Claim Missing Document
Check
Articles

Found 6 Documents
Search

The Application of Artificial Intelligence in Waste Classification as an Effort In Plastic Waste Management Listyalina, Latifah; Utami, Ratri Retno; Arifin, Uma Fadzilia; Putri, Naimah
Telematika Vol 21, No 1 (2024): Edisi Februari 2024
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v21i1.11977

Abstract

Purpose: Sorting waste before it is deposited in the Final Disposal Site (TPA) is crucial to reduce the increasing amount of waste accumulation each year. This issue can be addressed by implementing machines capable of automatically sorting waste.Design/methodology/approach: This research is quantitative and utilizes secondary data, namely image data of various types of waste. The images will be classified into organic and inorganic waste using a deep learning model. The measurement conducted involves assessing the accuracy of the designed deep learning model in classifying waste images into appropriate categories.Fondings/results: Based on the available dataset, waste identification will be performed, including food waste, paper, wood, leaves, electronic waste, metal, plastic, and bottles. The overall accuracy of the model is 94.42%, indicating that the model correctly classifies 94.42% of waste samples.Originality/value/state of the art: This research can classify 8 types of waste classes successfully using deep learning.
Study of Histological Skin Structure of Python reticulatus and Varanus salvator Putri, Naimah; Wibowo, Raden Lukas Martindro Satrio Ari; Rahmawati, Atiqa; Jonathan, Sebastian; Tarigan, Deo Steven Barney
Jurnal Sains dan Teknologi Peternakan Vol 5 No 2 (2024): Jurnal Sains dan Teknologi Peternakan
Publisher : Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31605/jstp.v5i2.3814

Abstract

Reptile skin is covered with scales that form a protective barrier, making it waterproof and enabling life on land. The present study investigated the histological structure of the skin of the Python reticulatus and Varanus salvator. The samples used were Python reticulatus and Varanus salvator skin taken from the dorsal region. Preparations were made using the hematoxylin eosin (HE) staining method which was carried out at the Microbiology of the leather processing technology, Politeknik ATK Yogyakarta. The results showed that the histological structure of Python reticulatus skin consisted of two layers, epidermis and dermis. The epidermis was composed of stratum corneum, stratum granulosum, and stratum basale. The dermis consists of an outer layer called the stratum laxum (stratum spongiosum) and an inner layer called the stratum compactum. Meanwhile, the histological skin structure of Varanus salvator skin consists of epidermis which included oberhautchen, α-keratin layer, β-keratin layer, supra basale layer, and basale layer. The dermis consists of superficial dermis and deep dermis. There are differences between Python reticulatus skin that is distinguished by its ability to ecydis (skin shedding) the epidermis and Varanus salvator skin have osteoderm (OD) within their dermis layer
The Application of Artificial Intelligence in Waste Classification as an Effort In Plastic Waste Management Listyalina, Latifah; Utami, Ratri Retno; Arifin, Uma Fadzilia; Putri, Naimah
Telematika Vol 21 No 1 (2024): Edisi Pertama 2024
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v21i1.11977

Abstract

Purpose: Sorting waste before it is deposited in the Final Disposal Site (TPA) is crucial to reduce the increasing amount of waste accumulation each year. This issue can be addressed by implementing machines capable of automatically sorting waste.Design/methodology/approach: This research is quantitative and utilizes secondary data, namely image data of various types of waste. The images will be classified into organic and inorganic waste using a deep learning model. The measurement conducted involves assessing the accuracy of the designed deep learning model in classifying waste images into appropriate categories.Fondings/results: Based on the available dataset, waste identification will be performed, including food waste, paper, wood, leaves, electronic waste, metal, plastic, and bottles. The overall accuracy of the model is 94.42%, indicating that the model correctly classifies 94.42% of waste samples.Originality/value/state of the art: This research can classify 8 types of waste classes successfully using deep learning.
Pengembangan Intelligent Leather Inspection Method Berbasis Interpretable Artificial Intelligence Frannita, Eka Legya; Wulandari, Dwi; Putri, Naimah; Rahmawati, Atiqa; Prananda, Alifia Revan
TIN: Terapan Informatika Nusantara Vol 6 No 2 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v6i2.7425

Abstract

The Industry 4.0 revolution, characterized by the widespread adoption of artificial intelligence and automation, has fundamentally transformed quality inspection processes in manufacturing sectors. Nevertheless, the leather tanning industry continues to rely on conventional visual inspection methods conducted by human operators, which are inherently susceptible to subjectivity, inter-operator variability, and inconsistent outcomes. This study proposes an integrated deep learning framework utilizing the NasNet-Large architecture combined with Local Interpretable Model-Agnostic Explanations (LIME) to automate objective defect detection and quality classification of pickled leather. The research employs a digital image dataset comprising four distinct leather grade categories, each annotated with expert-validated ground truth labels and professional interpretations. Experimental results demonstrate consistent model performance with 75% accuracy in both training and validation phases while achieving improved testing accuracy of 79%. LIME-based interpretability analysis reveals significant spatial convergence between model-identified defect regions and expert-annotated ground truth references. These findings indicate that the developed model exhibits remarkable competence in replicating professional leather quality inspection capabilities. The proposed approach not only enhances inspection efficiency by reducing human-dependent errors but also provides transparent decision-making interpretability - a critical requirement for reliable AI implementation in industrial applications. This research contributes to the advancement of explainable AI systems in material quality assessment, offering methodological innovation and practical implementation value for the leather manufacturing sector.
Histological and Chemical Studies of Goat Skin Transformation Processing of Raw Skin into Tanned Leather Rahmawati, Atiqa; Putri, Naimah; Wibowo, Ari
Jurnal Agripet Vol 25, No 1 (2025): Volume 25, No. 1, April 2025
Publisher : Faculty of Agriculture

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17969/agripet.v25i1.43456

Abstract

Fresh goat skin and skins tanned with different tanning agents were prepared for histological, chemical, and physical analyses. Fresh skin samples were fixed in 10% formalin solution, processed using the paraffin embedding technique, sectioned, and stained with hematoxylin and eosin to determine the histological structure. Samples of goat tanned skin, treated with various tanning agents (chrome, aldehyde, chamois, and vegetable), underwent chemical analysis using Fourier Transform Infrared Spectroscopy (FTIR) followed by physical analyses, including tensile strength, tear strength, thickness, and shrinkage temperature. The results showed that the histological structure of fresh skin consisted of two layers: the epidermis and dermis, while tanned leather only exhibited the dermis layer. The epidermis was removed during the tanning process. FTIR analysis of chrome-tanned leather showed bands at 1633 cm1 (amide I), 1554 cm1 (amide II), and 1240 cm1 (amide III). Aldehyde-tanned leather showed bands at 1651 cm1, 1550 cm1, and 1271 cm1 (amide I, II, and III), while vegetable-tanned leather displayed bands at 1634 cm1 (amide I), 1552 cm1 (amide II), and 1239 cm1 (amide III). Shifts in peak positions, intensity, and the number of signature peaks were observed across the tanning agents (chrome, aldehyde, oil, and vegetable). The use of different tanning agentswet blue, wet white, vegetable-tanned, and chamoisresulted in distinct grain-surface structures, significantly influencing the physical characteristics of the leather.
Characterization of Amino Acid Mutations of Newcastle Disease Virus (NDV) In Swan Geese (Anser cygnoides) In East Java, Indonesia Putri, Naimah; Karni, Ine
Journal of Applied Veterinary Science And Technology Vol. 5 No. 1 (2024): April 2024
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/javest.V5.I1.2024.1-6

Abstract

Background: Newcastle disease (ND) is a highly contagious viral disease affecting the poultry industry. The NDV is classified into three strains based on their relative virulence, namely velogenic or highly virulent, mesogenic or moderately virulent, and lentogenic or lowly virulent. The clinical manifestations of the disease vary depending on many factors, such as host susceptibility and the virulence of the NDV strain. Objective: This study aims to analyze the amino acid mutations of the NDV in unvaccinated swan goose (Anser cygnoides) from various locations in Java. Methods: Samples were collected through cloacal swabs and isolated by inoculation in Specific Pathogen-Free (SPF) embryonated eggs that were nine days old. Hemagglutination and hemagglutination inhibition tests were conducted to confirm that the isolated virus was NDV. The isolated virus was processed using reverse transcription-polymerase chain reaction (RT-PCR) with primers that amplified partial sequences of the fusion (F) gene, which was analyzed to determine the pathotype. Results: The results indicated the presence of mutations in several regions. The amino acid changes occurred in 17 variable sites (7.2%) between RefSeq/JF950510 and ND/SW1/2018, 12 variable sites (5.1%) between RefSeq/JF950510 and ND/SW2/2018, 13 variable sites (5.5%) between RefSeq/JF950510 and ND/SW3/2018, and 19 variable sites (8.1%) between RefSeq/JF950510 and ND/SW4/2018. The amino acid sequences of the cleavage site of the fusion (F) protein revealed that all isolates had low virulence. Conclusion: The results indicated that mutations in the region outside the cleavage site not were incapable of altering the virulence of the virus.