Ovarian cancer ranks as the fifth leading cause of cancer-related mortality in women. Late-stage diagnosis (stages III and IV) is a major challenge due to the often vague and inconsistent initial symptoms. Current diagnostic methods, such as biomarkers, biopsy, and imaging tests, face limitations, including subjectivity, inter-observer variability, and extended testing times. This study proposes a novel convolutional neural network (CNN) algorithm for predicting and diagnosing ovarian cancer, addressing these limitations. In this paper, CNN was trained on a histopathological image dataset, divided into training and validation subsets and augmented before training. The model achieved a remarkable accuracy of 94%, with 95.12% of cancerous cases correctly identified and 93.02% of healthy cells accurately classified. The significance of this study lies in overcoming the challenges associated with the human expert examination, such as higher misclassification rates, inter-observer variability, and extended analysis times. This study presents a more accurate, efficient, and reliable approach to predicting and diagnosing ovarian cancer. Future research should explore recent advances in this field to enhance the effectiveness of the proposed method further.

Health emergencies occur in passenger cars where victims do not have immediate access to either layperson or professional, proper medical services, resulting in deterioration of their health or death. Installation of robotic first aid system for passenger-car occupants has been proposed. This study is part of a larger work of designing the system and seeks to identify the safest location inside the vehicle for it to survive any form of impact in a crash and retain the ability to assist the victims. The study population comprised 70 passenger cars (14 automakers across 7 segments) involved in road traffic accidents, which had been recovered by a roadside vehicle assistance company based in Harare, Zimbabwe, and were on the company’s premises on September 23rd, 2017. Vehicle damage was rated considering direction of force in comparison to a clock-point diagram, area damaged, and the damage severity on a scale of 1 to 7, following an official vehicle damage guide for traffic crash investigators. Data were analysed in Microsoft Office Excel 2016. In cases where vehicles were damaged in more than one area, all areas were recorded, hence 95 points of impact were analysed. Damage direct to the front denoted by 12 on the clock-point was the most common at 26%. This was compatible with the rate of frontal damage on vehicles, which was the highest at 51%, followed by the right and left sides that had 22% and 19%, respectively, the rear at 6%, and lastly the top (due to 2 recorded rollovers) at 2%. 56% of the damaged areas had a severity rating of either 5, 6, or 7. By eliminating all areas which had received damage in the study population, the robotic first aid system’s best chances of car crash survival are at the middle, towards the floor of the vehicle. It is advisable that the system does not depend on components in the proximity of the vehicle’s body as they are prone to damage in crashes. There is need for further research into the magnitude of impact that could reach the middle of different vehicles to define the strength of the robotic first aid system.

The rate of production of horticultural produce had been seen increasing from the past century owing to the increase of population. Manual sorting and grading of tomatoes had become a challenge in market places and fruit processing firms since the demand of the fruit had increased. Considering grading of tomatoes, color is of major importance when it comes to the maturity of the tomatoes. Hence, there is a need to accurately classify them according to color. This process is very complicated, tiresome, and laborious when it is done manually by a human being. Apart from being labor-demanding, human sorting, and grading results in inaccuracy in classifying of tomatoes which is a loss to both the farmer and customer. This chapter had been prepared focusing on the automatic and effective tomato fruit grading system using artificial intelligence particularly using artificial neural network in Matlab. The system makes use of the image processing toolbox and the ANN toolbox to process and classify the tomatoes images according to color and size.

In large scale industrial applications, the controlling and optimization of the parameters must be done efficiently and effectively so as to attain smooth operation of the plant. In this paper the main control parameters in the boiler are coal flows, temperatures in the combustion zone, air to fuel ratio, ash content that is the percentage of ash in raw coal, and mineral content. These parameters are to be monitored so as to avoid clinker formation on the platen super heater tubes in the boiler. Condition Based Maintenance (CBM) was used as the main maintenance method to monitor the boiler parameters and a branch known as fuzzy logic for the monitoring of the boiler parameters. The results show that the boiler should stop or continue to run depending on the Furnace Draught Pressure (FDP). When the FDP is within the range -7.5 – 5kPa the fuzzy controller send a message to continue run the boiler, fro -10kpa to -7.5kPa the fuzzy controller send a message to stop the boiler, also from 6kPa to 10kPa the fuzzy will send a message to stop the boiler. The boiler will only run when the logic is 1 and when the logic is zero the boiler should stop but in the case that the logic is 0 but there is no clinker that is forming the run command will be executed that is the fuzzy read the environment and act according to the environment. On the ID fans when the electrical consumption is within the range 0.9225-0.9375kPa the fuzzy controller send a message to run the boiler because there will be no clinker formation and this is shown by the accepted range of electrical consumption, any value outside this range the fuzzy controller will send a message to stop the boiler. The fuzzy logic controller is used in the sense that it is adaptive and can control itself when necessary.

The Arduino is programmed to control the robot navigation. The Garbage Collection Robot is designed to collect solid waste at public places (schools, workplaces, and parks) and residential areas. The design of the robot is such that when it starts, it maneuvers as per programmed route. The Garbage Collector can sense by means of capacitive proximity sensors if the obstacle is living (for example, a human being) or non-living (for example, vehicle) and then gives appropriate warning signals like flashing light, hoot, or voice commands. The robot is equipped with vision capabilities in order for it to detect colors, namely green, red, yellow, blue, and black for organics, plastic, metal, paper, and glass, respectively. When the GCR sees a particular color code on garbage container, it picks up the bin, carries it in its carriage, then offloads it at a desired station to wait for recycling or final dumping.