Karachi Institute of Economics and Technology

A software-defined network (SDN) is a new architecture approach for constructing and maintaining networks with the main goal of making the network open and programmable. This allows the achievement of specific network behavior by updating and installing software, instead of making physical changes to the network. Thus, SDNs allow far more flexibility and maintainability compared to conventional device-dependent architectures. Unfortunately, like their predecessors, SDNs are prone to distributed denial of service (DDoS) attacks. These attack paralyze networks by flooding the controller with bogus requests. The answer to this problem is to ignore machines in the network sending these requests. This can be achieved by incorporating classification algorithms that can distinguish between genuine and bogus requests. There is abundant literature on the application of such algorithms on conventional networks. However, because SDNs are relatively new, they lack such abundance both in terms of novel algorithms and effective datasets when it comes to DDoS attack detection. To address these issues, the present study analyzes several variants of the decision tree algorithm for detection of DDoS attacks while using two recently proposed datasets for SDNs. The study finds that a decision tree constructed with a hill climbing approach, termed the greedy decision tree, iteratively adds features on the basis of model performance and provides a simpler and more effective strategy for the detection of DDoS attacks in SDNs when compared with recently proposed schemes in the literature. Furthermore, stability analysis of the greedy decision tree provides useful insights about the performance of the algorithm. One edge that greedy decision tree has over several other methods is its enhanced interpretability in conjunction with higher accuracy.

When controlling difficult industrial processes characterised by open-loop instability and/or poor damping, predictive functional control (PFC) practitioners often face two critical design challenges. The first one arises due to the intrinsic simplicity of the PFC control algorithm that, instead of optimising the future control trajectory in real time like other predictive controllers, simply assumes constant control action, thereby producing unreliable model predictions in the long range and thus inconsistent closed-loop performance. The second issue is related to the controller tuning, which may become ambiguous and unsystematic due to the existence of an inconsistent relationship between the controller parameters and closed-loop behaviour. This paper presents a dual-loop control strategy that aims at mitigating both weaknesses simultaneously by combining the concepts of pre-stabilisation and relative tuning within the framework of predictive functional control. Two challenging industrial case studies have been analysed through computer simulations that successfully validate the efficacy of the proposal under various real world scenarios.

The two growing concepts within the domain of international marketing are global citizenship and ethical consumerism. The present study probes into how the concerns of global citizenship, environment, social, cultural, and others affect ethical consumerism, with cultural awareness as a moderating factor. Guided by “Cultural Intelligence Theory”, this study contributes to an all-rounded understanding of ethical consumer behaviour. The research approach is explanatory in nature. For this, a sample of 388 male and female consumers aged 20 to 60, purchasing domestic and imported FMCG products in Karachi, Pakistan, has been considered for the study. The data is analyzed using the technique of Structural Equation Modeling through SMART PLS 4.0 software. The results provide insights into the dynamics of how cultural intelligence and global citizenship influence the ethical consumption pattern.

Infectious diseases like COVID-19 continue to pose critical challenges globally, underscoring the need for effective control strategies that go beyond traditional vaccinations and treatments. This study introduces an advanced SEI1I2I3QCR model, uniquely incorporating fractional-order delay differential equations to account for latency periods and dynamic transmission patterns of COVID-19, improving accuracy in capturing disease progression and peak oscillations. Stability analyses of the model reveal the critical role of delay and fractional order parameters in managing disease dynamics. Additionally, we applied optimal control theory to simulate non-pharmaceutical interventions, such as quarantine and awareness campaigns, demonstrating a notable reduction in infection rates. Numerical simulations align the model closely with real-world COVID-19 data from China, validating its utility in guiding pandemic response strategies. Our findings emphasize the significance of integrating time-delay factors and fractional calculus in epidemic modeling, offering a novel framework for pandemic management through targeted, cost-effective control measures.

IoT-DS-AI nexus proposed in this book offers crucial services not only for individual health management, but also for entire population. The technologies assisting in continuous health monitoring and management using IoT sensors, ambient devices, mobile applications, data analytics and artificial intelligence algorithms hold potential to offer services to the government and other policymakers of healthcare sector. The population health trends and disease risks can be communicated to authorities using centralized dashboards, which could assist in the policy making about conducting awareness/vaccination campaigns, allocating healthcare resources, etc. Many such applications were already witnessed during COVID-19 peak duration. Moreover, IoT, DS and AI techniques also provide an insight into the status of equipment and healthcare resources including workforce at each location. Using this information, the hospitals’ leadership and state-level policymakers can relocate or hire more staff member to ensure timely response to the patients, in order to improve overall service quality for the patients. This chapter presents a detailed discussion on the use of IoT, DS and AI for population health surveillance and resource optimization.

UN has developed Sustainable Development Goals (SDGs) for highlighting a uniform framework addressing global challenges. The focus of SDGs is to improve quality of life on the planet by dealing with issues related to poverty, hunger, education, inequality, climate change, environment and health. The goals are set to be achieved by 2030 and nations around the world are implementing innovative measures to contribute to this global agenda. This chapter begins with an overview of 17 SDGs, followed by a discussion on the ways in which technology could support each SDG. A detailed account of SDG 3 has then been given and the three key technologies internet of Things (IoT), Artificial Intelligence (AI) and Data Science, which are the focus of this book have been defined. IoT, AI and DS can significantly contribute to SDG 3 by offering greater accessibility and precision in healthcare. A nexus based on these technologies, and referred as IoT-DS-AI nexus has been proposed for illustrating end-to-end technology architecture to be deployed for global healthcare systems. Finally, the roadmap to the book has been presented by listing the contents of subsequent chapters.

Personalized medicine promises to revolutionize the patient treatment by offering tailored medical services to the individual characteristics of each patient. It can improve the patient outcomes by reducing prescription errors and minimizing adverse drug reactions, as it focuses on prevention rather than reaction. The large volumes of data collected and processed by IoT-DS-AI nexus offers a unique opportunity to medical experts for developing customized treatment plans. Conventionally, the diagnosis and treatment have always been developed based on the population averages, which may not be fully effective for everyone.; however, use of smart technologies have eliminated this limitation, by providing an individual insight into genetic makeup, medical history, lifestyle factors and environmental influences. The wearable and ambient devices help to collect large amount of data from patients, which are then fed into advanced DS and AI models for developing personalized plans. This chapter first sheds light on the limitations of traditional medicine, followed by factors used for developing personalized medicine, such as genetic makeup, medical history, lifestyle, and environmental influences. Subsequently, the deployment protocols of IoT, AI and DS for developing personalized medicines are described and finally, ethical challenges associated with the domain are discussed.

It has been established so far that IoT-DS-AI nexus can offer significant assistance to the governments for achieving SDG-3. However, there are various challenges associated with the use of these technologies, mainly due to the involvement of human subject. The use of proposed nexus requires patients and general users to share lot of personal and family data, which raises privacy and security concerns; this is a crucial challenge because globally accepted standardization and legal frameworks are not yet developed. There are also issues pertaining to outdated infrastructure, need for processing high volumes of data, increasing vulnerabilities, and user resistance for adoption of technology. Some of the measures to manage these challenges include ensuring performance and reliability of the technology solutions, developing interoperable solutions and developing internationally accepted ethical, security and legal frameworks. This chapter sheds light on the major challenges and way forward for adopting the IoT-DS-AI nexus in an attempt to achieve SDG-3. Due to the increasing affordability and acceptance of IoT, DS and AI technologies by the patients and doctors, disruptive applications have been developed over the past decade. As the funds by venture capitalists, public and private sectors continue to grow in the industry, there are chances of even more rapid development and adoption. The prospect IoT, DS and AI in the healthcare is promising as new functions are being added into the healthcare products services with technological advances in all the domains of IoT-DS-AI nexus earlier illustrated in Fig. 1.4. As this nexus promises to improve the quality of care both at individual and population level, it can largely contribute to the achievement of SDG 3. The rapidly advancing capabilities in the hardware, communication techniques, big data analytics are revolutionizing the way healthcare is delivered. For example, AI techniques like predictive analytics and natural language processing are being used to anticipate patient needs and improve diagnostic accuracy. Similarly, Data Science methods such as data mining and statistical modeling help uncover patterns in patient data, leading to more personalized treatment plans. IoT devices, equipped with advanced sensors and connectivity, facilitate continuous monitoring and real-time data collection, ensuring that healthcare providers can respond promptly to any changes in a patient’s condition. Together, these technologies enhance patient outcomes, streamline healthcare operations, and pave the way for innovative treatments and interventions. The end-to-end connected healthcare system starting at the patient’s wearables or ambient sensors and ending at the central dashboards/physician’s devices is expected to arrive soon. The technology will be mainly beneficial for the chronic patients, and since chronic disease management is not a once-off event, a continuously evolving IoT-DS-AI nexus to facilitate holistic monitoring and management. Unlike the conventional healthcare systems where the diagnosis and treatment strategies were largely based on the population averages, the use of computing and communication technologies ensures highly customized medical assessment and administration (Shaik T, Wiley Interdiscip Rev: Data Min Knowl Discov 2023:e1485, 2023). However, the critical scenarios requiring generating/collecting data from multiple points involving diverse technologies and stakeholders give rise to several open issues and challenges. We present some of the major challenges and recommendations for realizing the use of IoT-DS-AI nexus in the healthcare:

Smart phones have become part and parcel of the modern lifestyle. In addition to offering usual contacting service, these devices offer a wide variety of mobile applications ranging from games to money transfer and from home automation to fitness and chronic disease management. m-Health is the concept emerged with the development and usage of mobile applications dedicated for healthcare. Such apps offer a unique opportunity for users to have control over their own health through lifestyle, diet and medication management. Moreover, the users also get a chance to remotely connect to their doctors and community for timely advise and intervention, reducing their risk levels. Thus, m-Health could largely contribute to SDG 3, as it offers a broader access to healthcare for communities who might lack conventional healthcare facilities. This chapter opens with a brief discussion on history and evolution of mobile apps, then describes most commonly available and accessible categories of mobile apps developed for a wide variety of applications including fitness tracking, remote health monitoring, epidemic tracking, and mental health monitoring. The major technologies supporting m-health and discussed along with the challenges and barriers causing hinderances for widescale adoption of m-health, and finally, future opportunities are presented.

Being able to continuously/remotely collect patient data has been the major motivation for developing wearable devices and mobile applications. These devices enable real-time monitoring of vital signs, physical activity, and other health metrics, providing valuable data for early detection of health issues, personalized treatment plans, and improved patient outcomes. The collected data is then fed into the second level of IoT-DS-AI nexus, where data cleaning, processing and analytics take place to provide a comprehensive insight into the bulky data. Various types of analysis and visualizations are offered to assist the decision-makers. Interactive dashboards, apps and other interfaces are provided for quick review of the health trends for individual patients and populations. Finally, AI comes into the picture with a focus on predicting the health trends. Since patient state is continuously monitored, a better and accurate prediction about future risk is possible. Hence, achieving SDG 3 becomes possible by having more frequent data points and more precise predictions about health risks. This chapter sheds lights into techniques from all three domains of IoT, DS and AI that offer huge potential to improve the patient outcomes in a quick and cost-effective manner as compared to the conventional healthcare systems.

In the ever-evolving landscape of technology, digital imaging stands out for the changes it has step with both art and science of visual representation. The imaging has always been crucial in the processes of medical diagnosis and prognosis, and thus offers a great contribution towards SDG 3. Recently, several technologies including Machine Learning, Deep Learning, Convolutional Neural Networks, Generative Adversarial Networks, and Recurrent Neural Networks have reshaped the way conventional imaging was done. These techniques are used for image classification, segmentation, synthesis, enhancement, and generation of medical reports. The paradigm-changing effects of Transfer Learning and Deep Reinforcement Learning in medical image interpretation and treatment optimization are expounded upon. This chapter discusses the potential of data science in digital imaging: noise reduction, edge detection, predictive modeling, CAD systems, Natural Language Processing (NLP) for text and sentiment analysis. Furthermore, the chapter presents the future impacts made by technologies and further elaborates the challenges and ethical concerns, which include data privacy and standardization. It calls for responsible innovation, transparency, and stakeholder engagement to deploy the full potential of digital imaging toward the advancement of patient-centered care and scientific discovery in reshaping healthcare delivery in the future.

Background Machine learning has tremendous potential in acute medical care, particularly in the field of precise medical diagnosis, prediction, and classification of brain tumors. Malignant gliomas, due to their aggressive growth and dismal prognosis, stand out among various brain tumor types. Recent advancements in understanding the genetic abnormalities that underlie these tumors have shed light on their histo-pathological and biological characteristics, which support in better classification and prognosis. Objectives This review aims to predict gene alterations and establish structured correlations among various tumor types, extending the prediction of genetic mutations and structures using the latest machine learning techniques. Specifically, it focuses on multi-modalities of Magnetic Resonance Imaging (MRI) and histopathology, utilizing Convolutional Neural Networks (CNN) for image processing and analysis. Methods The review encompasses the most recent developments in MRI, and histology image processing methods across multiple tumor classes, including Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. It identifies challenges in tumor classification, segmentation, datasets, and modalities, employing various neural network architectures. A competitive analysis assesses the performance of CNN. Furthermore it also implies K-MEANS clustering to predict Genetic structure, Genes Clusters prediction and Molecular Alteration of various types and grades of tumors e.g. Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. Results CNN and KNN structures, with their ability to extract highlights in image-based information, prove effective in tumor classification and segmentation, surmounting challenges in image analysis. Competitive analysis reveals that CNN and outperform others algorithms on publicly available datasets, suggesting their potential for precise tumor diagnosis and treatment planning. Conclusion Machine learning, especially through CNN and SVM algorithms, demonstrates significant potential in the accurate diagnosis and classification of brain tumors based on imaging and histo-pathological data. Further advancements in this area hold promise for improving the accuracy and efficiency of intra-operative tumor diagnosis and treatment.

Terrain Aided Navigation (TAN) technology has become increasingly important due to its effectiveness in environments where Global Positioning System (GPS) is unavailable. In recent years, TAN systems have been extensively researched for both aerial and underwater navigation applications. However, many TAN systems that rely on recursive Unmanned Aerial Vehicle (UAV) position estimation methods, such as Extended Kalman Filters (EKF), often face challenges with divergence and instability, particularly in highly non-linear systems. To address these issues, this paper proposes and investigates a hybrid two-stage TAN positioning system for UAVs that utilizes Particle Filter. To enhance the system’s robustness against uncertainties caused by noise and to estimate additional system states, a Fuzzy Particle Filter (FPF) is employed in the first stage. This approach introduces a novel terrain composite feature that enables a fuzzy expert system to analyze terrain non-linearities and dynamically adjust the number of particles in real-time. This design allows the UAV to be efficiently localized in GPS-denied environments while also reducing the computational complexity of the particle filter in real-time applications. In the second stage, an Error State Kalman Filter (ESKF) is implemented to estimate the UAV’s altitude. The ESKF is chosen over the conventional EKF method because it is more suitable for non-linear systems. Simulation results demonstrate that the proposed fuzzy-based terrain composite method achieves high positional accuracy while reducing computational time and memory usage.

Presents corrections to the paper, Corrections to “Decentralized Asynchronous Formation Planning of Multirotor Aerial Vehicles in Dynamic Environments Using Flexible Formation Graphs and Tight Trajectory Hulls”.

Deep Reinforcement Learning (DRL) is a powerful approach for generating control strategies for a variety of complex systems, representing an emerging paradigm in control applications. An important feature of Deep RL is that it does not explicitly model the process, but instead it relies on optimization-driven techniques to devise effective control policies. Despite its remarkable success in simulated environments, RL holds great potential in real-world applications. This article explores the complex challenges involved in implementing Deep Reinforcement Learning (DRL) algorithms on a cable-driven parallel robot. A key contribution of this work as specific advancement is the integration of a Proportional-Integral-Derivative (PID) controller within the RL framework, establishing a unique approach to CDPR control that leverages adaptive learning capabilities. A Reinforcement Learning (RL) agent for reference tracking is trained using the novel application of the adaptive-featured Twin Delayed Deep Deterministic (TD3) policy gradient algorithm, tailored to enhance CDPR adaptability and precision in dynamic environments. The first step is to test the performance of the trained agent on point-to-point robotic application tasks. As a result of such tasks, it is possible to evaluate the level of adaptability and performance of the RL agent. Multiple experiments are conducted to assess the versatility of the RL agent involving linear and circular scenarios. This research significantly advances the field by demonstrating the applicability of RL for complex robotic structures like CDPRs, showcasing promising results that underline the robustness and adaptability of the proposed approach. As a result of the TD3 adaptive learning process, the trained agent is able to perform the designated action in order to determine which policy stands out as the most rewarding.

The purpose of this study is to find symmetries and asymmetries in the exchange rate and macroeconomic fundamentals of advanced European markets, namely Denmark, the Euro Area, and United Kingdom, for the period of 2011 to 2022 via application of the NARDL technique. The findings reveal that interest rate affects DKK exchange rate asymmetrically in the long and short run, whereas money supply affects it in the short run. Foreign reserves are found to be helpful for all three currencies in stabilizing the exchange rate. A decline in gold price weakens GBP, DKK, and EUR in the long run. Previous studies suggest that the existence of asymmetrical relationships justifies the selection of NARDL for empirical analysis. This study makes a contribution to the existing literature, as it proves that forecasting via NARDL is also robust for analysis. The findings have significant policy implications for financial applications.

This work explores the possibility of reducing computations in a distributed estimation setup, utilizing a self organizing hierarchical particle swarm optimization algorithm. Reducing computations is essential for any application using wireless sensors in a distributed network, as the sensors need to save processing power in order to last longer. An event triggering approach is used to remove redundant computations from the algorithm. This results in a slight degradation in performance but the trade-off is a significant reduction in computations. In practical applications, such as intruder detection in a cybersecurity setup, the proposed algorithm can prove to be an asset with its rapid estimation compared with the standard algorithms.