Over the past few years, workout tech was able to utilise smart software and camera tracking to enhance training alone. This paper presents a fitness assistant that is a browser-based implementation that works on AI, automatically counting the reps and identifying the incorrect postures in real-time using a standard web camera. It takes the place of special gear by using tools such as MediaPipe and TensorFlow to map significant body points when exercising. These systems accompany your limbs in examining the way in which joints bend and move as time goes on. When something is out of place, feedback appears immediately - assistance in correcting the technique in time. This correctly improves the accuracy of learning and reduces the risk of exercise injury. The device is paired with an interactive online training program to train, monitor progress or review previous outcomes - no wearable devices are required. It has passed tests with regards to its ability to detect correct form during the execution of such moves as squats, lunges, or push-ups and pose checks. The proposed option would be effective in terms of online fitness, monitoring progress in recovery, or upgrading gym equipment - it provides a low-cost solution to exercise progression smarter.

The consolidation of public safety strategies based on closer ties between police institutions and the community has proven to be an effective approach to preventing urban crime. With the advancement of emerging technologies, such as data analysis, smart cameras, real-time monitoring, and digital platforms, the potential of preventive policing practices is expanding. This article discusses the integration between community policing and innovative technologies, analyzing how these resources strengthen decision-making, improve communication between the police and the population, and contribute to crime reduction. Through theoretical review and analysis of experiences applied in different urban contexts, it argues that the synergy between collaborative practices and technological tools enables more efficient, transparent, and participatory security models. It concludes that the strategic adoption of these instruments must be accompanied by governance policies, ethical principles, and citizen participation to guarantee their legitimacy and effectiveness.

ABSTRACT The rapid IoT device proliferation has greatly increased the attack exposure, making IoT networks highly susceptible to cyber threats. Conventional intrusion detection systems (IDSs) have trouble with the complexity of IoT networks due to their massive, heterogeneous, and real‐time data streams. It is the immense amount of information produced by various IoT devices (e.g., sensors, cameras, and wearables) that send data streams continuously in real time. This impacts IDSs as it becomes difficult to process, analyze, and identify threats rapidly and precisely. The variety and velocity of data can overwhelm conventional IDSs, resulting in delays, ignored attacks, or false positives, particularly under limited computational resources common in IoT settings. Existing IDS methods frequently have poor scalability, large false‐positive rates, and insufficient real‐time threat detection, failing to ensure both data security and privacy. To address these issues, this paper introduces an optimized deep learning‐driven model called dual sampling dilated pre‐activation residual attention convolutional neural network optimized using greylag goose optimization (DSD‐PRA‐ConNet‐GGO), which integrates blockchain technology for intrusion detection and prevention in IoT networks. The methodology starts with data acquisition from various IoT devices and sensors, such as smart cameras and environmental sensors, to capture traffic patterns and potential intrusions. The system shows superior performance, achieving 15.59% to 36.88% higher accuracy compared to existing methods such as LSTM‐IDS, ML‐XGBoost, RNN‐IDS, and DL‐DFCN, based on evaluations conducted using the BoT‐IoT dataset, which includes a wide range of realistic attack scenarios and benign traffic commonly encountered in IoT environments.

Abstract Introduction/Objective Medical student engagement in pathology remains a challenge in modern curricula. To address this, we implemented an innovative, immersive learning model that blends simulation, technology, and clinical relevance to transform how our students interact with laboratory medicine. Methods/Case Report We established a diagnostic teaching simulation lab equipped with microscopes integrated with tablets, allowing students to digitally view, annotate, and save slides while creating personalized flashcards. Point-of-care testing simulations were incorporated to mirror real-world diagnostic scenarios. As part of the Transition to Residency course, targeted sessions reinforced transfusion medicine and autopsy indications. Students also participated in community outreach initiatives aimed at increasing public awareness of laboratory medicine. Additionally, technologies like smart camera glasses and augmented reality (AR) headsets were incorporated into student activities. Results Student engagement markedly increased. In post-session surveys, 95% of students (N = 126) found the sessions helpful, with the most frequent feedback being requests for more lab sessions. Beyond the classroom, students engage in community outreach. Conclusion This forward-thinking approach has redefined how students experience pathology. The program has sparked new interest in pathology electives and fostered a greater appreciation for laboratory medicine’s clinical impact. This model demonstrates the power of combining diagnostic simulation and digital tools to elevate pathology education and engagement.

The integration of machine vision systems with programmable logic controllers (PLCs) is increasingly crucial for automated quality assurance in Industry 4.0 environments. This paper presents an applied case study of vision–PLC integration, focusing on real-time synchronization, deterministic communication, and practical industrial deployment. The proposed platform combines a Cognex In-Sight 2802C smart camera (Cognex Corporation, Natick, MA, USA) with an Allen-Bradley Compact GuardLogix PLC through Ethernet/IP implicit cyclic exchange. Three representative case studies were investigated: 3D-printed prototypes with controlled defects, automotive electrical connectors inspected using Cognex ViDi supervised learning tools, and fiber optic tubes evaluated via a custom fixture-based heuristic method. Across all scenarios, detection accuracy exceeded 95%, while PLC-level triple verification reduced false classifications by 28% compared to camera-only operation. The work highlights the benefits of PLC-driven inspection, including robustness, real-time performance, and dynamic tolerance adjustment via HMI interfaces. At the same time, several limitations were identified, including sensitivity to lighting variations, limited dataset size, and challenges in scaling to full production environments. These findings demonstrate a replicable integration framework that supports intelligent manufacturing. Future research will focus on hybrid AI–PLC architectures, extended validation on industrial production lines, and predictive maintenance enabled by edge computing.

Inspired by the stabilization of a bird's head by the arc-shaped supporting structure of its neck, a nonlinear vibration isolator that imitates these properties is proposed. The geometry and stiffness properties of the isolator, which consists of three rods connected by torsional springs, are designed for a specific payload to realize an isolator with a very low natural frequency offering good vibration isolation properties over a wide frequency range. A prototype is constructed to isolate a smart phone camera mounted on a bicycle from vibration excitation due to a rough road. The results show that the isolator is effective above a frequency of approximately 1 Hz.

Abstract This article describes a case study in which adhesive failures were observed in smart camera assemblies during production. The analysis demonstrated that Raman spectroscopy enables rapid, nondestructive detection of silicone contamination in camera assemblies, enhancing failure analysis and improving manufacturing reliability.

The widespread adoption of smart cameras in areas such as security monitoring, intelligent transportation, and industrial quality inspection is fueled by the growing number of Internet of Things (IoT) devices and continuous progress in artificial intelligence (AI) algorithms. However, traditional video surveillance systems rely on cloud computing and face challenges like limited bandwidth, high latency, and privacy risks. Edge computing, a distributed architecture that brings computation and storage closer to the data source, offers an effective way to improve smart camera video processing and recognition. Therefore, the paper investigates smart camera video processing and recognition systems based on edge computing reviewing key technologies and implementation methods via recent research and typical applications. In addition, it examines the progress and features of edge platform architecture, video analysis and object detection algorithms, resource scheduling and energy management, model compression, and data security and privacy protection. The results show that edge-intelligent video systems are effective in reducing network load, lowering response latency, and improving the security of local data processing. However, they still face technical challenges in heterogeneous resource management, real-time scheduling, and multi-task collaboration. As such, this paper further reviews the main existing issues and offers a practical outlook on system optimization and future applications.

The use of smart cameras in industrial automation has opened up great opportunities to improve accuracy, efficiency, and productivity in the object detection and sorting process. The problems faced in object detection and sorting systems are the variability of environmental conditions, such as changing lighting and varying conveyor speeds, which can affect the accuracy of object detection. Therefore, this study aims to optimize the object detection and sorting process using the Festo SBOI-Q-R3C-WB smart camera through advanced image processing techniques, machine learning algorithms, and parameter adjustments such as sensor feature analysis, pattern matching, and lighting settings (300–1000 lux) and image filters. Experiments were conducted with cylindrical objects, varying conveyor speeds (0.5–2 m/s), and lighting intensity to evaluate system performance. The results showed that optimization of the Region of Interest (ROI) and the Canny Edge Detection algorithm successfully increased the detection accuracy from 82% (baseline) to 95%. The increase in lighting (optimal at 700 lux) and the use of adaptive contrast filters provided an additional 15% performance, resulting in a final accuracy of 98%. Statistical analysis using a paired t-test (α = 0.05) showed that the reduction in sorting errors was significant, from 8.5% (conventional system) to 1.7% (optimal system), with a p-value < 0.001. The system was also able to adapt to changes in conveyor speed up to 2 m/s and variations in object shape, with consistent accuracy above 95%. These findings prove that the integration of Festo's smart camera with optimized algorithms is a reliable solution for industrial automation, especially in dynamic sorting applications. Further developments could include the integration of deep learning for more complex object detection and increased processing speed through edge computing

ABSTRACT Smart cameras are increasingly integrated into intergenerational co-parenting in urban Chinese dual-earner families. This study investigates how smart cameras mediate parenting and reshape family dynamics in this context. Based on in-depth interviews with 19 working mothers,it explores how smart cameras influence mothering practices and familial relationships by enhancing visibility. The adoption of smart cameras in parenting is propelled by both the strategic initiatives of working mothers and the commercial imperatives of technology providers. Working mothers simultaneously occupy dual roles as both viewers and the viewed. They monitor domestic parenting activities remotely while at work, facilitating virtual participation that mitigates feelings of guilt and anxiety. Additionally, they anticipate that their parenting efforts at home will be recognized and appreciated by their husbands, potentially fostering greater paternal engagement. The visibility afforded by smart cameras functions as both a facilitator and a potential source of conflict in parenting communication, contingent on existing co-parenting dynamics and the quality of familial relationships. Overall, smart cameras embody working mothers’ innovative strategies for leveraging digital media to mitigate tensions between professional responsibilities and family obligations, thereby shaping new maternal practices and facilitating the redistribution of parenting labour.

This paper presents the novel, smart, commutable, and self-regulated SSF-Roundabout as one of the potential solutions in the environment of smart mobility. The SSF-Roundabout implements traffic counting systems, smart cameras, LED road markers, and Variable Message Signs (VMS) on arms. Based on the instantaneous detection of the traffic demand level, vehicles can be properly channelled or not into right-turn bypass lanes, which the roundabout is equipped with in every arm, to guarantee the requested capacity, Level of Service (LOS), and safety. In total, fifteen very different layout configurations of the SSF-Roundabout are available. Several traffic analyses were performed by using ad hoc traffic engineering closed-form models and case studies based on many origin-destination traffic matrices (MO/D(t)) and proportions of CAVs in the traffic stream (from 0% to 100%). Simulation results demonstrate the correlation between layout scenarios, traffic intensity, distribution among arms, and composition in terms of CAVs and their impact on entry and total capacity, control delay, and LOS of the SSF-Roundabout. For instance, the right-turn bypass lane activation may produce an entry capacity increase of 48% and a total capacity increase of 50% in the case of 100% of CAVs in traffic streams.

BackgroundManaging sleep is a challenging experience in early parenthood, and infant sleep problems are associated with negative outcomes within the family. A large market of devices to monitor infants’ real-time health information during sleep has emerged, including smart cameras, under-mattress sensors and wearable devices. The impacts of these products on maternal and parental mental health and medical decision-making are poorly understood.MethodsWe performed a systematic search for products detecting health data from sleeping children on the global retail platform Amazon in March 2023. A total of 11 262 unique reviews from 48 eligible products were retrieved from the USA, Canada, UK, and Australia sites and subjected to sentiment and thematic analyses to capture the characteristics of user families, contexts of device use and impacts on maternal and child health.ResultsParental anxiety and infants’ high-risk medical status were cited by families as the main reasons to purchase products. When devices worked well, their use was associated with improved parental sleep quality and decreased anxiety. However, poor device performance was commonly reported and was linked to increased parental stress and anxiety and disrupted child sleep. Users reported making medical decisions based on device output. Price, privacy, and unsafe use of devices emerged as ethical issues.ConclusionsUse of a smart sleep device in the home is common and has implications for the health of both children and adults. Benefits and harms must be understood by parents and healthcare providers in order to support evidence-based decision-making around their use.

Radio frequency (RF)-based wireless systems are broadly used in communication systems such as mobile networks, satellite links, and monitoring applications. These systems offer outstanding advantages over wired systems, particularly in terms of ease of installation. However, researchers are looking for safer alternatives as a result of worries about possible health problems connected to high-frequency radiofrequency transmission. Using the visible light spectrum is one promising approach; three cutting-edge technologies are emerging in this regard: Optical Camera Communication (OCC), Light Fidelity (Li-Fi), and Visible Light Communication (VLC). In this paper, we propose a Multiple-Input Multiple-Output (MIMO) modulation technology for Internet of Things (IoT) applications, utilizing an LED array and time-domain on-off keying (OOK). The proposed system is compatible with both rolling shutter and global shutter cameras, including commercially available models such as CCTV, webcams, and smart cameras, commonly deployed in buildings and industrial environments. Despite the compact size of the LED array, we demonstrate that, by optimizing parameters such as exposure time, camera focal length, and channel coding, our system can achieve up to 20 communication links over a 20 m distance with low bit error rate.

The frequent occurrence of construction accidents is a severe challenge faced by the construction industry. Traditional management methods can no longer meet the safety requirements of modern engineering construction. This study is centered on technology empowerment. It has established an accident prevention management system that covers pre-event prevention, in-process monitoring, and post-event emergency response. A comprehensive safety management solution has been formed by integrating advanced technologies such as Building Information Modeling (BIM), big data and machine learning, intelligent personnel training systems, multi-sensor integration systems, unmanned aerial vehicles (UAVs) paired with smart camera, AI behavior recognition, and the interaction between the Internet of Things (IoT) and command platforms. This technical system is expected to lower the accident rate and increase the effectiveness and precision of construction safety management. This system provides strong support for the safe and stable development of the construction industry, and also offers references for safety management in other fields.

In general, deficient birth weight neonates suffer from hypoglycemia, and this can be quite disadvantageous. Like oxygen, glucose is a building block of life and constitutes the significant share of energy produced by the fetus and the neonate during gestation. The fetus receives glucose from the placenta continuously during gestation, but this substrate delivery changes abruptly, and the fetus’s metabolism changes significantly at birth. Hypoglycemia is one of the most frequent pathologies affecting the change of newborns in neonatal critical care units. This work is now introducing a system, HAPI-BELT, empowered by dual intelligent sensors and Deep Learning (DL) algorithms for tracking and continuously detecting hypoglycemia in preterm newborns. This article comprises a smart belt with an intelligent camera and photoplethysmography (PPG) attached. This device tracks changes in the infant’s motion, skin colour, and breathing patterns; this is done through a PPG sensor strapped either on the belly or chest of an infant, logging information on heart functioning. The digital data gathered by this PPG sensor and image data captured from the smart camera are then processed by a Raspberry Pi Zero 2 W. It does most of the data analysis and decision-making. Feature Extraction (FE) is done through CAT-Swarm Optimization. Based on features, the sorted-out data gets evaluated through a GRU-LSTM (Gated Recurrent Unit - Long Short-Term Memory) network to identify the state of the infant as usual and suggestive of hypoglycemia—blood glucose below 70 mg/dL, pale complexion, profuse perspiration. When hypoglycemia is identified, an alert is sent to the medical professionals to take necessary action with utmost urgency. Therefore, an integrated approach ensuring timely medical interventions and real-time monitoring can help better outcomes for preterm newborns.

Abstract Workplace safety in construction is a significant issue worldwide. It is well known that thousands of accidents happen every year. Worker safety is a top priority and can be addressed with innovative technology. AI can transform safety practices by reducing accidents and streamlining operations. This paper examines how AI technologies like drones, IoT sensors, smart cameras, and predictive algorithms can be used in risk monitoring and prevention. These tools enable immediate hazard detection and alertness so you can take preventative measures and have better working conditions on-site. Based on case studies in Italy, Spain, and France, we show that AI solutions have reduced workplace accidents by 35%, so they work. However, AI in construction has challenges, such as high implementation costs, resistance to change, and ethical issues around workers’ privacy. Despite these obstacles, the benefits – from cost savings to increased productivity and worker protection – far outweigh the drawbacks. The paper argues for public policies encouraging AI in construction safety and proposes further research avenues to develop the best solutions. This could be the way to a safer workplace through AI, as the study shows that AI can offer a more proactive and data-driven approach, a safer and more sustainable future for the industry.

Current privacy protections for smart home devices rarely consider bystanders' privacy, whose preferences are varied and may differ from primary users. We use Contextual Integrity theory to explore context-dependent variation in privacy norms regarding smart home bystanders’ data. We conducted a vignette-based survey with 761 participants in the US, varying parameter values to capture acceptability judgments regarding bystander information flows in certain situations: domestic work, shared housing, visiting a friend overnight, and Airbnb. We found that recipients and purposes of sharing impact acceptance the most. Sharing interaction logs was more acceptable than audio or video. Sharing smart speaker data was less acceptable than smart camera or smart door lock data. We found nuanced interaction effects between factors in different smart home situations, and differences between protections most favored by participants playing bystander vs. owner roles. We provide design and policy recommendations for smart home privacy protections that consider bystanders' needs.

Arrays of photodetector-based pixel sensors are ubiquitous in modern devices, such as smart phone cameras, automobiles, drones, laptops etc. Two-dimensional (2D) material-based photodetector arrays are a relevant candidate, especially for applications demanding planar form factors. However, shortcomings in pixel density and prototyping without cross contamination limit technology adoption and impact. Also, while 2D material detectors offer high absorption, graphene’s closed bandgap results in undesirably high dark currents. Here, we introduce the experimental demonstration of dense planar photodetector arrays. We demonstrate a micrometer-narrow pitched 2D detector pixels and show this approach’s repeatability by verifying performing of a 16-pixel detector array. Such dense and repeatable detector realization is enabled by a novel, selective, contamination-free 2D material transfer system, that we report here in automated operation. The so realized photodetectors responsivity peaks at a high 0.8 A/W. Furthermore, we achieve uniform detector performance via bias voltage tuning calibration to maximize deployment. Lastly, we demonstrate 2D arrayed photodetectors not only on a silicon chip platform but verify array performance on flexible polymer substrates. Densley-arrayed, flat, bendable, and uniform performing photodetector pixels enable emerging technologies in the space where lightweight and reliable performance is required, such as for the smart phone and emerging VR/AR markets, but also for smart gadgets, wearables, and also for size-weight-power-constrained aviation and space platforms.

Smart-home devices, such as smart speakers and cameras, provide convenient home automation and media control, but the sensors that continuously collect data in users' homes create privacy concerns. To attempt to increase trust, device manufacturers and researchers have developed privacy features, such as indicator lights, hardware controls, and microphone jammers. To inform the design of more trustworthy products, we conducted a 489-participant online survey to understand how device type, brand, and privacy features impact trust. Our survey also examined whether providing more information about privacy features' limitations changed participants' perceptions. Contrary to our expectations, device brand did not significantly impact trust. Hardware mute controls were most effective at increasing trust. Participants expressed high intent to use familiar software-backed features, while expressing reservations about novel features proposed by researchers (e.g., jamming devices). Participants' reactions after seeing information about privacy features' limitations varied by feature, suggesting that the features' strengths and weaknesses are not equally well-understood. Based on our findings, we make several recommendations, including that device manufacturers and researchers explore making software-backed features more secure, as our results suggest that users may use those features even if they do not consider them reliable or trustworthy.

In the age of smart cities, maintaining safe and reliable data transmission over large-scale sensor networks is becoming more important. These networks, which are often made up of smart cameras and IoT devices, are susceptible to abnormalities like rogue nodes, sensor failures, and traffic spikes, which may jeopardize system integrity and performance. Traditional centralized anomaly detection methods suffer from latency and scalability difficulties, particularly in high-density settings. To solve this issue, this paper proposes a new anomaly detection system that combines Ant Colony Optimization (ACO) and clustering approaches in an OMNeT++ simulation environment. The system uses a fog-cloud architecture, with fog nodes doing localized processing and clustering to decrease latency and data overhead, and ACO for efficient data routing and anomaly detection. Simulations were run with three distinct sensitivity settings: baseline, high, and low, to assess detection accuracy, precision, recall, and F1-score. The suggested technique showed considerable increases in all measures, with baseline scenario accuracy improving from 86.5% (without detection) to 92.4% (with detection), and F1-score from 0.64 to 0.837. Furthermore, the system demonstrated improved processing efficiency and decreased network use at both the fog and cloud levels, indicating its applicability for real-time anomaly identification in dynamic and scalable smart city networks.