google Scholar, and Science Direct. The review provides a comprehensive discussion and analysis of these selected studies, considering various aspects such as benchmark DR datasets, classification tasks, preprocessing techniques, learning approaches, and performance evaluation measures. Within the literature on DR grading, supervised-based learning techniques have been found to be more prevalent than semi-supervised learning techniques. Furthermore, researchers predominantly addressed this problem as an image-level classification task, overlooking the distinctive characteristics of lesions within each grade. Numerous proposed techniques primarily concentrate on detecting the early stages of DR, while a limited number of studies address the disease's advanced stages. The primary findings of our analysis reveal a potential direction for future research that emphasizes data- and model-centric approaches. • Proposing a taxonomy for categorizing the literature in DR grading. • Evaluating the DR benchmark datasets and highlighting their drawbacks. • Exploring various image processing methods that enhance DR models' performance. • Comparing different learning techniques used to develop DR grading models. • Highlighting open research gaps toward reliable DR grading approaches. [ABSTRACT FROM AUTHOR]

One of the key problems for researchers and network managers is anomaly detection in network traffic. Anomalies in network traffic might signal a network intrusion, requiring the use of a quick and dependable network intrusion detection system. Intrusion detection systems based on artificial intelligence (AI) techniques are gaining the interest of the research community as AI techniques have evolved in recent years. This research proposes a novel method for anomaly detection using artificial neural networks (ANNs) optimized using cuckoo search algorithm. For simulation purposes, the NSL-KDD dataset has been utilized with a 70:30 ratio where 70% of data is used for training and the remaining 30% is used for testing. The proposed model is then evaluated in terms of mean absolute error, mean square error, root-mean-square error, and accuracy. The results of the proposed work are compared with standard methods available in the literature including fuzzy clustering artificial neural network (FC-ANN), intrusion detection with artificial bee colony, neural network intrusion detection system, and selection of relevant feature. The results clearly show that the proposed method outperforms the listed standard methods. [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]