Internet of things(IoT)is used in various fields such as smart cities,smart home,manufacturing industries,and healthcare.Its application in healthcare has many advantages and disadvantages.One of its most common proto...Internet of things(IoT)is used in various fields such as smart cities,smart home,manufacturing industries,and healthcare.Its application in healthcare has many advantages and disadvantages.One of its most common protocols is Message Queue Telemetry Transport(MQTT).MQTT protocol works as a publisher/subscriber which is suitable for IoT devices with limited power.One of the drawbacks of MQTT is that it is easy to manipulate.The default security provided by MQTT during user authentication,through username and password,does not provide any type of data encryption,to ensure confidentiality or integrity.This paper focuses on the security of IoT healthcare over the MQTT protocol,through the implementation of lightweight generating and key exchange algorithms.The research contribution of this paper is twofold.The first one is to implement a lightweight generating and key exchange algorithm for MQTT protocol,with the key length of 64 bits through OMNET++simulation.The second one is to obtain lower power consumption from some existing algorithms.Moreover,the power consumption through using the proposed algorithm is 0.78%,1.16%,and 1.93% of power for 256 bits,512 bits,and 1024 respectively.On the other hand,the power consumption without using the encryption is 0.25%,0.51%,and 1.03% for the same three payloads length.展开更多
This paper proposes SW-YOLO(StarNet Weighted-Conv YOLO),a lightweight human pose estimation network for edge devices.Current mainstream pose estimation algorithms are computationally inefficient and have poor feature ...This paper proposes SW-YOLO(StarNet Weighted-Conv YOLO),a lightweight human pose estimation network for edge devices.Current mainstream pose estimation algorithms are computationally inefficient and have poor feature capture capabilities for complex poses and occlusion scenarios.This work introduces a lightweight backbone architecture that integrates WConv(Weighted Convolution)and StarNet modules to address these issues.Leveraging StarNet’s superior capabilities in multi-level feature fusion and long-range dependency modeling,this architecture enhances the model’s spatial perception of human joint structures and contextual information integration.These improvements significantly enhance robustness in complex scenarios involving occlusion and deformation.Additionally,the introduction of WConv convolution operations,based on weight recalibration and receptive field optimization,dynamically adjusts feature importance during convolution.This reduces redundant computations while maintaining or enhancing feature representation capabilities at an extremely low computational cost.Consequently,SW-YOLO substantially reduces model complexity and inference latency while preserving high accuracy,significantly outperforming existing lightweight networks.展开更多
人工智能技术在教育领域的深度应用,已成为国家教育数字化转型的核心战略。在计算机实践教学领域,实践学习资料的精准推荐是提升学生学习效能与质量的重要途径。针对高校教育规模化与学生需求多元化之间的矛盾,提出一种基于轻量级教育...人工智能技术在教育领域的深度应用,已成为国家教育数字化转型的核心战略。在计算机实践教学领域,实践学习资料的精准推荐是提升学生学习效能与质量的重要途径。针对高校教育规模化与学生需求多元化之间的矛盾,提出一种基于轻量级教育大模型的个性化实践学习资料推荐模型LightPLRec(Lightweight Personalized Learning Recommender for Dynamic Practice Materials),旨在依据学生个体特征的动态变化智能推荐个性化的实践学习资料。基于低算力需求的轻量级大模型,通过指令微调和强化学习方法构建了面向个性化实践学习资料推荐的教育大模型SPIR(Student Profile&Interest-based Re-commender)。通过整合多源异构数据,深度融入课程知识体系、学科前沿动态、产业发展趋势、国家战略导向,构建了跨学科、多模态的实践学习资料库,并设计了图转主题文本方法gragh2topic。依托于SPIR大模型的强大赋能和多源资料库的坚实支撑,提出了基于智能工作流的资料推荐方法。设计主题分析方法从学生能力评估结果中提取学生的能力特征,应用图卷积网络算法GCN从学生学习行为数据中挖掘学生的兴趣特征,创建了“能力-推荐智能体”和“兴趣-推荐智能体”,构建了双智能体协同驱动的智能化流程体系,实现了从学生个性化画像智能生成到实践学习资料动态推荐的系列工作流任务;并且构建了个性化资料推荐数据集,在该数据集上验证了所提模型的性能显著优于基线模型。其中,以Qwen2.5-3.0B为基模型训练的LightPLRec模型,在能力推荐与兴趣推荐这两项任务中展现出卓越性能,准确率分别高达0.947和0.939,其表现均优于DeepSeek-V3在同一数据集上的测评结果。该研究为教育大模型的垂直场景应用提供了技术范式,同时通过创建个性化实践学习资料动态推荐模型,为践行“因材施教”理念和培育高素质计算机实践人才提供了创新路径。展开更多
With the new era of the Internet of Things(IoT)technology,many devices with limited resources are utilized.Those devices are susceptible to a signicant number of new malware and other risks emerging rapidly.One of the...With the new era of the Internet of Things(IoT)technology,many devices with limited resources are utilized.Those devices are susceptible to a signicant number of new malware and other risks emerging rapidly.One of the most appropriate methods for securing those IoT applications is cryptographic algorithms,as cryptography masks information by eliminating the risk of collecting any meaningful information patterns.This ensures that all data communications are private,accurate,authenticated,authorized,or nonrepudiated.Since conventional cryptographic algorithms have been developed specically for devices with limited resources;however,it turns out that such algorithms are not ideal for IoT restricted devices with their current conguration.Therefore,lightweight block ciphers are gaining popularity to meet the requirements of low-power and constrained devices.A new ultra-lightweight secret-key block-enciphering algorithm named“LBC-IoT”is proposed in this paper.The proposed block length is 32-bit supporting key lengths of 80-bit,and it is mainly based on the Feistel structure.Energy-efcient cryptographic features in“LBC-IoT”include the use of simple functions(shift,XOR)and small rigid substitution boxes(4-bit-S-boxes).Besides,it is immune to different types of attacks such as linear,differential,and side-channel as well as exible in terms of implementation.Moreover,LBC-IoT achieves reasonable performance in both hardware and software compared to other recent algorithms.LBC-IoT’s hardware implementation results are very promising(smallest ever area“548”GE)and competitive with today’s leading lightweight ciphers.LBC-IoT is also ideally suited for ultra-restricted devices such as RFID tags.展开更多
文摘Internet of things(IoT)is used in various fields such as smart cities,smart home,manufacturing industries,and healthcare.Its application in healthcare has many advantages and disadvantages.One of its most common protocols is Message Queue Telemetry Transport(MQTT).MQTT protocol works as a publisher/subscriber which is suitable for IoT devices with limited power.One of the drawbacks of MQTT is that it is easy to manipulate.The default security provided by MQTT during user authentication,through username and password,does not provide any type of data encryption,to ensure confidentiality or integrity.This paper focuses on the security of IoT healthcare over the MQTT protocol,through the implementation of lightweight generating and key exchange algorithms.The research contribution of this paper is twofold.The first one is to implement a lightweight generating and key exchange algorithm for MQTT protocol,with the key length of 64 bits through OMNET++simulation.The second one is to obtain lower power consumption from some existing algorithms.Moreover,the power consumption through using the proposed algorithm is 0.78%,1.16%,and 1.93% of power for 256 bits,512 bits,and 1024 respectively.On the other hand,the power consumption without using the encryption is 0.25%,0.51%,and 1.03% for the same three payloads length.
文摘This paper proposes SW-YOLO(StarNet Weighted-Conv YOLO),a lightweight human pose estimation network for edge devices.Current mainstream pose estimation algorithms are computationally inefficient and have poor feature capture capabilities for complex poses and occlusion scenarios.This work introduces a lightweight backbone architecture that integrates WConv(Weighted Convolution)and StarNet modules to address these issues.Leveraging StarNet’s superior capabilities in multi-level feature fusion and long-range dependency modeling,this architecture enhances the model’s spatial perception of human joint structures and contextual information integration.These improvements significantly enhance robustness in complex scenarios involving occlusion and deformation.Additionally,the introduction of WConv convolution operations,based on weight recalibration and receptive field optimization,dynamically adjusts feature importance during convolution.This reduces redundant computations while maintaining or enhancing feature representation capabilities at an extremely low computational cost.Consequently,SW-YOLO substantially reduces model complexity and inference latency while preserving high accuracy,significantly outperforming existing lightweight networks.
文摘人工智能技术在教育领域的深度应用,已成为国家教育数字化转型的核心战略。在计算机实践教学领域,实践学习资料的精准推荐是提升学生学习效能与质量的重要途径。针对高校教育规模化与学生需求多元化之间的矛盾,提出一种基于轻量级教育大模型的个性化实践学习资料推荐模型LightPLRec(Lightweight Personalized Learning Recommender for Dynamic Practice Materials),旨在依据学生个体特征的动态变化智能推荐个性化的实践学习资料。基于低算力需求的轻量级大模型,通过指令微调和强化学习方法构建了面向个性化实践学习资料推荐的教育大模型SPIR(Student Profile&Interest-based Re-commender)。通过整合多源异构数据,深度融入课程知识体系、学科前沿动态、产业发展趋势、国家战略导向,构建了跨学科、多模态的实践学习资料库,并设计了图转主题文本方法gragh2topic。依托于SPIR大模型的强大赋能和多源资料库的坚实支撑,提出了基于智能工作流的资料推荐方法。设计主题分析方法从学生能力评估结果中提取学生的能力特征,应用图卷积网络算法GCN从学生学习行为数据中挖掘学生的兴趣特征,创建了“能力-推荐智能体”和“兴趣-推荐智能体”,构建了双智能体协同驱动的智能化流程体系,实现了从学生个性化画像智能生成到实践学习资料动态推荐的系列工作流任务;并且构建了个性化资料推荐数据集,在该数据集上验证了所提模型的性能显著优于基线模型。其中,以Qwen2.5-3.0B为基模型训练的LightPLRec模型,在能力推荐与兴趣推荐这两项任务中展现出卓越性能,准确率分别高达0.947和0.939,其表现均优于DeepSeek-V3在同一数据集上的测评结果。该研究为教育大模型的垂直场景应用提供了技术范式,同时通过创建个性化实践学习资料动态推荐模型,为践行“因材施教”理念和培育高素质计算机实践人才提供了创新路径。
基金funded by Scientic Research Deanship at University of Ha’il—Saudi Arabia through Project Number RG-20019。
文摘With the new era of the Internet of Things(IoT)technology,many devices with limited resources are utilized.Those devices are susceptible to a signicant number of new malware and other risks emerging rapidly.One of the most appropriate methods for securing those IoT applications is cryptographic algorithms,as cryptography masks information by eliminating the risk of collecting any meaningful information patterns.This ensures that all data communications are private,accurate,authenticated,authorized,or nonrepudiated.Since conventional cryptographic algorithms have been developed specically for devices with limited resources;however,it turns out that such algorithms are not ideal for IoT restricted devices with their current conguration.Therefore,lightweight block ciphers are gaining popularity to meet the requirements of low-power and constrained devices.A new ultra-lightweight secret-key block-enciphering algorithm named“LBC-IoT”is proposed in this paper.The proposed block length is 32-bit supporting key lengths of 80-bit,and it is mainly based on the Feistel structure.Energy-efcient cryptographic features in“LBC-IoT”include the use of simple functions(shift,XOR)and small rigid substitution boxes(4-bit-S-boxes).Besides,it is immune to different types of attacks such as linear,differential,and side-channel as well as exible in terms of implementation.Moreover,LBC-IoT achieves reasonable performance in both hardware and software compared to other recent algorithms.LBC-IoT’s hardware implementation results are very promising(smallest ever area“548”GE)and competitive with today’s leading lightweight ciphers.LBC-IoT is also ideally suited for ultra-restricted devices such as RFID tags.
