Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the global model based on the local model updates. While FL methods offer several advantages, including scalability and data privacy, they assume there are available computational resources at each edge-device/client. However, the Internet-of-Things (IoT)-enabled devices, e.g., robots, drone swarms, and low-cost computing devices (e.g., Raspberry Pi), may have limited processing ability, low bandwidth and power, or limited storage capacity. In this survey article, we propose to answer this question: how to train distributed machine learning models for resource-constrained IoT devices? To this end, we first explore the existing studies on FL, relative assumptions for distributed implementation using IoT devices, and explore their drawbacks. We then discuss the implementation challenges and issues when applying FL to an IoT environment. We highlight an overview of FL and provide a comprehensive survey of the problem statements and emerging challenges, particularly during applying FL within heterogeneous IoT environments. Finally, we point out the future research directions for scientists and researchers who are interested in working at the intersection of FL and resource-constrained IoT environments.

Ensuring minimum rights and safety of the garment workers has become a burning issue nowadays. The workers of garment factories are facing some labyrinths and broken out of fire is surely one of them. The investors are losing their interest and the prominence of this sector is getting toneless. In this paper, we have propounded a system which is capable to detect fire and can provide the location of the affected region. Raspberry Pi 3 has been used to control multiple Arduino which are integrated with a couple of sensors and camera. A 360° relay motor is assembled with the camera so that it can snap the image in whatever angle the fire is detected. We have provided a confirmation of the fire suspecting system to avoid any false alarm. The system will immediately send a message along with the image of the affected spot and Arduino's location. An admin can confirm or deny the impeachment and if the admin confirms the situation as a breaking out of fire, then the system will immediately raise an alarm and an automatic message will be sent to the nearby fire brigade.

Vehicle accident is the paramount thread for the people's life which causes a serious wound or even dead. The automotive companies have made lots of progress in alleviating this thread, but still the probability of detrimental effect due to an accident is not reduced. Infringement of spFieed is one of the elementary reasons for a vehicle accident. Therewithal, external pressure and change of tilt angle with road surface blameworthy for this mishap. As soon as the emergency service could divulge about an accident, the more the effect would be mitigated. For this purpose, we developed an Android based application that detects an accidental situation and sends emergency alert message to the nearest police station and health care center. This application is integrated with an external pressure sensor to extract the outward force of the vehicle body. It measures speed and change of tilt angle with GPS and accelerometer sensors respectively on Android phone. By checking conditions, this application also capable of reducing the rate of false alarm.

Federated Learning (FL) has gained widespread popularity in recent years due to the fast booming of advanced machine learning and artificial intelligence, along with emerging security and privacy threats. FL enables efficient model generation from local data storage of the edge devices without revealing the sensitive data to any entities. While this paradigm partly mitigates the privacy issues of users’ sensitive data, the performance of the FL process can be threatened and reach a bottleneck due to the growing cyber threats and privacy violation techniques. To expedite the proliferation of the FL process, the integration of blockchain for FL environments has drawn increasing attention from academia and industry. Blockchain has the potential to prevent security and privacy threats with its decentralization, immutability, consensus, and transparency characteristics. However, if the blockchain mechanism requires costly computational resources, then the resource-constrained FL clients cannot be involved in the training. Considering that, this survey focuses on reviewing the challenges, solutions, and future directions for the successful deployment of blockchain in resource-constrained FL environments. We comprehensively review variant blockchain mechanisms suitable for the FL process and discuss their trade-offs for a limited resource budget. Further, we extensively analyze the cyber threats that could be observed in a resource-constrained FL environment, and how blockchain can play a key role in blocking those cyber attacks. To this end, we highlight some potential solutions for the coupling of blockchain and FL that can offer high levels of reliability, data privacy, and distributed computing performance.

There is a dearth of research in developing low-cost solutions for distributed decision making in IoT networks. Most studies in the literature require the deployment of additional sensors for data collection. In this study, we propose to leverage available sensors built-in smartphones, to properly collect and broadcast data for different decision-making purposes in smart cities infrastructures, for example, intelligent transportation networks, smart health services, security and emergencies, industrial control, smart agriculture, home automation and so on. To this end, we first introduce our new platform (including software and mobile app implementation) to identify available sensors at each end-user device. We have identified a wide range of sensors including gyroscope, ambient light sensor, temperature, magnetic field sensor, orientation sensor, game rotation vector, linear acceleration, relative humidity, gravity, geomagnetic rotation vector, etc. As the sensors are already integrated within the phone, therefore, using these sensors can be beneficial considering the complexity, efficiency, and cost of the overall system. The challenge is to design a system that can trigger distributed devices to be self-activated and agreed to generate all available sensors data. Besides, as devices can send a continuous stream of data, therefore, size of data could be mounted and could be in the haphazard structure, which would give us hurdles to identify a device sensor data from another and to make an intelligent decision. To tackle all of these, we propose a distributed sensing approach that is capable to identify a device using token, can activate distributed end-user devices to send data to the cloud whenever it requires and store data in the cloud server maintaining proper format. This approach enables remote data collection leveraging available end-user devices and reduces the cost of installing new sensors for autonomous IoT applications. We then build on our efficient sensing platform to enable distributed intelligence among a network of smart devices. To this end, we leverage the computational capacity of these devices for local decision making, i.e., instead of broadcasting all sensing information to a centralized agent and solve a large-scale decision-making problem, each smart device communicates with a limited set of neighboring devices. This will also pave the way for implementing federated learning as a promising solution for distributed decision making.