Search Results (8)

In open-field agricultural environments, the inherent unpredictable situations pose significant challenges for effective human–robot interaction. This study aims to enhance natural communication between humans and robots in such challenging conditions by converting the detection of a range of dynamic human movements into specific robot actions. Various machine learning models were evaluated to classify these movements, with Long Short-Term Memory (LSTM) demonstrating the highest performance. Furthermore, the Robot Operating System (ROS) software (Melodic Version) capabilities were employed to interpret the movements into certain actions to be performed by the unmanned ground vehicle (UGV). The novel interaction framework exploiting vision-based human activity recognition was successfully tested through three scenarios taking place in an orchard, including (a) a UGV following the authorized participant; (b) GPS-based navigation to a specified site of the orchard; and (c) a combined harvesting scenario with the UGV following participants and aid by transporting crates from the harvest site to designated sites. The main challenge was the precise detection of the dynamic hand gesture “come” alongside navigating through intricate environments with complexities in background surroundings and obstacle avoidance. Overall, this study lays a foundation for future advancements in human–robot collaboration in agriculture, offering insights into how integrating dynamic human movements can enhance natural communication, trust, and safety. Full article

Realizing high-quality and increased production of fresh corn and promoting diversified development of the corn industry structure not only can effectively promote the development of agricultural economy, but also can enrich people’s dietary culture. However, existing fresh corn machinery has a high rate of ear damage during the harvesting process, and the overall harvesting efficiency is not ideal. To reduce damage during the harvesting of fresh corn, a device for breaking ears of fresh corn was designed based on the directional clamping of corn straw reverse breaking method. Based on the physico-mechanical characteristics parameters of fresh corn ears, the main structural parameters of the directional clamping and conveying mechanism and the ear-breaking mechanism were determined. The overall inclination angle of the device was 15°, and the effective conveying length of the directional clamping mechanism was 550 mm; the ear-snapping mechanism was a snapping roll composed of a pair of six radial distribution function fingers, with an effective operating radius of 320 mm. By simulating and analyzing the reverse breaking movement of directional clamping corn straw, the key motion parameter ranges of the directional clamping conveying mechanism and breaking mechanism were obtained. The results of the bench test showed that under the optimal conditions of a directional clamping feeding speed of 1.67 m/s, a breaking wheel speed of 80 rpm, and a travel speed of 1.06 m/s, the lowest ear damage rate was 0.57%, and the lowest impurity rate was 1.87%. In addition, it was observed that flexible harvesting can improve harvest efficiency and quality. The study also found that actively applying force to the device can effectively avoid the problem of machine blockage and reduce the damage rate of ears (the following text uses ears instead of fresh corn ears). Full article

Seeds can harbor a wide range of microorganisms, especially fungi, which can cause different sanitary problems. Seed quality and seed longevity may be drastically reduced by fungi that invade seeds before or after harvest. Seed movement can be a pathway for the spread of diseases into new areas. Some seed-associated fungi can also produce mycotoxins that may cause serious negative effects on humans, animals and the seeds themselves. Seed storage is the most efficient and widely used method for conserving plant genetic resources. The seed storage conditions used in gene banks, low temperature and low seed moisture content, increase seed longevity and are usually favorable for the survival of seed-borne mycoflora. Early detection and identification of seed fungi are essential activities to conserve high-quality seeds and to prevent pathogen dissemination. This article provides an overview of the characteristics and detection methods of seed-borne fungi, with a special focus on their potential effects on gene bank seed conservation. The review includes the following aspects: types of seed-borne fungi, paths of infection and transmission, seed health methods, fungi longevity, risk of pathogen dissemination, the effect of fungi on seed longevity and procedures to reduce the harmful effects of fungi in gene banks. Full article

Making the Internet of Things “green” has become a major research focus in recent years. The anticipated massive increase in the numbers of sensor and communication devices makes this endeavor even more important, resulting in various solution approaches ranging from energy harvesting to energy efficient routing schemes. In this work, we propose a system that can perform some of the main tasks of the Internet of Things, namely identification and sensing of an indoor moving object, by the means of visible light sensing in combination with off-the-shelf retroreflective foils, without the necessity to place any actively powered components on the object itself. By utilizing the supervised machine learning approach of random forest, we show that these two tasks can be fulfilled with up to 99.96% accuracy. Based on our previous findings in this regard, we propose some advancements and improvements of the overall system, yielding better results in parallel with an increased complexity of the system. Furthermore, we expand the number of performable tasks toward additional movement direction determination. The achieved results demonstrate the applicability of visible light sensing and its potentials for a “green” Internet of Things. Full article

The occurrence of musculoskeletal diseases (MSDs) among oil palm harvesters has been studied extensively, but there is a lack of published studies on the evaluation of the range of harvesting movements. This information is important to design the ergonomic tools needed in the manual harvesting of oil palm. We examined the upper limb motion of oil palm harvesters to determine the effects of age and initial shoulder postures on their range of harvesting movements. Twenty male harvesters performed a manual push-pull-cutting technique (≥3 m fresh fruit branches (FFBs) height). The study was conducted by capturing the 1-D push-pull cutting technique harvesting movement via the Quintic system at the sagittal plane. The active range of harvesting movements during the harvesting phases and the range of the harvesting movement of the initial and maximum postures of their upper arms were calculated based on the kinematic data generated with the Quintic Biomechanics system (Version 29). Participants were divided into three groups based on their age, and two groups based on their initial support shoulder position, and dominant shoulder position. Data were analysed using the ANOVA and t-test. The joint movement angle pattern of the harvesters was classified into three phases: preparation, execution, and ending. The age-related variances for the initial and maximum support shoulder postures were determined. The range of harvesting movements and the active range of harvesting movements during the preparation phase at the support shoulder and wrist region were also observed. The initial support shoulder posture displayed a statistical variance in the maximum support and dominant range of harvesting movements of the shoulder. It was also linked to a reduced active range of harvesting movements for the support shoulder flexion and dominant wrist ulnar deviation at the preparation phase. Furthermore, the initial dominant shoulder exhibited a statistically significant difference for the dominant arm and a reduced active range of harvesting movements in the dominant wrist ulnar deviation at the preparation phase. This study produced important evidence about factors to be considered for the ergonomic design of harvesting tools and workplaces, especially within the oil palm industry. Full article

During daily activities, such as chewing, eating, speaking, and so forth, the human jaw moves, and the earcanal is deformed by its anatomic neighbor called the temporomandibular joint (TMJ). Given the frequency of those jaw joint activities, the earcanal dynamic movement is a promising source of energy in close proximity to the ear, and such energy can be harvested by using a mechanical–electrical transducer dubbed energy harvester. However, the optimal design of such micromachine requires the characterization of the TMJ’s range of motion, its mechanical action on the earcanal, and its mechanical power capability. For that purpose, this research presents two methods for analyzing the earcanal dynamic movements: first, an in situ approach based on the measurement of the pressure variation in a water-filled earplug fitted inside the ear canal, and second, an anatomic-driven mechanism in the form of a chewing test fixture capable of reproducing the TMJ kinematics with great precision. The pressure earplug system provides the earcanal global dynamics, which can be derived as an equivalent displaced volume, while the chewing test fixture provides the discrete displacement along the earcanal wall. Both approaches are complementary and contribute to a better analysis of the interaction between the TMJ and earcanal. Ultimately, knowledge of the maximum displacement area and the derived generated power within the earcanal will lead to the design of a micromachine, allowing for the further investigation of in-ear energy harvesting strategies. Full article

The killer phenomenon is defined as the ability of some yeast to secrete toxins that are lethal to other sensitive yeasts and filamentous fungi. Since the discovery of strains of Saccharomyces cerevisiae capable of secreting killer toxins, much information has been gained regarding killer toxins and this fact has substantially contributed knowledge on fundamental aspects of cell biology and yeast genetics. The killer phenomenon has been studied in Pichia membranifaciens for several years, during which two toxins have been described. PMKT and PMKT2 are proteins of low molecular mass that bind to primary receptors located in the cell wall structure of sensitive yeast cells, linear (1→6)-β-d-glucans and mannoproteins for PMKT and PMKT2, respectively. Cwp2p also acts as a secondary receptor for PMKT. Killing of sensitive cells by PMKT is characterized by ionic movements across plasma membrane and an acidification of the intracellular pH triggering an activation of the High Osmolarity Glycerol (HOG) pathway. On the contrary, our investigations showed a mechanism of killing in which cells are arrested at an early S-phase by high concentrations of PMKT2. However, we concluded that induced mortality at low PMKT2 doses and also PMKT is indeed of an apoptotic nature. Killer yeasts and their toxins have found potential applications in several fields: in food and beverage production, as biocontrol agents, in yeast bio-typing, and as novel antimycotic agents. Accordingly, several applications have been found for P. membranifaciens killer toxins, ranging from pre- and post-harvest biocontrol of plant pathogens to applications during wine fermentation and ageing (inhibition of Botrytis cinerea, Brettanomyces bruxellensis, etc.). Full article

Pedestrian movement is woven into the fabric of urban regions. With more people living in cities than ever before, there is an increased need to understand and model how pedestrians utilize and move through space for a variety of applications, ranging from urban planning and architecture to security. Pedestrian modeling has been traditionally faced with the challenge of collecting data to calibrate and validate such models of pedestrian movement. With the increased availability of mobility datasets from video surveillance and enhanced geolocation capabilities in consumer mobile devices we are now presented with the opportunity to change the way we build pedestrian models. Within this paper we explore the potential that such information offers for the improvement of agent-based pedestrian models. We introduce a Scene- and Activity-Aware Agent-Based Model (SA²-ABM), a method for harvesting scene activity information in the form of spatiotemporal trajectories, and incorporate this information into our models. In order to assess and evaluate the improvement offered by such information, we carry out a range of experiments using real-world datasets. We demonstrate that the use of real scene information allows us to better inform our model and enhance its predictive capabilities. Full article