Optimization of Artificial Neural Networks using Genetic Algorithm for Palm Fruit Ripeness Classification

Global population and income growth has driven the demand for agricultural land. This rapid conversion of land use to agriculture has affected the social and economic welfare of local communities within the landscape. Indonesia is a country that has recently undergone rapid land-use change due to increasing demand in global crop commodities. Oil palm, the largest export commodity in Indonesia, has been identified as a key driver of deforestation and biodiversity loss in this region. Oil palm has also replaced agricultural lands that were previously used to grow food crops for local subsistence, as well as other cash crops such as rubber. The agricultural sector is a main contributor to the national economy and is a major element in Indonesia’s economic growth and development strategy. Despite experiencing rapid economic and social changes over the past two decades, rural poverty, malnutrition, and food insecurity continue to persist at high rates. 
\nUnderstanding the social and economic consequences of land-use change is therefore imperative to address how to support the welfare and development of local communities affected within the landscape. This dissertation explores the human dimension of the recent land-use changes and particularly focuses on the impact of agricultural specialization and oil palm expansion in Indonesia. This dissertation has two research objectives. The first research objective is to analyze how agricultural specialization has affected diets in rural Indonesian households over a time. The second research objective is to examine how the oil palm expansion has affected smallholder farmers in terms of household economic welfare and intra-household gender roles. 
\nDespite great strides in reducing hunger over the last two decades, malnutrition remains a major challenge in Indonesia. High rates of child stunting coexist with high and increasing rates of overweight and obesity despite rapid economic growth and reductions in poverty over the last two decades. Part of this economic growth has been driven by a change in agricultural production systems from traditional farming techniques that typically grow multiple crops to more intensified, specialized and commercialized farms. The objective of the first essay is to analyze how changes in the structure of agricultural production have affected diets in rural Indonesian households over time. We use three waves of a panel data from the Indonesian Family Life Survey with a balanced sample of 2785 rural households between 2000 and 2015 to observe transitions in households’ food choices over time in response to the changes in production systems. We find positive relationships between production diversity and household dietary diversity as well as between market access and household dietary diversity. However, we see that there has been an overall decline in dietary diversity in households where production diversity has also reduced. This decline in dietary diversity was mostly driven by the decreased consumption of nutritious food groups (fruits, vegetables, legumes, and fish). Although the magnitude of the association between dietary diversity and production diversity was relatively small, the association between household production and consumption of some of these important food groups was quite substantial. The overall impact of increased specialization in Indonesia during the period 2000–2015 on dietary quality appears to have been negative.
\nAfter looking at national household dietary quality implications, we zoom in on oil palm producing households. The rapid expansion of oil palm in tropical regions has substantial implications for socioeconomic development. Several studies show that smallholder farmers benefit economically from cultivating oil palm. However, most existing studies examine short-term impacts with cross-sectional data, which has two disadvantages. First, issues of endogeneity are difficult to address with cross-sectional data. Second, dynamic and risk effects cannot be analyzed. In this second essay, we address both issues by using three waves of panel data from smallholder farmers in Indonesia and pseudo fixed effects panel estimators. We show that oil palm cultivation increases household living standards, measured by annual consumption expenditure, by 13% on average. Moreover, we demonstrate that oil palm cultivation reduced households’ economic risk, measured in terms of potential decreases in living standard due to income variability. The risk-reduction effect is evident despite fluctuating international palm oil prices and consequences for oil palm revenues and profits. Oil palm requires less labour than alternative crops, thus freeing family labour for other economic activities. We find that oil palm farmers are more involved in off-farm activities, which helps to smooth income and consumption. Policy support may be required to address oil palm adoption constraints that some smallholders face. In addition, fostering the non-farm economy and improving household access to lucrative off-farm jobs are important for equitable rural development.
\nTo our knowledge, there are only few studies that address the intra-household implications of oil palm expansion in Indonesia. Male and female household members might be affected differently by the increasing adoption expanding oil palm cultivation. The last essay explores the gender-disaggregated implications of oil palm cultivation among smallholder households in Indonesia. By using panel and cross-sectional data of 700 smallholder households, we examine the disaggregated farm labor input over time, 24-hour time allocation and females’ economic decision-making power. Results show that oil palm cultivation decreases on-farm family labor input, especially female labor. When looking at the male and female time allocation, results suggest that females spend less time on farms, more time on work inside the house and enjoy more leisure time as the share of farm under oil palm cultivation increases. For the male counterparts, differences in time allocation were not statistically significant, except for more leisure time among male members as the intensity of oil palm cultivation increases. Findings reveal that females are more likely to lose intra-household decision-making power in relation to farm management and farm income allocation. These findings make important contributions to addressing rural development policies aiming to expand cash crop production while also improve women’s welfare.
\n\tThis dissertation concludes by providing a synopsis of all three essays, discussing the limitations, possible future research areas, and broader policy conclusions from the findings presented above. For the first research objective, results point to more nuanced policies, targeting nutrition as such. For the second research objective, findings from essay two and three suggest that positive gains from commercial oil palm cultivation occurred in terms of household welfare but the gender implications are rather mixed. In this context rural non-farm sector is important to support income diversification, especially regarding the economic involvement of females that are no longer working on-farm in oil palm cultivation.

In this study, performances comparison to discriminate five mental states of five artificial neural network (ANN) training methods were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw electroencephalogram (EEG) signals. The five ANN training methods used were (a) Gradient Descent Back Propagation (b) Levenberg-Marquardt (c) Resilient Back Propagation (d) Conjugate Learning Gradient Back Propagation and (e) Gradient Descent Back Propagation with movementum.

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.

Abstract. Primananda S, Soedijo S, Gazali A, Aidawati N, Fitriana CDA, Sukarman, Prasetyo AE, Rozziansha TAP. 2025. Ecological design for the propagation of Sycanus dichotomus in insectariums for sustainable oil palm pest management. Biodiversitas 26: 617-627. The oil palm industry plays a substantial role in national and global economies, and sustainable agricultural practices are critical to its longevity including aspects related to pest management. This study aimed to identify effective methods for propagating the predatory insect Sycanus dichotomus as part of integrated pest management in oil palm plantations. The primary focus is on ecological design within the insectarium, selecting appropriate refugia plants, and determining the sex ratio to support an efficient predator population. The study was conducted at an oil palm plantation in Central Kalimantan, Indonesia, which serves as a natural ecosystem for S. dichotomus. A multifactorial experimental design was employed, combining variables such as insectarium type manifested as paranet density, adults sex ratio, and refugia plant type. The most optimal results for enhancing the productivity of the predator S. dichotomus were achieved using an insectarium with 100% sunlight intensity, a sex ratio of males to females of 2:4, and Cassia cobanensis as the host plant. The maturation rate from eggs to nymphs increased in an insectarium with 25% sunlight intensity and Antigonon leptopus as the host plant, resulting in high fertility and the presence of 1st, 3rd, and 5th instar nymphs. The interaction between egg groups and the total eggs was highly correlated (80%), and the development of instar 1 and instar 3 showed a fair correlation at 60%, indicating key relationships that support the predator's growth and reproduction under these conditions. Additionally, the study demonstrated that balancing sunlight exposure and selecting appropriate host plants significantly affect the development and reproductive success of S. dichotomus. This research highlights the importance of microclimatic conditions in the insectarium, refugia plants, and sex ratio as crucial factors for rearing S. dichotomus. It provides important insights for the propagation of predator techniques to support the sustainable oil palm industry. These findings underscore the importance of an integrated approach to pest management, ensuring long-term sustainability and economic viability in oil palm cultivation.

Malaysian oil palm plantation sector: exploiting renewable energy toward sustainability production

Tengkawang is the flora mascot of West Kalimantan Province and has long been the mainstay of life for people living around forest areas.Its fruit can be processed into fat and sold as green butter, borneo tallow, or tengkawang oil, which is used as a chocolate substitute, and ingredient in lipstick, candles, and medicines.Its wood is used as raw material for the sawmill and plywood industry.Currently, tengkawang trees are threatened with extinction and have been replaced by rubber and oil palm plantations.The objective of this study is to analyze the financial feasibility of three land cultivation models and formulate a land cultivation model in community forests.This study used three models of land cultivation, namely tengkawang cultivation, rubber cultivation, and oil palm cultivation, which are managed through monoculture.This research used a descriptive method with survey and interview techniques using questionnaires.The financial analysis findings indicate that all three land cultivation models are viable, with profitability ranking in the following order: tengkawang, rubber, and oil palm.Consequently, tengkawang proves to be the more financially rewarding option when compared to rubber and oil palm.

Oil palm cultivation is one of the most important occupation in South East Asia. Since oil palm plantations cover the wide range of area, it is difficult to count the population of oil palm manually. This paper presents a new method to detect and identify oil palms over the plantation from aerial images regard- less of their sizes using features such as shape, size, and texture. The proposed method can handle the problem of identifying oil palms from an aerial image when oil palms are too close to each other which cause them to be detected as a single stand. The process consists of removing non-tree components from an image, distinguishing oil palms from other components, identifying individual oil palm, and counting the number of oil palms. In this paper, oil palm can be detected and distinguished from other components using ideal low-pass filter and normalized cross correlation. Then a proposed multi-scale clustering meth- od and erosion are used to identify individual oil palm from a bush. The method was evaluated on a set of 21 aerial images taken over oil palm plantations from different regions of Thailand by attaching a digital camera to a remote airplane. The experimental results reveal that our proposed method can detect most of the oil palms with the accuracy as high as 90%.

Palm oil industry in South East Asia and the effluent treatment technology—A review

Oil palm is one of the plantation commodities that Indonesia relies on to generate foreign exchange annually. The oil palm industry generates both solid and liquid waste. Oil palm waste is a byproduct of the oil palm industry that is not reused; however, with technological advancements, this waste can be utilized as supplementary feed, especially for ruminants. The waste obtained from oil palm plantations and oil palm mills includes oil palm fruit bunches, oil palm fibers, oil palm shells, oil palm kernel meal, oil palm leaves, and oil palm sludge. Mucuna barcteata can also be used as a protein source for animal feed. Research was conducted in the Sei Mangkei plantation, and feed trials were carried out in the Bangun PTPN III Plantation (Simalungun). The methods employed included surveys and laboratory research. Proximate analysis of the suspected feed sources was conducted by PT Saraswanti Indo Genetech Bogor, which encompassed total energy, moisture and ash content, total fat, protein, carbohydrates, crude fiber, calcium, and phosphorus. The weight gain of cattle after being fed the experimental diet was observed over a three-month period. The research results indicate that oil palm byproducts can support a population of 12,365 head of beef cattle per year. Mucuna bracteata, oil palm kernel meal, oil palm fronds, and solid decanter can be used as animal feed. A feed mixture containing 30% Mucuna resulted in the highest weight gain in cattle compared to the other three treatments, with an average daily gain of 0.97.

SUMMARYResearch backgroundBiogas production from palm oil mill effluent (POME) is inherently unstable due to variations in feedstock composition and operating conditions. These fluctuations can lead to inconsistent biogas quality, variable methane content and fluctuating hydrogen sulphide (H2S) concentration. This poses significant challenges for bioscrubbers in removing H2S to meet quality standards for gas engines used for electricity generation. This research aims to address these challenges by integrating simulation models with a computer programme and artificial neural network (ANN) to predict the performance of a bioscrubber at a POME treatment plant in Johor, Malaysia.Experimental approachFirst, the process flowsheet model was simulated using a computer programme. The H2S removal was then predicted using a machine learning algorithm, specifically ANN, based on two years of historical data obtained from the biogas plant. A detailed techno-economic analysis was also carried out to determine the economic feasibility of the process.Results and conclusionsThe simulation results showed a biogas yield of 26.12 Nm3 per m3 POME, which is in line with industry data with less than 1 % deviation. The ANN model achieved a high coefficient of determination (R2) of 0.9 and a low mean squared error (MSE), with the bioscrubber reaching an H2S removal efficiency of approx. 96 %. The techno-economic analysis showed that the process is feasible with a net present value (NPV) of $131 000 and a payback period of 7 years.Novelty and scientific contributionThe integration of ANN and the computer programme provides a robust framework for predicting bioscrubber performance and ensuring stable bioscrubber operation due to their complementary strengths. ANN accurately predicts H2S removal based on daily recorded data, while the computer programme estimates parameters that are not monitored daily, such as chemical oxygen demand (COD), biological oxygen demand (BOD) and total suspended solids (TSS). This research provides valuable insights into sustainable biogas production practices and offers opportunities to improve energy efficiency and environmental sustainability in the palm oil industry.

Indonesia is the world's top producer of crude palm oil, and this strategic commodity has boosted the nation's economic growth. The palm oil industry expanded significantly following the launch of the Perkebunan Inti Rakyat (PIR) transmigration program by the Indonesian government during the Suharto era. In the 1980s the PIR program brought many Javanese transmigrants to Riau to cultivate palm oil, helping Riau Province become Indonesia's largest producer of palm oil, accounting for almost one fifth of national production in 2018. The growth of the palm oil industry has spurred economic growth in Riau while also contributing to an increase in environmental degradation, deforestation, forest fires, and the risks associated with land use change, leading to a clash of narratives between pro-palm oil coalitions and environmental groups. Drawing on evidence from Riau, this study investigates the competing claims of groups touting economic growth and others decrying environmental degradation. To what extent does the palm oil industry drive economic growth and affect environmental conditions in Riau? How do we account for the lack of sustainability policies implementation in Indonesia? This study includes qualitative data obtained from smallholders in eight villages in Riau as well as the perspectives of provincial NGOs, researchers, and government representatives. This study finds that the economic benefits enjoyed, and risks encountered, by smallholders are highly variable with a different balance of outcomes in each village. Many smallholders claim that palm oil harvests have improve their economic situation while also acknowledging environmental problems. However, they argue that economic necessity leaves them no choice but to join the palm oil boom. The government has played a contradictory role by facilitating the growth of the palm oil sector and encouraging it to meet production targets while also passing sustainability policies and imposing moratoriums to respond to local, national, and global pressures.

Effects of oil-palm (Elaeis guineensis Jacq.) management on silicon (Si) cycling under smallholder oil-palm plantations have hardly been investigated. As oil palms are Si accumulators, we hypothesized that management practices and topsoil erosion may cause Si losses and changes in spatial Si concentration patterns in topsoils under oil-palm cultivation. To test this hypothesis, we took topsoil samples under mature oil-palm plantations in well-drained and riparian areas of Jambi Province, Indonesia. The samples were taken from four different management zones within each oil-palm plot: palm circles, oil-palm rows, interrows and below frond piles. We quantified mobile Si (SiM) and Si in amorphous silica (SiAm) by CaCl2 and NaCO3 extraction, respectively. Both fractions are important Si pools in soils and are essential for plant-soil Si cycling. We further installed sediment traps on sloping, well-drained oil-palm plantations to estimate the annual loss of soil and SiAm caused by erosion. In well-drained areas, mean topsoil SiAm concentrations were significantly higher below frond piles (3.97 ±1.54 mg g-1) compared to palm circles (1.71± 0.35 mg g-1), oil-palm rows (1.87 ± 0.51 mg g-1) and interrows (1.88 ± 0.39 mg g-1). In riparian areas, highest mean topsoil SiAm concentrations were also found below frond piles (2.96 ± 0.36 mg g-1) and in grass-covered interrows (2.71 ± 0.13 mg g-1), whereas topsoil SiAm concentrations of palm circles were much lower (1.44 ± 0.55 mg g-1). We attributed the high SiAm concentrations in topsoils under frond piles and in grass-covered interrows to phytolith release from decaying oil-palm fronds, grasses, and sedges. The significantly lower SiAm concentrations in palm circles (in both well-drained and riparian areas), oil-palm rows and unvegetated interrows (only in well-drained areas) were explained by a lack of litter return to these management zones. Mean topsoil SiM concentrations were in a range of ~10 – 20 µg g-1. They tended to be higher in riparian areas, but the differences between well-drained and riparian sites were not statistically significant. Soil-loss calculations based on erosion traps confirmed that topsoil erosion was considerable in oil-palm interrows on slopes. Erosion estimates were in a range of 4 – 6 Mg ha-1 yr-1, involving SiAm losses in a range of 5 – 9 kg-1 ha-1 yr-1. Based on the observed spatial Si patterns, we concluded that smallholders could efficiently reduce erosion and support Si cycling within the system by (1) maintaining a vegetation cover in oil-palm rows and interrows, (2) incorporating oil-palm litter into farm management and (3) preventing soil compaction and surface-crust formation.

The year 2020 faced unprecedented challenge for most of the global economic growth due to the outbreak of Coronavirus disease (COVID-19). Despite a downward trend performance of the Malaysian oil palm industry, particularly for the first half of 2020, the impact is less severe due to the encouraging palm oil export revenue through the National Economic Recovery Plan (PENJANA) which nurtures a notable increase in crude palm oil (CPO) price. In honouring the Malaysian pledge on forest conservation, land expansion for the oil palm cultivation remains stagnant over the years. The effort is now shifting towards enhancing the oil palm yield performance through new planting materials and good agricultural practices, coupled with systematic pest and disease management. Sustainability continues to be the key agenda of the oil palm industry, in moving forward to sustain the industry ecosystem. The industry is now open for innovative palm oil processes to comply with the dynamic and stringent food safety and quality standards and trade regulations. Owing to the distinction in food and feed applicability together with health prospects, translating the information into consumer-friendly language is becoming crucial for effective communication. Valorisation via the concept of 'waste to wealth' has compelled series of innovations in capitalising oil palm co-products for greener bioenergy and oleochemicals, and source of phytonutrients to generate higher earnings without having to heavily rely on palm oil trade as commodity. Mandatory enactment of the Malaysian Sustainable Palm Oil (MSPO) certification scheme has portrayed a success story of showing the utmost commitment towards sustainability. With persistent dedication, the oil palm industry is envisaged to be self-sustaining, amidst the never-ending challenges surrounding economy, well-being and environment.

1. Introduction Nordin, Simeh, Shariff and Baharim (2007), proved in their studies that there is a relationship between the price of crude oil and biodiesel. The results showed that the increase in oil prices during the period of the last few years encouraged some countries to begin to pay attention to the use of alternative fuels, among others from the plant (biodiesel). The increase of petroleum will increase biodiesel production. Ramli, Abas, R. and Ayatollah (2007) in their studies proved that the crude oil price is affected by biodiesel, the first derivative product of palm oil which produces palm oil (known as crude palm oil or abbreviated with CPO), utilizing biodiesel which comes from palm oil, the results showed that the biodiesel increase has affected the crude palm oil price. The development industries based on this CPO in addition directed to produce food products such as cooking oil, margarine, shortening, Cocoa Butter subtitute (CBS), and vegetable ghee, it is also directed to produce non-food products, such as industrial oleochemical primary (fatty acid, fatty alcohol, glycerin) and other oleochemical derivatives, namely surfactants, cosmetics, farmacy, and bioenergy. Oil palm plantations and palm oil industry as a means to improve the socio-economic conditions of rural communities through the implementation of operations Inti-Plasma programs (Zen et al., 2006). When the world oil price increases, many countries use CPO as raw material of bio-diesel fuel as a substitute (Karuppuswamy, Sundararaj and Elangovan, 2007; Pociovalisteanu et al., 2010; Thalassinos and Politis, 2012; Thalassinos et al., 2012). These conditions favor the use of biodiesel as a variety of targets alternatives to fossil energy applied to several countries in the world (Kennerly and Neely, 2003). In 2020, the European Union set a target of 10 percent biofuels of raw palm oil. Zen, Barlow and Gondowarsito (2006) studied that the crude oil prices have an influence on the palm oil as pointed out by Ahuja and Khamba (2008). It has been proved that there is an influence of biodiesel on the production of palm oil. The research result on the biodiesel and its impact on crude palm oil and its implications for palm oil, showed that the growing number of biodiesel has a positive and significant effect towards crude oil palm as well as the implications for the production of palm oil rises (Ashayeri, 2007). The increase of demand and the use of palm oil as a fuel is expected to cause disruption of the availability of CPO as raw materials for food, especially palm oil (Chand and Shirvani, 2000; Enkawa and Schvaneveldt, 2001). Novelty of this research is to add the existing variables into world oil price of the biodiesel and its impact on crude palm oil and its effect on oil palm. 2. Theory and Hypothesis As Santoso (2014) has pointed out bio-diesel is a natural renewable energy source that made from biomass or vegetable oil. As the bio-diesel has physical properties very similar to petroleum derived diesel fuel or ADO (Automobile Diesel Oil), bio-diesel has been used for motor engine since 1880's. In 1920's, bio-diesel production infrastructure has been nearly eliminated since diesel engine manufacturers altered their engine to utilize petroleum diesel that was much cheaper than Bio-diesel production. Recently, an increase on oil consumption, crude oil price, and ADO import have lead to consider bio-diesel utilization for transportation sector in Indonesia. An increase of the crude oil price that lead to a decreasing cost differential for bio-diesel production, bio-diesel utilization as alternative energy source in Indonesia is a real possibility. Some environmental impact concerns would also increase the bio-diesel utilization prospect. Oil palm is a highly profitable crop adapted to the humid tropics and the area devoted to this crop is likely to expand significantly in the future. It has many environmentally favourable attributes over its full life cycle. …


 Oil palm (Elaeis guineensis) was first introduced to Sri Lanka, as a commercial crop, about 55 years ago and was first established in Galle District as a rain fed perennial cash crop. Palm Oil Mill Effluent (POME) is identified as a problematic waste while releasing directly to the water streams. Both POME and Empty Fruit Benches (EFB) consists of all these required nutrients in higher proportions for oil palm plants. This study was carried out with the duel intentions (objectives) of finding a solution to the disposal of waste material accumulated in oil palm factories over many years and to improve the productivity of marginally yielding oil palm fields in Thalgaswella estate Talgaswella. The study was designed using RCBD and there are eleven treatments. Fertilizer/mixtures were prepared based of the Nitrogen amount (0.63 kg/palm/year) supplied from the recommended inorganic fertilizer mixtures and rest of the organic fertilizer mixtures were prepared with using different proportions of POME and EFB to balance Potassium (K) & Prosperous (P). A ten-year-old oil palm field was selected in year 2019 for this experiment and maintained the field for three years before the data collection. There were 33 plots, each containing six palm trees. Organic treatments included different quantities of Empty Fruit Bunches (EFB), Palm Oil Mill Effluent (POME). Oil content of the fruits was analyzed at AEN oil palm factory using (Instrument-FOSS DA1650) in year 2023. All the data were analyzed with Minitab and mean separations were done using DMRT at α≤0.05 level. Results clearly show that the application of organic fertilizer to the oil palm cultivation gives significantly higher oil yield. These findings can help to improving the productivity of marginal oil palm cultivations, while providing a sustainable solution to the disposal of POME and EFB.
 
 Key words: Oil palm, Palm Oil Mill Effluent (POME), Empty Fruit Benches (EFB), Waste, productivity