Stock value prediction and trading, a captivating and complex research domain, continues to draw heightened attention. Ensuring profitable returns in stock market investments demands precise and timely decision-making. The evolution of technology has introduced advanced predictive algorithms, reshaping investment strategies. Essential to this transformation is the profound reliance on historical data analysis, driving the automation of decisions, particularly in individual stock contexts. Recent strides in deep reinforcement learning algorithms have emerged as a focal point for researchers, offering promising avenues in stock market predictions. In contrast to prevailing models rooted in artificial neural network (ANN) and long short-term memory (LSTM) algorithms, this study introduces a pioneering approach. By integrating ANN, LSTM, and natural language processing (NLP) techniques with the deep Q network (DQN), this research crafts a novel architecture tailored specifically for stock market prediction. At its core, this innovative framework harnesses the wealth of historical stock data, with a keen focus on gold stocks. Augmented by the insightful analysis of social media data, including platforms such as S&P, Yahoo, NASDAQ, and various gold market-related channels, this study gains depth and comprehensiveness. The predictive prowess of the developed model is exemplified in its ability to forecast the opening stock value for the subsequent day, a feat validated across exhaustive datasets. Through rigorous comparative analysis against benchmark algorithms, the research spotlights the unparalleled accuracy and efficacy of the proposed combined algorithmic architecture. This study not only presents a compelling demonstration of predictive analytics but also engages in critical analysis, illuminating the intricate dynamics of the stock market. Ultimately, this research contributes valuable insights and sets new horizons in the realm of stock market predictions.

Machine learning (ML) was used to develop classification models to predict individual tumor patients’ outcomes. Binary classification defined whether the tumor was malignant or benign. This paper presents a comparative analysis of machine learning algorithms used for breast cancer prediction. This study used a dataset obtained from the National Cancer Institute (NIH), USA, which contains 1.7 million data records. Classical and deep learning methods were included in the accuracy assessment. Classical decision tree (DT), linear discriminant (LD), logistic regression (LR), support vector machine (SVM), and ensemble techniques (ET) algorithms were used. Probabilistic neural network (PNN), deep neural network (DNN), and recurrent neural network (RNN) methods were used for comparison. Feature selection and its effect on accuracy were also investigated. The results showed that decision trees and ensemble techniques outperformed the other techniques, as they both achieved a 98.7% accuracy.

Social media platforms have allowed many people to publicly express and disseminate their opinions. A topic of considerable interest among researchers is the impact of social media on predicting the stock market. Positive or negative feedback about a company or service can potentially impact its stock price. Nevertheless, the prediction of stock market movement using sentiment analysis (SA) encounters hurdles stemming from the imprecisions observed in SA techniques demonstrated in prior studies, which overlook the uncertainty inherent in the data and consequently directly undermine the credibility of stock market indicators. In this paper, we proposed a novel model to enhance the prediction of stock market movements using SA by improving the process of SA using neutrosophic logic (NL), which accurately classifies tweets by handling uncertain and indeterminate data. For the prediction model, we use the result of sentiment analysis and historical stock market data as input for a deep learning algorithm called long short-term memory (LSTM) to predict the stock movement after a specific number of days. The results of this study demonstrated a predictive accuracy that surpasses the accuracy rate of previous studies in predicting stock price fluctuations when using the same dataset.

Cybercrime investigations rely heavily on digital evidence to establish links between suspects and the criminal conduct they are allegedly involved in. As a result, digital evidence must be protected since it is complex, volatile, and susceptible to alteration. In the digital evidence method, the chain of custody (CoC) is essential. As a result of the CoC, it is possible to establish that the evidence was never tampered with. Due to the inherent uncertainty of digital evidence, the trustworthiness of the CoC cannot be judged at this time. It is the duty of forensic examiners to challenge this inclination and publicly admit the inherent ambiguity in whatever evidence they use to make their decisions. This article suggests a new paradigm for maintaining the integrity of digital evidence in order to overcome these challenges. To handle the uncertainty generated by error-prone technologies while dealing with CoC documents, the new paradigm used a fuzzy hash inside the blockchain data structure. Traditional hashing methods are only able to tell whether two inputs are precisely the same or not because they are sensitive to even the smallest input changes. Using fuzzy hash functions, we can figure out how dissimilar two images are by comparing their similarities. As an example of how this paradigm may be applied to computer systems and make digital investigations more successful, we utilize image forensics as the focus of an in-depth look at how it works.

Digital evidence is critical in cybercrime investigations because it is used to connect individuals to illegal activity. Digital evidence is complicated, diffuse, volatile, and easily altered, and as such, it must be protected. The Chain of Custody (CoC) is a critical component of the digital evidence procedure. The aim of the CoC is to demonstrate that the evidence has not been tampered with at any point throughout the investigation. Because the uncertainty associated with digital evidence is not being assessed at the moment, it is impossible to determine the trustworthiness of CoC. As scientists, forensic examiners have a responsibility to reverse this tendency and officially confront the uncertainty inherent in any evidence upon which they base their judgments. To address these issues, this article proposes a new paradigm for ensuring the integrity of digital evidence (CoC documents). The new paradigm employs fuzzy hash within blockchain data structure to handle uncertainty introduced by error-prone tools when dealing with CoC documents. Traditional hashing techniques are designed to be sensitive to small input modifications and can only determine if the inputs are exactly the same or not. By comparing the similarity of two images, fuzzy hash functions can determine how different they are. With the symmetry idea at its core, the suggested framework effectively deals with random parameter probabilities, as shown in the development of the fuzzy hash segmentation function. We provide a case study for image forensics to illustrate the usefulness of this framework in introducing forensic preparedness to computer systems and enabling a more effective digital investigation procedure.

The adoption of electronic patient records in hospitals will provide numerous benefits, but it will also present new issues. One of these is the creation of deadlocks, which causes delays in conducting tasks such as obtaining patient information. If the underlying system is distributed, the deadlock situation gets even more problematic. The strategy for preventing deadlock requires basic information from the transaction structure and requested resources. However, in most circumstances, this information is either unavailable or ambiguous. Because the cost of processing and storing sophisticated structures (e.g., wait-for graphs) is so high for a system in comparison to an array of structures, most discovery and resolved-deadlock protocols use them. Due to imprecise knowledge in specifying the transactions’ attributes, distributed deadlock resolution methods present a new problem in dealing with uncertainty. To address this problem, a variety of fuzzy logic-based techniques have been proposed. However, very little attention has been paid to dealing with ambiguous, vague, incomplete, and inconsistent information about transaction attributes in a single framework. In this paper, we used neutrosophic logic, a generalization of fuzzy logic, to solve the problem of uncertainty in distributed real-time deadlock-resolving systems. The proposed method is structured to reflect multiple types of knowledge and relations among all features and tripartitions the transactions’ features include validation factor degree, slackness degree, degree of deadline-missed transaction based on the degree of membership of truthiness, degree of membership of indeterminacy, and degree of membership of falsity. We developed a tool set and conducted experiments using benchmark datasets. There is an increase in detection rate and a large drop in rollback rate when this new strategy is used. Our technology resolved all database deadlocks and significantly increased database performance by up to three orders of magnitude.