Publication Search

Batik motif classification has attracted growing attention in visual computing due to its role in cultural heritage preservation, textile informatics, museum documentation, and automated cataloging. Although many studies report high classification accuracy, robustness under real-world acquisition conditions remains insufficiently understood. Batik images are frequently affected by illumination variation, blur, folds, watermark overlays, wearable deformation, scale inconsistency, and background clutter, creating challenges that extend beyond conventional image-noise assumptions. Existing studies largely focus on improving classification performance, while the interactions among acquisition variability, feature representation, evaluation practice, and deployment constraints remain fragmented. This systematic literature review addresses this gap by synthesizing batik classification research through a robustness-aware perspective. Using query expansion, backward and forward citation chaining, relevance screening, and thematic coding, 116 candidate records were identified, resulting in 50 highly relevant studies for detailed analysis. The review reveals that robustness is shaped less by denoising alone than by the combined effects of acquisition conditions, representation design, evaluation realism, and deployment context. Handcrafted descriptors remain competitive for small datasets and structured motifs due to their data efficiency and interpretability, whereas deep learning models achieve the highest reported accuracy when supported by sufficient data diversity and realistic augmentation. Hybrid representations emerge as the most consistently balanced approach, combining local texture stability with higher-level abstraction across heterogeneous acquisition settings. The review further identifies recurring robustness failure patterns, including background dependency, illumination instability, motif-scale inconsistency, wearable deformation, and source-shift vulnerability. Based on these findings, a robustness-oriented research agenda is proposed, emphasizing cross-acquisition evaluation, representation-stability analysis, batik-specific robustness benchmarks, acquisition-aware augmentation, and deployable lightweight or hybrid architectures. The study contributes a domain-specific synthesis that reframes batik motif classification from an accuracy-centric task toward a robustness-aware visual recognition problem.

Breast tumors are classified into two types, namely benign and malignant tumors, the latter commonly referred to as breast cancer. Breast cancer is one of the major health problems affecting women worldwide, including in Indonesia. According to WHO data in 2022, there were 2.3 million breast cancer cases with 685,000 deaths globally, while in Indonesia, 396,914 cases and 234,511 deaths were reported. The high incidence rate is exacerbated by low public awareness in recognizing early symptoms and performing early detection, resulting in 60–70% of cases being diagnosed at an advanced stage, supported by findings that 65.6% of female students still have a low level of knowledge. Female students were selected as research subjects because they are in a vulnerable reproductive age group and have an important role in increasing awareness of early detection, yet they still have limited knowledge. Based on this, this study aims to design a web-based early detection system for breast tumor risk using the Forward Chaining method, which functions as a tool to identify early symptoms, assess risk levels, and provide information on prevention and initial management. This study employed the method with the Expert System Development Life Cycle (ESDLC) model, consisting of the stages of assessment, knowledge acquisition, design, testing, and documentation, along with the Forward Chaining inference method.

  Abstract. This study aims to develop and evaluate an artificial intelligence–based expert system to support fault diagnosis in Air Handling Units (AHUs). Early fault identification in AHU systems is often constrained by reliance on technician experience, which may lead to inconsistent diagnostic outcomes. The proposed system is intended to provide a consistent, explainable, and practical decision-support tool to assist maintenance personnel, particularly less-experienced technicians, in identifying AHU faults accurately. Methodology: The research adopts a rule-based expert system approach using forward chaining inference. Knowledge acquisition was conducted through structured interviews with experienced HVAC technicians and supported by technical documentation. The resulting knowledge base consists of observable symptoms, diagnostic rules, and corresponding corrective actions. The system was implemented as an Android-based mobile application to enable direct field usage. System validation was performed using real operational fault scenarios, with expert diagnoses serving as the reference standard. Findings: Evaluation results indicate full agreement between the system-generated diagnoses and expert assessments across all tested scenarios. This demonstrates that the proposed system is capable of producing accurate and consistent diagnostic outcomes within its defined knowledge domain. Implications: The system operates using deterministic rules without incorporating uncertainty modeling or probabilistic reasoning. Additionally, validation was limited to a finite number of real-world scenarios, which may affect generalizability to broader AHU configurations. Practical implications: The expert system can be utilized as a practical diagnostic aid in routine AHU maintenance, improving response time, diagnostic consistency, and technician training effectiveness. Originality: This study contributes a mobile-based, explainable expert system specifically tailored for AHU fault diagnosis, emphasizing practical deployment and rule transparency rather than data-intensive learning models.

The purpose of this scientific paper is to design and implement a knowledge-based expert system to assist students in determining their major specializations at Vocational High Schools (SMK) more objectively and accurately. A major problem frequently faced by SMK students is the mismatch in department selection caused by a lack of understanding regarding their own potential and the specific criteria of each competency. To address this issue, the system was developed using the Forward Chaining method as the inference engine. This method operates in a data-driven manner, beginning with the collection of facts such as interests, academic abilities, and psychological aspects, which are then matched against a Knowledge Base consisting of IF-THEN logical rules. Based on system testing results, the inference engine is capable of processing the list of facts to generate a specialization diagnosis for SMK students and provide the most relevant departmental recommendations, such as Computer and Network Engineering (TKJ), Accounting, Office Automation and Governance (OTKP), or Marketing. The research results indicate that the implementation of the Forward Chaining method is effective in accelerating the decision-making process and minimizing placement errors. This expert system is expected to serve as a tool for Guidance and Counseling (BK) teachers in providing appropriate career direction for students based on structured empirical data.

This study aims to design and develop an expert system to assist in diagnosing diseases in dairy cattle at Cibugary Farm using the Forward Chaining method. The background of this research lies in the limited knowledge of farmers in identifying early symptoms of diseases, which often leads to delays in medical treatment and negatively affects dairy cattle productivity. To address this issue, an expert system was designed to replicate the reasoning process of a human expert through a knowledge base containing diagnostic rules derived from observable symptoms. The Forward Chaining method was chosen because of its capability to trace facts from known symptoms toward a conclusion regarding the type of disease affecting the cattle. The system was developed by incorporating common disease symptoms, inference rules, and a decision-making mechanism that simulates expert analysis. Testing was carried out on several diagnostic scenarios to evaluate the accuracy and efficiency of the system. The results of the study indicate that the expert system can provide an initial diagnosis quickly and accurately, producing outputs consistent with expert assessments. This functionality assists farmers in making timely decisions regarding appropriate medical interventions, thereby reducing treatment delays and minimizing the risk of disease transmission within the herd. Consequently, the Forward Chaining-based expert system is expected to serve as an innovative solution to improve dairy cattle health management and support sustainable livestock productivity at Cibugary Farm.

Health is important for every human being. Health, education and income of each individual are three important factors that greatly influence the quality of human resources. Anxiety disorders are a significant mental health problem and can affect an individual's quality of life. Early detection of anxiety disorders is important to provide appropriate intervention and prevent the development of more serious conditions. This research aims to develop an expert system that is able to detect anxiety disorders based on symptoms reported by penggunas. This system uses a forward chaining method and a knowledge base compiled from medical literature and consultations with mental health experts. Several stages of system creation include collecting data on symptoms of anxiety disorders, preparing a knowledge base, implementing a forward chaining inference algorithm, and kuatating the system using test data and expert consultation. The expert system developed in this research is able to provide accurate initial information regarding the symptoms of anxiety disorders in adolescents based on the symptoms input by the pengguna. By utilizing a knowledge base and appropriate diagnostic rules, the system can identify key symptoms that indicate the presence of an anxiety disorder.

Diseases in cattle, especially Foot and Mouth Disease (FMD), have a major economic impact on farmers. FMD is a highly contagious viral disease in even-toed ungulates such as cattle, buffalo, goats, and sheep. This virus from the genus Aphthovirus, family Picornaviridae spreads rapidly through direct contact, air, or contaminated objects. The impact of FMD is very detrimental, including decreased milk production in dairy cows, weight loss in beef cattle, and death in severe cases. In addition, high medical costs, restrictions on livestock trade, and reduced consumer confidence in livestock products are also important consequences. The FMD outbreak in Indonesia in 2022, especially in East Java, caused major losses for farmers. Therefore, a fast and accurate diagnostic system is needed for early detection of the disease. Early diagnosis helps farmers take appropriate treatment measures such as isolating infected livestock, administering drugs, and disinfecting pens to prevent the spread. This article discusses the implementation of the forward chaining method in an expert system for diagnosing cattle diseases, including FMD. This method analyzes cattle symptoms and matches them with rules in the knowledge base systematically, from symptoms to diagnosis. With this approach, the expert system can provide a fast and accurate diagnosis and appropriate treatment recommendations. This is expected to help farmers reduce losses, increase productivity, and support the sustainability of cattle farming businesses in Indonesia.

Chilli farming is an important sector in Ende District, but plant disease problems are often an obstacle that hampers productivity. Farmers often have difficulty recognizing the symptoms of disease in chili plants and determining appropriate treatment steps. To overcome this problem, this research aims to design and build a web-based expert system that can help diagnose chili plant diseases using the Forward Chaining method. This expert system was developed by collecting knowledge from agricultural experts and literature related to chili plant diseases, as well as applying the Forward Chaining method for the reasoning process. Users, especially farmers, can enter the symptoms experienced by chili plants into the system, then the system will produce a disease diagnosis and appropriate treatment recommendations based on these symptoms. This research uses a case study at Maju Tani Agriculture in Ende District to ensure that the expert system developed is relevant to local conditions. This system is implemented in the form of a web-based application so that it can be accessed easily by farmers using devices connected to the internet. The test results show that this expert system can provide accurate and efficient diagnoses, as well as assist farmers in making decisions to overcome chili plant disease problems. It is hoped that this system can increase agricultural productivity and reduce the risk of losses due to plant diseases.

This research aims to develop a web-based expert system with the Forward Chaining method that can diagnose and provide treatment for people with stroke disease. The expert system will be used to help the diagnosis process by analyzing the symptoms reported by the patient. The Forward Chaining method will be used as an inference approach in this expert system. The system will use a knowledge base that contains medical rules obtained from experts. The inference process will be carried out by linking the symptoms reported by the patient with the information in the knowledge base to determine possible diagnoses and appropriate treatments. This expert system will be implemented in the form of a web-based application that can be accessed by the general public. The results of this study show that the expert system to diagnose and provide treatment using the forward chaining method is successfully built and the application can be used to help the general public diagnose by entering the symptoms felt and the expert system will provide diagnostic results and provide treatment.

Kucing adalah hewan peliharaan populer yang sering kali rentan terhadap berbagai penyakit. Ketidakmampuan pemilik untuk mendiagnosa penyakit kucing secara tepat waktu sering kali mengharuskan konsultasi dengan dokter hewan yang sebagian besar hanya tersedia di perkotaan. Penelitian ini bertujuan mengembangkan sistem pakar berbasis web menggunakan metode Forward Chaining dan Certainty Factor untuk membantu mendiagnosa penyakit pada kucing. Metodologi pengembangan sistem ini mencakup tahap persiapan, prototyping, dan penyelesaian. Pada tahap persiapan, masalah dirumuskan dan wawancara dengan dokter hewan dilakukan untuk membangun knowledge base. Tahap prototyping melibatkan pembuatan mesin inferensi dan knowledge base, sementara tahap penyelesaian meliputi implementasi sistem ke dalam antarmuka pengguna berbasis web menggunakan PHP dan framework Laravel. Hasil uji sistem menunjukkan konsistensi tinggi dengan hasil diagnosa manual menggunakan Excel. Sebagai contoh, diagnosa penyakit Virus Panleukopenia memiliki nilai certainty factor sebesar 94,62% pada aplikasi, sementara perhitungan manual menunjukkan 95,21%, dengan perbedaan hanya 0,41%. Hal ini menunjukkan bahwa sistem pakar yang dikembangkan mampu memberikan diagnosa yang cepat dan akurat. Kesimpulannya, sistem pakar berbasis web ini dapat diandalkan untuk mendiagnosa penyakit kucing dan membantu dokter hewan serta pemilik kucing melakukan diagnosa awal dengan lebih efisien.

Abstract -  Corn plants are one of the plants that are easy to grow and relatively fast to get results but also a plant that is vulnerable to pests and diseases. The symptoms that arise require an expert or agricultural expert to be able to diagnose. Limited time and expert labor is one of the causes of delayed diagnosis, causing a decrease in farmers' yields. This is the basis for making this expert system by adopting knowledge from agricultural experts about the symptoms of corn disease using the Forward Chaining method. To support the research conducted, researchers used the Research and Development (R&D) research method and the design used the Object Oriented Programming (OOP) method using the Unified Modeling Language (UML). Software is built using the PHP programming language, MySQL as a database, and Bootstrap as an interface design with a web-based system.    

This research discusses "Information Search Behavior Using the Electronic Journal Portal "ScienceDirect" in Fulfilling Student Information Needs". The subject matter of this research is the information search behavior of students of the Library Science Study Program at the State Islamic University of North Sumatra. This type of research uses descriptive methods, with a qualitative research approach. This approach aims to identify information search behavior using ScienceDirect Information search behavior using the ScienceDirect electronic journal portal has conducted searches using the stages put forward by Ellis. The results showed that the purpose of information searchers using ScienceDirect was to find references in completing coursework and looking for journals only as reading material. The information sought is articles related to courses majoring in library science and looking for scientific papers on losing weight. In Ellis' theory, there are 8 stages that are passed in the information search process, namely, starting, chaining, browsing, differenting, monitoring, extracting, verifying, and ending. From the analysis, it can be concluded that all informants go through these 8 stages to get the information they need. Some of the differences between using ScienceDirect and using other portals: (a) Availability of articles (sometimes in ScienceDirect not in other portals, and vice versa) (b) Articles obtained are in English, other portals use Indonesian (c) Provides scientific papers from international authorized authors Some obstacles in searching for information using ScienceDirect electronic journals: (a) The articles searched are not very complete (b) Articles in English (c) Network constraints (d) Many paid articles (e) Having to register Many articles are paid (e) Must register for an account (f) Search settings are not easy.

An expert system is a collection of system engineering devices which have a structured way of thinking from one or more experts regarding certain scientific fields, both specific and complex, which are created based on an instructional element that identifies and also analyzes data at the level of irregular problems or analysis. mathematics regarding problems that cover certain aspects, but are related to the process of detecting printers and repairing them from the school which is carried out independently, then along with the development of website-based information technology which can make it easier to detect printer damage for users, then in detecting printer damage for users there are several factors that influence this, such as, not all staff at the school have knowledge in detecting printer damage and there is no system that supports detecting printer damage so it is difficult to find solutions for staff to repair, based on this problem as a solution, an expert system application design is needed. for detecting printer damage to users who support the website-based printer detection process using the forward chaining method, the concept of forward chaining with search or forward tracking techniques starting with existing information or combining rules to obtain a certain conclusion or goal as a result of the solution.

Sapi merupakan hewan yang hidup di darat, yang menjadikan salah satu dari sekian banyak sumber protein dan lemak yang dibutuhkan manusia. Sapi merupakan hewan pemakan tumbuhan yang sangat berguna bagi banyak orang terutama dari segi susu, daging, kulit dan kotorannya. Komoditas telur, daging, dan susu ialah komoditas pangan yang memiliki protein dan lemak yang tinggi. Sapi juga termasuk dalam kategori hewan ternak. Dalam menjaga kualitas serta pemeliharaan sapi ditemukannya kendala, yakni adanya penyakit yang menyerang sapi. Hal ini menjadi hambatan bagi peternak sapi. Kendala dalam mendiagnosis penyakit sapi ialah kurangnya pengetahuan peternak tentang penyakit sapi, keterbatasan waktu, dan pengambilan keputusan dalam proses pencegahan. Dari teknik berternak hingga penanganan penyakit, seharusnya berkonsultasi dengan ahlinya (dokter hewan) untuk mendapatan solusi terbaik dari permasalahan tersebut agar peternak mendapatkan hasil yang maksimal Dalam hal ini sistem pakar dijadikan sebagai alternatif kedua dalam membantu mengatasi pemecahan masalah. sistem pakar ini memberikan informasi tentang berbagai jenis penyakit yang menyerang hewan sapi, sistem pakar ini menggunakan metode Forward Chaining, dimana Sistem ini diharapkan dapat membantu dalam penanganan konsultasi peternak sapi dalam mendiagnosa penyakit. Sistem ini disediakan untuk memberi peluang peternak agar dapat membantu mengetahui gejala sebelum ditangani dokter hewan dan dapat mencegah gejala penyakit tersebut secara cepat.

Gangguan mental pada anak merupakan gangguan kesehatan yang terdiri dari keterbelakangan mental autis dan anxiety disorder. Banyak orang awam yang tidak menyadari bahwa anaknya mengidap gangguan autisme. Ketidaktahuan ini disebabkan oleh kurangnya informasi tentang gangguan tumbuh kembang anak, gejalanya, dan kurangnya dokter spesialis tumbuh kembang anak dan psikolog. Penyebab autisme sendiri sudah ada sebelum bayi lahir, bahkan sebelum vaksinasi. Sistem pakar adalah cabang AI (Artificial Intelligence) yang menggunakan keahlian secara luas untuk memecahkan masalah. Pakar adalah seseorang yang memiliki keahlian dalam bidang tertentu dan memiliki pengetahuan atau keterampilan khusus yang orang lain di bidangnya tidak tahu atau tidak mampu. Berdasarkan kondisi di atas, maka dibangunlah sebuah sistem yang menggunakan teknologi komputerisasi yang dapat mengadopsi kemampuan seorang ahli atau pakar yaitu teknologi Artificial Intelligence atau Kecerdasan Buatan.

Seiring dengan merebaknya penyakit yang banyak menyerang sapi maka penulis mengangkat judul Sistem pakar dengan metode forward chainning. sistem pakar adalah ilmu informasi yang berisi  seorang pakar sehingga  layak menjadi seorang pakar,  aplikasi ini dirancang dengan basis pengetahuan  fakta dan  penalaran,  dari kumpulan data - data faktual dengan mencari aturan atau gejala gejala yang sesuai hipotesis dapat digunakan untuk menentukan penentuan gejala yang sudah diidentifikasi. Perancangan aplikasi ini  berbasis mobile dengan bahasa pemrograman Java pada Android sebagai client dan database MySQL sebagai server dengan  PHP sebagai link login sehingga aplikasi ini sangat mudah digunakan dan cepat saat ingin mengakses aplikasi tersebut.  expert sistem (sistem pakar) juga dikenal sebagai sistem yang berusaha menerapkan     pemikiran manusia untuk kemudian diimplementasikan dalam  perangkat lunak, sehingga komputer dapat menyelesaikan masalah Topik seperti yang biasanya dilakukan oleh seorang profesional dalam sistem pakar ini menggunakan metode forward chainning  forward chainning ini menggunakan aturan  (if) kemudian dilanjutkan pada kesimpulan atau informasi turunan (then) sehingga menemukan fakta yang dapat ditarik sebagai kesimpulan. Forward chaining berarti menggunakan set aturan tindakan bersyarat. Teknik ini menggunakan data untuk menentukan aturan mana yang akan dieksekusi, atau  menambahkan data ke memori  untuk diproses guna menemukan hasilnya.

Kejang demam adalah bangkitan kejang yang terjadi pada kenaikan suhu tubuh (suhu rektal di atas 38 Celcius) yang disebabkan oleh suatu proses ekstrakranium. Memasukkan sendok kedalam mulut, menahan gerakan anak, memberikan selimut tebal, memberikan kopi, merupakan perilaku salah dalam penanganan kejang demam sebelum dibawa ke rumah sakit. Kejang demam pada dasarnya merupakan penyakit yang tidak berbahaya dan tidak berdampak pada sistem neurologi. Namun, kejang demam ini merupakan pengalaman yang menakutkan dan menimbulkan kecemasan pada orang tua. Hal ini disadari sebagai salah satu faktor tingkat kecemasan pada sebagian orang tua bertambah. Tujuan penelitian untuk memberi pengetahuan keluarga tentang kejang demam dengan perilaku penanganan kejang demam sebelum dibawa ke rumah sakit.

Teeth are one of human‘s organs that feeds on food. As an organ, the tooth definitely can be attacked by some disease. There are many cases of dental disease that occur from dental diseases common to people to chronic dental diseases that can be dangerous. The low level of public concern about dental disease is a problem faced today. Evidenced by the small number of people who diligently consult with dentists about the health of their teeth. An alternative option is needed that can make it easier for people to be able to consult or diagnose dental health and disease without having to see a doctor of dental health. Therefore, in this essay an expert system was created to provide alternative choices for people. This expert system was created with the php hypertext preprocessor programming language. Using the forward chaining method as a tracking method. The purpose of making this expert system is to be able to be a substitute for a dental expert so that people can already do the diagnosis of dental disease anywhere and anytime.

Penyakit hipertensi merupakan manifestasi gangguan keseimbangan hemodinamik sistem kardiovaskular yang mana patofsiologinya multifaktor yang cukup banyak mengganggu kesehatan masyarakat. Pada umumnya pasien tidak mengetahui bahwa menderita penyakit hipertensi sebelum memeriksakan tekanan darahnya, ini menyebabkan hipertensi merupakan suatu penyakit kronis yang disebut dengan silent killer. Salah satu yang dapat membantu dalam proses penegakkan diagnosa hipertensi dengan mengembangkan sebuah Rancangan Sistem Pakar Penegakan Diagnosa Penyakit Hipertensi, dalam penelitian ini menggunakan metode penelitian Inferensi Forward Chaining, Metode Support Vector Machine (SVM). Data yang digunakan yaitu data primer dan sekunder. Tujuan dari penelitian ini memudahkan tenaga medis dan penderita dalam mengetahui gejala awal penegakan diagnosa hipertensi, agar segera bisa dilakukan penangan yang cepat dan akurat. Hasil dari penelitian model SVM linear terhadap 247 data pasien menunjukkan akurasi 85% pada proses training dan 91,89 % pada proses testing.  

Tomato (solanum lyco persicum) is a plant from the solanceae family, native to Central and South America, from Mexico and Peru. Tomatoes have a short life cycle and a height ranging from 1 to 3 meters. Currently, farmers often experience disturbances from pests and diseases of tomatoes due to a lack of knowledge. They do not know how to control it and to eliminate pests that reduce productivity. In identifying diseases in tomato plants we use the Forward Chaining method which is a description that starts from knowing the facts and then matching them with IF and IF-THEN rules. Diseases with a high prevalence in tomatoes are: fruit worms, earthworms, green aphids, white flies, fruit flies (bractrotera) and the diseases are: fusarium wilt, leaf spot disease, bacterial spot, fruit rot. This expert system application provides tomato disease information and disease diagnosis, including control solutions that can be used to reduce the risk of tomato crop damage