Social media is used to categorise products or services, but analysing vast comments is time-consuming. Researchers use sentiment analysis via natural language processing, evaluating methods and results conventionally through literature reviews and assessments. However, our approach diverges by offering a thorough analytical perspective with critical analysis, research findings, identified gaps, limitations, challenges and future prospects specific to deep learning-based sentiment analysis in recent times. Furthermore, we provide in-depth investigation into sentiment analysis, categorizing prevalent data, pre-processing methods, text representations, learning models, and applications. We conduct a thorough evaluation of recent advances in deep learning architectures, assessing their pros and cons. Additionally, we offer a meticulous analysis of deep learning methodologies, integrating insights on applied tools, strengths, weaknesses, performance results, research gaps, and a detailed feature-based examination. Furthermore, we present in a thorough discussion of the challenges, drawbacks, and factors contributing to the successful enhancement of accuracy within the realm of sentiment analysis. A critical comparative analysis of our article clearly shows that capsule-based RNN approaches give the best results with an accuracy of 98.02% which is the CNN or RNN-based models. We implemented various advanced deep-learning models across four benchmarks to identify the top performers. Additionally, we introduced the innovative CRDC (Capsule with Deep CNN and Bi structured RNN) model, which demonstrated superior performance compared to other methods. Our proposed approach achieved remarkable accuracy across different databases: IMDB (88.15%), Toxic (98.28%), CrowdFlower (92.34%), and ER (95.48%). Hence, this method holds promise for automated sentiment analysis and potential deployment.

Heart Rate Monitors (HRMs) have become widely used since the last two decades. It used as training aid for various types of sports. And the development of new HRMs has evolved rapidly. Thus, in order to determine the exercise intensity of training session or race, HRMs are mainly used. Compared to the other indication of exercise intensity, Heart rate is easy to monitor, compatible to use in most situation and relatively cheap. Thus, it is most beneficial if wireless sensor network can be implementing into the system. Other than monitored their condition by themselves, this system may allowed a number of athletes being monitored simultaneously. Arduino-Nano board was used to interface with nRF24AP1 and XBee. The wireless sensor network consists of a microcontroller on Arduino-Nano board, nRF24AP1 and the XBee wireless communication module which is based on the IEEE 802.15.4. This system will involve peer to peer communication of ANT+ and mesh networking among the XBee.

Recent advances in wireless communication standards and medical monitoring system have made it possible to effectively combine mesh networking with Non-Invasive medical application which is Pulse Oximeter in order to create reliable, large-scale wireless Network. This Mesh networking will enable doctors and nurses to observe and monitor a number of patients simultaneously from one location without being with the patient's physically. This project is mainly concerned about monitoring patient's condition simultaneously via Wireless Mesh Network. Wireless Mesh Network is a network that allows data transmitted to the node's nearest neighbors and it can be easily maintained as each node are self configuring and self healing. Data obtained from multiple pulse oximeters will be stored and processed using Arduino-Nano, then transmitted to a centralized unit, where the information for multiple oximeter will be displayed simultaneously. The efficiency of data transmission was monitored and verified. Mesh networking for pulse oximeter had been successfully design to show the active pulse oximeter. Besides, the data transmit and received by the XBee were accurate and it had been proved through several observations.

Air pollution is one of the pollutions that release harmful chemicals and if not controlled, it will affect the human respiratory system. Currently, there are two Air Pollution Monitoring system located in Kuantan district to record the pollution’s reading once it detects the air pollutant however, the origin of the pollution cannot be detected by the system. As a solution, a Smart Environment Monitoring System for Air Pollution Using Internet of Things (IoTs) is developed to overcome the weaknesses. This project involved both hardware and software developments, in which hardware development includes the Arduino Uno, Carbon Monoxide (MQ 7), smoke/gas (MQ 135) sensors, a buzzer and LCD display. This system is design so that the current reading can be viewed by admin in a real-time value. Besides, they can also view the data for every 8 hours. These data can be printed in PDF format. In addition, when the reading reached unhealthy value, it will warn the community via its alarm system embedded in this system. However, this system is subject to limitation especially on data delays from sensors to database. As only one existing monitoring system that located at Beserah, thus this new feature will add a sub-sensor that located at the designated area which potentially expose to the air pollution.