Neural machine translation(NMT)has advanced with deep learning and large-scale multilingual models,yet translating lowresource languages often lacks sufficient training data and leads to hallucinations.This often resu...Neural machine translation(NMT)has advanced with deep learning and large-scale multilingual models,yet translating lowresource languages often lacks sufficient training data and leads to hallucinations.This often results in translated content that diverges significantly from the source text.This research proposes a refined Contrastive Decoding(CD)algorithm that dynamically adjusts weights of log probabilities from strong expert and weak amateur models to mitigate hallucinations in lowresource NMT and improve translation quality.Advanced large language NMT models,including ChatGLM and LLaMA,are fine-tuned and implemented for their superior contextual understanding and cross-lingual capabilities.The refined CD algorithm evaluates multiple candidate translations using BLEU score,semantic similarity,and Named Entity Recognition accuracy.Extensive experimental results show substantial improvements in translation quality and a significant reduction in hallucination rates.Fine-tuned models achieve higher evaluation metrics compared to baseline models and state-of-the-art models.An ablation study confirms the contributions of each methodological component and highlights the effectiveness of the refined CD algorithm and advanced models in mitigating hallucinations.Notably,the refined methodology increased the BLEU score by approximately 30%compared to baseline models.展开更多
Nuclei segmentation is a challenging task in histopathology images.It is challenging due to the small size of objects,low contrast,touching boundaries,and complex structure of nuclei.Their segmentation and counting pl...Nuclei segmentation is a challenging task in histopathology images.It is challenging due to the small size of objects,low contrast,touching boundaries,and complex structure of nuclei.Their segmentation and counting play an important role in cancer identification and its grading.In this study,WaveSeg-UNet,a lightweight model,is introduced to segment cancerous nuclei having touching boundaries.Residual blocks are used for feature extraction.Only one feature extractor block is used in each level of the encoder and decoder.Normally,images degrade quality and lose important information during down-sampling.To overcome this loss,discrete wavelet transform(DWT)alongside maxpooling is used in the down-sampling process.Inverse DWT is used to regenerate original images during up-sampling.In the bottleneck of the proposed model,atrous spatial channel pyramid pooling(ASCPP)is used to extract effective high-level features.The ASCPP is the modified pyramid pooling having atrous layers to increase the area of the receptive field.Spatial and channel-based attention are used to focus on the location and class of the identified objects.Finally,watershed transform is used as a post processing technique to identify and refine touching boundaries of nuclei.Nuclei are identified and counted to facilitate pathologists.The same domain of transfer learning is used to retrain the model for domain adaptability.Results of the proposed model are compared with state-of-the-art models,and it outperformed the existing studies.展开更多
Electricity is essential for keeping power networks balanced between supply and demand,especially since it costs a lot to store.The article talks about different deep learning methods that are used to guess how much g...Electricity is essential for keeping power networks balanced between supply and demand,especially since it costs a lot to store.The article talks about different deep learning methods that are used to guess how much green energy different Asian countries will produce.The main goal is to make reliable and accurate predictions that can help with the planning of new power plants to meet rising demand.There is a new deep learning model called the Green-electrical Production Ensemble(GP-Ensemble).It combines three types of neural networks:convolutional neural networks(CNNs),gated recurrent units(GRUs),and feedforward neural networks(FNNs).The model promises to improve prediction accuracy.The 1965–2023 dataset covers green energy generation statistics from ten Asian countries.Due to the rising energy supply-demand mismatch,the primary goal is to develop the best model for predicting future power production.The GP-Ensemble deep learning model outperforms individual models(GRU,FNN,and CNN)and alternative approaches such as fully convolutional networks(FCN)and other ensemble models in mean squared error(MSE),mean absolute error(MAE)and root mean squared error(RMSE)metrics.This study enhances our ability to predict green electricity production over time,with MSE of 0.0631,MAE of 0.1754,and RMSE of 0.2383.It may influence laws and enhance energy management.展开更多
Epilepsy is considered as a serious brain disorder in which patients frequently experience seizures.The seizures are defined as the unexpected electrical changes in brain neural activity,which leads to unconsciousness...Epilepsy is considered as a serious brain disorder in which patients frequently experience seizures.The seizures are defined as the unexpected electrical changes in brain neural activity,which leads to unconsciousness.Existing researches made an intense effort for predicting the epileptic seizures using brain signal data.However,they faced difficulty in obtaining the patients'characteristics because the model's distribution turned to fake predictions,affecting the model's reliability.In addition,the existing prediction models have severe issues,such as overfitting and false positive rates.To overcome these existing issues,we propose a deep learning approach known as Deep dual‐patch attention mechanism(D^(2)PAM)for classifying the pre‐ictal signals of people with Epilepsy based on the brain signals.Deep neural network is integrated with D^(2)PAM,and it lowers the effect of differences between patients to predict ES.The multi‐network design enhances the trained model's generalisability and stability efficiently.Also,the proposed model for processing the brain signal is designed to transform the signals into data blocks,which is appropriate for pre‐ictal classification.The earlier warning of epilepsy with the proposed model obtains the auxiliary diagnosis.The data of real patients for the experiments provides the improved accuracy by D2PAM approximation compared to the existing techniques.To be more distinctive,the authors have analysed the performance of their work with five patients,and the accuracy comes out to be 95%,97%,99%,99%,and 99%respectively.Overall,the numerical results unveil that the proposed work outperforms the existing models.展开更多
Agriculture is undoubtedly a leading field for livelihoods in China.As the population increases,it is necessary to increase agricultural productivity.By capturing the support and the increment in production on farms,t...Agriculture is undoubtedly a leading field for livelihoods in China.As the population increases,it is necessary to increase agricultural productivity.By capturing the support and the increment in production on farms,the need for freshwater used for irrigation increases too.Presently,agriculture accounts for 80% of overall water uptake in China.Unexpected overflow of water carelessly leads to waste of water.Therefore we created a programmed plant irrigation system with Arduino that mechanically supplies water to the plants and keeps it updated by transferring the message to user.Plant irrigation system employs the soil moisture sensor which controls a degree of moisture in the soil.If the humidity degree is lower,Arduino activates a pump of water to supply water to the system.The pump of water stops by design when the organism detects sufficient moisture in the ground.Each time the system is switched off or on,an electronic messaging is conveyed to the end-user through the IoT unit,informing the position of the soil moisture and the pump of water.A spray motor and the pump of water are grounded on the crane concept.Widely,this system is applicable for in small fields,gardens farms,etc.This design is entirely programmed and needed no human involvement.Furthermore,transmission of the sensor readings send through a Thing speak frequency to produce graphic elements for better inquiry.This study gathers the ideas of IoT(Internet of Things)with some engineering tools like machinery,artificial intelligence and use of sensors in an efficient way to respond current needs and extraction of resources by availing scientific methods and procedures that work on inputs.Moreover,this study further defines the engineering works that have been part of this field,but it requires more efficiency and reduction of energy as well as costs by adding more contribution of IoT in the field of agriculture engineering.展开更多
Smartphone is a very useful and compact device that fits in person’s pocket, but at the same time it can be used as a tool for criminal activities. In this day and age, people increasingly rely on smart phones rather...Smartphone is a very useful and compact device that fits in person’s pocket, but at the same time it can be used as a tool for criminal activities. In this day and age, people increasingly rely on smart phones rather than desktop computers or laptops to exchange messages, share videos and audio messages. A smartphone is almost equivalent in its application to a PC, hence there are security risks associated with its use such as carrying out a digital crime or becoming a victim of one. Criminals can use smartphones for a number of activities. Namely, committing a fraud over e-mail, harassment via text messages, drug trafficking, child pornography, communications related to narcotics, etc. It is a great challenge for forensic experts to extract data from a smartphone for forensic purposes that can be used as evidence in the court of law. In this case study, I show how to obtain the root access of Samsung S3 phone, how to create DD image and then how to examine DD image via commercial tool like UFED physical analyzer trial version which doesn’t support Android devices? I will extract the messages for Viber on trial version of UFED Physical analyzer.展开更多
Drought is a major environmental factor limiting cotton (Gossypium hirsutum L.) productivity worldwide and projected climate changes could increase their negative effects in the future. Thus, targeting the molecular m...Drought is a major environmental factor limiting cotton (Gossypium hirsutum L.) productivity worldwide and projected climate changes could increase their negative effects in the future. Thus, targeting the molecular mechanisms correlated with drought tolerance without reducing productivity is a challenge for plant breeding. In this way, we evaluated the effects of water deficit progress on AtDREB2A-CA transgenic cotton plant responses, driven by the stress-inducible rd29 promoter. Besides shoot and root morphometric traits, gas exchange and osmotic adjustment analyses were also included. Here, we present how altered root traits shown by transgenic plants impacted on physiological acclimation responses when submitted to severe water stress. The integration of AtDREB2A-CA into the cotton genome increased total root volume, surface area and total root length, without negatively affecting shoot morphometric growth parameters and nor phenotypic evaluated traits. Additionally, when compared to wild-type plants, transgenic plants (17-T0 plants and its progeny) highlighted a gradual pattern of phenotypic plasticity tosome photosynthetic parameters such as photosynthetic rate and stomatal conductance with water deficit progress. Transgene also promoted greater shoot development and root robustness (greater and deeper root mass) allowing roots to grow into deeper soil layers. The same morpho-physiological trend was observed in the subsequent generation (17.6-T2). Our results suggest that the altered root traits shown by transgenic plants are the major contributors to higher tolerance response, allowing the AtDRE2A-CA-cotton plants to maintain elevated stomatal conductance and assimilate rates and, consequently, reducing their metabolic costs involved in the antioxidant responses activation. These results also suggest that these morpho-physiological changes increased the number of reproductive structures retained per plant (26% higher) when compared with its non-transgenic counterpart. This is the first report of cotton plants overexpressing the AtDRE2A-CA transcription factor, demonstrating a morpho-physiological and yield advantages under drought stress, without displaying any yield penalty under irrigated conditions. The mechanisms by which the root traits influenced the acclimation of the transgenic plants to severe water deficit conditions are also discussed. These data present an opportunity to use this strategy in cotton breeding programs in order to improve drought adaptation toward better rooting features.展开更多
Artificial intelligence-based automatic systems can reduce time,human error and post-harvest operations.By using such systems,food items can be successfully classified and graded based on defects.For this context,a ma...Artificial intelligence-based automatic systems can reduce time,human error and post-harvest operations.By using such systems,food items can be successfully classified and graded based on defects.For this context,a machine vision system was developed for fruit grading based on defects.The prototype consisted of defective fruit detection and mechanical sorting systems.Image processing algorithms and deep learning frameworks were used for detection of defective fruit.Different image processing algorithms including preprocessing,thresholding,morphological and bitwise operations combined with a deep leaning algorithm,i.e.,convolutional neural network(CNN),were applied to fruit images for the detection of defective fruit.The data set used for training CNN model consisted of fruit images collected from a publiclyavailable data set and captured fruit images:1799 and 1017 for mangoes and tomatoes,respectively.Subsequent to defective fruit detection,the information obtained was communicated to microcontroller that further actuated the mechanical sorting system accordingly.In addition,the system was evaluated experimentally in terms of detection accuracy,sorting accuracy and computational time.For the image processing algorithms scheme,the detection accuracy for mango and tomato was 89% and 92%,respectively,and for CNN architecture used,the validation accuracy for mangoes and tomatoes was 95% and 94%,respectively.展开更多
Mechanical damage induced by vibration during harvesting and post-harvest handling could decrease the quality,quantity,and shelf life of the fresh grape cluster.Usually,fresh grape clusters are harvested by gripping a...Mechanical damage induced by vibration during harvesting and post-harvest handling could decrease the quality,quantity,and shelf life of the fresh grape cluster.Usually,fresh grape clusters are harvested by gripping and cutting from the main rachis in the present robotic harvesting system,then transported towards the basket during post-harvest handling.However,serious cluster vibration and corresponding berry falling may occur during the robotic transportation of hanging grape clusters.Therefore,this study was designed to perform experimental and theoretical hanging force analysis to explore the vibration mechanism of hanging grape clusters during robotic transportation.A lead screw lathe with an attached linear actuator was used to investigate the effects of four different speeds(0.4,0.6,0.8,1.0 m/s)with four acceleration levels(6,8,10,12 m/s2)on the vibration of the hanging grape cluster.By the experiments,the peak hanging force of the grape cluster at the start,constant speed,and stop phase of the actuator was recorded using a single axis force sensor,and the cluster’s swing angle was measured with a digital camera.The experimental results showed a linear relationship between the swing angle and hanging force of the cluster at the start and stop phase of the actuator.The multi-stage cluster’s vibration during robotic transportation was observed,and the behavior of cycled damping after a sudden stop of the actuator was found.The simulated results of hanging force of grape cluster in damping phase were agreed with experimental results with R2 more than 0.90 at an optimum acceleration of 10 m/s2.To conclude,this research provides theoretical basics for understanding the complex vibration mechanism of the hanging cluster fruits during speedy robotic transportation operations with low-loss of berry drop both on industrial and farm levels.展开更多
基金M.Faheem is supported by VTT Technical Research Center of Finland.
文摘Neural machine translation(NMT)has advanced with deep learning and large-scale multilingual models,yet translating lowresource languages often lacks sufficient training data and leads to hallucinations.This often results in translated content that diverges significantly from the source text.This research proposes a refined Contrastive Decoding(CD)algorithm that dynamically adjusts weights of log probabilities from strong expert and weak amateur models to mitigate hallucinations in lowresource NMT and improve translation quality.Advanced large language NMT models,including ChatGLM and LLaMA,are fine-tuned and implemented for their superior contextual understanding and cross-lingual capabilities.The refined CD algorithm evaluates multiple candidate translations using BLEU score,semantic similarity,and Named Entity Recognition accuracy.Extensive experimental results show substantial improvements in translation quality and a significant reduction in hallucination rates.Fine-tuned models achieve higher evaluation metrics compared to baseline models and state-of-the-art models.An ablation study confirms the contributions of each methodological component and highlights the effectiveness of the refined CD algorithm and advanced models in mitigating hallucinations.Notably,the refined methodology increased the BLEU score by approximately 30%compared to baseline models.
文摘Nuclei segmentation is a challenging task in histopathology images.It is challenging due to the small size of objects,low contrast,touching boundaries,and complex structure of nuclei.Their segmentation and counting play an important role in cancer identification and its grading.In this study,WaveSeg-UNet,a lightweight model,is introduced to segment cancerous nuclei having touching boundaries.Residual blocks are used for feature extraction.Only one feature extractor block is used in each level of the encoder and decoder.Normally,images degrade quality and lose important information during down-sampling.To overcome this loss,discrete wavelet transform(DWT)alongside maxpooling is used in the down-sampling process.Inverse DWT is used to regenerate original images during up-sampling.In the bottleneck of the proposed model,atrous spatial channel pyramid pooling(ASCPP)is used to extract effective high-level features.The ASCPP is the modified pyramid pooling having atrous layers to increase the area of the receptive field.Spatial and channel-based attention are used to focus on the location and class of the identified objects.Finally,watershed transform is used as a post processing technique to identify and refine touching boundaries of nuclei.Nuclei are identified and counted to facilitate pathologists.The same domain of transfer learning is used to retrain the model for domain adaptability.Results of the proposed model are compared with state-of-the-art models,and it outperformed the existing studies.
基金funded by the Academy of Finland and the University of Vassa,Finland.
文摘Electricity is essential for keeping power networks balanced between supply and demand,especially since it costs a lot to store.The article talks about different deep learning methods that are used to guess how much green energy different Asian countries will produce.The main goal is to make reliable and accurate predictions that can help with the planning of new power plants to meet rising demand.There is a new deep learning model called the Green-electrical Production Ensemble(GP-Ensemble).It combines three types of neural networks:convolutional neural networks(CNNs),gated recurrent units(GRUs),and feedforward neural networks(FNNs).The model promises to improve prediction accuracy.The 1965–2023 dataset covers green energy generation statistics from ten Asian countries.Due to the rising energy supply-demand mismatch,the primary goal is to develop the best model for predicting future power production.The GP-Ensemble deep learning model outperforms individual models(GRU,FNN,and CNN)and alternative approaches such as fully convolutional networks(FCN)and other ensemble models in mean squared error(MSE),mean absolute error(MAE)and root mean squared error(RMSE)metrics.This study enhances our ability to predict green electricity production over time,with MSE of 0.0631,MAE of 0.1754,and RMSE of 0.2383.It may influence laws and enhance energy management.
文摘Epilepsy is considered as a serious brain disorder in which patients frequently experience seizures.The seizures are defined as the unexpected electrical changes in brain neural activity,which leads to unconsciousness.Existing researches made an intense effort for predicting the epileptic seizures using brain signal data.However,they faced difficulty in obtaining the patients'characteristics because the model's distribution turned to fake predictions,affecting the model's reliability.In addition,the existing prediction models have severe issues,such as overfitting and false positive rates.To overcome these existing issues,we propose a deep learning approach known as Deep dual‐patch attention mechanism(D^(2)PAM)for classifying the pre‐ictal signals of people with Epilepsy based on the brain signals.Deep neural network is integrated with D^(2)PAM,and it lowers the effect of differences between patients to predict ES.The multi‐network design enhances the trained model's generalisability and stability efficiently.Also,the proposed model for processing the brain signal is designed to transform the signals into data blocks,which is appropriate for pre‐ictal classification.The earlier warning of epilepsy with the proposed model obtains the auxiliary diagnosis.The data of real patients for the experiments provides the improved accuracy by D2PAM approximation compared to the existing techniques.To be more distinctive,the authors have analysed the performance of their work with five patients,and the accuracy comes out to be 95%,97%,99%,99%,and 99%respectively.Overall,the numerical results unveil that the proposed work outperforms the existing models.
基金sponsored by the synergistic innovation center of Jiangsu modern agriculture equipment and technology(No.4091600014).
文摘Agriculture is undoubtedly a leading field for livelihoods in China.As the population increases,it is necessary to increase agricultural productivity.By capturing the support and the increment in production on farms,the need for freshwater used for irrigation increases too.Presently,agriculture accounts for 80% of overall water uptake in China.Unexpected overflow of water carelessly leads to waste of water.Therefore we created a programmed plant irrigation system with Arduino that mechanically supplies water to the plants and keeps it updated by transferring the message to user.Plant irrigation system employs the soil moisture sensor which controls a degree of moisture in the soil.If the humidity degree is lower,Arduino activates a pump of water to supply water to the system.The pump of water stops by design when the organism detects sufficient moisture in the ground.Each time the system is switched off or on,an electronic messaging is conveyed to the end-user through the IoT unit,informing the position of the soil moisture and the pump of water.A spray motor and the pump of water are grounded on the crane concept.Widely,this system is applicable for in small fields,gardens farms,etc.This design is entirely programmed and needed no human involvement.Furthermore,transmission of the sensor readings send through a Thing speak frequency to produce graphic elements for better inquiry.This study gathers the ideas of IoT(Internet of Things)with some engineering tools like machinery,artificial intelligence and use of sensors in an efficient way to respond current needs and extraction of resources by availing scientific methods and procedures that work on inputs.Moreover,this study further defines the engineering works that have been part of this field,but it requires more efficiency and reduction of energy as well as costs by adding more contribution of IoT in the field of agriculture engineering.
文摘Smartphone is a very useful and compact device that fits in person’s pocket, but at the same time it can be used as a tool for criminal activities. In this day and age, people increasingly rely on smart phones rather than desktop computers or laptops to exchange messages, share videos and audio messages. A smartphone is almost equivalent in its application to a PC, hence there are security risks associated with its use such as carrying out a digital crime or becoming a victim of one. Criminals can use smartphones for a number of activities. Namely, committing a fraud over e-mail, harassment via text messages, drug trafficking, child pornography, communications related to narcotics, etc. It is a great challenge for forensic experts to extract data from a smartphone for forensic purposes that can be used as evidence in the court of law. In this case study, I show how to obtain the root access of Samsung S3 phone, how to create DD image and then how to examine DD image via commercial tool like UFED physical analyzer trial version which doesn’t support Android devices? I will extract the messages for Viber on trial version of UFED Physical analyzer.
基金supported by grants of funds from the Brazilian government(EMBRAPA,CNPq,CAPES and FAPDF).
文摘Drought is a major environmental factor limiting cotton (Gossypium hirsutum L.) productivity worldwide and projected climate changes could increase their negative effects in the future. Thus, targeting the molecular mechanisms correlated with drought tolerance without reducing productivity is a challenge for plant breeding. In this way, we evaluated the effects of water deficit progress on AtDREB2A-CA transgenic cotton plant responses, driven by the stress-inducible rd29 promoter. Besides shoot and root morphometric traits, gas exchange and osmotic adjustment analyses were also included. Here, we present how altered root traits shown by transgenic plants impacted on physiological acclimation responses when submitted to severe water stress. The integration of AtDREB2A-CA into the cotton genome increased total root volume, surface area and total root length, without negatively affecting shoot morphometric growth parameters and nor phenotypic evaluated traits. Additionally, when compared to wild-type plants, transgenic plants (17-T0 plants and its progeny) highlighted a gradual pattern of phenotypic plasticity tosome photosynthetic parameters such as photosynthetic rate and stomatal conductance with water deficit progress. Transgene also promoted greater shoot development and root robustness (greater and deeper root mass) allowing roots to grow into deeper soil layers. The same morpho-physiological trend was observed in the subsequent generation (17.6-T2). Our results suggest that the altered root traits shown by transgenic plants are the major contributors to higher tolerance response, allowing the AtDRE2A-CA-cotton plants to maintain elevated stomatal conductance and assimilate rates and, consequently, reducing their metabolic costs involved in the antioxidant responses activation. These results also suggest that these morpho-physiological changes increased the number of reproductive structures retained per plant (26% higher) when compared with its non-transgenic counterpart. This is the first report of cotton plants overexpressing the AtDRE2A-CA transcription factor, demonstrating a morpho-physiological and yield advantages under drought stress, without displaying any yield penalty under irrigated conditions. The mechanisms by which the root traits influenced the acclimation of the transgenic plants to severe water deficit conditions are also discussed. These data present an opportunity to use this strategy in cotton breeding programs in order to improve drought adaptation toward better rooting features.
文摘Artificial intelligence-based automatic systems can reduce time,human error and post-harvest operations.By using such systems,food items can be successfully classified and graded based on defects.For this context,a machine vision system was developed for fruit grading based on defects.The prototype consisted of defective fruit detection and mechanical sorting systems.Image processing algorithms and deep learning frameworks were used for detection of defective fruit.Different image processing algorithms including preprocessing,thresholding,morphological and bitwise operations combined with a deep leaning algorithm,i.e.,convolutional neural network(CNN),were applied to fruit images for the detection of defective fruit.The data set used for training CNN model consisted of fruit images collected from a publiclyavailable data set and captured fruit images:1799 and 1017 for mangoes and tomatoes,respectively.Subsequent to defective fruit detection,the information obtained was communicated to microcontroller that further actuated the mechanical sorting system accordingly.In addition,the system was evaluated experimentally in terms of detection accuracy,sorting accuracy and computational time.For the image processing algorithms scheme,the detection accuracy for mango and tomato was 89% and 92%,respectively,and for CNN architecture used,the validation accuracy for mangoes and tomatoes was 95% and 94%,respectively.
基金The research was supported by the National Science Foundation of China(Grant No.31971795)and Priority Academic Program Development of Jiangsu Higher Education Institutions(Grant No.PAPD-2018-87)The authors are grateful to the National Science Foundation of China.The first author thanks the China Scholarship Council(2017GXZ026592)for providing 36 months scholarship for studying in China.The first author would like to thank his mother and wife Sidra for their moral support。
文摘Mechanical damage induced by vibration during harvesting and post-harvest handling could decrease the quality,quantity,and shelf life of the fresh grape cluster.Usually,fresh grape clusters are harvested by gripping and cutting from the main rachis in the present robotic harvesting system,then transported towards the basket during post-harvest handling.However,serious cluster vibration and corresponding berry falling may occur during the robotic transportation of hanging grape clusters.Therefore,this study was designed to perform experimental and theoretical hanging force analysis to explore the vibration mechanism of hanging grape clusters during robotic transportation.A lead screw lathe with an attached linear actuator was used to investigate the effects of four different speeds(0.4,0.6,0.8,1.0 m/s)with four acceleration levels(6,8,10,12 m/s2)on the vibration of the hanging grape cluster.By the experiments,the peak hanging force of the grape cluster at the start,constant speed,and stop phase of the actuator was recorded using a single axis force sensor,and the cluster’s swing angle was measured with a digital camera.The experimental results showed a linear relationship between the swing angle and hanging force of the cluster at the start and stop phase of the actuator.The multi-stage cluster’s vibration during robotic transportation was observed,and the behavior of cycled damping after a sudden stop of the actuator was found.The simulated results of hanging force of grape cluster in damping phase were agreed with experimental results with R2 more than 0.90 at an optimum acceleration of 10 m/s2.To conclude,this research provides theoretical basics for understanding the complex vibration mechanism of the hanging cluster fruits during speedy robotic transportation operations with low-loss of berry drop both on industrial and farm levels.
