CCTV Research Articles

Object Detection Using CNN

Object detection system using Convolutional Neural Network(CNN) that can accurately identify and classify objects in videos. The purpose of object detection using CNN to enhance technology such as security cameras, smart devices by enabling them to identify and understand objects in videos. Object detection using CNN is a fascinating filed in computer vision. Detection can be difficult since there are all kinds of variations in orientation, lighting, background that can result in completely different videos of the very same object. Now with the advance of deep learning and neural network, we can finally tackle such problems without coming up with various heuristics real-time. The project “Object detection using CNN for video streaming” detects objects efficiently based on CNN algorithm and apply the algorithm on image or video data. In this project, we develop a technique to identify an object considering the deep learning pre-trained model MobileNet for Single Shot Multi-Box Detector (SSD). This algorithm is used for real-time detection and for webcam, which detects the objects in a video stream. Therefore, we use an object detection module that can detect what is in the video stream. In order to implement the module, we combine the MobileNet and the SSD framework for a fast and efficient deep learning-based method of object detection. The main purpose of our research is to elaborate the accuracy of an object detection method SSD and the importance of pre-trained deep learning model MobileNet. The experimental results show that the Average Precision (AP) of the algorithm to detect different classes as car, person and chair is 99.76%, 97.76% and 71.07%, respectively. The main objective of our project is to make clear the object detecting accuracy. The existing methods are Region Based Convolutional Neural Network(R-CNN) and You Only Look Once(YOLO).R-CNN could not pushed real time speed though its system is updated and new versions of it are deployed and YOLO network is popular but YOLO is to struggle to detect objects grouped close together, especially smaller ones. To avoid the drawbacks of these methods we proposed this model which included single shot multi-box detector (SSD), this algorithm is used for real time detection and Mobile-Net architecture.

A Novel Approach for Surveillance Compression using Neural Network Technique

The integration of closed-circuit television (CCTV) monitoring is crucial in the field of video processing, which provides an efficient method for comprehensive surveillance. However, a key challenge associated with this practice is its substantial demand for storage space. Typically, surveillance footage is stored in hard disk drives, and due to limited storage spaces, it is deleted after some time. To address this issue, an innovative method for compressing CCTV video, named object detection-based surveillance compression (ODSC), is introduced. Our ODSC model is divided into two steps: -i) depending upon the objects in the video, determine the significant and non-significant frames of surveillance video using the neural network approach YOLOv5s & YOLOv7-tiny and Yolov8s ii) construct the video of significant frames. Following a comprehensive analysis of the experimental outcomes, it is noted that YOLOv8s stands out with a remarkable detection accuracy of 99.7% on the COCO dataset. Our ODSC approach is reducing the storage space greatly and achieving an average compression ratio of up to 96.31% using YOLOv8s, which surpasses the existing state-of-the-art methods.

Harnessing the power of artificial intelligence: A new door for quick surgery in Pakistan.

Artificial intelligence (AI) has the potential to transform surgery in Pakistan, improving results, reducing complications, and increasing patient safety. Deep learning, a branch of machine learning, can assist surgeons in making wise judgments. Pubmed and Research Gate discuss the promise of AI in surgery. Incorporating AI in healthcare systems can expedite diagnosis and management while avoiding injudicious resource allocation. AI-based techniques in cardiology, nephrology, and neurology enable high-accuracy detection of cardiovascular disease risks, kidney disease treatment, and epileptic episode identification. Neurological devices like bispectral index monitor (BIS) and Near-infrared spectroscopy (NIRS) utilize advanced technology for reliable monitoring and objective diagnosis of neurological issues (Ahmed, 2022). AI uses electronic data and neural network methods to evaluate operating room logistics, time management, and anesthesiologist activities using electronic data and neural network methods (Khan F. H., 2019). AI algorithms are effectively detect minute differences for accurate diagnosis, with studies showing high specificity, sensitivity, and inter-operator repeatability. AI can be used to train and assess neurosurgical residents and early mid-career surgeons, improving diagnosis and 3D simulation labs (Shlobin, 2022). Surgeons play a crucial role in adopting AI-based technologies for surgical care by partnering with data scientists to capture novel clinical data and generate meaningful interpretations. They should demand transparency and interpretability in algorithms to hold AI accountable for its predictions and recommendations.AI advancements in plastic surgery practice, research, and education offer opportunities for improvement. Combining AI-enabled decision-making tools with predictive analytics and human intuition, surgeons can make real-time decisions based on 3D planning, anatomical localization, and navigation (Rasteau, 2022). While current AI tools cannot perform complex surgical procedures, advancements may enable them to perform more complex tasks in the future. Pakistan is a significant market for AI-based solutions, utilizing technology in various industries to address challenges and boost demand. The country has enhanced its self-security systems, including AI-powered missiles, cyber security, and effective cameras (Khan, 2022). AI allows tasks to be completed more precisely and efficiently, with machine learning and deep learning being advanced subtypes. In developing countries like Pakistan, AI tools are needed for patient-centred diagnosis and treatment assistance, especially in emergency surgery such as cardiac illnesses or life threatening bleeding caused road traffic accident. Hence insuring patient receive care timely. An appropriate budget should be allocated for AI technologies in the health sector.

Seat belt detection using gated Bi-LSTM with part-to-whole attention on diagonally sampled patches

One of the high-risk behaviors leading to severe traffic injuries is not wearing a seat belt. It is therefore very important to be able to automatically detect seat belts from surveillance images, encourage drivers to wear seat belts, and enhance passenger safety. In this paper, a novel deep neural network, Gated Bi-directional Long Short-Term Memory network with part-to-whole attention (GBL-PA), is proposed for seat belt detection from surveillance images. The innovation of our model lies in its unique diagonal sampling strategy, which meticulously captures the seat belt’s fine details, typically oriented from top right to bottom left across the torso of vehicle occupants. Our framework’s novelty is further encapsulated by the part-to-whole attention mechanism, which intelligently harmonizes the detailed local information from seat belt-specific patches with the broader contextual insights from the regional proposals. The pioneering design of a Gated Bi-directional LSTM network facilitates the dynamic integration of interactions across patches to deliver an optimized final prediction. The superiority of GBL-PA is established through rigorous comparison with the state-of-the-art methods on a new, large benchmark dataset comprising 14,936 images from traffic surveillance footage. Our framework demonstrates a notable improvement, achieving a mean Average Precision (mAP) of 72.3%, which surpasses the second best, YOLOX, by 0.9% mAP. This significant and consistent outperformance across various metrics underscores the transformative potential of GBL-PA in the realm of traffic safety enforcement. The source code of our framework is available at ANONYMISED.

Artificial Intelligence Based CCTV-Accident Detection System

Urban infrastructure and public safety are severely hampered by traffic congestion and accidents. This research suggests an enhanced traffic light control system that makes use of deep learning methods and IoT integration to address these problems. The system computes vehicle density in real-time and indicates smart light conditions at traffic signals by combining the object identification algorithm of YOLOv3 with Internet of Things sensors. The secret to the system is the use of YOLOv3 for precise vehicle identification and categorization in video feeds recorded by security cameras. The technology can effectively identify cars, collisions, and violent incidents on the road by utilising YOLOv3. In order to enable quick emergency response, the system sends notification alerts via GSM connection to neighbouring police stations and hospitals upon detection. In addition, the suggested system uses Internet of Things devices to calculate the number of vehicles at crossings. Traffic signal timings can be dynamically adjusted thanks to this real-time data on vehicle flow, which improves traffic flow and lessens congestion. IoT integration also makes it possible for traffic signals to have smart light indication, which adjusts signal timings in response to current traffic circumstances to improve efficiency and safety.

Building A Smart Campus: Designing An Architectural Framework For Campus Security Gates And Vehicle Asset Management With GPS Tracking Technology

Modern technology must be integrated into educational institutions as they develop into "smart campuses" in order to guarantee the security and effectiveness of day-to-day operations. This study combines GPS tracking technology to present an architectural framework for the deployment of intelligent security gates and automotive asset management systems. The objective is to build a secure and effective environment that improves campus security and maximizes the use of available resources. The suggested architecture combines a centralized software platform with innovative hardware elements, including GPS trackers, RFID readers, and security cameras. RFID-enabled security gates improve access control by limiting entrance to the college grounds to only authorized people and vehicles. Surveillance cameras simultaneously offer real-time monitoring to guarantee adherence to security procedures.
 The vehicle asset management system utilizes GPS technology to monitor campus vehicles in real-time, increasing fleet management efficiency and enhancing general campus security. GPS tracking integration allows scheduling maintenance, optimizing routes, and notifying authorities of unwanted vehicle movements.

SMART HOME MONITORING SYSTEM

The Project is about building a low-cost home automation system. It mainly focuses on creating an Internet based home automation system that can be automatically configured to run based on various conditions or that can be used to control multiple components through the internet. Wireless technology is used to enable remote access from a smartphone, PC, manually and voice command. The system is an accessible interface, affordable construction, and easy installation made it easier for controlling household electrical appliances and devices. The created system supports wireless control of lights, fans, air conditioners, televisions, Alarm, security cameras, electronic doors, computer systems, audio/visual devices, and more. It can be combined into a single portable unit. It is user friendly. Key Words: Wireless Control, Wi-Fi, Microcontroller, ESP RainMaker, Relay, Controlling of appliances, Monitoring.

Securing public spaces: public willingness to sacrifice convenience and privacy for security at three U.S. public venues

The use of security countermeasures at public venues has escalated dramatically over the past 20 years. We present a study of public venue patrons (N = 1276) examining how public perceptions of efficacy and intrusiveness of four security measures deployed at three different public assembly venues in the U.S. impact planned attendance. Enhanced use of these countermeasures,—Closed-Circuit Televisions (CCTVs), security guards, metal detectors, and bag checks—was evaluated by customers for their effectiveness in ensuring safety against crime and terrorism. We found that the perceived efficacy of the countermeasure in reducing these risks was positively associated with an increased likelihood of customer attendance at the venue. Moreover, customer beliefs about the overall enhancement of venue security and the sense of personal safety offered by these countermeasures also predicted their likelihood of attending. Unexpectedly, the study found that attitudes towards the privacy and convenience aspects of the countermeasures were not significant predictors of venue attendance. Results indicated that both cost and the extent of risk reduction predicted willingness to pay for enhanced security countermeasures. As the cost associated with a security measure increased, customers’ willingness to pay decreased. Conversely, as the perceived risk reduction offered by the security measures increased, customers indicated an increased willingness to pay. We found customers’ beliefs, attitudes, and intentions towards security measures were generally consistent across all three venues, indicating generalizability of findings across a range of public assembly venues in the U.S. Overall, the study provides evidence that customers support security countermeasures and endorse their implementation, which offers valuable insights for venue managers and policymakers aiming to enhance security measures at public assembly venues.

Squirrel search method for deep learning-based anomaly identification in videos

The monitoring of human behavior and traffic surveillance in various locations has become increasingly important in recent years. However, identifying abnormal activity in real-world settings is a challenging task due to the many different types of worrisome and abnormal actions, including theft, violence, and accidents. To address this issue, this paper proposes a new framework for deep learning-based anomaly identification in videos using the squirrel search algorithm and bidirectional long short-term memory (BiLSTM). The proposed method combines the squirrel search algorithm, an optimization technique inspired by nature, with BiLSTM for anomaly recognition. The framework uses the knowledge gained from a sequence of frames to categorize the video as either typical or abnormal. The proposed method was exhaustively tested in several benchmark datasets for anomaly detection to confirm its functionality in challenging surveillance circumstances. The results show that the proposed framework outperforms existing methods in terms of area under curve (AUC) values, with a test set AUC score of 93.1%. The paper also discusses the importance of feature selection and the benefits of using BiLSTM over traditional unidirectional long short-term memory (LSTM) models for anomaly detection in videos. Overall, the proposed framework provides a highly precise computerization of the system, making it an effective tool for identifying abnormal human behavior in surveillance footage.

Fugitive Location Identification System Using Photo Matching Across Distributed Surveillance Networks

Abstract: Using image matching algorithms from distributed CCTV surveillance networks, this research suggests a criminal identification method. This method aims to increase the effectiveness and efficiency of identifying and apprehending criminals by using the capabilities of networked surveillance cameras. The distributed CCTV network and the matching algorithm make up the two primary parts of the suggested system. The vast array of security cameras that make up the distributed CCTV network are positioned in different areas, including streets, buildings, and public areas. These cameras provide data to a central computer by taking pictures of people in real time.

소년예고범죄 예방을 위한 형사정책적 개선방안에 관한 연구

According to a media article, the Ministry of Justice announced a “comprehensive countermeasure against juvenile crimes” in October last year and announced legislation to revise the Juvenile Act to lower the age limit for young people from the current age of 14 to the age of 13. Since then, the National Assembly has also issued a series of bills, including criminal penalties for violent crimes. However, amendments to the Juvenile Act have been pending in the National Assembly for nearly a year. This is in conflict with the opposition that it violates the human rights of juvenile offenders and that it is difficult to expect the effect of preventing crime. In October last year, the National Human Rights Commission of Korea expressed opposition, saying that the lowering of the age of young people is contrary to the perspective of returning and recovering boys required by the UN (United Nations) international human rights standards and is not desirable as an alternative to crime prevention and recidivism. In response, the Ministry of Justice said, “Even if the age standard for juvenile is lowered, minor juvenile crimes will be sent to the juvenile department as they are now,” and explained, “Even if it is actually legislated, only violent crimes such as rape and robbery will be punished,” but it has not even been discussed. Some say that the degree of development of teenagers has increased compared to the past due to access to media, and that discussions on countermeasures should be made quickly. As we saw earlier, many of the posts were confirmed to be the work of teenagers, and the desire to be recognized as heroes within a group that mainly feels friendly as an online meme seeking stimulation and fun and a trend was revealed. This is very similar to terrorism in that socially isolated criminals carry out indiscriminate attacks against an unspecified number of people as an expression of anger toward others. Recently, the Ministry of Justice, the Ministry of Health and Welfare, and the National Police Agency held a meeting of related organizations to strengthen the response to the crime of abnormal motives (aka 'don't ask'). The meeting was prepared to discover additional measures and seek ways to strengthen cooperation with related ministries, recognizing that the public's anxiety is high due to a series of abnormal motive crimes such as the recent deadly weapon rampage, and to share measures to respond to abnormal motive crimes by each ministry, gather opinions on ways to cooperate and support the Ministry of Public Administration and Security, and discuss issues such as expanding crime prevention infrastructure such as security cameras (CCTV), expanding joint response models for mentally ill people, and supporting autonomous crime prevention activities. Boys' pre-announcement crimes are not yesterday or today because they have caused difficulties in their work in the past due to indiscriminate prank calls by investigative agencies. However, it seems that crime of don't ask and crime of abnormal motivation, which is not just a prank phone call, should no longer be ignored in our society.

Fire Detection by using DenseNet 201 algorithm and Surveillance Cameras images

Early warning of fires is very important to reduce loss of life and property. It is a technology that has become one of the most important design elements for smart cities in the future. Most current solutions rely on temperature and smoke sensors, which have limited detection ranges and scenarios and long response times. These are used inside some buildings and cannot be used in the external environment, as they are not a preferred solution. In addition to the above, sensor systems are costly because of the hardware and installation requirements, and they require regular upkeep. With the development of artificial intelligence and learning machines, fire detection has been used based on deep learning. Widely. Therefore, a solution to computer vision technology is proposed, which uses a convolutional neural network (CNN), Reducing false alarms. The use of computer vision techniques is certainly better than sensor-based systems, by utilizing security camera footage at specific periods to detect a fire when it breaks out. Our system achieved excellent results with an average predictive accuracy of 98% on the dataset. This accuracy and low cost make it a good alternative to systems that use sensors. The contribution of this study is to improve the detection process by conducting a classification process instead of detecting an object (fire), which requires complex mathematical calculations, large resources, and a long time.

Endpoint cybersecurity: When smart devices turn stupid

With the proliferation of ever-cheaper IoTs (or smart devices) from smart doorbells to WiFi security cameras and baby monitors and hybrid work arrangements involving relaxed BYOD (Bring Your Own Device) policies, cybersecurity education must build awareness on the threats that endpoints pose. While securing corporate networks from cyberattack gains much attention, there is a dearth of educational material that exemplifies the processes by which endpoints are used in hacks, and how to build defenses against endpoint vulnerabilities. This teaching case provides a Defense in Depth (DiD) learning framework on how to defend industrial cyber-physical systems, digital infrastructure and assets. The case illustrates the applicability of a DiD framework independent of attack vector yet particular to endpoint vulnerabilities and shows how lessons from the past can help defend and mitigate future cyberattacks.

Deep Learning-Based Intelligent Video Surveillance System for Real-Time Motion Detection

The proliferation of surveillance systems demands advanced solutions to effectively monitor and analyze video feeds for security and safety purposes. In this paper, we propose a Deep Learning-Based Intelligent Video Surveillance System (DIVSS) designed to enhance traditional Closed-Circuit Television (CCTV) setups. DIVSS integrates state-of-the-art deep learning techniques for real-time motion detection and object recognition, enabling proactive threat detection and automated response mechanisms. The system utilizes convolutional neural networks (CNNs) for robust feature extraction and classification, enabling accurate identification of objects of interest amidst complex backgrounds and varying[1] lighting conditions. Furthermore, DIVSS incorporates region of interest (ROI) monitoring to focus attention on specific areas within the surveillance footage, optimizing computational resources and improving response times. We evaluate the performance of DIVSS through comprehensive experiments conducted on diverse surveillance scenarios, demonstrating its effectiveness in enhancing security measures and providing actionable[3] insights for surveillance operators. The proposed system represents a significant advancement in video surveillance technology, offering unparalleled capabilities for proactive threat detection and real-time response in dynamic environments. Keywords— Deep learning has transformed video surveillance, enabling real-time motion detection and object recognition using Convolutional Neural Networks (CNNs). This technology provides proactive threat detection, intelligent systems for ROI monitoring, and enhances overall security measures.

Broadband nonlinear modulation of incoherent light using a transparent optoelectronic neuron array

Nonlinear optical processing of ambient natural light is highly desired for computational imaging and sensing. Strong optical nonlinear response under weak broadband incoherent light is essential for this purpose. By merging 2D transparent phototransistors (TPTs) with liquid crystal (LC) modulators, we create an optoelectronic neuron array that allows self-amplitude modulation of spatially incoherent light, achieving a large nonlinear contrast over a broad spectrum at orders-of-magnitude lower intensity than achievable in most optical nonlinear materials. We fabricated a 10,000-pixel array of optoelectronic neurons, and experimentally demonstrated an intelligent imaging system that instantly attenuates intense glares while retaining the weaker-intensity objects captured by a cellphone camera. This intelligent glare-reduction is important for various imaging applications, including autonomous driving, machine vision, and security cameras. The rapid nonlinear processing of incoherent broadband light might also find applications in optical computing, where nonlinear activation functions for ambient light conditions are highly sought.

Text Recognition for Library Collection in Different Light Conditions

Book arrangement problems in Indonesia mainly utilize traditional systems. However, it contributes to user frustration and dissatisfaction, leading to difficulties in the retrieval process and hindering book monitoring. Therefore, an efficient arrangement is needed to make it easier for librarians to organize collections at the library. Hence, this study proposes and evaluates Optical Character Recognition (OCR) approaches such as Tesseract-OCR and Efficient and Accurate Scene Text (EAST) by considering various light factors and device applications. An evaluation was performed to determine the effectiveness of the methods for detecting classification numbers using the Character Error Rate (CER) and Word Error Rate (WER). The results obtained can be seen from the lighting and the use of image capture tools that can affect the text detection results. The higher the lighting, the better the text detection results obtained. However, in the extraction tool using a security camera yields a better output than the others. In conclusion, the modernization of book arrangement systems by implementing OCR through security cameras could enhance user experience in the retrieval process.

Anomaly Detection in Heterogeneous Data Using Graph Convolutional Networks

Closed-circuit television (CCTV) surveillance systems are ubiquitous tools for ensuring public and private safety. However, manual monitoring of surveillance footage is arduous and time-consuming, often resulting in delayed identification and response to potential threats. In this paper, we present a novel real-time threat detection system tailored for CCTV surveillance, employing cutting-edge deep learning methodologies, particularly graph convolutional networks (GCNs), to detect and classify high-movement levels within video frames. By treating videos as segments and delineating between anomalous (potentially threatening) and normal (safe) segments, our system facilitates continuous real-time monitoring of surveillance footage, enabling the timely identification of potential threats such as abuse, burglaries, explosions, shootings, fighting, shoplifting, road accidents, arson, robbery, stealing, assault, and vandalism. To assess the efficacy of our system, we conducted extensive experiments on a large-scale dataset comprising CCTV footage, yielding promising results. Additionally, we introduce a novel, comprehensive dataset comprising 128 hours of real-world surveillance videos, encompassing various anomalies and normal activities. This dataset serves dual purposes: general anomaly detection, and the recognition of specific anomalous activities. Our experimental findings demonstrate the superior performance of our method in anomaly detection compared to state-of-the-art approaches. Furthermore, we provide an analysis of several recent deep learning baselines for anomalous activity recognition, revealing the challenging nature of our dataset and the potential it holds for future research endeavors. Through the integration of advanced deep learning techniques and comprehensive dataset creation, our proposed system stands to significantly enhance the efficiency and effectiveness of CCTV surveillance, facilitating faster response times and bolstering security for individuals in diverse environments.

Behaviour Indicators of Animal Welfare in Purebred and Crossbred Yearling Beef Reared in Optimal Environmental Conditions.

The aim of this study was to monitor the behaviour of purebred and crossbred beef cattle reared in the same optimal environmental conditions according to Classyfarm®. Thirty-yearling beef 11.5 months old, including 10 Limousines (LMS), 10 Sardo-Bruna (SRB), and 10 crossbred Limousine × Sardo-Bruna (LMS × SRB), balanced for sex and body weight, were used. Animals were evaluated for five months by two trained operators by SCAN ("sternal resting", "lateral resting", " central or peripheral position in the pen", standing", "walking", "feeding", "drinking", and "ruminating) and FOCUS ("displacement for space", "displacement for feed or water", "play-fighting", "self-grooming", "allo-grooming", "stereotyping", and "mounting") protocols. Feeding behaviour was monitored by a CCTV system. The application of the SCAN sampling evidenced that SRB animals preferred the "standing" activity over the LMS animals, while the LMS × SRB did not differ from them. The "standing" and " ruminating "activities were observed mostly in females than males (p < 0.05). For behaviour parameters assessed by the FOCUS methodology, the n-events of "allo-grooming" were higher (p < 0.05) in SRB than in LMS and LMS × SRB genetic types. Males showed higher (p < 0.05) n-events than females for "play-fighting". For feeding behaviour, the "eating concentrate" activity (expressed as n-events) was higher (p < 0.05) in SRB than LMS × SRB and LMS being intermediate (p < 0.05). The duration of "eating concentrate" (expressed in minutes) was higher (p < 0.05) in females than males. In conclusion, behaviour indicators of animal welfare did not evidence substantial differences among genetic types and between sexes reared in the same "optimal" environmental conditions. Female beef and the autochthon's cattle breed of Sardinia, although typically hardy, showed a wide behavioural repertoire.

Prioritising quality: investigating the influence of image quality on forensic facial comparison

Morphological analysis in forensic facial comparison was recently validated for judicial use. However, no image quality assurance systems exist for this purpose, despite image triage being considered the best practice approach. Hence, this study aimed at testing a semi-quantitative scoring method to assess image quality and investigated facial image resolution and lighting quality quantitatively in a context of forensic facial comparison. For this purpose, 400 facial comparison photographic and CCTV image pools developed from the Wits Face Database were used. These facial images were analysed in prior studies that investigated the validity of morphological analysis. A semi-quantitative image quality scoring system was adapted and tested on the above sample and compared across correct and incorrect matches obtained as part of previous studies using a logistic regression model. In addition, facial images were cropped to the closest pixel comprising the face, head and neck areas; then, a face-to-image pixel proportion was calculated as an estimator of resolution quality; and pixel exposure qualities were obtained to be compared to facial comparison outcomes. Ideal and high image quality scores were related to correctness of matches, while low-quality scores were related to incorrect matches. High pixel proportions were related to true matches and low exposure was related to false positives, while high exposure was related to false negatives. These results suggest that an easy method for image triage could be employed by scoring image quality. Quantitative measures should be investigated further for thresholding quality suitability for confidence of facial comparisons.

Internet of Things and JavaScript

The Internet of Things is the concept of a data network between devices ("things"): smart mobile phones, smart refrigerators, smart watches, virtual assistants like Internet browsers, etc., equipped with built-in tools and technologies for each to interact with each other or with external environment. JavaScript was created to bring any browser web page to life and easily apply it to the Internet of Things host client method, which runs JavaScript on its host device (such as a smartphone) and sends signals with it to client devices such as drones cameras or security cameras, and receives images from these cameras on the host device, in the method of embedded JavaScript of the Internet of Things, which is the implementation of JavaScript codes from the web page of the Internet browser on specific devices, such as smartphones. This article provides examples of the implementation of JavaScript codes from the developed web page of the Internet browser, used by the author, which allow implementing the developed web applications on smartphones.