Ensure Data Privacy Research Articles

Empowering safe and secure autonomy: Federated learning in the era of autonomous driving

Artificial Intelligence (AI) has a significant impact on empowering autonomous driving systems to perceive and interpret the environment effectively. However, ensuring data privacy and security in autonomous driving systems is a critical challenge. To surmount these hurdles, federated learning has emerged as an effective strategy. Federated learning is a decentralized machine learning approach that facilitates the cooperative training of models across a diverse set of connected devices, enabling them to collectively learn and improve their performance, while preserving data privacy. This approach eliminates the necessity of sharing raw data and only involves sharing model updates with a central aggregator, thereby ensuring privacy and minimizing data exposure. This paper examines the implementation of federated learning in autonomous driving. It explores the principles of federated learning, including decentralized training, local model updates, model aggregation, privacy preservation, iterative learning, and heterogeneity handling. Two specific approaches, Deep Federated Learning (DFL) and End-to-End Federated Learning, are discussed, highlighting their benefits in enhancing privacy and maintaining prediction accuracy. The paper also discusses the applications of federated learning in communication and control aspects of autonomous driving. It emphasizes the scalability, adaptability, edge computing, real-time learning, federated transfer learning, and privacy-preserving data sharing as potential future prospects for federated learning in autonomous driving. Overall, federated learning offers a unique opportunity to address privacy concerns in autonomous driving systems while harnessing the collective intelligence of a fleet of vehicles. It has the potential to revolutionize the field and contribute to the development of safe and secure autonomous driving technologies.

Intelligent Chatbot for Personalized Healthcare Assistant

This work addresses the growing demand for personalized healthcare by leveraging advancements in artificial intelligence (AI). The objective is to create an intelligent chatbot system within the healthcare sector, functioning as a virtual assistant to deliver personalized and easily accessible healthcare information. The chatbot employs Natural Language Processing (NLP) techniques and machine learning algorithms to comprehend and respond to user queries on diverse healthcare topics. It is equipped with an extensive knowledge base comprising the latest medical research `and best practices. Additionally, the project emphasizes ensuring data privacy and security, aligning with healthcare regulations and industry standards.

Federated Learning-based neural networks for airline passenger satisfaction prediction

Preserving user data privacy is paramount for airlines. However, achieving highly accurate predictions of passenger satisfaction while safeguarding the privacy of individual companys data remains a considerable challenge. To achieve this objective, we utilized a privacy-preserving machine learning technique known as Federated Learning (FL). FL allows model training on decentralized devices while ensuring data security and privacy. The FL process comprises client training processes, communication rounds, and weight aggregation. We simulate FL principles using multiple processes to enable distributed learning. Clients preprocess data and train local models, ensuring data privacy. Communication rounds involve clients downloading the global model, local training, and transmitting updates to a central server. Weight aggregation methods like Federated Averaging merge these updates, preserving data privacy. Additionally, we leverage Artificial Neural Networks (ANNs) as foundational techniques. ANNs consist of input, hidden, and output layers, with weight adjustments based on real value differences to achieve accuracy. Our approach combines FL with ANNs to demonstrate FLs potential in privacy-preserving predictive analytics. We use the Airline Passenger Satisfaction dataset for modeling and evaluate the impact of neural network depth and submodel quantity on prediction accuracy. Our experimental results reveal that neither the depth of neural networks nor the number of submodels significantly affects prediction accuracy. FL emerges as a promising approach to balance data privacy and prediction accuracy effectively.

REVIEWING THE TRANSFORMATIONAL IMPACT OF EDGE COMPUTING ON REAL-TIME DATA PROCESSING AND ANALYTICS

Edge computing has emerged as a pivotal paradigm shift in the realm of data processing and analytics, revolutionizing the way organizations handle real-time data. This review presents a comprehensive review of the transformational impact of edge computing on real-time data processing and analytics. Firstly, the review delves into the fundamental concepts of edge computing, elucidating its architectural framework and highlighting its distinct advantages over traditional cloud-centric approaches. By distributing computational resources closer to data sources, edge computing mitigates latency issues and enhances responsiveness, thereby enabling real-time data processing at the edge. Furthermore, this review explores how edge computing facilitates the seamless integration of analytics capabilities into edge devices, empowering organizations to derive actionable insights at the source of data generation. Leveraging advanced analytics algorithms, such as machine learning and artificial intelligence, edge computing enables autonomous decision-making and predictive analytics in real time, fostering innovation across diverse industry verticals. Moreover, the review examines the transformative implications of edge computing on various sectors, including healthcare, manufacturing, transportation, and smart cities. By enabling localized data processing and analytics, edge computing enhances operational efficiency, ensures data privacy and security, and unlocks new opportunities for business optimization and value creation. This review underscores the profound impact of edge computing on real-time data processing and analytics, revolutionizing the way organizations harness data to drive informed decision-making and gain competitive advantage in today's dynamic business landscape. As edge computing continues to evolve, its transformative potential is poised to redefine the future of data-driven innovation and digital transformation.
 Keywords: Edge, Computing, Analytics, Data, Impact, Review.

PPPCT: Privacy-Preserving framework for Parallel Clustering Transcriptomics data

Single-cell transcriptomics data provides crucial insights into patients’ health, yet poses significant privacy concerns. Genomic data privacy attacks can have deep implications, encompassing not only the patients’ health information but also extending widely to compromise their families’. Moreover, the permanence of leaked data exacerbates the challenges, making retraction an impossibility. While extensive efforts have been directed towards clustering single-cell transcriptomics data, addressing critical challenges, especially in the realm of privacy, remains pivotal. This paper introduces an efficient, fast, privacy-preserving approach for clustering single-cell RNA-sequencing (scRNA-seq) datasets. The key contributions include ensuring data privacy, achieving high-quality clustering, accommodating the high dimensionality inherent in the datasets, and maintaining reasonable computation time for big-scale datasets. Our proposed approach utilizes the map-reduce scheme to parallelize clustering, addressing intensive calculation challenges. Intel Software Guard eXtension (SGX) processors are used to ensure the security of sensitive code and data during processing. Additionally, the approach incorporates a logarithm transformation as a preprocessing step, employs non-negative matrix factorization for dimensionality reduction, and utilizes parallel k-means for clustering. The approach fully leverages the computing capabilities of all processing resources within a secure private cloud environment. Experimental results demonstrate the efficacy of our approach in preserving patient privacy while surpassing state-of-the-art methods in both clustering quality and computation time. Our method consistently achieves a minimum of 7% higher Adjusted Rand Index (ARI) than existing approaches, contingent on dataset size. Additionally, due to parallel computations and dimensionality reduction, our approach exhibits efficiency, converging to very good results in less than 10 seconds for a scRNA-seq dataset with 5000 genes and 6000 cells when prioritizing privacy and under two seconds without privacy considerations.Availability and implementationCode and datasets availability: https://github.com/University-of-Windsor/PPPCT.

Role of Artificial Intelligence in Surgical Decision-Making: A Comprehensive Review

Artificial intelligence (AI) has emerged as a promising technology that can revolutionize surgical decision-making (SDM). This comprehensive review aims to explore the current state of AI in SDM and highlight its benefits, challenges, and future directions. The integration of AI in SDM offers numerous advantages. AI algorithms can analyze medical images, such as radiographs, computed tomography scans, and magnetic resonance imaging, to detect abnormalities and assist in pre-operative assessments. By leveraging electronic health records, AI can provide personalized surgical recommendations based on patient-specific data.Additionally, AI can analyze genetic data to assess genetic predispositions and tailor treatment plans accordingly. Intra-operatively, AI can aid in real-time analysis of surgical videos and imaging, helping surgeons identify critical structures and guide precise incisions. AI algorithms can also monitor physiological indicators to detect early signs of complications and predict outcomes, improving intra-operative decision-making. Post-operatively, AI can analyze vital signs, imaging, and patient data to detect complications, provide outcomes analysis, and facilitate personalized patient care. However, challenges and limitations exist. Data quality and availability, interpretability of AI algorithms, data security, integration into surgical workflows, and regulatory considerations are important challenges. Addressing these challenges involves ensuring data privacy, developing transparent AI models, establishing robust infrastructure, engaging clinicians, and establishing regulatory frameworks. AI-powered surgical robots and systems can enhance surgical precision and automation. Improvements in interpretability and explainability foster trust and ethical considerations. Also, data sharing and collaboration advancements could refine AI algorithms’ accuracy and generalizability. Personalized medicine and precision surgery are achieved through AI integration. Also, education and training could benefit from AI-powered decision support systems.

DIGITAL MARKETING IN TOURISM: A REVIEW OF PRACTICES IN THE USA AND AFRICA

Digital marketing has become an indispensable tool in the tourism industry, shaping the way destinations engage with travelers and promoting economic growth. This study provides a comprehensive review of digital marketing practices in the USA and Africa, shedding light on the similarities, differences, and emerging trends. In the USA, a mature and competitive tourism market, digital marketing strategies are highly sophisticated. Utilizing platforms such as social media, search engine optimization (SEO), and content marketing, American destinations strive to capture the attention of a diverse and discerning audience. The integration of data analytics and personalized marketing campaigns has allowed for precise targeting, enhancing the overall effectiveness of promotional efforts. Additionally, the USA's tourism industry has embraced influencer collaborations and immersive technologies to create compelling narratives and experiences. Contrastingly, in Africa, the digital marketing landscape is characterized by a blend of traditional and modern approaches. While some regions are still grappling with infrastructural challenges, others are leveraging digital platforms to showcase their rich cultural and natural attractions. Social media campaigns, mobile applications, and partnerships with travel influencers are gaining traction to enhance visibility. Moreover, the emergence of online travel agencies and booking platforms has facilitated easier access for international tourists interested in exploring the diverse offerings of the African continent. Despite regional disparities, both the USA and Africa face common challenges such as ensuring data privacy, adapting to rapidly evolving technologies, and fostering sustainable tourism practices. As the tourism industry continues to recover from global disruptions, the importance of digital marketing as a catalyst for growth and resilience cannot be overstated. This study contributes to the understanding of digital marketing in tourism by presenting a comparative analysis of practices in the USA and Africa. The insights derived from this review offer valuable guidance for industry stakeholders, policymakers, and marketers seeking to navigate the dynamic landscape of digital promotion in the tourism sector.
 Keywords: Digital Marketing, USA, Africa, Business, Innovation, Review.

Artificial Intelligence (AI) Ethics in Accounting

The rapid advancement of artificial intelligence (AI) has revolutionized the accounting profession, automating tasks, identifying patterns, and improving accuracy. However, the increasing reliance on AI raises ethical concerns regarding privacy, bias, transparency, and accountability. This research paper delves into the ethical considerations of AI implementation in accounting practices.Thepaper begins by examining the potential benefits of AI in accounting, highlighting its ability to streamline operations, enhance efficiency, and reduce errors. However, it also acknowledges the ethical risks associated with AI, including data privacy breaches, biased decision-making, lack of transparency, and accountability issues.The paper proposes a framework for responsible AI implementation in accounting to address these ethical concerns. The framework emphasizes establishing clear ethical guidelines,ensuring data privacy and security, mitigating AI algorithms' bias, promoting AI decisionmaking transparency, and establishing accountability mechanisms.The paper further explores the role of accountants in addressing AI ethics. Accountants are responsible for upholding ethical standards and ensuring that AI systems are used responsibly and ethically. They must be aware of the ethical implications of AI and have the knowledge and skills to mitigate ethical risks.In conclusion, the paper emphasizes the need for a proactive approach to AI ethics in accounting. By establishing clear ethical guidelines, promoting responsible AI implementation, and empowering accountants with ethical knowledge and skills, the accounting profession can harness the potential of AI while upholding ethical principles and safeguarding public trust.

SecureTLM: Private inference for transformer-based large model with MPC

Transformer-based Large Models (TLM), such as generative pre-trained models (GPT), have become increasingly popular for practical applications through Deep Learning as a Service (DLaaS). They have been extensively used in natural language processing and computer vision. However, concerns regarding potential private data leakage arise with this type of inference service. While some private inference techniques can protect privacy, they often introduce high latency and approximate replacements in the design protocols, resulting in changes to the model structure and decreased accuracy. In this research, we present SecureTLM, a private inference method based on secure multi-party computation (MPC) that does not require modifications to the underlying model structure. SecureTLM offers protocols for crucial computations in TLM, such as Multiplication, Softmax, GeLU, and LayerNorm, without altering the model structure. Experimental results demonstrate that SecureTLM ensures data privacy, maintains correctness, and achieves efficiency in private inference tasks.

Blockchain and signcryption enabled asynchronous federated learning framework in fog computing

Federated learning combines with fog computing to transform data sharing into model sharing, which solves the issues of data isolation and privacy disclosure in fog computing. However, existing studies focus on centralized single-layer aggregation federated learning architecture, which lack the consideration of cross-domain and asynchronous robustness of federated learning, and rarely integrate verification mechanisms from the perspective of incentives. To address the above challenges, we propose a Blockchain and Signcryption enabled Asynchronous Federated Learning (BSAFL) framework based on dual aggregation for asynchronous cross-domain federated learning scenarios. In particular, we first design two types of signcryption schemes to secure the interaction and access control of collaborative learning between domains. Second, we construct a differential privacy approach that adaptively adjusts privacy budgets to ensure data privacy and local models' availability of intra-domain user. Furthermore, we propose an asynchronous aggregation solution that incorporates consensus verification and elastic participation using blockchain. Finally, security analysis demonstrates the security and privacy effectiveness of BSAFL, and the evaluation on real datasets further validates the high model accuracy and performance of BSAFL.

Ensuring Data Privacy and Security in AI-Enabled E-commerce Platforms

The integration of artificial intelligence (AI) into e-commerce has brought remarkable advancements, significantly enhancing how businesses interact with customers and manage operations.

The role of mobile health applications in improving patient engagement and health outcomes: A critical review

Mobile health applications (apps) have revolutionized healthcare delivery by enhancing patient engagement and improving health outcomes. This critical review examines the role of mobile health apps in improving patient engagement and health outcomes. The review discusses the benefits of mobile health apps in empowering patients to manage their health, facilitating communication between patients and healthcare providers, and promoting healthy behaviors. Mobile health apps have transformed the way patients engage with their healthcare by providing them with convenient access to health information and resources. These apps enable patients to track their health metrics, such as physical activity, diet, and medication adherence, allowing for better self-management of chronic conditions. By empowering patients to take control of their health, mobile health apps can lead to improved health outcomes and reduced healthcare costs. Furthermore, mobile health apps facilitate communication between patients and healthcare providers, enabling remote monitoring and virtual consultations. This improved communication can lead to more timely interventions and better coordination of care, ultimately improving patient outcomes. Mobile health apps also promote healthy behaviors by providing patients with personalized recommendations and reminders to engage in preventive care activities. Despite their potential benefits, mobile health apps also face challenges, such as ensuring data privacy and security, and addressing disparities in access to technology. Future research should focus on evaluating the effectiveness of mobile health apps in improving patient engagement and health outcomes, and on developing strategies to overcome these challenges. In conclusion, mobile health apps have the potential to significantly improve patient engagement and health outcomes. By empowering patients to manage their health, facilitating communication with healthcare providers, and promoting healthy behaviors, mobile health apps are transforming healthcare delivery and improving patient care.

Ethical considerations in healthcare IT: A review of data privacy and patient consent issues

This paper delves into the ethical considerations in healthcare Information Technology (IT), focusing on data privacy and patient consent issues. It explores the intersection of technological advancements in healthcare IT and the ethical imperatives guiding their application, specifically examining challenges in ensuring data privacy and obtaining informed consent amidst the complexities introduced by digital health technologies. Through a review of existing ethical theories, regulatory frameworks, and the implications of artificial intelligence (AI) and big data, the paper highlights technological solutions and policy recommendations to address these ethical challenges. It emphasizes the importance of balancing innovation with ethical considerations to protect patient rights and maintain trust in the healthcare system. The paper advocates for ongoing research and stakeholder engagement to evolve ethical standards aligned with technological advancements in healthcare IT.

Real-time data acquisition and analysis for predictive modelling of mental healthcare in Indian women with menstrual disorders: unveiling insights and implications from extensive surveys

The consistency and duration of the menstrual cycle exhibit significant associations with specific psychiatric conditions throughout an individual’s lifespan. The proposed methodology surveys the relationship between psychiatric disorders and the length or regularity of the menstrual cycle and analyzes the difficulties undergone by the women. A comprehensive dataset is generated and a mathematical model using an exploratory data analytics approach is developed, in order to establish a correlation between these variables. It utilizes a cyclic methodology, leveraging shared menstrual data and a predictive model derived from vehicles to enhance network learning. A decentralized secure learning procedure is implemented to ensure data privacy and security. The transfer learning techniques helps to enhance the ability to learn from diverse data distributions in IoMT (Internet of Medical Things) networks, improve the robustness of the learning process. This approach presents a practical and effective solution for IoMT network learning, allowing each participant to contribute their individual features to collectively extract valuable insights from the data. The decentralization facilitates end-users in accessing their personal medical records while ensuring privacy, irrespective of their location and time. This system also achieves a minimal delay sensitivity of 3.2%, by providing timely access to the required information.

A distributed robust state estimation method based on alternating direction method of multipliers for integrated electricity‐heat system

AbstractIntegrated electricity‐heat system (IEHS) has been paid more and more attention in recent years for its advantage in improving energy efficiency, reducing carbon emissions and increasing renewable energy penetration. To ensure the safety, reliability and economic operation of IEHS, several centralised state estimation (SE) methods for IEHS have been proposed. However, power systems and heat systems often belong to different management entities, and there are industrial barriers such as information privacy, operational differences, and target differences between them, which leads to less applicability of centralised SE methods. In addition, the robustness of existing distributed SE methods for IEHS is not satisfactory. To this end, a distributed robust state estimation (DRSE) model for IEHS based on the alternating direction method of multipliers (ADMM) is proposed. Firstly, by introducing auxiliary state variables and measurements, a robust linear SE model based on weighted least absolute values (WLAV) is proposed. Then, second‐order cone constraints composed of auxiliary state variables are added to the SE model, leading a SOCP‐based robust SE model. Finally, the ADMM algorithm is used to solve the proposed SOCP‐based robust SE model. Simulations demonstrate that the proposed method has higher estimation accuracy in both general and strongly correlated adverse data tests and also can ensure data privacy, good robustness and high estimation accuracy. This indicates that the method proposed has good robustness and solves the problem of weak robustness of existing distributed static state estimation methods.

Artificial intelligence in respiratory care: Current scenario and future perspective.

This narrative review aims to explore the current state and future perspective of artificial intelligence (AI) in respiratory care. The objective is to provide insights into the potential impact of AI in this field. A comprehensive analysis of relevant literature and research studies was conducted to examine the applications of AI in respiratory care and identify areas of advancement. The analysis included studies on remote monitoring, early detection, smart ventilation systems, and collaborative decision-making. The obtained results highlight the transformative potential of AI in respiratory care. AI algorithms have shown promising capabilities in enabling tailored treatment plans based on patient-specific data. Remote monitoring using AI-powered devices allows for real-time feedback to health-care providers, enhancing patient care. AI algorithms have also demonstrated the ability to detect respiratory conditions at an early stage, leading to timely interventions and improved outcomes. Moreover, AI can optimize mechanical ventilation through continuous monitoring, enhancing patient comfort and reducing complications. Collaborative AI systems have the potential to augment the expertise of health-care professionals, leading to more accurate diagnoses and effective treatment strategies. By improving diagnosis, AI has the potential to revolutionize respiratory care, treatment planning, and patient monitoring. While challenges and ethical considerations remain, the transformative impact of AI in this domain cannot be overstated. By leveraging the advancements and insights from this narrative review, health-care professionals and researchers can continue to harness the power of AI to improve patient outcomes and enhance respiratory care practices. Based on the findings, future research should focus on refining AI algorithms to enhance their accuracy, reliability, and interpretability. In addition, attention should be given to addressing ethical considerations, ensuring data privacy, and establishing regulatory frameworks to govern the responsible implementation of AI in respiratory care.

Mammography with deep learning for breast cancer detection.

X-ray mammography is currently considered the golden standard method for breast cancer screening, however, it has limitations in terms of sensitivity and specificity. With the rapid advancements in deep learning techniques, it is possible to customize mammography for each patient, providing more accurate information for risk assessment, prognosis, and treatment planning. This paper aims to study the recent achievements of deep learning-based mammography for breast cancer detection and classification. This review paper highlights the potential of deep learning-assisted X-ray mammography in improving the accuracy of breast cancer screening. While the potential benefits are clear, it is essential to address the challenges associated with implementing this technology in clinical settings. Future research should focus on refining deep learning algorithms, ensuring data privacy, improving model interpretability, and establishing generalizability to successfully integrate deep learning-assisted mammography into routine breast cancer screening programs. It is hoped that the research findings will assist investigators, engineers, and clinicians in developing more effective breast imaging tools that provide accurate diagnosis, sensitivity, and specificity for breast cancer.

ORGANIZATION OF INFORMATION PROTECTION AT THE «DRIVE PETROL» ENTERPRISE USING A CRYPTOGRAPHIC ALGORITHM AES

In today's digital age, information protection is becoming a dominant task, as the number of threats in the field of cyber security is constantly increasing. In this context, the implementation of effective protection means, among which encryption takes a key place, becomes especially important. The AES (Advanced Encryption Standard) cipher appears to be an exceptionally powerful tool aimed at ensuring data privacy. Information security is an extremely important aspect in the digital age, where cyber security threats are constantly increasing. In this context, encryption becomes a necessity, and the AES (Advanced Encryption Standard) cipher appears to be an exceptionally effective tool for ensuring data privacy. AES is used to protect information by converting it into cryptographically unreadable form. Due to the high degree of complexity and the possibility of using keys of different lengths, from 128 to 256 bits, AES guarantees a high level of security. Its resistance to attacks provides reliable protection against unauthorized access. One of the key advantages of AES is its versatility – it is used in a variety of industries, including finance, medicine, telecommunications, and more. The cipher has high performance, which makes it the optimal solution for protecting confidential information in a world where security becomes a priority. The application of AES not only protects data from unauthorized access, but also contributes to the overall level of security in the digital environment, ensuring excellent compatibility with various industries and user needs.

Data privacy model using blockchain reinforcement federated learning approach for scalable internet of medical things

AbstractInternet of Medical Things (IoMT) has typical advancements in the healthcare sector with rapid potential proof for decentralised communication systems that have been applied for collecting and monitoring COVID‐19 patient data. Machine Learning algorithms typically use the risk score of each patient based on risk factors, which could help healthcare providers decide about post‐COVID‐19 care and follow‐up where the data privacy is another severe concern. The authors investigate the applicability of a distributed reinforcement learning approach in a Federated Learning (FL) multi‐disciplinary reinforcement system and explores the potential benefits of incorporating Blockchain Technology (BT) in the distributed system. Intermediate dependency features and transactions are avoided by applying Blockchain‐enabled reinforcement FL for the post‐COVID‐19 patient data of IoMT applications. The proposed approach helps to improvise clinical monitoring and ensure secure communication and data privacy in a decentralised manner. The main objective is to improve the efficiency and scalability of the reinforcement FL process in a distributed environment while ensuring data privacy and security through BT for IoMT applications. Results show that proposed approach achieve comparatively high reliability and outperforms the existing approaches.

A Hybrid Cryptographic Mechanism for Secure Data Transmission in Edge AI Networks

As Edge AI systems become more prevalent, ensuring data privacy and security in these decentralized networks is essential. In this work, a novel hybrid cryptographic mechanism was presented by combining Ant Lion Optimization (ALO) and Diffie–Hellman-based Twofish cryptography (DHT) for secure data transmission. The developed work collects the data from the created edge AI system and processes it using the Autoencoder. The Autoencoder learns the data patterns and identifies the malicious data entry. The Diffie–Hellman (DH) key exchange generates a shared secret key for encryption, while the ALO optimizes the key exchange and improves security performance. Further, the Twofish algorithm performs the data encryption using a generated secret key, preventing security threats during transmission. The implementation results of the study show that it achieved a higher accuracy of 99.45%, lower time consumption of 2 s, minimum delay of 0.8 s, and reduced energy consumption of 3.2 mJ.