Search results

This paper discusses data-collection strategies that use digitized historical newspaper archives to study social conflicts and social movements from a global and historical perspective focusing on nationalist movements. I present an analysis of State-Seeking Nationalist Movements (SSNMs) dataset I, which includes news articles reporting on state-seeking activities throughout the world from 1804 to 2013 using the New York Times and the Guardian/Observer. In discussing this new source of data and its relative value, I explain the various benefits and challenges involved with using digitized historical newspaper archives for world-historical analysis of social movements. I also introduce strategies that can be used to detect and minimize some potential sources of bias. I demonstrate the utility of the strategies introduced in this paper by assessing the reliability of the SSNM dataset I and by comparing it to alternative datasets. The analysis presented in the paper also compares the labor-intensive manual data-coding strategies to automated approaches. In doing so, it explains why labor-intensive manual coding strategies will continue to be an invaluable tool for world-historical sociologists in a world of big data.

The objective of the proposed work is to identify the most commonly occurring non–small cell carcinoma types, such as adenocarcinoma and squamous cell carcinoma, within the human population. Another objective of the work is to reduce the false positive rate during the classification.

In this work, a hybrid method using convolutional neural networks (CNNs), extreme gradient boosting (XGBoost) and long-short-term memory networks (LSTMs) has been proposed to distinguish between lung adenocarcinoma and squamous cell carcinoma. To extract features from non–small cell lung carcinoma images, a three-layer convolution and three-layer max-pooling-based CNN is used. A few important features have been selected from the extracted features using the XGBoost algorithm as the optimal feature. Finally, LSTM has been used for the classification of carcinoma types. The accuracy of the proposed method is 99.57 per cent, and the false positive rate is 0.427 per cent.

The proposed CNN–XGBoost–LSTM hybrid method has significantly improved the results in distinguishing between adenocarcinoma and squamous cell carcinoma. The importance of the method can be outlined as follows: It has a very low false positive rate of 0.427 per cent. It has very high accuracy, i.e. 99.57 per cent. CNN-based features are providing accurate results in classifying lung carcinoma. It has the potential to serve as an assisting aid for doctors.

It can be used by doctors as a secondary tool for the analysis of non–small cell lung cancers.

It can help rural doctors by sending the patients to specialized doctors for more analysis of lung cancer.

In this work, a hybrid method using CNN, XGBoost and LSTM has been proposed to distinguish between lung adenocarcinoma and squamous cell carcinoma. A three-layer convolution and three-layer max-pooling-based CNN is used to extract features from the non–small cell lung carcinoma images. A few important features have been selected from the extracted features using the XGBoost algorithm as the optimal feature. Finally, LSTM has been used for the classification of carcinoma types.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

Software defect prediction (SDP) is a critical aspect of software quality assurance, aiming to identify and manage potential defects in software systems. In this paper, we have proposed a novel hybrid approach that combines Gray Wolf Optimization with Feature Selection (GWOFS) and multilayer perceptron (MLP) for SDP. The GWOFS-MLP hybrid model is designed to optimize feature selection, ultimately enhancing the accuracy and efficiency of SDP. Gray Wolf Optimization, inspired by the social hierarchy and hunting behavior of gray wolves, is employed to select a subset of relevant features from an extensive pool of potential predictors. This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.

The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets. This feature selection process harnesses the cooperative hunting behavior of wolves, allowing for the exploration of critical feature combinations. The selected features are then fed into an MLP, a powerful artificial neural network (ANN) known for its capability to learn intricate patterns within software metrics. MLP serves as the predictive engine, utilizing the curated feature set to model and classify software defects accurately.

The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness. The model achieves a remarkable training accuracy of 97.69% and a testing accuracy of 97.99%. Additionally, the receiver operating characteristic area under the curve (ROC-AUC) score of 0.89 highlights the model’s ability to discriminate between defective and defect-free software components.

Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions. The goal is to enhance SDP’s accuracy, relevance and efficiency, ultimately improving software quality assurance processes. The confusion matrix further illustrates the model’s performance, with only a small number of false positives and false negatives.

An abundance of techniques has been presented so forth for waste classification but, they deliver inefficient results with low accuracy. Their achievement on various repositories is different and also, there is insufficiency of high-scale databases for training. The purpose of the study is to provide high security.

In this research, optimization-assisted federated learning (FL) is introduced for thermoplastic waste segregation and classification. The deep learning (DL) network trained by Archimedes Henry gas solubility optimization (AHGSO) is used for the classification of plastic and resin types. The deep quantum neural networks (DQNN) is used for first-level classification and the deep max-out network (DMN) is employed for second-level classification. This developed AHGSO is obtained by blending the features of Archimedes optimization algorithm (AOA) and Henry gas solubility optimization (HGSO). The entities included in this approach are nodes and servers. Local training is carried out depending on local data and updations to the server are performed. Then, the model is aggregated at the server. Thereafter, each node downloads the global model and the update training is executed depending on the downloaded global and the local model till it achieves the satisfied condition. Finally, local update and aggregation at the server is altered based on the average method. The Data tag suite (DATS_2022) dataset is used for multilevel thermoplastic waste segregation and classification.

By using the DQNN in first-level classification the designed optimization-assisted FL has gained an accuracy of 0.930, mean average precision (MAP) of 0.933, false positive rate (FPR) of 0.213, loss function of 0.211, mean square error (MSE) of 0.328 and root mean square error (RMSE) of 0.572. In the second level classification, by using DMN the accuracy, MAP, FPR, loss function, MSE and RMSE are 0.932, 0.935, 0.093, 0.068, 0.303 and 0.551.

The multilevel thermoplastic waste segregation and classification using the proposed model is accurate and improves the effectiveness of the classification.

This research navigates the confluence of data analytics, machine learning, and artificial intelligence to revolutionize the management of urban services in smart cities. The study thoroughly investigated with advanced tools to scrutinize key performance indicators integral to the functioning of smart cities, thereby enhancing leadership and decision-making strategies. Our work involves the implementation of various machine learning models such as Logistic Regression, Support Vector Machine, Decision Tree, Naive Bayes, and Artificial Neural Networks (ANN), to the data. Notably, the Support Vector Machine and Bernoulli Naive Bayes models exhibit robust performance with an accuracy rate of 70% precision score. In particular, the study underscores the employment of an ANN model on our existing dataset, optimized using the Adam optimizer. Although the model yields an overall accuracy of 61% and a precision score of 58%, implying correct predictions for the positive class 58% of the time, a comprehensive performance assessment using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metrics was necessary. This evaluation results in a score of 0.475 at a threshold of 0.5, indicating that there's room for model enhancement. These models and their performance metrics serve as a key cog in our data analytics pipeline, providing decision-makers and city leaders with actionable insights that can steer urban service management decisions. Through real-time data availability and intuitive visualization dashboards, these leaders can promptly comprehend the current state of their services, pinpoint areas requiring improvement, and make informed decisions to bolster these services. This research illuminates the potential for data analytics, machine learning, and AI to significantly upgrade urban service management in smart cities, fostering sustainable and livable communities. Moreover, our findings contribute valuable knowledge to other cities aiming to adopt similar strategies, thus aiding the continued development of smart cities globally.

A zero-day vulnerability is a complimentary ticket to the attackers for gaining entry into the network. Thus, there is necessity to device appropriate threat detection systems and establish an innovative and safe solution that prevents unauthorised intrusions for defending various components of cybersecurity. We present a survey of recent Intrusion Detection Systems (IDS) in detecting zero-day vulnerabilities based on the following dimensions: types of cyber-attacks, datasets used and kinds of network detection systems.

Purpose: The study focuses on presenting an exhaustive review on the effectiveness of the recent IDS with respect to zero-day vulnerabilities.

Methodology: Systematic exploration was done at the IEEE, Elsevier, Springer, RAID, ESCORICS, Google Scholar, and other relevant platforms of studies published in English between 2015 and 2021 using keywords and combinations of relevant terms.

Findings: It is possible to train IDS for zero-day attacks. The existing IDS have strengths that make them capable of effective detection against zero-day attacks. However, they display certain limitations that reduce their credibility. Novel strategies like deep learning, machine learning, fuzzing technique, runtime verification technique, and Hidden Markov Models can be used to design IDS to detect malicious traffic.

Implication: This paper explored and highlighted the advantages and limitations of existing IDS enabling the selection of best possible IDS to protect the system. Moreover, the comparison between signature-based and anomaly-based IDS exemplifies that one viable approach to accurately detect the zero-day vulnerabilities would be the integration of hybrid mechanism.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

This study aims to use a unique customer-information data set from a Norwegian bank to identify how small changes in firm-specific factors correlate with the risk of a client subsequently being involved in suspicious transactions. It provides insight into the importance of updating client risk based on changes in transaction volume and credit risk to enable effective resource use in transaction monitoring.

Changes in a firm’s bank use and accounting data were tested against subsequent flagged and reported customers to identify which changes led to a significant increase in the probability of engaging in a transaction identified as suspicious. Prioritizing resources to firms that remain suspicious after further controls can improve the risk-based approach and prioritize detection efforts. The main factors were customer probability of default (credit score), size and changes in customer characteristics. The cross-sectional data set contained administrative data on 8,538 corporate customers (219 with suspicious transactions that were subsequently flagged, 64 of which were reported). A binomial logit model was used.

Changes in transaction volume and bank use are significant in predicting subsequent suspicious transactions. Customer credit score changes were significantly positively correlated with the likelihood of flagging and reporting. Change is a stronger indicator of suspicious transactions than the level. Thus, frequent updating of client risk and using a scale rather than risk categories can improve client risk monitoring. The results also showed that the current anti-money laundering (AML) system is size-dependent; the greater the change in customer size, the greater the probability of the firm subsequently engaging in a suspicious transaction.

Client risk classification, monitoring changes in a client’s use of the bank and business risk should receive more attention.

The authors demonstrate that client risk classifications should be dynamic and sensitive to even small changes, including monitoring the client’s credit risk changes.

Directing AML efforts to clients with characteristics indicating risk and monitoring changes in factors contributing to risk can increase efficiency in detecting money laundering.

To the best of the authors’ knowledge, this is the first study to focus on changes in a firm's use of a bank and link this to the probability of detecting a suspicious transaction.

The purpose of this study is to explore and use artificial intelligence (AI) techniques for identifying the relevant attributes necessary to file a suspicious activity report (SAR) using historical customer transactions. This method is known as predictive modeling, a statistical approach which uses machine learning algorithm to predict outcomes by using historical data. The models are applied to a modified data set designed to mimic transactions of retail banking within the USA.

Machine learning classifiers, as a subset of AI, are trained using transactions that meet or exceed the minimum threshold amount that could generate an alert and report a SAR to the government authorities. The predictive models are developed to use customer transactional data to predict the probability that a transaction is reportable.

The performance of the machine learning classifiers is determined in terms of accuracy, misclassification, true positive rate, false positive rate and false negative rate. The decision tree model provided insight in terms of the attributes relevant for SAR filing based on the rule-based criteria of the algorithm.

This research is part of emerging studies in the field of compliance where AI/machine learning technology is used for transaction monitoring to identify relevant attributes for suspicious activity reporting. The research methodology may be replicated by other researchers, Bank Secrecy Act/anti-money laundering (BSA/AML) officers and model validation analysts for BSA/AML compliance models.