Optimization of Trash Identification on the House Compound Using a Convolutional Neural Network (CNN) and Sensor System.

This study aims to optimize the object identification process, especially identifying trash in the house compound. Most object identification methods cannot distinguish whether the object is a real image (3D) or a photographic image on paper (2D). This is a problem if the detected object is moved from one place to another. If the object is 2D, the robot gripper only clamps empty objects. In this study, the Sequential_Camera_LiDAR (SCL) method is proposed. This method combines a Convolutional Neural Network (CNN) with LiDAR (Light Detection and Ranging), with an accuracy of ±2 mm. After testing 11 types of trash on four CNN architectures (AlexNet, VGG16, GoogleNet, and ResNet18), the accuracy results are 80.5%, 95.6%, 98.3%, and 97.5%. This result is perfect for object identification. However, it needs to be optimized using a LiDAR sensor to determine the object in 3D or 2D. Trash will be ignored if the fast scanning process with the LiDAR sensor detects non-real (2D) trash. If Real (3D), the trash object will be scanned in detail to determine the robot gripper position in lifting the trash object. The time efficiency generated by fast scanning is between 13.33% to 59.26% depending on the object's size. The larger the object, the greater the time efficiency. In conclusion, optimization using the combination of a CNN and a LiDAR sensor can identify trash objects correctly and determine whether the object is real (3D) or not (2D), so a decision may be made to move the trash object from the detection location.

An integrated decision making approach for selecting a sustainable waste water treatment technology.

Growing global energy demand and the depletion of fossil fuels have highlighted the need for alternate and environmentally benign energy sources. The volume of untreated waste water being disposed of straight into fresh water is becoming a major concern. An integrated treatment method can address the problems of bio-energy generation and wastewater management as both processes can use wastewater as a substrate. Linear diophantine fuzzy sets help handle the uncertainty and difficulties that arise while deciding on an effective treatment technique. The use of control parameters makes these fuzzy sets unique and superior to other existing fuzzy sets. A modified strategy incorporating the Pivot pairwise relative criteria importance assessment and Interactive multi-criteria decision making methodologies is proposed for the linear diophantine fuzzy environment. The applicability and effectiveness of the developed model are established by choosing an appropriate wastewater treatment technology in the context of linear diophantine fuzzy sets. In addition, sensitivity analysis is used in this study to determine the stability of the developed framework. Further, comparison analysis is also addressed to assess the validity of the acquired results.

An interactive math braille learning application to assist blind students in Bangladesh.

Due to the lack of affordable assistive tools for learning mathematics, blind students in Bangladesh still use outdated learning tools like Tailor Frame. Therefore, demand for a low-cost technological tool is there that will help the blind students to learn math braille and calculate numbers more easily. To provide an effective and affordable assistive tool, this study begins with a needs assessment study to identify the basic needs of blind students in learning math braille and solving mathematical calculations. Afterward, a mobile phone based interactive assistive application is proposed to improve the learning facilities of math braille using Nemeth code for blind students in Bangladesh. Interfaces of the application are designed based on their needs. Besides, interaction methods (such as, hearing & touching) of blind students with the physical world were another criterion in designing very interactive interfaces that provide self-learning facilities. The interfaces are evaluated by the teachers, experts, and end users in order to identify the usability. The evaluation shows a promising result toward the acceptability of the designed application. Therefore, this application can be helpful for the blind students to learn math braille using Nemeth Code.

Intra-Rater Reliability and Minimal Detectable Change of Vertical Ground Reaction Force Measurement during Gait and Half-Squat Tasks on Healthy Male Adults.

BACKGROUND: The understanding of vertical ground reaction force (VGRF) during walking and half-squatting is necessary and commonly utilised during the rehabilitation period. The purpose of this study was to establish measurement reproducibility of VGRF that reports the minimal detectable changes (MDC) during walking and half-squatting activity among healthy male adults. METHODS: 14 male adults of average age, 24.88 (5.24) years old, were enlisted in this study. The VGRF was assessed using the force plates which were embedded into a customised walking platform. Participants were required to carry out three trials of gait and half-squat. Each participant completed the two measurements within a day, approximately four hours apart. RESULTS: Measurements of VGRF between sessions presented an excellent VGRF data for walking (ICC Left = 0.88, ICC Right = 0.89). High reliability of VGRF was also noted during the half-squat activity (ICC Left = 0.95, ICC Right = 0.90). The standard errors of measurement (SEM) of VGRF during the walking and half-squat activity are less than 8.35 Nm/kg and 4.67 Nm/kg for the gait and half-squat task respectively. CONCLUSION: The equipment set-up and measurement procedure used to quantify VGRF during walking and half-squatting among healthy males displayed excellent reliability. Researcher should consider using this method to measure the VGRF during functional performance assessment.