EAI Endorsed Transactions on Scalable Information Systems

Secrecy Offloading Analysis of NOMA-based UAV-aided MEC in IoT Networks with Imperfect CSI and SIC

2023-12-21T19:01:30+00:00

Nonorthogonal multiple access (NOMA) increases spectrum efficacy by permitting multiple devices to share link resources. It can be used to provide convenient offloading computing services for edge devices (EDs) in unmanned aerial vehicle (UAV) and mobile-edge computing (MEC) networks. However, due to the Line-of-Sight (LoS) of UAV transmission, NOMA-based UAV-MEC systems are susceptible to information eavesdropping. In this paper, we investigate a secure offloading model for a NOMA-based UAV-aided MEC in Internet of Things (IoT) network concerning an aerial eavesdropper (EAV) that considers imperfect channel state information (ipCSI) and imperfect successive interference cancellation (ipSIC).We derive the expression of secrecy successful computation probability (SSCP) across the entire system to analyze EAV’s impact on the performance of the NOMA-based UAV-aided MEC in IoT networks. In addition, we present a formulation of an optimization problem that optimizes the SSCP through the optimization of the UAV’s altitude and location, as well as the offloading ratio. To address this issue, a genetic algorithm (GA)-based approach was implemented. The results of our study were corroborated by the Monte Carlo simulations, which assessed system performance by considering multiple system parameters including the UAV’s location, altitude, average transmit signal-to-noise ratio (SNR), and offloading ratio.

Auto imputation enabled deep Temporal Convolutional Network (TCN) model for pm2.5 forecasting

2024-02-13T06:20:28+00:00

Data imputation of missing values is one of the critical issues for data engineering, such as air quality modeling. It is challenging to handle missing pollutant values because they are collected at irregular and different times. Accurate estimation of those missing values is critical for the air pollution prediction task. Effective forecasting is a significant part of air quality modeling for a robust early warning system. This study developed a neural network model, a Temporal Convolutional Network (TCN) with an imputation block (TCN-I), to simultaneously perform data imputation and forecasting tasks. As pollution sensor data suffer from different types of missing values whose causes are varied, TCN is attempted to impute those missing values in this study and perform prediction tasks in a single model. The results prove that the TCN-I model outperforms the baseline models.

FaceNet – A Framework for Age Variation Facial Digital Images

2024-02-24T20:55:25+00:00

Automated face recognition plays a vital role in forensics. The most important evidence in the criminal investigation is the facial images captured from the crime scene, as they represent the identity of the people involved in crime. The role of law enforcement agencies is to identify the facial images from the suitable database. This information can be treated as strong evidence for the law enforcement agencies which becomes the most important evidence in global counter-terrorism initiatives. Contour of chin and cheek, distance
between different features and shapes of facial components are some of the parameters considered by the forensic experts for manual facial identification process. This process is time consuming, and it is a tedious job. To address this issue, there is a need for developing an automated face recognition system for forensics. As a result, FaceNet – a framework for age variation facial digital images is discussed in this research work. Experiments are evaluated on CSA dataset with three age variations which provides a recognition accuracy of
86.8% and performs better than the existing algorithms.

Multitask Sentiment Analysis and Topic Classification Using BERT

2024-03-04T07:25:53+00:00

In this study, a multitask model is proposed to perform simultaneous news category and sentiment classification of a diverse dataset comprising 3263 news records spanning across eight categories, including environment, health, education, tech, sports, business, lifestyle, and science. Leveraging the power of Bidirectional Encoder Representations from Transformers (BERT), the algorithm demonstrates remarkable results in both tasks. For topic classification, it achieves an accuracy of 98% along with balanced precision and recall, substantiating its proficiency in categorizing news articles. For sentiment analysis, the model maintains strong accuracy at 94%, distinguishing positive from negative sentiment effectively. This multitask approach showcases the model's versatility and its potential to comprehensively understand and classify news articles based on content and sentiment. This multitask model not only enhances classification accuracy but also improves the efficiency of handling extensive news datasets. Consequently, it empowers news agencies, content recommendation systems, and information retrieval services to offer more personalized and pertinent content to their users.

Cross-Sectional Analysis of Australian Dental Practitioners’ Perceptions of Teledentistry

2024-03-25T09:18:20+00:00

INTRODUCTION: There has been an increased use of teledentistry by dental practitioners in Australia as a response to the COVID-19 pandemic. Previous studies conducted analysing the opinions of dental practitioners were performed prior to the pandemic, and therefore it is important to determine if perceptions regarding teledentistry have changed following the outbreak.

OBJECTIVES: The aim of this study was to determine the perceptions of oral healthcare professionals regarding teledentistry in a clinical setting.

METHODS: The cross-sectional study involved an anonymous electronic questionnaire with a sample of 152 dental practitioners. The questionnaire contained 28 questions utilizing a 5-point Likert-scale to assess the perceptions of general dentists on teledentistry regarding diagnosis, accessibility, patient care, technology and finances. Chi-squared test and analysis of variance (ANOVA) were used to analyse the results and percentages of agreement and disagreement were calculated.

RESULTS: The participants of the questionnaire believed that teledentistry was effective for consultations and in the diagnosis of simple cases. They indicated large benefits of teledentistry in improving access, delivering post-operative care, and triaging patients, and found it particularly useful during the COVID-19 pandemic. However, the participants felt that teledentistry was ineffective in diagnosing complex cases such as pathology. Concerns were also raised regarding the interventional capacity of teledentistry, the quality of the technology, data security and medicolegal issues. In general, participants preferred in-person care in comparison with teledentistry. They were neutral regarding finance.

CONCLUSION: The study provided an insight into the perceptions of Australian dental practitioners regarding teledentistry post-COVID-19. Opinions have changed slightly, but there are large hurdles still to overcome before teledentistry is more widely accepted. Research should be continued to further improve teledentistry in the future.

JWTAMH: JSON Web Tokens Based Authentication Mechanism for HADOOP.

2024-03-15T08:31:54+00:00

The Hadoop platform has become a widely adopted distributed computing platform for handling large-scale data processing tasks. However, the security of the Hadoop platform has become a major concern due to the increased risk of cyber-attacks. To address this concern, various security mechanisms have been proposed for the Hadoop platform, including authentication and access control. This research paper proposes a token-based authentication mechanism to enhance the security of the Hadoop platform. The proposed mechanism utilizes a combination of Kerberos and JSON Web Tokens (JWT) for secure communication between Hadoop components. The experimental results demonstrate the effectiveness of the Single point of failure, Guessing attack, Replay Attack, Brute force attack, and Dictionary attack. The proposed model has better performance in terms of average processing time and accuracy of authentication than other models.

A novel color image encryption method using Fibonacci transformation and chaotic systems

2024-03-18T09:33:05+00:00

INTRODUCTION: With the rapid increase in network information data, the protection of image data has become a challenging task, where image encryption technology can play an important role. This paper studies color image encryption algorithms and proposes a novel method for color image encryption to enhance the security and effectiveness of image encryption.
OBJECTIVES: The purpose of this study is to effectively integrate different channel information of color images, thereby improving the effect of pixel decomposition based image encryption algorithm. Different indicators are used to analyze the effect of image encryption, and it is also compared with existing image encryption algorithms.
METHODS: Initially, through pixel decomposition, the pixel values of the R, G, B channels of the color image, each with a depth of 8 bits, are decomposed into two integers between 0-15 and combined into a new data matrix. Then, multiple rounds of scrambling are performed on the transformed matrix. Next, the Fibonacci transformation matrix is applied to the scanned matrix to further change the values of its elements. Finally, XOR diffusion operation is carried out to obtain the encrypted image.
RESULTS: Experimental results show that the proposed method achieves relatively good results in multiple image encryption indicator tests. The algorithm not only inherits the advantages of existing image encryption but also effectively integrates the information of each channel of the color image, providing better security.
CONCLUSION: This study further proves the effectiveness of image encryption algorithms based on pixel decomposition and provides a new idea for better color image encryption algorithms, which is expected to be applied to other issues such as information hiding and data protection.

An IoT-enabled device for remotely monitoring and controlling solar photovoltaic systems

2024-05-04T05:16:22+00:00

This article presents an Internet of Things (IOT) solution that focuses on managing and tracking the operation of a solar system and is intended for both home and commercial application. A MOSFET driver, a DC-DC SEPIC converter, a single-phase voltage source inverter with active clamping, and a DC-DC Landsman converter are all used by the system to condition electricity. This allows for real-time online contact with an internet server and includes measurements of the output voltage and current from the solar panel and battery to monitor DC load and AC load. The ESP32 Wi-Fi MOD and PIC microcontroller work together to seamlessly provide an online connection to the internet server. The outcomes of the experiments demonstrate how well voltage control works and how well IOT functions. Through a user-friendly GUI interface on the internet, users can effortlessly control the DC-DC converter and get real-time data on battery voltage, current, and state of charge by combining solar energy with the power source.

Fortifying Patient Data Security in the Digital Era: A Two-Layer Approach with Data Hiding and Electrocardiogram

2024-04-05T05:42:52+00:00

In an era dominated by digital technology, the imperative of securing patient data cannot be overstated. The deployment of advanced protective measures, including encryption, firewalls, and robust authentication protocols, is an absolute necessity when it comes to preserving the confidentiality and integrity of sensitive patient information. Furthermore, the establishment of stringent access controls serves as a fundamental safeguard, ensuring that only authorized personnel are granted access to this invaluable data. An innovative development in the realm of patient data protection is the utilization of ElectroCardioGram (ECG) as a unique identifier for individuals. In the context of this study, ECG data is ingeniously embedded within cover images using a technique known as Reversible Data Hiding (RDH). RDH offers a distinctive advantage by ensuring that the original image can be fully restored without loss of data after extraction. This achievement is made possible through the application of inventive pixel interpolation and histogram shifting algorithms. Crucially, the study's simulations, conducted across a diverse array of images, underscore the enhanced embedding capacity of the RDH technique while maintaining a commendable balance in terms of the Peak Signal to Noise Ratio (PSNR) and boundary map. This empirical evidence corroborates the efficacy of the approach and its potential to provide an advanced level of security for patient data in the digital landscape.

Comparative Analysis of Bitcoin Mining Machines and Their Global Environmental Impact

2024-04-30T13:22:51+00:00

The amount of power required to mine one Bitcoin (BTC) can vary significantly depending on several factors, including the type of mining hardware being used, its efficiency, the cost of electricity, and the overall network difficulty at any given time. Mining BTC involves solving complex mathematical problems to validate transactions on the blockchain network, which requires significant computational power. This research paper focuses on dedicated mining machines, combining essential data and information into a singular comparison evaluation of these machines.

An efficient Video Forgery Detection using Two-Layer Hybridized Deep CNN classifier

2024-05-03T06:50:54+00:00

Video forgery detection is crucial to combat misleading content, ensuring trust and credibility. Existing methods encounter challenges such as diverse manipulation techniques, dataset variation, real-time processing demands, and maintaining a balance between false positives and negatives. The research focuses on leveraging a Two-Layer Hybridized Deep CNN classifier for the detection of video forgery. The primary objective is to enhance accuracy and efficiency in identifying manipulated content. The process commences with the collection of input data from a video database, followed by diligent data pre-processing to mitigate noise and inconsistencies. To streamline computational complexity, the research employs key frame extraction to select pivotal frames from the video. Subsequently, these key frames undergo YCrCb conversion to establish feature maps, a step that optimizes subsequent analysis. These feature maps then serve as the basis for extracting significant features, incorporating Haralick features, Local Ternary Pattern, Scale-Invariant Feature Transform (SIFT), and light coefficient features. This multifaceted approach empowers robust forgery detection. The detection is done using the proposed Two-Layer Hybridized Deep CNN classifier that identifies the forged image. The outputs are measured using accuracy, sensitivity, specificity and the proposed Two-Layer Hybridized Deep CNN achieved 96.76%, 96.67%, 96.21% for dataset 1, 96.56%, 96.79%, 96.61% for dataset 2, 95.25%, 95.76%, 95.58% for dataset 3, which is more efficient than other techniques.

Eye Disease Detection Using Deep Learning Models with Transfer Learning Techniques

2024-05-03T07:22:24+00:00

INTRODUCTION: Diabetic Retinopathy, Cataract and Glaucoma are the major eye diseases posing significant diagnostic challenges due to their asymptotic nature at their early stages. These diseases if not detected and diagnosed at their early stages may lead to severe visual impairment and even can cause blindness in human beings. Early detection of eye diseases showed an exceptional recovery rate. Traditional diagnostic methods primarily relying on expertise in the field of ophthalmology involve a time-consuming process. With technological advancements in the field of imaging techniques, a large volume of medical images have been created which can be utilized for developing more accurate diagnostic tools in the field. Deep learning (DL) models are playing a significant role in analyzing medical images. DL algorithms can automatically learn the features which indicate eye diseases from eye image datasets. Training DL models, however, requires a significant amount of data and computational resources. To overcome this, we use advanced deep learning algorithms combined with transfer-learning techniques. Leveraging the power of deep learning, we aim to develop sophisticated models that can distinguish different eye diseases in medical image data.

OBJECTIVES: To improve the accuracy and efficiency of early detection methods, improve diagnostic precision, and intervene in these challenging ocular conditions in a timely manner.

METHODS: The well-known Deep Learning architectures VGG19, InceptionV3 and ResNet50 architectures with transfer learning were evaluated and the results are compared.

RESULTS: VGG19, InceptionV3 and ResNet50 architectures with transfer learning achieved 90.33%, 89.8% and 99.94% accuracies, respectively. The precision, recall, and F1 scores for VGG19 were recorded as 79.17%, 79.17%, and 78.21%, while InceptionV3 showed 82.56%, 82.38%, and 82.11% and ResNet50 has 96.28%, 96.2%, and 96.24%.

CONCLUSION: The Convolutional Neural Network models VGG19, Inception v3, ResNet50 combined with transfer learning achieve better results than the original Convolutional Neural Network models.

OPIN-ITP: Optimized Physics Informed Network with Trimmed Score Regression Based Insider Threats Prediction in Cloud Computing

2024-05-21T10:23:11+00:00

INTRODUCTION: Insider threats are a major issue for cyber security. In contrast to external attackers, insiders have more privileges and authorized access to data and resources, which can cause an organization great harm. To completely understand an insider's activities throughout the organization, a more sophisticated method is needed.

OBJECTIVES: Based on an organization's login activity, this study proposes a novel conceptual method for insider threat detection. Behavioural activities such as HTTP, Email and Login details are collected to create a dataset which is further processed for pre-processing using data transformation and Trimmed Score Regression (TSR).

METHODS: These pre-data are given to the feature extraction process using Deep Feature Synthesis (DFS) extraction. The extracted data are fed to Physics Informed Neural Networks (PINN) for insider threat detection.

RESULTS: The prediction process of PINN was improved through optimally choosing parameters such as learning rate and weight using Hunter-prey Optimization (HPO). The proposed model offers 68% detection rate, 98.4% accuracy, 5% FDR, 95% F1_score and 0.7005 sec execution time.

CONCLUSION: Observed outcomes are compared to other traditional approaches of validation. The contrast with traditional approaches shows that the proposed model provides better outcomes than in traditional models and is therefore a good fit for real-time threat prediction.

Enhanced Edge Detection through Binary Particle Swarm Optimization and L0 Guided Filtering

2024-07-29T07:14:51+00:00

Detecting edges holds significant importance in image processing, serving as a fundamental step in numerous computer vision applications. This paper presents an innovative method for performing edge detection by combining Binary Particle Swarm Optimization (BPSO) with L₀ Guided Filtering. The proposed method aims to address the challenge of accurately detecting edges in noisy and complex images by leveraging the benefits of both BPSO and L₀ guided filtering. The process begins with the initialization of the BPSO algorithm, where binary particles traverse the solution space to optimize parameters critical for edge detection. These optimized parameters are subsequently employed in the L₀ guided filtering framework, a sophisticated edge preserving filter known for its ability to maintain fine details while effectively reducing noise. The synergy of BPSO and L₀ guided filtering demonstrates improved adaptability to diverse image characteristics, enhancing the overall robustness of edge detection. The binary nature of BPSO allows for efficient exploration of the solution space, facilitating faster convergence to optimal parameters. Concurrently, the L₀ guided filtering ensures edge preserving smoothing, contributing to the suppression of unwanted artifacts. Experimental evaluations on benchmark datasets showcase the effectiveness of the proposed method compared to traditional edge detection techniques. The results indicate superior edge localization and reduced sensitivity to noise, highlighting the potential of the BPSO Based Edge Detection under L₀ Guided Filtering in real world applications. The presented approach offers a valuable contribution to the advancement of edge detection methodologies, demonstrating its potential for enhancing the performance of computer vision systems in various domains.

Large data density peak clustering based on sparse auto-encoder and data space meshing via evidence probability distribution

2024-08-17T00:28:46+00:00

The development of big data analysis technology has brought new development opportunities to the production and management of various industries. Through the mining and analysis of various data in the operation process of enterprises by big data technology, the internal associated data of the enterprises and even the entire industry can be obtained. As a common method for large-scale data statistical analysis, clustering technology can effectively mine the relationship within massive heterogeneous multidimensional data, complete unlabeled data classification, and provide data support for various model analysis of big data. Common big data density clustering methods are time-consuming and easy to cause errors in data density allocation, which affects the accuracy of data clustering. Therefore we propose a novel large data density peak clustering based on sparse auto-encoder and data space meshing via evidence probability distribution. Firstly, the sparse auto-encoder in deep learning is used to achieve feature extraction and dimensionality reduction for input high-dimensional data matrix through training. Secondly, the data space is meshed to reduce the calculation of the distance between the sample data points. When calculating the local density, not only the density value of the grid itself, but also the density value of the nearest neighbors are considered, which reduces the influence of the subjective selection truncation distance on the clustering results and improves the clustering accuracy. The grid density threshold is set to ensure the stability of the clustering results. Using the K-nearest neighbor information of the sample points, the transfer probability distribution strategy and evidence probability distribution strategy are proposed to optimize the distribution of the remaining sample points, so as to avoid the joint error of distribution. The experimental results show that the proposed algorithm has higher clustering accuracy and better clustering performance than other advanced clustering algorithms on artificial and real data sets.

Drone-Assisted Climate Smart Agriculture (DACSA): The design of the groundwork flow data for drone operations

2024-08-14T08:44:13+00:00

The success of precision farming hinges on effective ground support and workflow. In pursuit of this, we undertook a thorough requirement study of the system necessary for precision farming and developed a precision farming data flow model in ground support. The prototype hardware ground support and conceptual data flow provided valuable guidance in the successful realization of Drone-Assisted Climate Smart Agriculture (DACSA). Using open-source software to accommodate a range of data processing algorithms becomes crucial in operationalizing ground support for precision farming. This study has culminated in a comprehensive prototype model for precision farming operations that can be executed with confidence. The management system of flow data for precision farming has been drawn, this platform is specifically crafted to streamline agriculture operations by transforming diverse inputs into useful spatial data. To maintain the growth of the database, it is necessary to incorporate it in the entire crop cycle. The integration of this database can significantly enhance the precision of predicting plant performance. While this innovative approach is still in progress, it has already demonstrated its potential in supporting informed decision-making. For the next, it is imperative that we prioritize research aimed at creating decision-support algorithms that can effectively gather and blend information pertaining to soil, crops, and weather into actionable maps. These maps must incorporate location-specific data and be utilized by agricultural professionals for on-site decision-making. Moreover, they must be well-suited for drone usage in tasks such as monitoring, mapping, or spraying.

Cybersecurity Awareness Model with Methods: Analytical Hierarchy Process and Structural Equation Model

2024-08-14T12:22:01+00:00

This era of revolution has influenced all sectors of society, including education, where technological advancements are now integral to online teaching and learning. However, not everyone fully understands the potential negative impacts of internet usage. The purpose of this research was to investigate and analyze cybersecurity awareness. The study focused on students at Aerospace Air Marshal Suryadarma University. The research employed a quantitative design, either descriptive (where subjects are typically measured once) or experimental (where subjects are measured multiple times). A descriptive study establishes a relationship between variables, while an experimental study determines causation. To analyze the collected data, SEM AMOS was utilized to measure students' awareness of cybersecurity. The study focused on five key areas: (a) regulation, (b) internet usage, (c) password security, (d) data security, and (e) cyberattacks. Based on the research framework and these focus areas, several indicators were developed for the study. The findings concluded that students are aware of cybersecurity issues.

Development of New Spray Dust Suppression Materials in Metal Mines and Prediction of Algorithm Simulation Effect

2024-08-19T07:31:04+00:00

PROBLEM: Dust contamination in metal mining poses substantial dangers to environmental quality and human health. Modern mining operations cannot use traditional spray dust suppression methods because they are poorly adapted to changing climate conditions, low efficient, and detrimental to the environment.

INTRODUCTION: Dust pollution seriously impacts the environment and human health in metal mine operations. Traditional spray dust suppression technology has many problems, such as limited effect, environmental impact, and poor climate adaptability.

OBJECTIVES: The purpose of this article is to develop a new type of spray dust suppression material and predict its dust suppression effect through algorithm simulation. Firstly, efficient and environmentally friendly dust-reducing materials were screened, and after evaluating the dust-reducing effect under laboratory conditions, the optimal material combination was determined.

METHODS: Using computational fluid dynamics (CFD), a numerical model of the spray process was constructed to simulate the dust suppression effect of different materials under different climatic conditions.

RESULTS: The results show that the highest dust reduction efficiency of the new spray dust reduction material is more than 4.3% higher than that of the traditional material, and it shows good stability.

CONCLUSION: The new spray dust control material and its effect prediction method studied in this article provide an effective solution for dust control in metal mines, which has important theoretical value and practical application prospects.

New directions for adapting intelligent communication and standardization towards 6G

2024-02-16T07:43:38+00:00

Rapid advancements in wireless communication technology have made it easier to transfer digital data globally. With the complete assistance of artificial intelligence, the sixth-generation (6G) system—a new paradigm in wireless communication—is anticipated to be put into use between 2027 and 2030. Faster system capacity, faster data rate, lower latency, higher security, and better quality of service (QoS) in comparison to the 5G system are some of the main concerns that need to be addressed beyond 5G. Combining the growing need for more network coverage, lower latency, and greater data rates is the aim of 6G. It is recommended that to meet these needs and enable new services and applications, intelligent communication be implemented. The main enablers and facilitators for implementing intelligent communication beyond 5G are outlined in this paper. The article provides the horizon for new adaptations and standardization for integrating 6G intelligent communication in future networks and outlines the requirements and use-case scenarios for 6G. It also highlights the potential of 6G and key enablers from the standpoint of flexibility. It examines key research gaps like spectrum efficiency, network parameters, infrastructure deployment, and security flaws in past transitions while contrasting 5G and 6G communication. To overcome these challenges, modernizing 6G research domains are essential. Therefore, this review article focuses on the importance of 6G wireless communication and its network architecture, which also provides the technological paradigm shift from 5G to 6G. Furthermore, it highlights popular domains such as Artificial Intelligence, Internet of Things, Managing Big Data, Wireless Mobile networks, and Massive MIMO (Multiple Input Multiple Output), Quantum communication, Block chain Technology, Terahertz Communications (THz), Cell-free Communications and Intelligent Reflecting Surface as research objectives.

A Review on DDoS Attack in Controller Environment of Software Defined Network

2024-04-19T09:42:22+00:00

Distributed Denial of Service (DDoS) attacks pose a significant threat to the security and availability of networks. With the increasing adoption of Software-Defined Networking (SDN) and its multi-controller architectures, there is a need to explore effective DDoS attack detection mechanisms tailored to these environments. An overview of the current research on detecting DDoS attacks in SDN environments, with a focus on different detection techniques, methodologies and problems is presented in this survey paper. The survey attempt to identify the limitations and strengths of current approaches and propose potential research directions for improving DDoS detection in this context.

Bridging the Gap to 6G: Leveraging the Synergy of Standardization and Adaptability

2024-05-16T12:46:00+00:00

The field of wireless network and communication technology is evolving from generation to generation from 1G to 6G as of now till expected to be deployed and used by 2030. It is to succeed in 5G and bring significant improvements in terms of connectivity, speed, and size in next-generation communication technology. 6G aims to deal with the rising need for more rapid information speed, low latency, and wider network coverage. This intelligent communication is proposed to meet these demands and enable new services and applications. This review paper highlights the key enablers and challenges involved in implementing intelligent communication beyond 5G. The paper identifies the research gaps for incorporating beyond 5G communication networks and outlines the possible 6G key objectives from a flexibility standpoint. It reviews infrastructure deployment, network densification, spectrum capacity and network energy efficiency in predecessors to 6G. This paper emphasizes the need for standardization and adaptation of research areas to revolutionize 6G wireless communication, focusing on areas like, ultra massive MIMO, Terahertz Communications, Cell-Free Communications, Intelligent Reflecting Surface, Visible Light Communication, Internet of Things, Big Data management, Artificial Intelligence, and network connectivity techniques.

Computational Approaches for Anxiety and Depression: A Meta- Analytical Perspective

2024-06-02T06:08:56+00:00

INTRODUCTION: Psychological disorders are a critical issue in today’s modern society, yet it remains to be continuously neglected. Anxiety and depression are prevalent psychological disorders that persuade a generous number of populations across the world and are scrutinized as global problems.

METHODS: The three-step methodology is employed in this study to determine the diagnosis of anxiety and depressive disorders. In this survey, a methodical review of ninety-nine articles related to depression and anxiety disorders using different traditional classifiers, metaheuristics and deep learning techniques was done.

RESULTS: The best performance and publication trend of traditional classifiers, metaheuristic and deep learning techniques have also been presented. Eventually, a comparison of these three techniques in the diagnosis of anxiety and depression disorders has been appraised.

CONCLUSION: There is further scope in the diagnosis of anxiety disorders such as social anxiety disorder, phobia disorder, panic disorder, generalized anxiety, and obsessive-compulsive disorders. Already, there has been a lot of work has been done on conventional approaches to the prognosis of these disorders. So, there is need to need to scrutinize the prognosis of depression and anxiety disorders using the hybridization of metaheuristic and deep learning techniques. Also, the diagnosis of these two disorders among academic fraternity using metaheuristic and deep learning techniques need to be explored.

A Review of Prediction Techniques used in the Stock Market

2024-10-12T01:19:53+00:00

The prediction of stock market movements is a critical task for investors, financial analysts, and researchers. In recent years, significant advancements have been made in the field of stock prediction, driven by the integration of machine learning and data analysis techniques. Though stock market predictions are highly desired, there are many factors contributing towards volatility of the market. There is a need for extensive study and concentration on various predictive techniques to investigate different scenarios triggering such volatility. This paper reviews the latest methodologies employed for predicting stock prices, with a particular focus on the Australian stock market. Key techniques such as time series analysis like ARIMA & GARCH, machine learning models like SVM, LSTM & Neural Network, and sentiment analysis are discussed, highlighting their applications, key strengths, and some limitations.