The issue of smog in smart cities (SCs) poses serious health risks due to the rising concentrations of air pollutants (APs), including particulate matter, carbon, and sulfur. Their complex and dynamic behavior makes data-driven analysis challenging. Thus, accurate source identification and forecasting of those APs are vital for assessing psychotic disorder risks in hospitalized patients. To address this, a model namedPsych-Airhas been proposed. The proposedPsych-Airmodel employs federated learning (FL) with a customized multivariate bidirectional GRU (BGRU) architecture featuring cross-variable gated attention and parallel temporal encoders. Unlike conventional FL schemes,Psych-Airincorporates heterogeneity-aware and pollutant-sensitive federated optimization, enabling stable and communication-efficient learning across non-IID smart city environments. It also models pollutant and meteorological time series as an interdependent tensor stream, with dynamic gating and synchronized bidirectional states capturing pollutant-specific patterns. A shared fusion layer learns spatiotemporal signatures predictive of psychotic disorder onset while operating securely in a decentralized environment.Psych-Aireffectively isolates latent triggers from noisy environmental data, achieving clinically relevant forecasting. FL-based BGRU identifies key pollutant sources, accounting for 46% of Air Quality Index impact in SCs. The model outperforms traditional ML, DL, and FL methods by 20%, 15%, and 10%, respectively, and supports the assessment of psychotic disorders through statistical analysis. Additionally, Psych-Air promotes sustainable, energy-efficient smart cities by reducing annual costs and CO emissions, proving adaptable across various urban settings.

Collaborative filtering (CF) is dedicated to learning the representations of users and items based on interactive data. Regrettably, the lack of fine-grained modeling of interactive motivation makes the model less interpretable. A feasible solution is to combine the disentangling idea with the graph neural network (GNN) and capture different types of interaction relationships by using a message propagation mechanism on the graph of user–item interaction. However, this process typically relies on the disentangling of users’ hidden intents, ignoring the significance of item features to user engagement. This fact leads to the inadequate interpretability of existing models. To make up for the deficiency, this article proposes a new feature-aware disentangled GNN (FDGNN) for the recommendation. By learning the relationship between user behavior and important features of items, the model aims to achieve better recommendation performance and model interpretability. In the end, we first realize the feature partition based on mutual information and then design an attention-based graph disentangling model to realize the fine-grained disentangling of user intents. In addition, to further ensure the independence of the disentangled intents, we augment the model with disagreement regularization. Through multilayer embedding propagation, FDGNN can display a capture CF effect in feature semantics. The interpretability and efficiency of our proposed approach are demonstrated by numerous pertinent experiments.

With the advent of Internet of Things (IoT) applications, smart IoT devices are ubiquitous. Executing these devices on cloud data centers can lead to network congestion and transmission delay that causes failure instances in cloud architecture. Therefore, fog computing is derived to satisfy the low latency, location awareness, and mobility requirements of massive IoT applications near end users. Concerned with the high requirements of compute-intensive business applications, fog computing structure becomes complex due to limited computing capacity, and therefore these applications are offloaded to the cloud. Therefore, to overcome the offloading problem of workflow tasks in this work, a novel method named: Improved Chemical Reaction Optimization for Workflow Scheduling in a Hybrid Environment (ICRO-WSHE) has been proposed. The proposed algorithm aims at minimizing the execution cost of workflow applications under the defined deadline constraints. The algorithm is based on CRO, which has fewer parameters and the fastest convergence speed. However, the existing CRO has drawbacks in terms of getting stuck in the local optimum and having difficulty obtaining real optimal solutions. Therefore, the proposed mechanism modifies the existing CRO algorithm and includes the suitable features of PSO (Particle Swarm Optimization) and FQR (Fitness-based Quasi Reflection) methods to prevent the shortcomings of the CRO method. Further, a double-point synthesis operation is incorporated to increase the exploration rate and improve the working of the proposed algorithm. The result of the simulation experiment based on different types of workflows shows that the proposed method outperforms existing algorithms and proves to be a practical approach.

The burgeoning volume of data from the IoT applications and intelligent devices processed on the cloud data centers can lead to network congestion and transmission delay. Compared to cloud computing, fog computing focuses on ubiquitous connected heterogeneous devices and addresses the transmission latency by placing the fog nodes at the network edge. Concerning the limited resources of fog nodes enable the computationally intensive tasks to offload on the cloud resources. Scheduling of deadline-constrained workflows with minimum execution cost is challenging due to complex and uncertain computation offloading problems. Therefore, an intelligent fuzzy scheduler is designed to offload tasks characterized with uncertain parameters to the appropriate resources. A new salp swarm algorithm has been exploited to learn and optimize fuzzy task-resource allocation rules. In addition to this, to overcome the shortcomings of the salp swarm algorithm, it is employed with one of the best opposition methods named: Fitness-based quasi-reflection method. The inclusion of the opposition method enhances the proposed ISSS-FQR (Intelligent salp swarm scheduler with the fitness-based quasi-reflection method) approach and improves the learning process. Simulation studies on the benchmark workflows are carried out to demonstrate the efficacy of ISSS-FQR. ISSS-FQR has been compared with the classical algorithms, including chemical reaction optimization and ant colony optimization algorithms for workflow scheduling problems (CR-AC), Cost-Makespan aware scheduling (Deadline-based CMaS), and Directional and non-local convergent particle swarm optimization (DNCPSO). From the analyzed result, ISSS-FQR outperforms the rest of the classical algorithms, which proves the effectiveness of ISSS-FQR. Note to Practitioners—This paper provides a novel method called ISSS-FQR for minimizing the cost of execution of IoT applications while satisfying the deadline constraint. An intelligent fuzzy scheduler is designed to offload tasks characterized with uncertain parameters to the appropriate resources. The ISSS-FQR combines the Salp Swarm Algorithm and the OBL method named FQR to learn the task-resource allocation rules. It is compared with three state-of-the-art algorithms called CR-AC, Deadline-based CMaS, and DNCPSO. From the analyzed result, it has been observed that ISSS-FQR outperforms the previous algorithms.

Extensive user check-in data incorporating user preferences for location is collected through Internet of Things (IoT) devices, including cell phones and other sensing devices in location-based social network. It can help traveling enterprises intelligently predict users' interests and preferences, provide them with scientific tourism paths, and increase the enterprises income. Thus, successive point-of-interest (POI) recommendation has become a hot research topic in augmented Intelligence of Things (AIoT). Presently, various methods have been applied to successive POI recommendations. Among them, the recurrent neural network-based approaches are committed to mining the sequence relationship between POIs, but ignore the high-order relationship between users and POIs. The graph neural network-based methods can capture the high-order connectivity, but it does not take the dynamic timeliness of POIs into account. Therefore, we propose anInteraction-enhanced andTime-awareGraphConvolutionNetwork (ITGCN) for successive POI recommendation. Specifically, we design an improved graph convolution network for learning the dynamic representation of users and POIs. We also designed a self-attention aggregator to embed high-order connectivity into the node representation selectively. The enterprise management systems can predict the preferences of users, which is helpful for future planning and development. Finally, experimental results prove that ITGCN brings better results compared to the existing methods.

Internet-of-Farming Things (IoFT)-enabled smart agriculture can collect data more reliably and frequently to track the crop’s status and other significant information. Considering that smart agriculture requires working with substantial amounts of sensitive data. In light of this, frequent data processing may threaten the confidentiality and integrity of data and IoFT device privacy. Although numerous privacy-preserving data aggregation methods have been implemented to address these issues, they also have certain security vulnerabilities, such as inadequate data confidentiality, collusion attacks, and malicious data mining attacks. Therefore, we introduce a three-tier architecture-assisted redactable blockchain-based secure data aggregation method with source authentication for the fog-enabled IoFT. This work provides an efficient and secure two-level data aggregation model. The proposed model supports resistance to collusion and malicious data mining threats launched by internal or external attackers. It can also achieve perfect data confidentiality and integrity against a malicious aggregator and an inquisitive control center for an authorized IoFT device. Specifically, the detailed performance analysis and theoretical concrete security proofs demonstrate the practicability and efficiency of the proposed model.

The emergence of the cloud platform with substantial resources to offer on-demand instigated the researchers to migrate the scientific workflows to the cloud environment. The scheduling of workflows with diverse QoS parameters is not a trivial task, but an NP-Complete problem. Several heuristics for QoS constrained workflows have been investigated. However, most of them focus only on time and cost and do not guarantee high resource utilization. The scheduling of the workflow tasks over the minimum cloud resources under the defined time limit is a grave concern. In this article, an algorithm named MFGA (Modified Fuzzy Adaptive Genetic Algorithm) has been formulated to minimize the makespan and improve resource utilization under both deadline and budget constraints. A fuzzy logic controller has also been devised to control the crossover and mutation rates that prevent MFGA from getting stuck in a local optimum. MFGA has a novel crossover technique that adds the fittest solutions in the population. Additionally, a new mutation technique has also been introduced, which minimizes the makespan and increases the reusability of the resources. The simulation experiments with the real workflows show that the proposed MFGA outperforms other state-of-the-art algorithms.

In this proposal, the impact of dynamic farm environment due to varying vegetation density on the Received Signal Strength (RSS), coverage and energy consumption of an IoT assisted Wireless Sensor Network (IoWSN) is analyzed through measurement campaign. Experimental observations on free-space and tree Path Loss Model (PLM) based sensor node deployment strategies in a cropping period have shown network disconnectivity due to incorrect assessment of excess attenuation caused by dynamically varying vegetation height and density during the monitoring period. To address the challenge, an empirically formulated PLM is proposed to estimate the excess attenuation at different crop development stages of medium grass vegetation. Further, using the formulated PLM, a Non-dominated Sorting Genetic Algorithm (NSGA-III) multi-objective optimization is performed to generate initial node deployment with a heterogeneous transmission range. To address the issue of over-coverage, transmitter output power scheduling is performed with predefined upper limit derived from the NSGA-III optimization. The output power is dynamically scheduled during the monitoring period based on changes in the captured RSS to minimize over-coverage. Improvements in coverage, connectivity, and energy efficiency compared to existing approaches are validated through Proof of Concept.

Precision agriculture, as the future of farming technology, addresses challenges faced by farmers by data mining of information collected through IoT-enabled crop monitoring infrastructures. The identification of crop disease is one of the widely studied challenges. Crop diseases cannot be accurately predicted by merely analyzing individual disease causes. This proposal presents a fuzzy-logic-based pest prediction mechanism assisting in beforehand preparedness for potential pest prevention. The experiments are performed for pests in rice and millet crops. The data mining over samples collected in a cropping cycle revealed the plausible correlation between temperature, relative humidity, and rainfall with pest breeding. The data collected through IoT monitoring infrastructure is analyzed for the ambient breeding condition of the pest. These conditions are then employed to design the knowledge base of the fuzzy system. More specifically, the linguistic variables of the fuzzy membership function are optimized using a genetic algorithm for close prediction of pest breeding in given environmental conditions. The proposal verified that the weather factors have a strong impact on the occurrence of pests and diseases, and the fuzzy-logic-based pest prediction through IoT application development services will help farmers to take precautionary measures beforehand.

This proposal examines the effect of grass vegetation elevation and density on path loss between sensors deployed in an IoT-enabled wireless sensor network (IoWSN) crop monitoring infrastructures. Observations via real-time measurement campaigns at different node heights and vegetation depths revealed that the sensor deployment made using free-space or tree vegetation based path loss model (PLM) experiences network disconnectivity due to variations in vegetation density in a cropping cycle. An empirical PLM is formulated to identify signal strength at different development phases of paddy and sugarcane medium grass vegetation. For this, the 2.4 GHz RF path loss coefficient (PLC) is estimated using data collected through measurement campaign over combinations of sensor height and vegetation density. Further, the formulated PLC is used to train multiple regression model to develop a generic PLM for all medium grass vegetation. Improvements in coverage and connectivity have been validated through proof of concept.

Advanced technology in agriculture can help to know about suitable environmental conditions, soil health status, water and fertilizer requirements, and crop monitoring at every plant growth stage, resulting in higher yield. In the past few decades, many countries have witnessed different rain and temperature patterns due to change in environmental conditions. The plantation schedule imparts mark-able effects on the crop yield. The correct and well-planned schedule can result in getting maximum productivity with limited resources. This study presents rule-based fuzzy classification method, for predicting the sowing fuzziness based on environmental conditions. The proposed study is a three-step procedure that identifies the sowing time of Cotton, Maize, and Groundnut. First, the knowledge and rule base of the fuzzy inference system is designed. In the second step rule base of the fuzzy inference system is optimized using multi-objective evolutionary algorithm NSGA-2, which helps maximize the accuracy and minimize the number of fuzzy rules taken for classification. Finally, the fuzziness of crop sowing in different slots is determined. Set of solutions in NSGA-2 are validated through a cross-validation approach. Further, the fuzziness of the sowing slot of Cotton, Maize, and Groundnut is correlated to yield in a given year to measure the model's effectiveness.

The advancement of cloud computing has great impact on the medical sector. Due to its storage facility, e-healthcare has emerged as a promising healthcare solution for providing fast and immediate treatment to patients. The PHRs collected and outsourced in the cloud leads to security concern. The data outsourced in the cloud is no more under the direct control of the patient, hence data should be encrypted prior its storage. Existing works based on group signature require high amount of computation. Other issues like confidentiality of private data, efficient key distribution, scalable and flexible fine-grained data access, revocation and tracing the malicious user is yet to be addressed to maintain the integrity of the patients. In this manuscript, we propose EPOC-1-based multi authority CP-ABE which can trace and revoke the malicious user who leaks the real identity and confidential data of the patient without any storage overhead. This methodology of white-box traceability presented in this manuscript, traces the malicious user efficiently. The proposed scheme is validated with some existing policies and makes the healthcare domain more securable under the cloud setup.