Brain tumours are a critical global health challenge, accounting for 85-90% of all primary central nervous system tumours, with an estimated 308,102 new cases globally in 2020. These tumours often lead to severe physical and cognitive impacts on patients, but early and accurate diagnosis is essential for improving survival rates through better treatment planning. Current diagnostic methods rely heavily on radiologist expertise, making the process time-consuming, expensive, and resource-intensive, placing strain on healthcare systems. In this work, we aim to address this diagnostic bottleneck by developing an AI-driven solution that integrates various aspects of brain tumour diagnosis (location, type, size, shape, and severity) into one comprehensive platform. Our solution, TDA, builds on the PRCnet model (tumor type and grade classification) and XAI-MRI model (brain tumor segmentation), and offer a comprehensive system capable of predicting all tumour vital characteristics together while providing interactive interface for correction, feedback and validated learning. Experimental evaluations on different scenarios shows that our proposed framework outperforms existing models.

Brain tumor segmentation from Magnetic Resonance Images (MRI) presents significant challenges due to the complex nature of brain tumor tissues. This complexity poses a significant challenge in distinguishing tumor tissues from healthy tissues, particularly when radiologists rely on manual segmentation. Reliable and accurate segmentation is crucial for effective tumor grading and treatment planning. In this paper, we proposed a novel ensemble dual-modality approach for 3D brain tumor segmentation using MRI. Initially, individual U-Net models are trained and evaluated on single MRI modalities (T1, T2, T1ce, and FLAIR) to establish each modality's performance. Subsequently, we trained U-net models using combinations of the best-performing modalities to exploit the complementary information and improve segmentation accuracy. Finally, we introduced the ensemble dual-modality by combining the two best-performing pre-trained dual-modalities models to enhance segmentation performance. Experimental results show that the proposed model enhanced the segmentation result and achieved a Dice Coefficient of 97.73% and a Mean IoU of 60.08%. The results illustrate that the ensemble dual-modality approach outperforms single-modality and dual-modality models. Grad-CAM visualizations are implemented, generating heat maps that highlight tumor regions and provide useful information to clinicians about how the model made the decision, increasing their confidence in using deep learning-based systems. Our code publicly available at: https://github.com/Ahmeed-Suliman-Farhan/Ensemble-Dual-Modality-Approach.

Brain tumors are the most prevalent and life-threatening cancer; an early and accurate diagnosis of brain tumors increases the chances of patient survival and treatment planning. However, manual tumor detection is a complex, cumbersome and time-consuming task and is prone to errors, which relies on the radiologist's experience. As a result, the development of an accurate and automatic tumor detection system is critical. In this paper, we proposed a new model called Parallel Residual Convolutional Network (PRCnet) model to classify brain tumors from Magnetic Resonance Imaging. The PCRnet model uses several techniques (such as filters of different sizes with parallel layers, connections between layers, batch normalization layer, and ReLU) and dropout layer to overcome the over-fitting problem, for achieving accurate and automatic classification of brain tumors. Our methodology used data augmentation techniques such as rotation, flipping, and scaling. These enhanced the diversity and quantity of the training dataset, contributing significantly to the model's improved performance. The PRCnet model is trained and tested on two different datasets and obtained an accuracy of 94.77% and 97.1% for dataset A and dataset B, respectively which is way better as compared to the state-of-the-art models. Our PRCnet code publicly available at: https://github.com/Ahmeed-Suliman-Farhan/PRCnet-Model.

Renewable energy-powered irrigation systems have emerged as sustainable solutions, particularly for farmers in off-grid areas. While existing research often highlights tank storage-based systems as the most cost-effective option, large-scale deployment of water tanks incurs significant costs and maintenance challenges. Additionally, there is limited research on the feasibility and optimisation of battery-based irrigation systems, which are often deemed costly despite their potential benefits. This study addresses this gap by identifying the optimal storage solution for hybrid energy-powered irrigation systems through a system-level optimisation model. The model evaluates the suitability of three storage options: direct-coupled water tank storage, battery-coupled storage, and a hybrid battery-tank storage system. Optimisation criteria include life cycle cost (LCC), loss of power supply probability (LPSP), and loss of load probability (LOLP), ensuring a comprehensive assessment of both cost and reliability. Results indicate that the hybrid battery-tank storage system is the most reliable, followed by battery-only storage, while tank-only storage, despite its lower initial cost, poses scalability and maintenance challenges. The LCC over a 25-year project lifetime is 31 pound k for battery-tank, 26 pound k for battery-only, and 23.3 pound k for tank-only systems. Despite the lower cost of tank storage, its complexity and maintenance make it the least preferred option for large-scale systems.

'鏡花水月'(Flower in the Mirror, Moon in the water) is metaphorically used to depict something that can be seen but is untouchable (illusions of their own from the real world). The mirror and water surfaces can be regarded as a latent space that consists of representations generated from reality and connected towards illusions. Assuming there is a mirror that can foresee the future, the mirror surface (i.e., latent space) essentially requires a generated representation from the latest observations (i.e., hallucinating future representations), and subsequently be decoded to hallucinate the scenarios in the future. Hallucinating future representations (i.e., prospective representation learning) has demonstrated better action prediction for robot motion and path planning. Therefore, this poster focuses on obtaining prospective aware representations from the latest sequential images by leveraging the advantages of contrastive learning to benefit performance of visual based mapless UAV indoor navigation The model and video are available at: https://github com/Yingxiu Chang/MulSCPL.

Quadrupedal robotics is an ever growing field with a wide range of applications. However, developing controllers for new behaviours can be challenging due to the complex nature of these robots. Imitation learning algorithms can help overcome some of these challenges, with robots learning from biological counterparts through motion capture data. Robots could also potentially use these techniques for copying behaviours from other robots/animals of similar morphology. Acquiring the required motion capture data from animals and remote locations can be difficult due to the bulky expensive equipment required. However, the use of pose estimation toolboxes such as DeepLabCut could negate this issue. This paper covers the methodology and results from initial proof of concept experiments for two key areas. Firstly, testing the feasibility of DeepLabCut in the use of tracking robotic quadrupeds. Secondly, if the data produced can be used to generate trajectories for deployment on a target robot. This will help to establish if the use of pose estimation toolboxes could potentially be useful in future imitation learning experiments.

Self-reconfigurable and morphing robots are used in numerous domains due to their adaptability to a variety of scenarios and environments which makes them ideal for exploration. While capable of adapting to an environment, many of these robots are incapable of successfully navigating an unknown environment without the use of expensive, complex and range limiting equipment. In addition, while Morphing Tracked Robots are excellent navigators, their reliance on computationally intensive components and substantial power demands contributes to their bulky design and restricted versatility, constraining their applicability across scenarios. We propose a new kind of robot (the MMTR) featuring the modularity from modular reconfigurable robots and the morphing ability found in flipper tracked robots. Combined with a simplified topological map generator using only encoders and an IMU. Through experiments, we have shown that the MMTR can navigate rough terrain using its morphing flippers and build a map using only inexpensive components.

Markerless motion tracking solutions have been used for many years to track the movements of humans and animals. However, the use of these tools to track the motion of robots is limited but has the potential of allowing robots to copy each other from vision alone. DeepLabCut is a markerless pose estimation toolbox that is primarily designed for tracking animals (including humans). Many forms of motion tracking rely on the use of bulky equipment. This limits the types of environment motion tracking can be performed, along with its potential deployment onto a robotic platform. However, markerless pose estimation toolboxes like DeepLabCut only require the use of a single camera, giving it potential for tracking animals and robots in a wider range of locations. This poster shows the method and results of initial experiments conducted with DeepLabCut, testing its ability to track Robotic Quadrupeds

Efficient energy management is vital for mobile robots' autonomy. It is essential for optimizing techniques like path planning and task scheduling. However, testing these approaches for diverse scenarios can be challenging, especially in large-scale environments with complex hardware requirements This paper introduces an energy estimation model considered for mobile robots with wheels, facilitating energy profiling within a simulator based on ROS/Gazebo, eliminating the necessity for tangible hardware The design of this model aims to compute energy consumption related to kinetic energy transformation and the overcoming of robot friction. Notably, only a limited number of researchers have utilized advanced robot simulation software to analyze energy consumption, often relying on static friction models. In contrast, our energy model incorporates an advanced dynamic friction model, the LuGre model, to offer a more precise assessment of power consumption attributed to friction.

Electric utility companies use short term load forecasting for day ahead operations to maintain the balance between generation and anticipated load. In addition, with the advancement of smart grid technology the need for short term load forecasting is even more significant, to plan demand side management, integrate electric vehicles and other renewable energy resources such as offshore wind energy, solar energy. Load forecasting can be done using statistical methods and artificial intelligence models. The later technique is more accurate and powerful and therefore researchers have and worked on its improvement using different models especially in the last two decades. To get the best possible match between original load values and anticipated values, four DL models long short-term memory, gated recurrent unit, hybrid CNN-LSTM and hybrid CNN-GRU have been studied in the paper. The objective of the study is to find out the best DL model by comparing them on three different publicly available datasets and it is observed that the LSTM and GRU models are effective on simple and small datasets while hybrid models are performing well in complex and large datasets.

Self-supervised contrastive learning focus more on classification tasks since the samples from different classes are easy to be distinguished based on the similarity calculation of contrastive loss functions. However, because the continuity nature of regression tasks where samples and labels don't have their associ-ated discreet classes, self-supervised contrastive learning methods face challenges to calculate the similarity between samples for regression tasks. Steering prediction (i.e., a regression task) is a crucial module for self-driving vehicle and U AV autonomous navigation, which is responsible to control the movement orientation. This paper applied the Supervised Contrastive Re-gression (SupCR) method for the vision-based steering prediction. To the best of our knowledge, the SupCR has not been explored in the areas of outdoor self-driving and U AV indoor navigation. The SupCR also obtains better regression performances compared to the bench-mark supervised learning model and other contrastive learning methods. The experiments explore the reasons for better performances of the SupCR according to the visualizations of representation distributions and attention heatmaps.

Unmanned aerial vehicles (UAVs) have drawn increased research interest in recent years, leading to a vast number of applications, such as, terrain exploration, disaster assistance and industrial inspection. Unlike UAV navigation in outdoor environments that rely on GPS (Global Positioning System) for localization, indoor navigation cannot rely on GPS due to the poor quality or lack of signal. Although some reviewing papers particularly summarized indoor navigation strategies (e.g., Visual-based Navigation) or their specific sub-components (e.g., localization and path planning) in detail, there still lacks a comprehensive survey for the complete navigation strategies that cover different technologies. This paper proposes a taxonomy which firstly classifies the navigation strategies into Mapless and Map-based ones based on map usage and then, respectively categorizes the Mapless navigation into Integrated, Direct and Indirect approaches via common characteristics. The Map-based navigation is then split into Known Map/Spaces and Map-building via prior knowledge. In order to analyze these navigation strategies, this paper uses three evaluation metrics (Path Length, Deviation Rate and Exploration Efficiency) according to the common purposes of navigation to show how well they can perform. Furthermore, three representative strategies were selected and 120 flying experiments conducted in two reality-like simulated indoor environments to show their performances against the evaluation metrics proposed in this paper, i.e., the ratio of Successful Flight, the Mean time of Successful Flight, the Mean Length of Successful Flight, the Mean time of Flight, and the Mean Length of Flight. In comparison to the CNN-based Supervised Learning (directly maps visual observations to UAV controls) and the Frontier-based navigation (necessitates continuous global map generation), the experiments show that the CNN-based Distance Estimation for navigation trades off the ratio of Successful Flight and the required time and path length. Moreover, this paper identifies the current challenges and opportunities which will drive UAV navigation research in GPS-denied environments.

Current research in 3D printing focuses on improving printing performance through various techniques, including decomposition, but targets only single printers. With improved hardware costs increasing printer availability, more situations can arise involving a multitude of printers, which offers substantially more throughput in combination that may not be best utilised by current decomposition approaches. A novel approach to 3D printing is introduced that attempts to exploit this as a means of significantly increasing the speed of printing models. This was approached as a problem akin to the parallel delegation of computation tasks in a multi-core environment, where optimal performance involves computation load being distributed as evenly as possible. To achieve this, a decomposition framework was designed that combines recursive symmetric slicing with a hybrid tree-based analytical and greedy strategy to optimally minimise the maximum volume of subparts assigned to the set of printers. Experimental evaluation of the algorithm was performed to compare our approach to printing models normally (“in serial”) as a control. The algorithm was subjected to a range of models and a varying quantity of printers in parallel, with printer parameters held constant, and yielded mixed results. Larger, simpler, and more symmetric objects exhibited more significant and reliable improvements in fabrication duration at larger amounts of parallelisation than smaller, more complex, or more asymmetric objects.

The rise of the intelligent, local charging facilitation and environmentally friendly aspects of electric vehicles (EVs) has grabbed the attention of many end-users. However, there are still numerous challenges faced by researchers trying to put EVs into competition with internal combustion engine vehicles (ICEVs). The major challenge in EVs is quick recharging and the selection of an optimal charging station. In this paper, we present the most recent research on EV charging management systems and their role in smart cities. EV charging can be done either in parking mode or on-the-move mode. This review work is novel due to many factors, such as that it focuses on discussing centralized and distributed charging management techniques supported by a communication framework for the selection of an appropriate charging station (CS). Similarly, the selection of CS is evaluated on the basis of battery charging as well as battery swapping services. This review also covered plug-in charging technologies including residential, public and ultra-fast charging technologies and also discusses the major components and architecture of EVs involved in charging. In a comprehensive and detailed manner, the applications and challenges in different charging modes, CS selection, and future work have been discussed. This is the first attempt of its kind, we did not find a survey on the charging hierarchy of EVs, their architecture, or their applications in smart cities.

We introduce the Urban Life agent-based simulation used by the Ground Truth program to capture the innate needs of a human-like population and explore how such needs shape social constructs such as friendship and wealth. Urban Life is a spatially explicit model to explore how urban form impacts agents' daily patterns of life. By meeting up at places agents form social networks, which in turn affect the places the agents visit. In our model, location and co-location affect all levels of decision making as agents prefer to visit nearby places. Co-location is necessary (but not sufficient) to connect agents in the social network. The Urban Life model was used in the Ground Truth program as a virtual world testbed to produce data in a setting in which the underlying ground truth was explicitly known. Data was provided to research teams to test and validate Human Domain research methods to an extent previously impossible. This paper summarizes our Urban Life model's design and simulation along with a description of how it was used to test the ability of Human Domain research teams to predict future states and to prescribe changes to the simulation to achieve desired outcomes in our simulated world.

Privacy preserving data publishing of electronic health record (EHRs) for 1 to M datasets with multiple sensitive attributes (MSAs) is an interesting and challenging issue. There is always a trade-off between privacy and utility in data publishing. Most of the privacy-preserving models shows critical privacy disclosure issues and, hence, they are not robust in practical datasets. The k-anonymity model is a broadly used privacy model to analyze privacy disclosures, however, this model is only useful against identity disclosure. To address the limitations of k-anonymity, a group of privacy model extensions have been proposed in past years. It includes a p-sensitive k-anonymity model, a p+-sensitive k-anonymity model, and a balanced p+-sensitive k-anonymity model. However these privacy-preserving models are not sufficient to preserve the privacy of end-users in practical datasets. In this paper we have formalize the behavior of an adversary which perform identity and attribute disclosures on balanced p+-sensitive k-anonymity model with the help of adversarial scenarios. Since balanced p+-sensitive k-anonymity model is not sufficient for 1 to M with MSAs datasets privacy preservation. We propose an extended privacy model called "1: M MSA-(p, l)-diversity" for 1: M dataset with MSAs. We then perform formal modeling and verification of the proposed model using High-Level Petri Nets (HLPN) to confirm privacy attacks invalidation. Experimental results show that our proposed "1: M MSA-(p, l)-diversity model" is efficient and provide enhanced data utility of published data.

Human emotions are strongly coupled with physical and mental health of any individual. While emotions exbibit complex physiological and biological phenomenon, yet studies reveal that physiological signals can be used as an indirect measure of emotions. In unprecedented circumstances alike the coronavirus (Covid-19) outbreak, a remote Internet of Things (IoT) enabled solution, coupled with AI can interpret and communicate emotions to serve substantially in healthcare and related fields. This work proposes an integrated IoT framework that enables wireless communication of physiological signals to data processing hub where long short-term memory (LSTM)-based emotion recognition is performed. The proposed framework offers real-time communication and recognition of emotions that enables health monitoring and distance learning support amidst pandemics. In this study, the achieved results are very promising. In the proposed IoT protocols (TS-MAC and R-MAC), ultralow latency of 1 ms is achieved. R-MAC also offers improved reliability in comparison to state of the art. In addition, the proposed deep learning scheme offers high performance ([Formula: see text]-score) of 95%. The achieved results in communications and AI match the interdependency requirements of deep learning and IoT frameworks, thus ensuring the suitability of proposed work in distance learning, student engagement, healthcare, emotion support, and general wellbeing.

Cancer is the second leading cause of mortality across the globe. Approximately 9.6 million people are estimated to have died due to cancer disease in 2019. Accurate and early prediction of cancer can assist healthcare professionals to devise timely therapeutic innervations to control sufferings and the risk of mortality. Generally, a machine learning (ML) based predictive system in healthcare uses data (genetic profile or clinical parameters) and learning algorithms to predict target values for cancer detection. However, optimization of predictive accuracy is an important endeavor for accurate decision making. Reject Option (RO) classifiers have been used to improve the predictive accuracy of classifiers for cancer like complex problems. In a gene profile all of the features are not important and should be shaved off. ML offers different techniques with their own methodology for feature selection (FS) and the classification results are dependent on the datasets each having its own distribution and features. Therefore, both FS methods and ML algorithms with RO need to be considered for robust classification. The main objective of this study is to optimize three parameters (learning algorithm, FS method and rejection rate) for robust cancer prediction rather than considering two traditional parameters (learning algorithm and rejection rate). The analysis of different FS methods (including t-test, Las Vegas Filter (LVF), Relief, and Information Gain (IG)) and RO classifiers on different rejection thresholds is performed to investigate the robust predictability of cancer. The three cancer datasets (Colon cancer, Leukemia and Breast cancer) were reduced using different FS methods and each of them were used to analyze the predictability of cancer using different RO classifiers. The results reveal that for each dataset predictive accuracies of RO classifiers were different for different FS methods. The findings based on proposed scheme indicate that, the ML algorithms along with their dependence on suitable FS methods need to be taken into consideration for accurate prediction.

State-of-the-art progress in cloud computing encouraged the healthcare organizations to outsource the management of electronic health records to cloud service providers using hybrid cloud. A hybrid cloud is an infrastructure consisting of a private cloud (managed by the organization) and a public cloud (managed by the cloud service provider). The use of hybrid cloud enables electronic health records to be exchanged between medical institutions and supports multipurpose usage of electronic health records. Along with the benefits, cloud-based electronic health records also raise the problems of security and privacy specifically in terms of electronic health records access. A comprehensive and exploratory analysis of privacy-preserving solutions revealed that most current systems do not support fine-grained access control or consider additional factors such as privacy preservation and relationship semantics. In this article, we investigated the need of a privacy-aware fine-grained access control model for the hybrid cloud. We propose a privacy-aware relationship semantics–based XACML access control model that performs hybrid relationship and attribute-based access control using extensible access control markup language. The proposed approach supports fine-grained relation-based access control with state-of-the-art privacy mechanism named Anatomy for enhanced multipurpose electronic health records usage. The proposed (privacy-aware relationship semantics–based XACML access control model) model provides and maintains an efficient privacy versus utility trade-off. We formally verify the proposed model (privacy-aware relationship semantics–based XACML access control model) and implemented to check its effectiveness in terms of privacy-aware electronic health records access and multipurpose utilization. Experimental results show that in the proposed (privacy-aware relationship semantics–based XACML access control model) model, access policies based on relationships and electronic health records anonymization can perform well in terms of access policy response time and space storage.

Experimentation is a critical capability of simulations that allows one to test different scenarios safely and cost-effectively. In particular, agent-based simulations have been used in experimenting with different policy options to aid decision makers. Highly utilized experimentation methods such as parameter sweeping aim to explore the relationship between the initial parameter values (i.e., input) and simulation results (i.e., outputs). Experimentation, which involves changes of simulation states on-the-fly, is often conducted ad-hoc and entails manual code adjustments which are time consuming and error-prone. In this paper, we present a framework that facilitates intervening in a running simulation to change simulation states in a semi-automated manner so that a simulation user can explore alternative worlds. In our framework, such an intervention is implemented using an injection mechanism. The framework allows the user to weigh different policy options rapidly with minimal effort. We illustrate its use in an urban agent-based model.