Malaysian Journal of Science and Advanced Technology

Performance Analysis of YOLO Architectures for Surgical Waste Detection in Post-COVID-19 Medical Waste Management

Zishan Ahmed — 2024-01-07

In the wake of the COVID-19 outbreak, there has been a dramatic uptick in the need for efficient medical waste management, making it imperative that more surgical waste management systems are developed. Used surgical masks and gloves are examples of potentially infectious materials that are the subject of this research. By utilizing its real-time object detection capabilities, the You Only Look Once (YOLO) deep learning-based object detection algorithm is used to identify surgical waste. Using the MSG dataset, a deep dive into the performance of three different YOLO architectures (YOLOv5, YOLOv7, and YOLOv8) was undertaken. According to the findings, YOLOv5-s, YOLOv7-x, and YOLOv8-m all perform exceptionally well when it comes to identifying surgical waste. YOLOv8-m was the best model, with a mAP of 82.4%, among these three. To mitigate post-COVID-19 infection risks and improve waste management efficiency, these results can be used to the creation of automated systems for medical waste sorting.

Bacteriological Analysis of Cow Milk (Nono) Sold Within Gusau Metropolis, Zamfara State

Oluchukwu Abba — 2024-01-07

Fresh cow milk popularly called Nono was collected from ten (10) different sellers at different areas within Gusau metropolis and one control was collected directly from a lactating cow and transported immediately to Microbiology Laboratory of Federal University Gusau where they wereassessed for their bacteriological quality. The total bacteria viable count of the ten Nono samples ranged between 6.6 x10⁵to 2.7 x10⁶cfu/ml, the total coliforms count ranged between 4.2x10⁵to 2.2x10⁶cfu/ml, the range of the total Staphylococcal count and total lactic acid bacterial count were 2.5x10⁵to 4.0x10⁶ cfu/ml and 5.9x10⁵ to 1.7x10⁶ cfu/ml respectively. The control sample had total viable count of 5.6 x 10³ cfu/ml, total staphylococcal count of 3.2 x 10³ cfu/ml, total lactic acid bacteria count of 4.2 x 10³ cfu/ml whereas the coliform count gotten was too few to count (TFTC). The isolates were identified based on their morphological characteristics, Gram's reactions and biochemical profiles and a total of seventy-four (74) bacterial isolates belonging to the genus Lactobacillus, Leuconostoc, Streptococcus, Micrococcus, Pediococcus, Escherichia coli, Pseudomonas, Proteus, Klebsiella, Enterobacter and Staphylococcus spp. were identified from the eleven samples analyzed. The presence of Lactic Acid Bacteria in Nono is very good as they are one of the most significant groups of probiotic which not only enhance lactose digestion but also stimulate the immune system, However, the presence of E. coli and the other enterobacteriaceae and Staphylococcus sp. is of public health concern because they can cause several diseases therefore it was concluded that the bacterial loads of the Nono samples were not satisfactory with the exception of the control which had organisms within the acceptable limit of 30,000/ml for raw milk. The presence of potential pathogenic bacteria in all of the Nono samples is an indication that the samples were contaminated and this can potentially cause diseases to the consumers, Hence the need for public enlightenment for handlers and producers of Nono to observe good manufacturing practices in production and storage of the product to avoid outbreak of infections associated with the organisms encountered in this study.

Effect of Different Strains of Bacillus Species on Lipid Peroxidation and Antioxidant Enzymes in Rice Exposed to Drought Stress

Salamatu Abdullahi — 2024-01-07

The impact of climate change-induced droughts in various regions worldwide has led to a range of stresses in plants, resulting in a decline in overall yield. Numerous strategies have been employed to alleviate stress on plants, but the use of plant growth-promoting rhizobacteria has emerged as a cost-effective and efficient approach. This study explores the influence of three distinct isolates of Bacillus species on lipid peroxidation and selected antioxidant enzymes in drought-stressed rice. Standard procedures were employed to assess antioxidant enzymes. Catalase, Ascorbate peroxidase, and Superoxide dismutase—while Malondialdehyde levels were utilized to gauge lipid peroxidation over 0, 3, 6, and 9 days of drought stress exposure. Among the three isolates, Bacillus subtilis SA1 (accession number OM184294) exhibited superior properties in inducing antioxidant enzymes, effectively countering the impact of generated free radicals. Additionally, this same organism demonstrated exceptional efficacy in reducing lipid peroxidation levels in the plant's leaves, thereby mitigating the adverse effects of free radicals. Consequently, this particular organism proves promising for minimizing the impact of drought stress in rice, complementing its role as a plant growth-promoting rhizobacteria.

The Environmental Footprint of Abandoned Asbestos Mines in Zimbabwe, Opportunities for Repurposing and Recovery of Mg And Other Metals from Gaths Mines

Desire Runganga — 2024-01-08

Asbestos mining in Zimbabwe left vast tracts of unrehabilitated land characterised by heaps of potentially carcinogenic tailings dumps. The research sought to trace the abandoned mines' environmental footprint, establish the tailings' tonnage, and explore the possibility of resuscitation against repurposing one of the prominent Gaths Mines for recovery of metals from the tailings. The mine has been under closure for two decades. the research findings indicated that over 2600km² of land has potentially been contaminated by asbestos tailings within the abandoned Gaths Mines. The research concluded that resuscitating Gaths mines for asbestos extraction was not feasible given the international scrutiny on asbestos as a hazardous substance. However, after confirming that the Gaths mines hosts over 140 million tonnes of asbestos with 40.3% Mg content and traces of platinum group metals and Al among other recoverable metals, the research concluded that repurposing the site was feasible. The overall estimate for the capex for a 50 000t/pa Mg Plant 25-year project was estimated at US$416,7 million against an estimated net cash flow of US$1 billion. The NPV for the project was estimated to exceed US$95,5 million at a discount rate of 10%. The project’s Internal Rate of Return was estimated at 16.14%. Overall, the research concluded that the site can potentially be converted from a liability to a legacy that will transform the host communities toward the creation of a sustainable city in Mashava, Zimbabwe.

Emotion Detection Using Machine Learning: An Analytical Review

Ashadu Jaman Shawon — 2024-01-08

This paper provides an analytical review of emotion detection using machine learning techniques. The study focuses on the attempts made in the past and present to develop emotion detecting systems. Numerous methods for identifying emotions have been introduced by students, and several outstanding works have already been found. In order to identify emotions, machine learning has been the primary focus. This paper also includes a summary of the frameworks, algorithms, and datasets that have been employed thus far to address this issue.

Robust, Resilient Enhanced CAMSHIFT Model: Advancing Face Detection and Tracking Stability in Challenging Environments

Alex Kok Bin See — 2024-01-27

This paper presents the development of a robust CAMSHIFT model for theoretical face detection and tracking. The proposed model integrates innovative techniques such as Perceptual Grouping, three Connected Component Operators, Weighted Adaptive Colour Histogram, and Selective Adaptation. Experimental results highlight its superior performance across scenarios like occlusions, varying illumination, near/far face tracking, skin-like background tracking, and disturbance from multiple faces. The normalized log-likelihood index serves as a robust indicator for face tracking analysis. Connected Component operations provide strong markers for error detection in video sequences. The enhanced CAMSHIFT algorithm exhibits resilience and stability, even in the presence of occlusions. Comparisons with the original CAMSHIFT reveal the enhanced model's superiority, extending tracking range to 500 cm, a calculated enhancement of 42.9 percent improvement. The study consistently favours the robust and resilient CAMSHIFT model in tracking against skin-like backgrounds and disturbances. Despite webcam convenience in used for algorithm development, the benefits of high-performance camera systems are envisioned for future research. This model is a significant advancement in face detection methods, promising improved adaptability and tracking capabilities.

Modulation of Duodenal TfR Expression in IDA Induced Rat with Date Palm and Goat Milk Intake

Nurainna Abd Majid — 2024-02-17

Iron deficiency anemia (IDA) is a medical condition characterized by insufficient iron levels in the body, resulting in a reduced ability to produce hemoglobin (Hb), a critical component of red blood cells. IDA is often associated with chronic fatigue, impaired cognitive function, and diminished well-being. Transferrin (Tf) is one of the major proteins in iron homeostasis, responsible for transporting iron through the blood to various tissues, while its carrier protein, transferrin receptor (TfR), mediates the cellular uptake of transferrin-bound iron into the cell. This study aims to evaluate the expression of TfR mRNA and protein in the small intestine following intervention with date palm and goat milk in IDA-induced rats. Twenty-four male Wistar rats were induced with IDA for 2 weeks using a low-iron diet. Following IDA detection, rats were supplemented with date palm and goat milk, singly and in combination. After four weeks, the rats were sacrificed, and the expression of TfR mRNA and protein in the small intestine was assessed using qPCR and immunohistochemistry, respectively. Data were analyzed using SPSS 24.0, with a significance level set at p<0.05. Results demonstrated that date palm and goat milk significantly improved Hb, serum iron, Tf saturation levels, and modulated the expression of TfR mRNA in the IDA-induced rats. Expression of TfR on the crypt region and brush border membrane of the small intestine was normalized following intervention. The findings indicate that supplementation of date palm and goat milk improved Hb and Tf saturation levels and significantly modulated duodenal TfR expression in IDA-induced rats.