Internet of things (IoT) refers to the interconnection and data interchange between various devices and systems through the internet and other communication networks. These items may be equipped with sensors, processing power, software, and other technologies. Multiple technologies have converged, leading to advancements in the sector. These technologies include machine learning, mobile computing, commodity sensors, and robust embedded systems. Independently and together, the Internet of Things enables the traditional domains of integrated devices, sensor networks, control mechanisms, and automating (including house and building automation). In the consumer market, Internet of Things (IoT) technology is most commonly associated with “smart home” products, such as lighting, thermostats, surveillance systems, cameras, and other home appliances that are compatible with one or more popular ecosystems and can be monitored by connected to that ecosystem, such as mobile phones. The healthcare industry also makes use of IoT. The Internet of Things continues to expand slowly, quietly, and inexorably around us as healthcare systems continue their journey towards incorporation and suppliers build more robust data analytics systems that can leverage client data of all shapes and sizes. This will allow providers to generate actionable information at a scale and sophistication never before. The dream of a connected, patient-centered, flawlessly automated healthcare ecosystem is closer than ever for those healthcare professionals that take the time today to comprehend and appreciate the Internet of Things.
Rationale and Implications
With each passing day, the healthcare industry becomes more reliant on the Internet of Things (IoT) to facilitate better patient engagement, raise the bar on treatment quality, and lower healthcare expenditures. Integrating well-being, healthcare, and patient support based on an individual’s specific biological, behavioral, social, and cultural traits is known as personalized healthcare. Putting patients in charge and focusing on providing the proper treatment for the right person at the right time may improve healthcare while saving money. Instead of relying on costly in-clinic treatment, a sustainable service monitors general health to foresee potential problems and guarantee that healthcare plans are followed. The Internet of Things (IoT) has the potential to manage the individualization of healthcare delivery and to provide each person with their own digital identity. In healthcare, several pieces of machinery are employed for treatment, communication, and the omnipresent system-of-system—classifications of Internet of Things-based individualized healthcare systems, Healthcare administration, and telemonitoring. Patients in hospitals who need continual careful attention to their physiological condition are monitored via noninvasive monitoring devices powered by the Internet of Things. Sensors capture physiological data for these monitoring systems, which is then evaluated and saved through gateways and the cloud. This data is sent wirelessly to healthcare providers for further examination, eliminating the need for periodic checks of vital signs by medical staff. Instead, it offers a steady stream of data that is automatically updated in real-time. Constant monitoring improves care quality without increasing costs or requiring caregivers to do additional tasks such as data collecting and analysis. Therefore, hospitals must equip themselves with Internet of Things devices to improve operational efficiencies.
Our research aims to answer the following questions on the impact of IoT on citizens’ quality of life and the efficiency of the health sector:
- To evaluate the accuracy with which various medical sensors measure different medical samples
- To examine how well the healthcare industry protects patient data and conducts other Internet-of-Things-related cyber operations.
- To evaluate computer vision technology for its potential to improve hospital building.
RQ1: How do the medical sensors ease the process of treatment in hospitals?
RQ2: How secure is the data provided by clients to the medical systems?
RQ3: How useful is computer vision technology in medical care?
Applications that deal with vital human data like pulse rate, ECG and EEG data, cardiac output, temperature, levels of certain compounds like oxygen and medications in the blood, and motions need a low data rate. Potential deployments include the hospital, the backyard, and the living room. The bedside monitor in either the home or hospital set may be replaced by data-gathering equipment or a gateway to a centralized database, which might be a mobile phone, but the underlying structure is the same. The fundamental objective of the software is to aid people with medical issues without limiting their mobility, as stated by Antunes et al. (2018, p.35). The researchers imagine a future where patients’ health is monitored in real time by portable treatment gadgets that measure parameters such as blood pressure, electrocardiogram (ECG), and glucose levels. Once validation is finished, data from various sensors is saved and examined. Some examples are blood-pressure gauges, glucose trackers, and ECG machines. Research and aggregate data may be used to analyze patients from different places and give appropriate treatment. Patients may also choose the implementation of a standardized door and entry management system, Internet convention structure, global framework, and microwave access (WiMAX) that is compatible with older technologies (Adeniyi et al., 2021, pg110).
The system utilizes WBAN and RFID tags to report on crucial operational indicators, covering a broad spectrum of components. Multiple sensors are connected to the patient’s body using the WBAN device. The customer wears a number of sensors, some of which are wireless sensor networks and others are medical sensors. The signals are organized to facilitate the speedy entry of patient information into a database. There is no guarantee that the administration won’t have any downtime at all during that period of time due to the design (Adeniyi et al., 2021, pg115).
A client’s input is needed for the therapeutic implant to match symptoms to a prescription document and determine the underlying illness. If the illness is not found by examining the symptoms, the program then runs tests recommended by the pre-stacked side effect database in an effort to locate the disease’s precise counterpart. If the system detects that the illness information is incomplete, it will immediately route the patient to the most knowledgeable expert. As needed, this physician will counsel the patient, conduct an in-depth analysis of the ailment, and revise the patient’s symptoms and medical records in the system. The data is collected by the server, converted to the standard format, and stored in the cloud where doctors may access it at their convenience. The system is designed to provide a decentralized healthcare infrastructure, with strict controls over data collection, storage, and retrieval (Uddin et al., 2020, p114). Further, it illustrates the many layers of the healthcare infrastructure at work in the data analysis. Some of the numerous things that a system’s multiple levels can do include collecting data, sending data, and storing data.
Healthcare Cyber Security
This study aims to define critical cyber challenges, solutions adopted by the medical sector, and improvements needed to help counter the trending up in cyberattacks like malicious links and ransomware attacks. These attacks have been successful because they take advantage of vulnerabilities in both technology and people, which have been introduced as a result of changes in work conditions in response to various health issues (Zhang et al., 2018, p2). Included will be reports, news stories, and company white papers that directly relate to cases recorded works or are the only sources accessible at the time of the research. We will only consider English-language publications published in the recent decade to focus on relevant topics.
In recent years, the healthcare industry has been a favorite target for hackers due to the prevalence of ransomware. This kind of malware entails a rogue software system holding a user’s computer or whole network hostage until a ransom is paid. The Protenus Breach Barometer Report shows that hacking was the primary cause of reported occurrences in 2019. Companies that are not prepared for disaster recovery and data backups often have little option but to pay the ransom demanded by cybercriminals after falling victim to one of these attacks. Businesses have shut down as a last option rather to pay the ransom. A healthcare organization’s susceptibility to a ransomware attack may be gauged by looking for certain characteristics, such as the quantity and kind of stored data, the use of unsupported operating systems, improper patch management procedures, and the absence of encryption standards (Parah et al., 2020, p24). The healthcare industry is especially susceptible to ransomware attacks because to the critical need of always-accessible electronic health data and networked medical equipment in delivering effective patient care. As a result, companies must be aware of, and ready for, the inevitable ransomware threats and attacks they will encounter (Sharma et al., 2021, p121).
Computer Vision Technology
Machine logs, medical files, media stories, and publications will all provide data for this study. The university will help in contacting various medical facilities to obtain data for the project. Thereafter, the information will be organized into tables for simpler examination. To test hypotheses, we’ll utilize SPSS. Thus, the results of the hypothesis testing that statisticians and mathematicians will do will be more readily available.
Computer vision, often known as machine vision, is the study of algorithms for visual tasks such as detecting, tracking, and classifying visual objects; estimating the depth of an image; segmenting an image into instances and concepts; and so on (Dessie et al., 2018, p30). The discipline of computer vision has sought to mimic the way the human brain analyzes visual input in order to get a better understanding of this process. Using computer vision technology, brain tumors may be diagnosed more quickly and accurately. Dong et al. (2020, p.83) state that deep learning may be used to train computer vision systems on data from malignant and healthy tissues, therefore enhancing the systems’ capacity to diagnose skin and breast cancer. Using computer vision software will help doctors save time and effort by allowing them to make more accurate diagnosis and provide more specific treatments. Due to advancements in the field, computer vision is now useful in a broad variety of medical settings.
Some diseases may only be treatable by physicians if discovered early on. As computer vision technology improves, it may soon be possible for doctors to detect warning signals before their patients do. This means that many more individuals will have access to the medical treatment they need. Early diagnosis might let doctors start treating patients with medicines or possibly perform life-saving surgeries sooner. In this setting, computer vision is being utilized to speed up diagnosis and boost treatment outcomes. Computer vision offers dynamic, high-definition 3D visualization in medical imaging (Bao et al., 2019, p47). The processing of medical images has been drastically altered by the introduction of deep learning algorithms during the last several years. These developments made it possible for medical image processing systems to make better use of facial recognition. With the use of machine learning and data analysis, interactive 3D models may now aid in medical diagnosis. More information may be gleaned from three-dimensional models than from two-dimensional still images. Because of this, 3D breast imaging enabled by state-of-the-art computer vision systems is more effective in detecting and preventing cancer in its earliest stages.
Wheelchair Management System
People with disabilities worldwide will be surveyed for their perspectives on using an autonomous wheelchair in everyday life. They will discuss the pros and cons since they began using the Bluetooth-controlled chair. Since hospitals and clinics are the most directly affected entities, they will also be included in this research. The study’s scope includes any literature on computerized medical equipment, such as reports, papers, periodicals, and websites. Also included are any relevant resources.
Traditional wheelchairs need users to depend on others for movement control, the handle control, which is primarily for healthy individuals. To utilize a wheelchair, an occupant detecting device must be attached to it. Regular wheelchairs prevent loved ones from receiving quick updates on the user’s condition, such as where the wheelchair is at any given moment, making it difficult to respond appropriately to medical crises. The hardship of using a wheelchair is increased since the user must always pay close attention to their surroundings (Al-Qaysi et al., 2018, p.224).
Accessing the features of home automation, which seeks to create a natural “smart home” nervous system, makes it more flexible and adaptable to the needs of the home dweller. However, a disabled individual must depend on the immersive mechanisms between a power wheelchair and smartphone/tablet devices, which act as intermediaries between the user and the environment (Shahin et al., 2019, p.120). Therefore, knowing how the motorized wheelchair can communicate with these tools is crucial. The armchair and the smartphone may communicate via a simple “Bluetooth module,” which is commonly included in the wheelchair’s controller or LCD screen module. Once the wheelchair and smartphone are paired, the user can control the various settings and gestures using the same controls to drive the wheelchair (Oliver et al., 2019, p.112). This is made possible because the smartphone recognizes the wheelchair’s transceiver similarly to a traditional wireless mouse. By having the wheelchair’s unique control, such as a joystick or special/alternative input, the wheelchair’s user will need to view the smartphone’s display, rather than interacting with it directly.
Several factors must be considered for this study to be fruitful. There have to be legal safeguards in place to make sure the study process goes off without a hitch. For instance, the research and analysis of data need legal permits for access to medical information and the breaching of institutional firewalls (Nijhuis et al., 2018, p.70). Official school letters and authorization to use the internet’s wealth of information resources. To conduct surveys legally, approvals from relevant government authorities are required.
Various tools and materials are needed to ensure the success of an in-depth study. The ability to connect to the internet and use computers with all the required software installed and in excellent functioning order are prerequisites. Wherever it’s necessary, convenient and reliable modes of transit also have to be timely and reliable (Hair et al., 2021, p.121). There must be enough finance and financial assistance to guarantee that all of the unavailable supplies are procured at the right time. In the academic world, risks and uncertainties have always been there. Several threats were found in this research. The most significant threat is the potential for data breaches due to a lack of proper authorization to access computers and documents at various organizations. The possibility of using erroneous information also exists.
Consequently, we will almost certainly get phony data that will mess with our analysis. On the other hand, researchers are responsible for delving into their sources to guarantee they are gathering accurate information (Nijhuis et al., 2018, p.75). The many researchers participating may have had a lacklustre response to an interest in the study. It’s possible that some scientists just wouldn’t be prepared to put up with the hassle and expense of doing such a study. Researchers are urged to treat the study as their own, show enthusiasm for it, and devote themselves wholeheartedly to ensuring its success.
Adeniyi, Emmanuel Abidemi, Roseline Oluwaseun Ogundokun, and Joseph Bamidele Awotunde. “IoMT-based wearable body sensors network healthcare monitoring system.” IoT in healthcare and ambient assisted living. Springer, Singapore, 2021. 103-121.
Al-Qaysi, Z. T., et al. “A review of disability EEG based wheelchair control system: Coherent taxonomy, open challenges and recommendations.” Computer methods and programs in biomedicine 164 (2018): 221-237.
Antunes, Rodolfo S., et al. “A survey of sensors in healthcare workflow monitoring.” ACM Computing Surveys (CSUR) 51.2 (2018): 1-37.
Bao, Yuequan, et al. “Computer vision and deep learning–based data anomaly detection method for structural health monitoring.” Structural Health Monitoring 18.2 (2019): 401-421.
Chofreh, Abdoulmohammad Gholamzadeh, et al. “The imperative and research directions of sustainable project management.” Journal of Cleaner Production 238 (2019): 117810.
Dessie, Awrajaw, et al. “Computer vision syndrome and associated factors among computer users in Debre Tabor Town, Northwest Ethiopia.” Journal of environmental and public health 2018 (2018).
Dong, Chuan-Zhi, and F. Necati Catbas. “A review of computer vision-based structural health monitoring at local and global levels.” Structural Health Monitoring 20.2 (2021): 692-743.
Hair, Joseph F., and Marko Sarstedt. “Explanation plus prediction—The logical focus of project management research.” Project Management Journal 52.4 (2021): 319-322.
Ma, Zhanyu, et al. “IEEE Access special section editorial: Recent advantages of computer vision.” IEEE Access 6 (2018): 31481-31485.
Nijhuis, Steven, Ruben Vrijhoef, and Joseph Kessels. “Tackling project management competence research.” Project Management Journal 49.3 (2018): 62-81.
Oliver, Samuel, and Asiya Khan. “Design and evaluation of an alternative wheelchair control system for dexterity disabilities.” Healthcare Technology Letters 6.4 (2019): 109-114.
Parah, Shabir A., et al. “Efficient security and authentication for edge-based internet of medical things.” IEEE Internet of Things Journal 8.21 (2020): 15652-15662.
Shahin, Mohamed K., et al. “A wheelchair control system using human-machine interaction: Single-modal and multimodal approaches.” Journal of Intelligent Systems 28.1 (2019): 115-132.
Sharma, Aashima, Sanmeet Kaur, and Maninder Singh. “A comprehensive review on blockchain and Internet of Things in healthcare.” Transactions on Emerging Telecommunications Technologies 32.10 (2021): e4333.
Uddin, Md Zia, et al. “A body sensor data fusion and deep recurrent neural network-based behaviour recognition approach for robust healthcare.” Information Fusion 55 (2020): 105-115.
Zhang, Mian, and Yuhong Ji. “Blockchain for healthcare records: A data perspective.” PeerJ Preprints 6 (2018): e26942v1.