Multi-disease conditions strain the body’s defenses, complicating recovery and increasing mortality risk. Therefore, effective concurrent prevention of multiple diseases is essential for mitigating complications and improving overall well-being. Explainable artificial intelligence (XAI) with an advanced multimodal large language model (LLM) can create an interactive system enabling the general public to engage in natural language without any specialized knowledge prerequisites. Counterfactual explanation, an XAI method, offers valuable insights by suggesting adjustments to patient features to minimize disease risks. However, addressing multiple diseases simultaneously poses challenging barriers. This article proposes an interactive multi-disease prevention system that uses Google Gemini Pro, a multimodal LLM, and a non-dominated sorting genetic algorithm, namely NSGA-II, to overcome such problems. This system recommends changes in feature values to concurrently minimize the risk of diseases such as heart attacks and diabetes. The system facilitates personalized feature value selection, significantly reducing disease attack probabilities to as low as possible. Such an approach holds the potential to simultaneously address the unresolved issue of preventing and managing multiple diseases for the general public.

Diabetes, a significant global health crisis, is primarily driven in India by unhealthy diets and sedentary lifestyles, with rapid urbanization amplifying these effects through convenience-oriented living and limited physical activity opportunities, underscoring the need for advanced preventative strategies and technology for effective management. This study integrates Shapley Additive explanations (SHAPs) into ensemble machine learning models to improve the accuracy and efficiency of diabetes predictions. By identifying the most influential features using SHAP, this study examined their role in maintaining high predictive performance while minimizing computational demands. The impact of feature selection on model accuracy was assessed across ten models using three feature sets: all features, the top three influential features, and all except these top three. Models focusing on the top three features achieved superior performance, with the ensemble model attaining a better performance in most of the metrics, outperforming comparable approaches. Notably, excluding these features led to a significant decline in performance, reinforcing their critical influence. These findings validate the effectiveness of targeted feature selection for efficient and robust clinical applications.

Electric vehicles (EVs) are an effective solution for reducing reliance on non-renewable energy sources. However, the lack of charging infrastructure and concerns over their range are some of the biggest hurdles to adopting EVs. Charging infrastructure for EVs is, however, on the rise. Proper planning of charging stations vis-à-vis road networks and related points of interest such as transportation hubs, schools, shopping centres, etc., alongside such roads become vital to laying out a plan for such infrastructure, particularly for developing countries like India where EV adoption is relatively in a nascent stage. Synthetic datasets can help overcome these hurdles and promote EV adoption. This article presents a synthetic dataset mechanism for EV charging infrastructure planning, taking the Indian city of Berhampur, Odisha with its existiing EV charging infrastructure as a reference. The dataset includes information on the number of charging sessions for EVs, allocation to chargers in EVCS, reach time, charging start and end time, waiting time, total time spent at EVCS, total charged amount, energy used, and cost for charging. This information can help city planners and utilities identify the optimal locations for charging stations and plan for future charging infrastructure augmentation. The dataset can also be used to predict energy usage for the near future and identify the key factors affecting the planning with the help of Explainable AI (XAI) techniques. This information can help forecast the demand for charging services and optimize energy usage in the city. The article contributes to the EV charging behaviour and infrastructure planning and aims to promote broader EV adoption for future sustainable transportation.

Concerns about fossil fuels and the harmful effects of climate change are pushing everyone to use green and clean energy. The use of electric vehicles is becoming a necessity to achieve this goal. It simultaneously needs the infrastructure for electric vehicle charging stations to meet the tremendous demand for electric vehicles. Hence, there will be a huge consumption of energy in this regard. This work proposes a novel approach for analyzing the factors influencing energy consumption at electric vehicle charging stations using an explainable AI technique such as SHAP explanation. The study aims to identify the key factors that affect energy consumption and provide insights into how these variables can be optimized to minimize energy consumption. The research methodology uses machine learning algorithms to model the relationship between energy consumption and several other factors. The SHAP explanation technique is then applied to interpret the models and identify the key factors, such as charging time and maximum power. Using SHAP for feature selection can lead to better predictive models by iden-tifying the essential features and interactions between features. Reducing the number of features in the model and focusing on the most important ones can also improve its interpretability and generalization performance of the model. The study's findings will be useful for policymakers, electric vehicle manufacturers, and charging station operators to optimize the energy efficiency of electric vehicle charging stations.

In the recent era, for most sustainable smart cities energy conservation is a major point of consideration as urbanization is been carried out at an exponential rate. Out of that most of the energy consumption is diverted toward households, and there is a huge scope for optimization of this energy. Hence predicting this household energy with the advancement of AI and Machine Learning techniques is considered a social contribution and area of interest for most researchers. But only predicting the energy consumption will not solve the problem of energy optimization for a city, it is also important to understand the factors responsible for such predictions so that all possible recourses could be carried out to those factors, and it becomes more accountable, trustworthy and justifiable its energy optimization decisions towards its all stakeholders. With the use of Explainable Artificial Intelligence (XAI) techniques such as LIME, SHAP is possible to improve the explainability of machine learning models. Here SHAP technique is adopted to understand the prediction model and identify mostly responsible factors for the energy consumption of households.

Since urbanization is occurring at an exponential rate today, energy saving is a key factor for the majority of sustainable smart cities. Out of that, the majority of energy usage is directed toward homes, where there is an enormous possibility for energy optimization. As a result, most academics believe that forecasting this household energy using the advent of AI and machine learning techniques will have social benefits. However, predicting energy consumption alone won't help a city optimize its utilization of energy; it's also crucial to comprehend the factors that influence such predictions so that any available countermeasures can be applied and the city can make decisions about energy optimization that are more accountable, trustworthy, and justifiable to all of its stakeholders. There are different categories of explainers that offer the ability to explore a black box model. Each of these explanations has a connection to a certain model feature. Here, dalex, a Python library that implements a type of explanation, is utilized. a model-neutral user interfaces for interactive fairness and interpretability. It can make machine learning models more understandable. This method is used in this case to know the prediction model and discover the factors responsible for household energy consumption together including their relative importance.

The availability of high-capacity networks, low-cost computers, storage devices as well as the widespread adoption of hardware virtualization, service-oriented architecture, and autonomic and utility computing has led to growth in cloud computing. In today's era of cloud-based services, all intelligent transportation systems are connected to improve transportation safety and enhance the comfort of driving. The vision of all vehicles connected poses a significant challenge to the collection and storage of large amounts of traffic-related data. We propose to integrate cloud computing and vehicular networks in such a way that the vehicles can share computation resources, storage resources, and bandwidth resources. The proposed architecture includes a vehicular cloud, a roadside cloud, and a central cloud. A game-theoretical approach is presented to optimally allocate cloud resources. Virtual machine migration due to vehicle mobility is solved based on a resource reservation scheme.

The cubic spline interpolation is frequently used for analysis the data set in various aspects of engineering and science problem. For a large set of data points defined with very large range, it is very difficult to interpolate by using traditional sequential algorithm. In this paper, we proposed a more systematic approach which has a parallel component known as skeleton which is implemented in various parallel paradigms like OpenMP, MPI, and CUDA etc. It is interesting that the skeleton approach is used with pipelining technique that gives better result as compared to the previous studies. This approach is applied to compute the cubic spline interpolating polynomial based on a large data set. The experimental result using the parallel skeleton technique on multi-core CPU and GPU shows better performance with respect to other parallel methods.

Compute Unified Device Architecture (CUDA) is an architecture and programming model that allows leveraging the high compute-intensive processing power of the Graphical Processing Units (GPUs) to perform general, non-graphical tasks in a massively parallel manner. Hadoop is an open-source software framework that has its own file system, the Hadoop Distributed File System (HDFS), and its own programming model, the Map Reduce, in order to accomplish the tasks of storage of very large amount of data and their fast processing in a distributed manner in a cluster of inexpensive hardware. This paper presents a model and implementation of a Hadoop-CUDA Hybrid approach to perform Sparse Matrix Vector Multiplication(SpMV) of very large matrices in a very high performing manner. Hadoop is used for splitting the input matrix into smaller sub-matrices, storing them on individual data nodes and then invoking the required CUDA kernels on the individual GPU-possessing cluster nodes. The original SpMV is done using CUDA. Such an implementation has been seen to improve the performance of the SpMV operation over very large matrices by speedup of around 1.4 in comparison to non-Hadoop, single-GPU CUDA implementation.