Sayeed Salih, Omayma Husain, Refan Mohamed Almohamedh
et al.
Generative Artificial Intelligence (GAI) is revolutionizing digital marketing by auto-content creation, personalized customer experience, and data-driven decisions. This study conducts a systematic literature review and case study analysis to explore GAI applications, benefits, and challenges in modern digital marketing. Drawing on an extensive analysis of academic journals and industry publications, the current research examines leading GAI software such as ChatGPT, DALL-E, MidJourney, Jasper.ai, and Synthesia based on how they aid in content creation, visual design, and video production. The research also provides real-world case studies in multiple industries, such as retail and fashion, food and beverages, and travel and tourism. The case findings illustrated how GAI augments marketing automation, facilitates customer engagement, and amplifies brand engagement, resulting in greater customer satisfaction, higher conversion rates, and better campaign performance. Although it has several benefits, the adoption of GAI is hampered by several critical barriers, such as data privacy, ethical risks, worker resistance, quality control issues, and infrastructure constraints. This research pinpoints these essential challenges and offers practical solutions. It provides actionable insights for businesses seeking to leverage GAI for competitive advantage in the evolving digital landscape by bridging the gap between theory and practice. The findings contribute to the growing discourse on AI-driven marketing strategies and lay the foundation for future research on GAI's long-term impact on consumer engagement and brand loyalty.
Abstract In cyberspace, intrusion and detection constitute dynamic and continuous game processes, where data streams are generated incrementally during intrusion. To mitigate intrusions and safeguard assets effectively, it is imperative to take prompt actions based on real-time detection and analysis of the currently available data streams. However, existing approaches that rely on complete and clean data struggle to keep pace with the continuous real-time flow of new network data. To address this issue, we introduce IL-IDS (Incremental Learning for Intrusion Detection Systems), a novel intrusion detection approach that utilizes incremental learning to enable accurate and timely detection of intrusions in real-world scenarios, where the need for real-time processing and learning from newly generated traffic data is paramount. IL-IDS performs in scenarios with limited data availability, where it initially transforms textual data streams into vectorized representations and leverages a variation autoencoder (VAE) to compress these vectors, efficiently extracting their latent features. Then a classifier is trained to distinguish attack and normal behaviors, and a three-way decision method is employed to establish a boundary for ambiguous data that pose challenges in direct classification. Concurrently, threat intelligence is integrated into this process to enhance the accuracy of decision-making. We validate the effectiveness and efficiency of IL-IDS with experiments on real-world deployments during an international activity, highlighting its robustness and reliability in intrusion detection applications, especially under conditions of confined data streams. Notably, IL-IDS has exhibited comparable accuracy and recall results, and attains exceptional 99.93% precision and 96.83% F1-score, which demonstrates a notable improvement of 5.27% and 2.59% respectively in comparison to intrusion detection models trained on complete and readily available data.
Abstract The ability to measure similarity or distance between data points is critical for various analytical tasks, including classification, clustering, and anomaly detection. However, traditional distance metrics such as Euclidean, Manhattan, and Hamming often struggle with mixed data types, varying attribute scales, and noise, limiting their robustness in diverse datasets. This paper introduces the Standard Deviation Score (SD-score), a novel similarity metric designed to address these challenges. By transforming traditional distance values into standard deviation units relative to a target point, the SD-score enables robust and interpretable similarity assessments. Extensive experimental evaluations demonstrate that the SD-score consistently outperforms conventional metrics in accuracy, precision, recall, and F-score within the k-Nearest Neighbors classification framework. Also, a comprehensive evaluation of the SD-score’s performance across Gaussian, skewed, and multimodal distributions showed promising results in the cluster coherence experiment, in which the Silhouette score was measured through the K-means clustering algorithm, emphasizing its adaptability to real-world data complexities. Additionally, the experiments detail improved handling of mixed numerical, ordinal, and categorical data types through a unified framework. The proposed metric incorporates inherent normalization mechanisms, reducing sensitivity to outliers and ensuring consistency across varying data scales and distributions, making it a versatile tool for real-world applications. This advancement in similarity measurement paves the way for more accurate and efficient data analysis across multiple domains.
Computer engineering. Computer hardware, Information technology
Abstract Machine learning, a revolutionary and advanced technology, has been widely applied in the field of stock trading. However, training an autonomous trading strategy which can effectively balance risk and Return On Investment without human supervision in the stock market with high uncertainty is still a bottleneck. This paper constructs a Bayesian-inferenced Gated Recurrent Unit architecture to support long-term stock price prediction based on characteristics of the stock information learned from historical data, augmented with memory of recent up- and-down fluctuations occur in the data of short-term stock movement. The Gated Recurrent Unit architecture incorporates uncertainty estimation into the prediction process, which take care of decision-making in an ever-changing dynamic environment. Three trading strategies were implemented in this model; namely, a Price Model Strategy, a Probabilistic Model Strategy, and a Bayesian Gated Recurrent Unit Strategy, each leveraging the respective model’s outputs to optimize trading decisions. The experimental results show that, compared with the standard Gated Recurrent Unit models, the modified model exhibits a huge tremendous/dramatic advantage in managing volatility and improving return on investment Return On Investment. The results and findings underscore the significant potential of combining Bayesian inference with machine learning to operate effectively in chaotic decision-making environments.
The combinatorial problem Max-Cut has become a benchmark in the evaluation of local search heuristics for both quantum and classical optimisers. In contrast to local search, which only provides average-case performance guarantees, the convex semidefinite relaxation of Max-Cut by Goemans and Williamson, provides worst-case guarantees and is therefore suited to both the construction of benchmarks and in applications to performance-critic scenarios. We show how extended floating point precision can be incorporated in algebraic subroutines in convex optimisation, namely in indirect matrix inversion methods like Conjugate Gradient, which are used in Interior Point Methods in the case of very large problem sizes. Also, an estimate is provided of the expected acceleration of the time to solution for a hardware architecture that runs natively on extended precision. Specifically, when using indirect matrix inversion methods like Conjugate Gradient, which have lower complexity than direct methods and are therefore used in very large problems, we see that increasing the internal working precision reduces the time to solution by a factor that increases with the system size.
Maruf Misaal, Lai Fatt Chuah, Mokhtar Kasypi
et al.
In an interconnected world dominated by global trade and intricate supply chain management, the transportation and management of dangerous cargo such as flammable liquids, toxic chemicals and radioactive materials, present multifaceted challenges. These hazardous substances pose significant environmental and health risks, necessitating rigorous safety measures and regulatory oversight. This comprehensive overview examines the various types of dangerous cargo, their environmental implications and notable case studies, highlighting the critical importance of international cooperation and stringent regulations. It delves into the regulatory frameworks governing the transport of hazardous materials by rail, sea, air and land, emphasizing the pivotal role of institutions like the International Maritime Dangerous Goods Code and the Environmental Protection Agency. Analysis indicates a need for improved response times in monitoring programs, necessitating adaptability to diverse environments and specific circumstances. Monitoring and impact assessment programs within emergency response frameworks differ from those aimed at detecting long-term trends in physical, biological and chemical variables.
Chemical engineering, Computer engineering. Computer hardware
Vu Tuan Hai, Nguyen Tan Viet, Jesus Urbaneja
et al.
Quantum compilation is the process of converting a target unitary operation into a trainable unitary represented by a quantum circuit. It has a wide range of applications, including gate optimization, quantum-assisted compiling, quantum state preparation, and quantum dynamic simulation. Traditional quantum compilation usually optimizes circuits for a single target. However, many quantum systems require simultaneous optimization of multiple targets, such as thermal state preparation, time-dependent dynamic simulation, and others. To address this, we develop a multi-target quantum compilation algorithm to improve the performance and flexibility of simulating multiple quantum systems. Our benchmarks and case studies demonstrate the effectiveness of the algorithm, highlighting the importance of multi-target optimization in advancing quantum computing. This work lays the groundwork for further development and evaluation of multi-target quantum compilation algorithms.
Abstract Film and movie genres play a pivotal role in captivating relevant audiences across interactive multimedia platforms. With a focus on entertainment, streaming providers are increasingly prioritizing the automatic generation of movie genres within cloud-based media services. In service management, the integration of a hybrid convolutional network proves to be instrumental in effectively distinguishing between a diverse array of video genres. This classification process not only facilitates more refined recommendations and content filtering but also enables targeted advertising. Furthermore, given the frequent amalgamation of components from various genres in cinema, there arises a need for social media networks to incorporate real-time video classification mechanisms for accurate genre identification. In this study, we propose a novel architecture leveraging deep learning techniques for the detection and classification of genres in video films. Our approach entails the utilization of a bidirectional long- and short-term memory (BiLSTM) network, augmented with video descriptors extracted from EfficientNet-B7, an ImageNet pre-trained convolutional neural network (CNN) model. By employing BiLSTM, the network acquires robust video representations and proficiently categorizes movies into multiple genres. Evaluation on the LMTD dataset demonstrates the substantial improvement in the performance of the movie genre classifier system achieved by our proposed architecture. Notably, our approach achieves both computational efficiency and precision, outperforming even the most sophisticated models. Experimental results reveal that EfficientNet-BiLSTM achieves a precision rate of 93.5%. Furthermore, our proposed architecture attains state-of-the-art performance, as evidenced by its F1 score of 0.9012.
A central challenge for ensuring the success of software projects is to assure the convergence of developers' and users' views. While the availability of large amounts of user data from social media, app store reviews, and support channels bears many benefits, it still remains unclear how software development teams can effectively use this data. We present an LLM-powered approach called DeeperMatcher that helps agile teams use crowd-based requirements engineering (CrowdRE) in their issue and task management. We are currently implementing a command-line tool that enables developers to match issues with relevant user reviews. We validated our approach on an existing English dataset from a well-known open-source project. Additionally, to check how well DeeperMatcher works for other languages, we conducted a single-case mechanism experiment alongside developers of a local project that has issues and user feedback in Brazilian Portuguese. Our preliminary analysis indicates that the accuracy of our approach is highly dependent on the text embedding method used. We discuss further refinements needed for reliable crowd-based requirements engineering with multilingual support.
Muhammed Ugur, Raghavendra Pradyumna Pothukuchi, Abhishek Bhattacharjee
Brain-computer interfaces (BCIs) connect biological neurons in the brain with external systems like prosthetics and computers. They are increasingly incorporating processing capabilities to analyze and stimulate neural activity, and consequently, pose unique design challenges related to ethics, law, and policy. For the first time, this paper articulates how ethical, legal, and policy considerations can shape BCI architecture design, and how the decisions that architects make constrain or expand the ethical, legal, and policy frameworks that can be applied to them.
This paper presents LLM4SecHW, a novel framework for hardware debugging that leverages domain specific Large Language Model (LLM). Despite the success of LLMs in automating various software development tasks, their application in the hardware security domain has been limited due to the constraints of commercial LLMs and the scarcity of domain specific data. To address these challenges, we propose a unique approach to compile a dataset of open source hardware design defects and their remediation steps, utilizing version control data. This dataset provides a substantial foundation for training machine learning models for hardware. LLM4SecHW employs fine tuning of medium sized LLMs based on this dataset, enabling the identification and rectification of bugs in hardware designs. This pioneering approach offers a reference workflow for the application of fine tuning domain specific LLMs in other research areas. We evaluate the performance of our proposed system on various open source hardware designs, demonstrating its efficacy in accurately identifying and correcting defects. Our work brings a new perspective on automating the quality control process in hardware design.
By treating data and models as the source code, Foundation Models (FMs) become a new type of software. Mirroring the concept of software crisis, the increasing complexity of FMs making FM crisis a tangible concern in the coming decade, appealing for new theories and methodologies from the field of software engineering. In this paper, we outline our vision of introducing Foundation Model (FM) engineering, a strategic response to the anticipated FM crisis with principled engineering methodologies. FM engineering aims to mitigate potential issues in FM development and application through the introduction of declarative, automated, and unified programming interfaces for both data and model management, reducing the complexities involved in working with FMs by providing a more structured and intuitive process for developers. Through the establishment of FM engineering, we aim to provide a robust, automated, and extensible framework that addresses the imminent challenges, and discovering new research opportunities for the software engineering field.
Heterogeneous Information Network(HIN) typically contains different types of nodes and interactions. Richer semantic information and complex relationships have posed significant challenges to current representation learning in HINs. Although most existing approaches typically use predefined meta-paths to capture heterogeneous semantic and structural information, they suffer from high cost and low coverage. In addition, most existing methods cannot precisely and effectively capture and learn influential high-order neighbor nodes. Accordingly, this study attempts to address the problems of meta-paths and influential high-order neighbor nodes with a proposed original HIN-HG model. HIN-HG generates a hyperadjacency graph of the HIN, precisely and effectively capturing the influential neighbor nodes of the target nodes. Then, convolutional neural networks are adopted with a multichannel mechanism to aggregate different types of neighbor nodes under different relationships. HIN-HG can automatically learn the weights of different neighbor nodes and meta-paths without manually specifying them. Meanwhile, nodes similar to the target node can be captured in the entire graph as higher-order neighbor nodes and the representation of the target node can be effectively updated through information propagation. The experimental results of HIN-HG on three real datasets-DBLP, ACM, and IMDB demonstrate the improved performance of HIN-HG compared with state-of-the-art methods in HIN representation learning, including HAN, GTN, and HGSL. HIN-HG exhibits improved accuracy of node classification by 5.6 and 5.7 percentage points on average in the multiple classification evaluation indices Macro-F1 and Micro-F1, respectively, thus improving the accuracy and effectiveness of node classification.
Multi-person pose estimation (MPE) remains a significant and intricate issue in computer vision. This is considered the human skeleton joint identification issue and resolved by the joint heat map regression network lately. Learning robust and discriminative feature maps is essential for attaining precise pose estimation. Even though the present methodologies established vital progression via feature map’s interlayer fusion and intralevel fusion, some studies show consideration for the combination of these two methodologies. This study focuses upon three phases of pre-processing stages like occlusion elimination, suppression strategy, and heat map methodology to lessen noise within the database. Subsequent to pre-processing errors will be eliminated by employing the quantization phase by embracing the pose detector. Lastly, Image-Guided Progressive Graph Convolution Network (IGP-GCN) has been built for MPE. This IGP-GCN consistently learns rich fundamental spatial information by merging features inside the layers. In order to enhance high-level semantic information and reuse low-level spatial information for correct keypoint representation, this also provides hierarchical connections across feature maps of the same resolution for interlayer fusion. Furthermore, a missing connection between the output high level information and low-level information was noticed. For resolving the issue, the effectual shuffled attention mechanism has been proffered. This shuffle intends to support the cross-channel data interchange between pyramid feature maps, whereas attention creates a trade-off between the high level and low-level representations of output features. This proffered methodology can be called Occlusion Removed_Image Guided Progressive Graph Convolution Network (OccRem_IGP-GCN), and, thus, this can be correlated with the other advanced methodologies. The experimental outcomes exhibit that the OccRem_IGP-GCN methodology attains 98% of accuracy, 93% of sensitivity, 92% of specificity, 88% of f1-score, 42% of relative absolute error, and 30% of mean absolute error.
Tea Miotti, Francesco Sansone, Veronica Lolli
et al.
The increase of greenhouse gases into the atmosphere represents today one of the most global concern. The inevitable depletion of fossil fuels and the adverse climate changes push the scientific community to seek renewable and sustainable sources of fuel. In this scenario microalgae can be potentially exploited as renewable and environmentally friendly fuel resources. Wastewaters (WW) can be used as culture media reducing the costs associated to their cultivation. Hence, the goal of this study was to examine the effect of an organic rich WW on Chlorella vulgaris growth and fatty acid methyl esters (FAME) profile. This strain shows high biomass productivity thriving in a wide range of WWs and is able to shift its metabolism from autotrophic to hetero/mixotrophic one. Glycerol can be used to convey metabolism towards lipids production. Therefore, C. vulgaris was cultivated in dairy waste (DWW) with different concentrations of glycerol under both metabolisms. When C. vulgaris was cultivated under mixotrophy attained a high biomass yield compared to heterotrophy. The highest biomass yield (1.72 g L-1) was obtained with 10 mL of glycerol in DWW compared to the control (1.08 g L-1). When a two-phase metabolism was adopted, that is the first ten days under mixotrophy followed by the last five days in heterotrophy (MHD), the biomass was almost doubled with 2 mL of glycerol in DWW. FAME profile reveled that compared to the control the highest saturated fatty acids (SFA), monounsaturated fatty acids (MUFA), and polyunsaturated fatty acids (PUFA) content were obtained under heterotrophy with 10 mL of glycerol, under MHD with 2 mL and with 4 mL of glycerol (46.73%wt, 41.79%wt, and 30.34%wt, respectively). A preliminary analysis on the saturated and unsaturated components of the FAME suggests that lipids extracted from C. vulgaris biomass cultivated mixotrophically and heterorophically in DWW could represents a feedstock to be exploited for biodiesel production.
Chemical engineering, Computer engineering. Computer hardware
Software testing is one of the crucial supporting processes of the software life cycle. Unfortunately for the software industry, the role is stigmatized, partly due to misperception and partly due to treatment of the role. The present study aims to analyze the situation to explore what restricts computer science and software engineering students from taking up a testing career in the software industry. To conduct this study, we surveyed 88 Pakistani students taking computer science or software engineering degrees. The results showed that the present study supports previous work into the unpopularity of testing compared to other software life cycle roles. Furthermore, the findings of our study showed that the role of tester has become a social role, with as many social connotations as technical implications.
A vector partition function is the number of ways to write a vector as a non-negative integer-coefficient sum of the elements of a finite set of vectors $Δ$. We present a new algorithm for computing closed-form formulas for vector partition functions as quasi-polynomials over a finite set of pointed polyhedral cones, implemented in the ``calculator'' computer algebra system. We include an exposition of previously known theory of vector partition functions. While our results are not new, our exposition is elementary and self-contained.
Image splicing combines images from different sources into one image, resulting in inconsistencies in the illumination direction, noise, and other characteristics of the image.Currently, most methods detect forged areas based on the inconsistency of noise in stitched images;however, the accuracy of noise estimation for image blocks of different sizes is generally not high, resulting in a low True Positive Rate(TPR), and the detection fails when the noise difference is small.To solve this problem, a noise estimation method based on adaptive Quaternion Singular Value Decomposition(QSVD) is proposed.The image is segmented by super-pixels, and the noise of these super-pixels is estimated by adaptive QSVD.Combined with image brightness, the image noise-brightness function is established by polynomial fitting, and the minimum distance measure from each super-pixel to the function curve is obtained.To improve detection accuracy, the color temperature feature of the super-pixel is extracted using a color temperature estimation algorithm.The distance measure and color temperature feature are fused as the final feature vector.The stitching region is located by FCM fuzzy clustering.Experiments on the Columbia IPDED splicing image dataset demonstrate that the detection TPR value of this method on the unprocessed image set is at least 8.21 percentage points highter than that of the comparison method.The method is robust to Gaussian blur, JPEG compression, and Gamma correction.