The management of physical resources is one of the current research priorities in the field of cloud manufacturing. Managing these physical resources is critical to the product lifecycle. Resource uniform description models can describe various forms of physical resources as data in a uniform format, which facilitates the management and retrieval of resource data. However, resource data is characterized by its large scale and complexity, while the issue of whether the existing resource unified description model can still accurately describe new resource data and whether the resource data can be fully matched with the model is an urgent one at present. In this paper, an optimization strategy based on deep reinforcement learning (DRL) for a resource uniform description model is proposed, which is to ensure that this model can autonomously propose a solution to the current situation when it cannot describe the resource data in a suitable way. A Markov decision process and deep Q network algorithm are introduced to train an agent that can independently optimize the model when the resource data does not match the model. Simulation experimental results validate the effectiveness of the DRL-based optimization strategy when the resource uniform description model does not match the resource data.

Deep neural networks often need to be trained with a large number of samples in a dataset. When the training samples in a dataset are not enough, the performance of the model will degrade. The Generative Adversarial Network (GAN) is considered to be effective at generating samples, and thus, at expanding the datasets. Consequently, in this paper, we proposed a novel method, called the Stacked Siamese Generative Adversarial Network (SSGAN), for generating large-scale images with high quality. The SSGAN is made of a Color Mean Segmentation Encoder (CMS-Encoder) and several Siamese Generative Adversarial Networks (SGAN). The CMS-Encoder extracts features from images using a clustering-based method. Therefore, the CMS-Encoder does not need to be trained and its output has a high interpretability of human visuals. The proposed Siamese Generative Adversarial Network (SGAN) controls the category of generated samples while guaranteeing diversity by introducing a supervisor to the WGAN. The SSGAN progressively learns features in the feature pyramid. We compare the Fréchet Inception Distance (FID) of generated samples of the SSGAN with previous works on four datasets. The result shows that our method outperforms the previous works. In addition, we trained the SSGAN on the CelebA dataset, which consists of cropped images with a size of 128 × 128. The good visual effect further proves the outstanding performance of our method in generating large-scale images.

This paper presents an intelligent helmet recognition model in complex scenes based on YOLOv5. Firstly, in construction site projects, consider that the photograph which needs to be identified has numerous problems. For example, helmet’s pixels are too tiny to detect, or a large number of workers makes helmets appear densely. A SE-Net channel attention module is added in different parts of the network layer of the model, so that the improved model can pay more attention to the global variables and increase the detection performance of small target information and dense target information. In addition, this paper constructs a helmet data set based on projects and adds training samples of dense targets and long-range small targets. Finally, the modified mosaic data enhancement reduces the influence of redundant background on the model and improves the recognition accuracy of the tiny target. The experimental results show that in the project, the average accuracy of helmet detection reaches 92.82%. Compared with SSD, YOLOv3, and YOLOv5, the average accuracy of this algorithm is improved by 6.89%, 8.28%, and 2.44% and has strong generalization ability in dense scenes and small target scenes, which meets the accuracy requirements of helmet wearing detection in engineering applications.

In order to effectively solve the problem of heterogeneous design/manufacturing/service resources and isolation in the whole lifecycle and realize unified description of design/manufacturing/service resources and resource sharing across subjects and stages, this paper proposes a hierarchical and modularized ontology-based resource-unified descriptive model, according to the characteristics of design/manufacturing/service resources. We analyze all kinds of properties of the resources, design a specific descriptive model of ontology, function, and service, ensure the consistency and independence of resource descriptions, and use the OWL (Web Ontology Language) ontology descriptive language and Protégé tools to verify. Then, based on the unified descriptive model, a resource matching method based on multi-level tags is proposed, which matches the task request with the resources in the resource library, selects the resources that meet the task request, and guarantees the resource sharing across subjects and stages. The resource matching work first performs task description and decomposition, and uses information entropy and rough set theory to sort the importance of subtasks, then uses the semantic similarity algorithm to complete multi-level tags’ matching. Finally, two examples are used to prove the feasibility and effectiveness of the experiment.

Leakage current, overload and short-circuit cause harmful effects on the human body as well as electrical appliances. They may cause an electrical shock and can be sources of fire. We present in this paper a smart Residual Current Circuit Breaker with Overcurrent protection (a smart RCBO) that protects users and electrical devices against the risks of leakage current and overcurrent. The purpose of this paper is to computerize a traditional RCBO as an innovative protection device. The smart RCBO is a programmable device that works based on microcontroller technology. This device is fully automated and has adjustable settings to ensure safety while allowing increased flexibility to better match users' needs.

Presents author name corrections in the paper, “Adaptable context-aware cooking-safe system,” (Yared, R. and Abdulrazak, B.), IEEE Trans. Services Comput., vol. 11, no. 2, pp. 236–248,Mar./Apr. 2018.

mHealth is an emerging research field that attracts health caregivers, researchers and application developers. mHealth solutions are based on sensors, mobile devices, and wireless networks to provide healthcare services to patients. mHealth enables professionals to make appropriate decisions and interventions, and patients can manage their activities of daily living independently. Walking activity is a very important indicator to evaluate the physical activity of people for healthy lifestyle. We present in this paper the design of our smart-phone based system to monitor walking activity that constitutes an assistive mHealth solution to notify people about the current level of their walking activity. In addition, we briefly review known existing mHealth solutions in order to clarify the techniques used to build mHealth solutions. We also discuss few challenges that face mHealth solutions.

Kitchen safety is a highly important concern for daily living activities. Cooking, usually, is accompanied with several risks particularly for elderly people, due to aging associated impairments. Therefore, cooking-safe environment is required to enhance safety. In this paper, we present our cooking-safe smart oven system which manages the detection of risk situations and determines their severity levels according to the contextual information around oven. The context is gathered via sensors deployed in the kitchen environment. The cooking-safe system is composed of sensor nodes, actuators, microcontroller, and a computing unit. Cooking related risks are managed by the fuzzy logic based reasoning engine of the cooking-safe system. We also present in details our risk prevention algorithms which constitute the basic concepts of the reasoning engine. We discuss the system evaluation in real-world environment, and the interventions via interactive interfaces with users.

Cooking activity is accompanied with several risks, mainly for elderly people due to attention and memory impairment. Literature reveals that the kitchen is the second most common place for domestic accidents. We argue that enhancing safety during cooking activities could be achieved via designing a cooking-safe environment based on insightful risk analysis and assessment study. This paper presents our study on risk analysis and assessment during cooking, in order to build a cooking-safe environment. The study is based on theoretical and real-world experimentations. Risk analysis and assessment enabled us to determine the three major risks (i.e., fire, burn and intoxication by gas/smoke) and the pertinent parameters to quantify these risks. The results reveal that the pertinent parameters are: concentrations of volatile organic compounds, alcohol, and carbon monoxide gases in the cooking smoke, utensil temperature, burner temperature, relative humidity, and presence of a utensil on burner. We present in details our study on risk analysis and assessment, including the methodology and the findings.

Physical activity is a very important indicator of healthy lifestyle. Physical activity recognition, classification and evaluation is a significant research area, both in academic as well as in healthcare domain to help patients achieving the benefits of performing physical activities. Physical activity recognition and evaluation enable professionals to make appropriate decisions and interventions, and patients can manage their activities of daily living independently. We present in this paper our smart-phone based system to recognize, classify and evaluate jogging, walking, and standing activities using the GPS and the accelerometer built-in smartphone sensors. Our system notifies caregivers and patients if the level of physical activities of patients falls below a certain threshold.

fall detection is very important to provide adequate interventions for aging people in risk situations. Existing techniques focus on detecting falls using wearable or ambient sensors. However, they do not consider fall orientations. In this paper, we present our novel fall detection system based on smart textiles and machine learning techniques. Using a non-linear support vector machine, we determine the fall orientation which will be helpful to study the impact of a fall according to its orientation. Additionally, we classify falls based on their orientations among 11 classes (moving upstairs, moving downstairs, walking, running, standing, fall forward, fall backward, fall right, fall left, lying, sitting). Results show the reliability of the proposed approach for falls detection (98% of accuracy, 97.5% of sensitivity and 98.5% specificity) and also for fall orientation (98.5% of accuracy).

While elderly people perform their daily indoor activities, they are subjected to several risks. To improve the quality of life of elderly people and promote healthy aging and independent living, elderly people need to be provided with an assistive technology platform to rely on during their activities. We reviewed the literature and identified the major indoor risks addressed by assistive technology that elderly people face during their indoor activities. In this paper, we identify these risks as: fall, wrong self-medication management, fire, burns, intoxication by gas/smoke, and the risk of inactivity. In addition, we discuss the existing assistive technology systems and classify the risk detection algorithms, techniques and the basic system principles and interventions to enhance safety of elderly people.

The recent advances in sensor technology empower adaptable smart systems targeting safety. Smart sensing in ambient intelligence systems enables to enhance safety during cooking which is very important for aging people. Therefore, we worked on a project of building a smart oven system. We studied the principal risks around oven and analyzed the characteristics and the basic functional principles of the existing sensors to select the most appropriate. In this paper, we present the analysis of the sensors used and the test results of each sensor in a real-world cooking environment.

Active life style promotes healthy aging. Cooking, particularly, is an important activity of daily living for elderly people. However, cooking is accompanied with several risks for this population category due to the aging related decline. Assistive technology is a promising solution to assist elderly people and enhance their safety. We introduce in this paper a context-aware cooking-safe environment, an innovative assistive technology to enhance safety of elderly people while cooking. We mainly focus in this paper on the hardware architecture of our system. The context is gathered via sensors deployed in kitchen environment. The system is composed of sensor nodes, microcontroller, and a computing unit. We also introduce in this paper a solution for sensors positioning and system integration in a real-world cooking environment. Furthermore, we present the results of sensors testing in real-world configurations.

Elderly people are subjected to several safety issues while performing Activities of Daily Living. On the other hand, Assistive technology is a promising solution to enhance safety of elderly people, and consequently improve their quality of life and independent living. We present in this paper a review of the major risks affecting elderly people in outdoor environment and the related assistive technology.

Risk situations may affect elderly people during outdoor Activities of Daily Living. The gravity of this problem becomes more significant with the rapidly growing number of elderly people around the world. Assistive technology is a promising solution to enhance safety of elderly people in outdoor environment. It plays an essential role in providing them with a higher quality of life and autonomy. In this paper, we present the result of our study on major risk factors that affect elderly people during outdoor activities. We also discuss existing assistive technology across recent work related to outdoor risks. In addition, we provide a framework for existing assistive technology that addresses outdoor risks. To the best of our knowledge, this is the first review about major risks that affect elderly people in outdoor environments, and that describes technological solutions in the domain of ambient assistive technology.

Kitchen is the second place where the majority of domestic accidents occur, and in particular oven presents the most principal source of fire accidents in residence. Therefore, enabling kitchen safety is a major factor for ageing people independent living. This paper presents the hardware architecture of our cooking-safe system that targets enhancing safety of ageing people while cooking. The system is based on insightful cooking risk analysis that enables to determine the pertinent parameters to be monitored and measured while cooking. This paper also presents the results of our experimental study that leads us to select the appropriate sensors to constitute the basic building block of our cooking-safe system. The system is composed of sensor nodes to monitor events around oven, then the sensory data is transmitted to a computing unit. The system proactively reacts to hazards in order to prevent cooking associated risks.

Risk analysis during cooking activities enables to build a cooking-safe system in order to enhance safety of elderly people in smart kitchen. The Kitchen is the second place where majority of domestic accidents occur, and in particular the oven presents the most principal reason of fire accidents in the residence. The paper presents insightful cooking risk analysis that permits to determine the pertinent parameters to be monitored and measured during cooking in order to prevent risks. We investigated several cooking experiments, and analyzed the composition of heated cooking materials, the concentrations of gases in the cooking smoke, and humidity. The pertinent parameters determined in this paper are: concentrations of gases in the cooking smoke, ambient temperature, utensil temperature, burner temperature, relative humidity, and presence of an object on burner.

Cloud federation is considered the future of cloud providers, and for its importance, many researchers proposed federation mechanisms and automatic pricing schemes. To the best of our knowledge, all the proposed federation mechanisms fall in the same fatal hazard by selecting very far cloud providers to establish federation with and this severely decrements their customer satisfaction. In this paper, we raise the awareness on the hazards of price-based cloud selection mechanisms and propose views on how to solve the discussed hazards.

Enabling kitchen safety is crucial for elderly people independent living. Cooking, usually, is accompanied with several risks particularly for elderly people, due to aging associated impairments. Therefore, cooking-safe environment is required to enhance safety of elderly people. This is the motivation behind our research work on building a cooking-safe system. In this paper, we present the fuzzy-logic based reasoning engine used for our cooking-safe system. The reasoning engine manages the detection of risk situations and determines their severity levels according to the contextual information around oven. In this study, we have considered three levels of risk severity based on experimentally determined threshold values.