Does kinship with the silverback matter? Intragroup social relationships of immature wild western lowland gorillas after social upheaval.

In primates living in one-male groups, the sole resident male is often an important social partner for group immatures. For such groups, however, replacement of the male and subsequent disruptions of their relationships are almost inevitable. Here, we described social relationships of immature wild western lowland gorillas within a habituated group, where two natal and eight immigrant immatures lived with the resident silverback. We recorded 5 m proximities among group members as an indicator of social closeness. We found that natal immatures spent more time within 5 m of the silverback than immigrant ones. The social closeness between the silverback and the younger immigrant immatures sharply increased after 1 year, but these values were still below those of the natal immatures. Regarding the development of independence from the mother, we found no significant difference between natal and immigrant immatures. The socially preferred nonmother mature for natal immatures was the silverback, whereas many immigrant immatures preferred a paternal adult sister who had previously co-resided with them in a previous group. Our results suggest that familiarity may be an important determinant of the social closeness between the silverback and immatures, but 1 year of co-residence might be too short to construct sufficient familiarity. The paternal sister may have played a pivotal role in the assimilation of immigrant immatures into the non-natal group. Nonetheless, it is not negligible that the silverback and immigrant immatures formed day-to-day close proximities. His tolerance toward co-residence with immigrant immatures can be considered a reproductive tactic.

Enhanced power grid performance through Gorilla Troops Algorithm-guided thyristor controlled series capacitors allocation.

This article introduces an innovative application of the Enhanced Gorilla Troops Algorithm (EGTA) in addressing engineering challenges related to the allocation of Thyristor Controlled Series Capacitors (TCSC) in power grids. Drawing inspiration from gorilla group behaviors, EGTA incorporates various methods, such as relocation to new areas, movement towards other gorillas, migration to specific locations, following the silverback, and engaging in competitive interactions for adult females. Enhancements to EGTA involve support for the exploitation and the exploration, respectively, through two additional strategies of periodic Tangent Flight Operator (TFO), and Fitness-based Crossover Strategy (FCS). The paper initially evaluates the effectiveness of EGTA by comparing it to the original GTA using numerical CEC 2017 single-objective benchmarks. Additionally, various recent optimizers are scrutinized. Subsequently, the suitability of the proposed EGTA for the allocation of TCSC apparatuses in transmission power systems is assessed through simulations on two IEEE power grids of 30 and 57 buses, employing various TCSC apparatus quantities. A comprehensive comparison is conducted between EGTA, GTA, and several other prevalent techniques in the literature for all applications. According to the average attained losses, the presented EGTA displays notable reductions in power losses for both the first and second systems when compared to the original GTA. Specifically, for the first system, the proposed EGTA achieves reductions of 1.659 %, 2.545 %, and 4.6 % when optimizing one, two, and three TCSC apparatuses, respectively. Similarly, in the second system, the suggested EGTA achieves reductions of 6.096 %, 7.107 %, and 4.62 %, respectively, when compared to the original GTA's findings considering one, two, and three TCSC apparatuses. The findings underscore the superior effectiveness and efficiency of the proposed EGTA over both the original GTA and several other contemporary systems.

Origin of the human malaria parasite Plasmodium vivax.

The geographic origin of Plasmodium vivax, a leading cause of human malaria, has been the subject of much speculation. Here we review the evolutionary history of P. vivax and P. vivax-like parasites in humans and non-human primates on three continents, providing overwhelming evidence for an African origin. This conclusion is consistent with recent reports showing that Duffy-negative humans in Africa are, in fact, susceptible to P. vivax, with parasites invading Duffy-antigen-expressing erythroid precursors. Thus, the African origin of P. vivax not only explains the distribution of the Duffy-negative genotype but also provides new insight into the history and status of P. vivax malaria in Africa and efforts geared toward its eradication.

Death of a one-armed blackback male due to severe injuries in a group of wild western lowland gorillas (Gorilla gorilla gorilla) in Moukalaba-Doudou National Park, Gabon.

The survival of limb-disabled primates in the wild has been widely reported. Nevertheless, their ultimate fate is little documented. It is important to understand the influence of limb disability on primate survival from a conservation perspective, as many African great apes suffer from limb injuries caused by entrapment in snares. Here, we report the death of a one-armed blackback male in a large one-male group of wild western lowland gorillas. The subject was a blackback male (14 years old) named Dodo, who lost his right forearm in August 2008. On 8 December 2019, Dodo was found to have suffered serious bleeding injuries to the front of his body, including large lacerations and puncture wounds. On 14 December his corpse was found in the forest. We provide evidence to suggest that his injuries were more likely caused by intraspecific aggression, though a predatory attack by a leopard could not be completely ruled out. His one-armed disability could have made him more vulnerable to attack from either a gorilla or leopard and led to his fatal injury. This report shows that a gorilla who had previously overcome a disability in one arm in childhood may die prematurely, in part, owing to this disability in young adulthood.

Enhanced gorilla troops optimizer powered by marine predator algorithm: global optimization and engineering design.

This study presents an advanced metaheuristic approach termed the Enhanced Gorilla Troops Optimizer (EGTO), which builds upon the Marine Predators Algorithm (MPA) to enhance the search capabilities of the Gorilla Troops Optimizer (GTO). Like numerous other metaheuristic algorithms, the GTO encounters difficulties in preserving convergence accuracy and stability, notably when tackling intricate and adaptable optimization problems, especially when compared to more advanced optimization techniques. Addressing these challenges and aiming for improved performance, this paper proposes the EGTO, integrating high and low-velocity ratios inspired by the MPA. The EGTO technique effectively balances exploration and exploitation phases, achieving impressive results by utilizing fewer parameters and operations. Evaluation on a diverse array of benchmark functions, comprising 23 established functions and ten complex ones from the CEC2019 benchmark, highlights its performance. Comparative analysis against established optimization techniques reveals EGTO's superiority, consistently outperforming its counterparts such as tuna swarm optimization, grey wolf optimizer, gradient based optimizer, artificial rabbits optimization algorithm, pelican optimization algorithm, Runge Kutta optimization algorithm (RUN), and original GTO algorithms across various test functions. Furthermore, EGTO's efficacy extends to addressing seven challenging engineering design problems, encompassing three-bar truss design, compression spring design, pressure vessel design, cantilever beam design, welded beam design, speed reducer design, and gear train design. The results showcase EGTO's robust convergence rate, its adeptness in locating local/global optima, and its supremacy over alternative methodologies explored.

Ape recognition of familiar human faces changed by time and COVID-19 face masks.

Reports of primates being able to recognise familiar humans are rare in the literature and tend to be regarded as anecdotal. The COVID-19 pandemic created two unique conditions facilitating the observation of spontaneous face recognition in zoo apes: i) lengthy gaps in contact with human visitors due to lockdowns and zoo closures, and ii) the wearing of face masks obscuring at least half the face of familiar individuals. Here, I report on the historical context of the familiarity between a primatologist and individual apes of two species, how those apes consistently showed recognition of this particular human over a time span of up to thirty years, how facial recognition was extended to family members, and how recognition persisted even when a significant portion of the face was obscured by a mask. This constitutes, to my knowledge, the first documented cases of recognition of familiar human faces changed by time and COVID-19 face masks in two great ape species. Although based on just two individuals, the documentation of this ability is important because it arose in a more naturalistic and spontaneous context compared to typical face processing research in which primates are tested with experimental stimuli in a laboratory setting. Implications for face processing theory and applications for the therapeutic utility of faces are discussed. These observations provide insight into the evolutionary origins of face recognition and, sitting at the interface of science and society, are of interest to a wide audience.

Changes in movement patterns in relation to sun conditions and spatial scales in wild western gorillas.

For most primates living in tropical forests, food resources occur in patchworks of different habitats that vary seasonally in quality and quantity. Efficient navigation (i.e., spatial memory-based orientation) towards profitable food patches should enhance their foraging success. The mechanisms underpinning primate navigating ability remain nonetheless mostly unknown. Using GPS long-term tracking (596 days) of one group of wild western lowland gorillas (Gorilla gorilla gorilla), we investigated their ability to navigate at long distances, and tested for how the sun was used to navigate at any scale by improving landmark visibility and/or by acting as a compass. Long episodic movements ending at a distant swamp, a unique place in the home range where gorillas could find mineral-rich aquatic plants, were straighter and faster than their everyday foraging movements relying on spatial memory. This suggests intentional targeting of the swamp based on long-distance navigation skills, which can thus be efficient over a couple of kilometres. Interestingly, for both long-distance movements towards the swamp and everyday foraging movements, gorillas moved straighter under sunlight conditions even under a dense vegetation cover. By contrast, movement straightness was not markedly different when the sun elevation was low (the sun azimuth then being potentially usable as a compass) or high (so providing no directional information) and the sky was clear or overcast. This suggests that gorillas navigate their home range by relying on visual place recognition but do not use the sun azimuth as a compass. Like humans, who rely heavily on vision to navigate, gorillas should benefit from better lighting to help them identify landmarks as they move through shady forests. This study uncovers a neglected aspect of primate navigation. Spatial memory and vision might have played an important role in the evolutionary success of diurnal primate lineages.

Three-dimensional unmanned aerial vehicle path planning utilizing artificial gorilla troops optimizer incorporating combined mutation and quadratic interpolation operators.

In real terrain and dynamic obstacle scenarios, the complexity of the 3D UAV path planning problem greatly increases. Thus, to procure the optimal flight path for UAVs in such scenarios, an augmented Artificial Gorilla Troops Optimizer, denoted as OQMGTO, is proposed. The proposed OQMGTO algorithm introduces three strategies: combination mutation, quadratic interpolation, and random opposition-based learning, aiming to enhance the ability to timely escape from local optimal path areas and rapidly converge to the global optimal path. Given the flight distance, smoothness, terrain collision, and other five realistic factors of UAVs, specific constraint conditions are proposed to address complex scenarios, aiming to construct a path planning model. By optimizing this model, OQMGTO algorithm solves the path planning problem in complex scenarios. The extensive validation of OQMGTO algorithm on CEC2017 test suite enhances its credibility as a powerful optimization tool. Comparison experiments are conducted in simulated terrain scenarios, including six multi-obstacle terrain scenarios and three dynamic obstacle scenarios. The experimental findings validate OOMGTO algorithm can assist UAV in searching for excellent flight paths, featuring high safety and reliability characteristics, which confirms the superiority of OOMGTO algorithm for path planning in simulated terrain scenarios. Furthermore, in four flight missions carried out in real terrains, OQMGTO algorithm demonstrates superior search performance, planning smooth trajectories without mountain collision.

Prosocial or photo preferences? Gorillas' prosocial choices using a touchscreen.

Three male Western lowland gorillas (Gorilla gorilla gorilla) were given the opportunity to select their own or conspecific photos on a touchscreen to indicate whether they wished the experimenter to deliver a food reward only to them or to them and the selected conspecific(s). This is only the second symbolic test of prosocial preferences with apes using a touchscreen, and the first with gorillas. The use of self and other photographs as symbols of prosocial choices was intuitive while controlling for the distraction of visible food rewards, and allowing for tests of transfer to further validate apparent prosocial intentions. Gorillas rapidly learned to avoid selecting a photograph of an empty enclosure that resulted in no rewards for any of the gorillas and transferred this learning to a novel photograph. The gorillas did not behave in a consistently self-interested or prosocial manner but they clearly rejected the opportunity to choose spitefully. Their preferences for certain photographs did not necessarily reflect a preference to be prosocial toward that particular individual because these preferences did not transfer to novel photographs of the same individuals. The results call into question whether gorillas recognize themselves and conspecifics in photographs but cannot conclusively speak to whether gorillas have prosocial preferences. They do stress the importance of carefully probing alternative explanations when inferring intentions from observable behaviors.

Dynamically stabilized recurrent neural network optimized with Artificial Gorilla Troops espoused Alzheimer's disorder detection using EEG signals.

Alzheimer's disease is an incurable neurological disorder that damages cognitive abilities, but early identification reduces the symptoms significantly. The absence of competent healthcare professionals has made automatic identification of Alzheimer's disease more crucial since it lessens the amount of work for staff members and improves diagnostic outcomes. The major aim of this work is "to develop a computer diagnostic scheme that makes it possible to identify AD using the Electroencephalogram (EEG) signal". Therefore, Dynamically Stabilized Recurrent Neural Network Optimized with Artificial Gorilla Troops espoused Alzheimer's Disorder Detection using EEG signals (DSRNN-AGTO-ADD) is proposed in this paper. Here, Dynamic Context-Sensitive Filter (DCSF) is considered to eliminate the noise, and interference from the EEG signal. Then Adaptive and Concise Empirical Wavelet Transform (ACEWT) is utilized to separate the filtered signals from the frequency bands, and to feature extraction from the EEG signals. Signal's characteristics, like logarithmic bandwidth power, standard deviation, variance, kurtosis, mean energy, mean square, norm are combined to ACEWT method to create feature vectors and enhance diagnostic performance. After that, the extracted features are fed to Dynamically Stabilized Recurrent Neural Network (DSRNN) for task classification. Weight parameter of DSRNN is enhanced using Artificial Gorilla Troops Optimization Algorithm (AGTOA). The proposed DSRNN-AGTOA-ADD algorithm is activated in MATLAB. The metrics including accuracy, specificity, sensitivity, precision, computation time, ROC are examined for AD diagnosis. The performance of the proposed DSRNN-AGTOA-ADD approach attains 12.98%, 5.98% and 23.45% high specificity; 29.98%, 23.32% and 19.76% lower computation Time and 29.29%, 8.365%, 8.551% and 7.915% higher ROC compared with the existing methods.

Positive clinical experience with paromomycin sulfate in treatment of Balantioides coli (=Balantidium coli) natural infection in zoo-kept Mandrill monkeys (Mandrillus sphinx) and Western lowland gorillas (Gorilla gorilla gorilla).

Balantioides coli (=Balantidium coli), a large ciliated protozoan, is reported in multiple free-ranging and captive primate species, often in association with a clinical presentation that requires medical intervention. This report describes the clinical effectiveness of paromomycin sulfate against B.coli in zoo-kept mandrill monkeys (Mandrillus sphinx, at orally doses of 8-31 mg/kg, once daily (SID) for 7 days) and gorillas (Gorilla gorilla gorilla, at orally doses of 1.4-3.1 mg/kg, SID for 5 days).

Gorilla optimization algorithm combining sine cosine and cauchy variations and its engineering applications.

To address the issues of lacking ability, loss of population diversity, and tendency to fall into the local extreme value in the later stage of optimization searching, resulting in slow convergence and lack of exploration ability of the artificial gorilla troops optimizer algorithm (AGTO), this paper proposes a gorilla search algorithm that integrates the positive cosine and Cauchy's variance (SCAGTO). Firstly, the population is initialized using the refractive reverse learning mechanism to increase species diversity. A positive cosine strategy and nonlinearly decreasing search and weight factors are introduced into the finder position update to coordinate the global and local optimization ability of the algorithm. The follower position is updated by introducing Cauchy variation to perturb the optimal solution, thereby improving the algorithm's ability to obtain the global optimal solution. The SCAGTO algorithm is evaluated using 30 classical test functions of Test Functions 2018 in terms of convergence speed, convergence accuracy, average absolute error, and other indexes, and two engineering design optimization problems, namely, the pressure vessel optimization design problem and the welded beam design problem, are introduced for verification. The experimental results demonstrate that the improved gorilla search algorithm significantly enhances convergence speed and optimization accuracy, and exhibits good robustness. The SCAGTO algorithm demonstrates certain solution advantages in optimizing the pressure vessel design problem and welded beam design problem, verifying the superior optimization ability and engineering practicality of the SCAGTO algorithm.

Ghosts of extinct apes: genomic insights into African hominid evolution.

We are accustomed to regular announcements of new hominin fossils. There are now some 6000 hominin fossils, and up to 31 species. However, where are the announcements of African ape fossils? The answer is that there are almost none. Our knowledge of African ape evolution is based entirely on genomic analyses, which show that extant diversity is very young. This contrasts with the extensive and deep diversity of hominins known from fossils. Does this difference point to low and late diversification of ape lineages, or high rates of extinction? The comparative evolutionary dynamics of African hominids are central to interpreting living ape adaptations, as well as understanding the patterns of hominin evolution and the nature of the last common ancestor.

Trabecular architecture of the distal femur in extant hominids.

Extant great apes are characterized by a wide range of locomotor, postural and manipulative behaviours that each require the limbs to be used in different ways. In addition to external bone morphology, comparative investigation of trabecular bone, which (re-)models to reflect loads incurred during life, can provide novel insights into bone functional adaptation. Here, we use canonical holistic morphometric analysis (cHMA) to analyse the trabecular morphology in the distal femoral epiphysis of Homo sapiens (n = 26), Gorilla gorilla (n = 14), Pan troglodytes (n = 15) and Pongo sp. (n = 9). We test two predictions: (1) that differing locomotor behaviours will be reflected in differing trabecular architecture of the distal femur across Homo, Pan, Gorilla and Pongo; (2) that trabecular architecture will significantly differ between male and female Gorilla due to their different levels of arboreality but not between male and female Pan or Homo based on previous studies of locomotor behaviours. Results indicate that trabecular architecture differs among extant great apes based on their locomotor repertoires. The relative bone volume and degree of anisotropy patterns found reflect habitual use of extended knee postures during bipedalism in Homo, and habitual use of flexed knee posture during terrestrial and arboreal locomotion in Pan and Gorilla. Trabecular architecture in Pongo is consistent with a highly mobile knee joint that may vary in posture from extension to full flexion. Within Gorilla, trabecular architecture suggests a different loading of knee in extension/flexion between females and males, but no sex differences were found in Pan or Homo, supporting our predictions. Inter- and intra-specific variation in trabecular architecture of distal femur provides a comparative context to interpret knee postures and, in turn, locomotor behaviours in fossil hominins.

Maximizing solar radiations of PV panels using artificial gorilla troops reinforced by experimental investigations.

This article's main objective is to maximize solar radiations (SRs) through the use of the gorilla troop algorithm (GTA) for identifying the optimal tilt angle (OTA) for photovoltaic (PV) panels. This is done in conjunction with an experimental work that consists of three 100 W PV panels tilted at three different tilt angles (TAs). The 28°, 30°, and 50° are the three TAs. The experimental data are collected every day for 181-day and revealed that the TA of 28° is superior to those of 50° and 30°. The GTA calculated the OTA to be 28.445°, which agrees with the experimental results, which show a TA of 28°. The SR of the 28o TA is 59.3% greater than that of the 50° TA and 4.5% higher than that of the 30° TA. Recent methods are used to compare the GTA with the other nine metaheuristics (MHTs)-the genetic algorithm, particle swarm, harmony search, ant colony, cuckoo search, bee colony, fire fly, grey wolf, and coronavirus disease optimizers-in order to figure out the optimal OTA. The OTA is calculated by the majority of the nine MHTs to be 28.445°, which is the same as the GTA and confirms the experimental effort. In only 181-day, the by experimentation it may be documented SR difference between the TAs of 28° and 50° TA is 159.3%. Numerous performance metrics are used to demonstrate the GTA's viability, and it is contrasted with other recent optimizers that are in competition.

Anoplocephalid tapeworms in mountain gorillas (Gorilla beringei beringei) inhabiting the Volcanoes National Park, Rwanda.

Cestodes of the family Anoplocephalidae parasitize a wide range of usually herbivorous hosts including e.g. rodents, ungulates, primates, elephants and hyraxes. While in some hosts, the epidemiology of the infection is well studied, information is lacking in others. In this study of mountain gorillas in the Virunga Massif, an extensive sample set comprising adult cestodes collected via necropsies, proglottids shed in feces, and finally, fecal samples from both night nests and identified individuals were analysed. Anoplocephala gorillae was the dominant cestode species detected in night nest samples and individually known gorillas, of which only 1 individual hosted a Bertiella sp. It was shown that the 2 species can be distinguished through microscopy based on egg morphology and polymerase chain reaction (PCR) assays for diagnostics of both species were provided. Sequences of mitochondrial (cox 1) and nuclear (ITS1, 18S rDNA, 28S rDNA) markers were used to evaluate the phylogenetic position of the 2 cestodes detected in mountain gorillas. Both types of fecal samples, from night nests and from identified individuals, provided comparable information about the prevalence of anoplocephalid cestodes, although the analysis of samples collected from identified gorilla individuals showed significant intra-individual fluctuation of A. gorillae egg shedding within a short period. Therefore, multiple samples should be examined to obtain reliable data for wildlife health management programmes, especially when application of anthelmintic treatment is considered. However, while A. gorillae is apparently a common symbiont of mountain gorillas, it does not seem to impair the health of its host.

Socioecological factors influencing intraspecific variation in ranging dynamics of western lowland gorillas (Gorilla gorilla gorilla) in Ndoki Forest.

Ranging dynamics are physical and behavioral representations of how different socioecological factors affect an organism's spatial decisions and space use strategies. Western lowland gorillas (Gorilla gorilla gorilla) are a model species to investigate the drivers of spatial dynamics based on both the natural variation in socioecological factors within the species and compared with their mountain gorilla counterparts. In this study, we evaluate the influences of resource seasonality and social dynamics on variation in home range size, utilization, and intergroup overlap among multiple gorilla groups over an 8-year study period in the northern Republic of Congo. This study shows that western lowland gorillas can have small home ranges comparable to mountain gorillas, rather than universally larger home ranges as previously supposed, and that home ranges are stable through time. The largest source of variation in space use was the degree of intergroup home range overlap. The study groups did not demonstrate intraspecific variation in range size nor changes in intergroup overlap with respect to seasonality of fruit resources, but all groups demonstrated expansion of monthly range and core area with group size, matching predictions of intragroup feeding competition. These findings highlight the potential impact of intergroup relationships on space use and prompt further research on the role of social dynamics in ranging strategies. In this study, we reveal a greater degree of variability and flexibility in gorilla ranging behavior than previously realized which is relevant to improving comparative studies and informing conservation strategies on behalf of these endangered primates.

Efficient Computation of Spatial Entropy Measures.

Entropy indices are commonly used to evaluate the heterogeneity of spatially arranged data by exploiting various approaches capable of including spatial information. Unfortunately, in practical studies, difficulties can arise regarding both the availability of computational tools for fast and easy implementation of these indices and guidelines supporting the correct interpretation of the results. The present work addresses such issues for the most known spatial entropy measures: the approach based on area partitions, the one based on distances between observations, and the decomposable spatial entropy. The newly released version of the R package SpatEntropy is introduced here and we show how it properly supports researchers in real case studies. This work also answers practical questions about the spatial distribution of nesting sites of an endangered species of gorillas in Cameroon. Such data present computational challenges, as they are marked points in continuous space over an irregularly shaped region, and covariates are available. Several aspects of the spatial heterogeneity of the nesting sites are addressed, using both the original point data and a discretised pixel dataset. We show how the diversity of the nesting habits is related to the environmental covariates, while seemingly not affected by the interpoint distances. The issue of scale dependence of the spatial measures is also discussed over these data. A motivating example shows the power of the SpatEntropy package, which allows for the derivation of results in seconds or minutes with minimum effort by users with basic programming abilities, confirming that spatial entropy indices are proper measures of diversity.

A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma.

One of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient's histopathology images to identify abnormal oral lesions. A deep learning framework was designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely, normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed swarm intelligence technique called the Modified Gorilla Troops Optimizer. While there are many optimization algorithms used in the literature for feature selection, weight updating, and optimal parameter identification in deep learning models, this work focuses on using optimization algorithms as an intermediate layer to convert extracted features into features that are better suited for classification. Three datasets comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures, namely, InceptionV2, MobileNetV3, and EfficientNetB3, are investigated as feature extraction layers. Two fully connected Neural Network layers, batch normalization, and dropout are used as classification layers. With the best accuracy of 0.89 among the examined feature extraction models, MobileNetV3 exhibits good performance. This accuracy is increased to 0.95 when the suggested Modified Gorilla Troops Optimizer is used as an intermediary layer.

ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework.

Autism Spectrum Disorder (ASD) treatment requires accurate diagnosis and effective rehabilitation. Artificial intelligence (AI) techniques in medical diagnosis and rehabilitation can aid doctors in detecting a wide range of diseases more effectively. Nevertheless, due to its highly heterogeneous symptoms and complicated nature, ASD diagnostics continues to be a challenge for researchers. This study introduces an intelligent system based on the Artificial Gorilla Troops Optimizer (GTO) metaheuristic optimizer to detect ASD using Deep Learning and Machine Learning. Kaggle and UCI ML Repository are the data sources used in this study. The first dataset is the Autistic Children Data Set, which contains 3,374 facial images of children divided into Autistic and Non-Autistic categories. The second dataset is a compilation of data from three numerical repositories: (1) Autism Screening Adults, (2) Autistic Spectrum Disorder Screening Data for Adolescents, and (3) Autistic Spectrum Disorder Screening Data for Children. When it comes to image dataset experiments, the most notable results are (1) a TF learning ratio greater than or equal to 50 is recommended, (2) all models recommend data augmentation, and (3) the DenseNet169 model reports the lowest loss value of 0.512. Concerning the numeric dataset, five experiments recommend standardization and the final five attributes are optional in the classification process. The performance metrics demonstrate the worthiness of the proposed feature selection technique using GTO more than counterparts in the literature review.