Blockchain technology is frequently referred to as the fourth industrial revolution, which will change the world. Blockchain technology sometimes referred to as distributed ledger technology creates an ecosystem that is decentralized, dispersed, and devoid of central authority. Since Bitcoin's introduction, research into non-financial use cases has continued to expand the technology's usefulness. Through categorization and integrity verification in both the industry and processing terminals, the blockchain paradigm regulates data collection and dissemination instances. From the Bitcoin digital currency system to more contemporary uses, the origin of this technology is traced. This paper presents essential ideas about Blockchain and offers our perspective on the challenges, the future changes, and the predictable effect of Blockchain. Blockchain has created an immense pool of opportunities for every field of life, e-commerce, supply chain, sustainable smart cities, or adoption of e-governance. The impact on various fields by use of Blockchain is discussed, also raising the research investigation questions.
Depression refers to a condition in which mental function continues to deteriorate and adversely affects daily life. Therefore, it is very important to diagnose depression accurately in the early stages. This study extracted depression-related features such as head pose, gaze, and facial expression changes from facial images and proposed a model for diagnosing depression using a decision tree. The proposed model learned the data using two databases. The performance of the algorithm was evaluated through the confusion matrix, receiver operating characteristic (ROC) curve, and achieved value 0.99 for area under the curve (AUC).
Cardiac tumors are uncontrolled bursts of tissues and cells in the heart. The heart is composed of several different tissues, cells, or valves as well as neurons and these neurons, tissues, cells, or valves are prone to heart actions. Usually, the heart, or Cardiac, only makes new tissues, cells or valves when old or damaged ones need to be replaced. If the growth is out of control for any reason, the cells or valves will continue to separate, causing an inflammation called a tumor. Cardiac tumors can happen at any age, but most of them happen between the ages of 55 and 65 in adults and between 3 and 12 in kids. Cancer treatment has been a major research area of medical researchers for several decades; however, the development of new treatments takes time and money. The utilization of computer technology in therapeutic resolution support is currently extensive and invasive across a large range of medicinal region for instance, cancer research, Cardiac tumors, gastroenterology etc. MRI is the feasible alternative nowadays for the study of tumor in soft tissues. Parallel computing is a computation form in which numerous computations are carried out in parallelism manner, running on the concept that huge issues can repeatedly be divided into slighter ones that are resolved at the similar point.
Optimizing resource allocation in Network Functions Virtualization (NFV) deployment remains a challenging problem due to the complex interactions between network functions and the limited resources available at the network edge. Deep reinforcement learning (DRL) has achieved impressive results in a variety of domains. This paper presents EdgeGym, a reinforcement learning environment to simulate the edge network contexts and constraints for NFV resource allocation. EdgeGym allows researchers and practitioners to evaluate and compare different reinforcement learning algorithms for optimizing the allocation of resources in NFV environments, taking into account various constraints such as affinity policies and maximum latency. We demonstrate the effectiveness of EdgeGym through extensive experiments on training and action masking efficiency. EdgeGym provides a reliable framework for advancing the DRL agent performance in NFV resource allocation and paves the way for further research in this area.
ThDeveloping a goal-oriented model for digital forensic evidence is critical because the reconstructed scenarios help forensic analysts not only understand steps taken by threat actors, but also present digital evidence in ways that are understandable in the court of law. In this paper, we propose a goal-oriented approach to reconstruct attack scenarios based on a forensic evidence acquisition model. We first build the model, from which digital forensic examiners can trace and collect forensic evidence, then formalize the graph and evaluate the semantics based on the evidence found on digital devices and their supporting environments. Finally, we apply the model to a typical scenario based on the semantics of the model. Our preliminary results show that our model can give any practitioner or investigator formal instructions to gather and rebuild the evidence in the simulation or real-world environment.
This research focuses on the individual stress caused by organizational transformation and how artificial intelligence (AI) might help. With the aid of AI, a big number of people and process may be supervised without the need of human intervention. Their health and well-being statistics may be computed, saved, and linked with specified moments. This technology also assists in making fewer mistakes by keeping a constant check on employee for their safety and efficiency. In this study, various research papers and articles have been reviewed to conceptualize the changes management practices and possible area of improvements. Along with research papers, survey was conducted with 250 participants to get more in-depth knowledge of existing challenges in this field. This paper concluded with the proposal of artificial intelligence (AI) based solution for better handling of change management challenges for organizations with the focus on employee wellbeing.
As the trend to use the Internet of Things (IoT) applications and devices increases, security and privacy have become key concerns. IoT application adoption has increased significantly over time, with sensitive data frequently gathered by IoT devices, accidentally or consciously. According to recent research, numerous types of IoT devices have substantial vulnerabilities, and in many cases, no security procedures are in place to secure them. The focus of this study was the security issues of Internet protocol (IP) cameras. The vulnerabilities of IP cameras were investigated in more depth, as well as their influence on security and privacy at the user level, in order to assist companies and security experts in predicting attacker behavior and securing the systems. The objective of this study was to research and uncover the security and privacy vulnerabilities associated with an IP camera. This was accomplished by performing a direct inspection of the camera. A real-world test was carried out with a VAVA Outdoor Wireless IP Security Cam, which was employed as a home security camera. Information was gathered from numerous sources on the Internet for this purpose, and then the software and hardware were used to examine the security features of this device. The findings of this study revealed that the IP camera contains security faults and vulnerabilities that put user safety at risk.
The Arabian Gulf water could play a vital role in the context of the next modern life that should occupy as well as avail countries resources. The distinguished natural characteristically which is generally considered drawbacks from one side due to water composition such as high salinity, need a fresh look to prove the unique feature of the water in the gulf could become a significant advantage through transparency, easy access, and conductive ions to carry the electric current flow, although it is widely recognized about the Arabian Gulf water is subject to high dissolution as well snags in desalination. But Gulf water antenna could give unprecedented features that would contribute positively to the whole area in users' connection demand, government security and civilization facilities. The paper proposed Gulf Seawater Antenna Model GSAM in line with the region's condition to accommodate the natural environmental stark parameters. While the comparative result shows the fluctuation between magnitude and phase response based on frequency utilized, as well as the water surface perforation which represents a segment of the proposed contribution without compromising the environment. At the same time, the clear exponential relation between conductivity and salinity led to offering a proper water antenna identification. Overall, the investigation proposed a water antenna in the gulf region to provide significant utilities based on its unique specifications using the most significant parameters that would promise avenues for novel notions research.
The monitoring of groundwater levels of hexavalent chromium is a vital task for the US Department of Energy's (DOE) remediation efforts at the Hanford Site, a decommissioned nuclear production facility operated by the Office of Environmental Management. While previous methods have shown promise for accurately modeling contaminants of concern at DOE sites, some contaminants, such as hexavalent chromium, remain a challenge to model due to the high variability and frequency of data collection. Recent Machine Learning (ML) techniques have shown promise to automatically handle these limitations, and regression-based ML models specifically have the potential to overcome these issues due to their ability to detect seasonal trends and patterns unapparent under simple visual inspection. This study focuses on several Autoregressive Integrated Moving Average (ARIMA)-based models, such as traditional ARIMA and Seasonal ARIMA, for modeling hexavalent chromium across 488 wells within the Hanford Site's 100-area from 1997 to 2022. After preprocessing by resampling the data to regular, monthly intervals and performing linear interpolation and normalization, we demonstrate the ARIMA models' predictive capabilities with time-series visualizations on training and testing data, as well as the models' forecasting results through 2024. The collected data sets enhance the ARIMA-based models' understanding of contaminant fate and transport at the Hanford site, which yields more reliable forecasts. There is potential for this data to be used to optimize pump and treat operations in terms of identifying appropriate periods of time and wells to recover the greatest amount of hexavalent chromium from the subsurface.
The U. S. Department of Energy's Office of Environmental Management handles one of the world's most significant groundwater and soil remediation efforts. The Hanford Site in Washington State contains several decommissioned nuclear production reactors, laboratories, and chemical reprocessing plants, which are the source of various contaminants of concern in groundwater reservoirs. While previous research has yielded significant insight into the behavior of groundwater contaminants at the Site, plumes that contain carcinogens such as hexavalent chromium can be challenging to model using traditional physical and statistical models. Recently, machine learning models, and specifically artificial neural network models, have shown promise in complementing existing methods due to their effectiveness in modeling sequential data, adaptability to different datatypes, and non-fixed parameters with the ability for fine-tuning. In this study, we propose a Long Short-Term Memory-based framework for predicting hexavalent chromium concentration at the Hanford Site using a dataset containing 2912 measurements collected from 121 wells between 2000 and 2008. Both the unoptimized and optimized versions of the model are evaluated using standard metrics including mean squared error, root mean squared error, and coefficient of determination. The optimized model achieves a mean squared error of 921.0, root mean squared error of 30.35, and coefficient of determination score of 0.94, indicating that the use of such network architecture may prove useful in aiding existing modeling operations for contaminants of concern at the Hanford Site and other similar facilities.
With the advancement of time and the advancement scientific knowledge, the blockchain technology has expanded in various applications. The security and data privacy of employee recruitment system has been compromised. Therefore, hiring managers can enhance job satisfaction by adopting blockchain technology to secure human resource data management. This paper provides current research status, issues and a deep investigation on the blockchain technology's potential use in the management of human resources.
Malware continues to gain momentum as it becomes more sophisticated against detection. Monitoring tools and antivirus software do not have the ability to keep up with the ever-going changes of these malignant variants. Due to these dilemmas, machine learning has gained popularity in classification and detection of malware related data. In this study, two separate datasets, Malware-Exploratory and CIC-MalMem-2022, undergo a series of supervised and unsupervised learning procedures to first gather information for observation. The developed model in this research utilizes three clustering algorithms for analysis, K-Means, DBSCAN, and GMM. The model also uses seven classification algorithms for predicting malware including Decision Tree, Random Forest, Ada Boost, KNeighbors, Stochastic Gradient Descent, Extra Trees, and Gaussian Naïve Bayes. Results have shown that Malware-Exploratory dataset averaged an accuracy score of 90% while CIC-MalMem-2022 dataset averaged a score of 99%. Both datasets also showed consistency across all three clustering algorithms. Besides, correlation between variables do not necessarily need to be highly related for malware detection. Future studies will determine if the results remain stable against feature selection and genetic algorithms.
Quantum computing presents potential advantages over classical computing in terms of computational complexity. Therefore, it is expected for quantum machine learning applications to have improvements in capacity and learning efficiency over classical machine learning methods. This paper aims to present a Systematic Literature Review of articles published between 2017 and 2022, identifying, analyzing, and comparing different proposals of quantum machine learning applications for network intrusion detection systems (IDS). This study focused on identifying papers that implemented quantum machine learning algorithms in the context of intrusion detection systems. The main algorithms found were variational hybrid quantum-classical, with models based on quantum support vector machines and quantum neural networks. Benefits compared to classical models were observed and described, such as reduced training time and improved classification accuracy for attacking traffic.
In this study, we propose a blood pressure estimation algorithm that uses a convolutional neural network with long short-term memory layers. The electrocardiogram photoplethysmogram was obtained from the UCI machine learning repository dataset. The bio-signal was split into 125 Hz and 8 s intervals. Blood pressure is estimated by automatically extracting features through an end-to-end approach. Blood pressure was classified into prehypertension, hypertension, and normotension. For the hypertension classification using DBP and SBP, we achieved average F1-scores of 0.88, 0.95, and 0.79 as well as 85% overall F1-scores. The proposed algorithms satisfied the standard of the Association for the Advancement of Medical Instrumentation and obtained grade A for SBP and DBP estimation according to the British Hypertension Society standard.
The malicious actors continuously produce malicious Android applications with a COVID-19 theme in the context of the pandemic. Users frequently grant the necessary permissions to install those phoney apps without paying much attention. Android permissions are essential points of weakness. Major privacy issues often result from this vulnerability. Hackers with malicious intent have viewed the COVID-19 pandemic as an opportunity to conduct malware attacks to profit financially and advance their nefarious goals. Through COVID-19-related content, people are becoming victims of phishing scams. The android malware seen explicitly during the pandemic of Covid-19 is discussed in this study, and we next analyze malware detection methods with a focus on these Covid-19-themed malware mobile applications. This research paper attempts to identify dangerous android permissions and the malware families that erupted during the Covid-19 outbreak.
The diagnosis of diabetic retinopathy may be streamlined and expedited with the help of deep learning, which is an efficient way to help an eye specialist examine the enormous amount of retinal images. For these strategies to be effective, big datasets must be consolidated and used for training. Medical data privacy laws frequently make it impossible to gather and share patient data on a single system. In this paper, we introduce a collaborative differentially private federated learning system that enables deep learning image analysis without transferring patient data between healthcare organizations. We investigated four different machine learning algorithms—AlexNet, ResNet50, SqueezeNet1.1, and VGG16—for varying amounts of noise using a dataset of 35120 retina images divided into five classes—No Diabetic Retinopathy, Mild, Moderate, Severe, and Proliferative Diabetic Retinopathy (PDR). Our ResNet50 model outperformed the state-of-the-art diabetic retinopathy prediction models with an accuracy 83.05 % when we added no noise, and with an accuracy 79.35% with a noise multiplier of 8.0. By including our checkpoint techniques, we have reduced the total communication overhead by 49 % when compared to federated learning without checkpoints.
Scalability, security, and communication delays in the Internet of Things can be resolved using blockchain technology, which is the final piece of the puzzle. Blockchain technology may provide the IoT sector with the panacea it needs. Blockchain technology can record massive amounts of access points, allowing for the recording of data and collaboration between equipment, and providing manufacturers in the IoT sector with significant cost reductions. By removing individual points of failure, this decentralized strategy would build a more robust environment for the operation of equipment. Wondering in the era of information technology. Blockchain has attracted a lot of interest in recent decades for its ability to provide decentralized, definitive, and auditable usage in the Internet of Things (IoT). The majority of Internet of Things (IoT) devices are facing significant adaptability and privacy difficulties. This study proposes an understanding of How blockchain works with IoT for security data records.
Student attendance system is used to measure student participation in a classroom. Before pandemic attendance was taken manually like in sheets or registers. But when the pandemic hit, everything was online, so even the classes. The attendance count is a very important problem that the administrator needs to be more careful about taking during the online classes as there are many chances of a proxy happening. So, we came up with this proposed system “Student attendance using QR code” This paper proposes an attendance system that is based on the QR code-based attendance system. The students need to scan the QR in the class according to the professor instruction. By implementing this proposed system, we can reduce proxy and time in taking attendance of students. In order to design this proposed system, we are using technologies like OpenCV through python, and some libraries like MYQR, PYbase64, Pyzbar.
One of the most avoidable environmental public health problems is childhood lead exposure, which can lead to a variety of disorders such as reduced muscle coordination, stunted bone and muscle growth, damaged nervous system, impaired speech and language, and seizures. It is difficult to predict whether someone will be exposed to lead, but studies have found a correlation between lead exposure and things like household income, ethnicity or refugee status, reliance on Medicaid, older homes built before 1978 with lead paint in poor condition, proximity to industry, and people working in lead-exposed environments like manufacturing, repair, welding, or renovation jobs. We predict potential lead exposure at the zip code level using data from Massachusetts and New York's Blood Lead Levels that are publicly available. Additionally, using data gathered from news stories and other media, we offer a sentimental analysis approach based on Long Short Term Memory (LSTM) deep learning algorithm to assess how well the lead programs are being implemented in these states. Using six different machine learning algorithms, we achieved the best performance with LightGBM, with an accuracy of 83.6 percent for New York and 89.1 percent for Massachusetts and an f1-score of 0.81 and 0.83, respectively. Through the average sentimental analysis ratings for New York and Massachusetts, we found a strong correlation with elevated blood lead levels reported within the states. When compared to earlier researchers' calculations of AUC ROC scores at the individual level, our methodology yields greater AUC ROC scores.
This paper proposes a new bearing fault diagnosis method which combines sparse wavelet decomposition and graph neural network with sparse connectivity. In our proposed method, the original vibration signal is decomposed into multi-resolution features by the sparse wavelet decomposition based on three typical bearing fault frequency bands in which the bandwidths are determined by the bearing physical parameters and machine rotating speed. The sparse wavelet decomposition generates three sets of sub-bands. The energy values from each sub-band signal set are calculated to form new one-dimensional data representing the energy distribution. Again, each one-dimensional data constitutes a subgraph. Three subgraphs representing the three fault frequency bands, respectively, are sparsely connected through a connection graph. After the sparse connectivity graph is constructed, GraphSAGE is employed instead of the traditional graph convolutional network for deep learning. For the Case Western Reserve University (CWRU) and self-collected bearing datasets, our proposed method can achieve high classification accuracy of 99.73%.
