mmWave radar enables human sensing in non-visual scenarios—e.g., through clothing or certain types of walls—where traditional cameras fail due to occlusion or privacy limitations. However, robust anomaly detection with mmWave remains challenging, as signal reflections are influenced by material properties, clutter, and multipath interference, producing complex, non-Gaussian distortions. Existing methods lack contextual awareness and misclassify benign signal variations as anomalies. We present mmAnomaly, a multi-modal anomaly detection framework that combines mmWave radar with RGBD input to incorporate visual context. Our system extracts semantic cues—such as scene geometry and material properties—using a fast ResNet-based classifier, and uses a conditional latent diffusion model to synthesize the expected mmWave spectrum for the given visual context. A dual-input comparison module then identifies spatial deviations between real and generated spectra to localize anomalies. We evaluate mmAnomaly on two multi-modal datasets across three applications: concealed weapon localization, through-wall intruder localization, and through-wall fall localization. The system achieves up to 94% F1 score and sub-meter localization error, demonstrating robust generalization across clothing, occlusions, and cluttered environments. These results establish mmAnomaly as an accurate and interpretable framework for context-aware anomaly detection in mmWave sensing.

Even though the traffic systems in developed countries have been analyzed rigorously and operated efficiently, the same does not generally hold for developing countries due to inadequate planning, design, and operations of their transportation systems. Because of inherent differences between internal infrastructures, the strategies deployed in developed countries may not be amenable to developing ones. Besides, developing countries’ traffic systems are not well-studied in the literature to the best of our knowledge. For example, it is yet to explore how a developed country’s lane-based traffic flow would perform in the context of a developing country, which generally experiences non-lane-based traffic. As such, by using our newly developed traffic simulator ‘RoadBird,’ we investigate outcomes of both lane-based and non-lane-based traffic from the contexts of both developing and developed countries. To do so, we run simulations over real road topologies (extracted from the GIS maps of major cities such as Dhaka, Miami, and Riyadh), considering different scenarios such as lane-based or non-lane-based flows, homogeneous or heterogeneous traffic, with or without pedestrians, etc. We also incorporate various car-following and lane-changing models to mimic traffic behaviors and investigate their performances. While the lane changing dilemma remains an open research question, our experimental evidence indicates: 1) lane-based approaches will not necessarily perform better in the case of currently-adopted non-lane-based scenarios, and 2) non-lane-based strategies may benefit system performance in lane-based scenarios while having heavy mixed traffic. Nonetheless, we reveal several new insights for on-road experiences both in developing and developed countries.

Inefficient traffic signal control system is one of the most important causes of traffic congestion in the cities of developing countries such as Bangladesh, India, Kenya, etc. This can be mitigated by adopting a decentralized traffic-responsive signal system, where vehicle detection is performed on the road through different image-based deep learning architectures amenable to limited-resource embedded platforms as available in developing countries. Deep learning architectures currently available in this regard demand high computational resources to achieve higher inference speed and better accuracy. Besides, the few existing limited-resource deep learning architectural alternatives neither attain higher inference speed nor substantial accuracy due to not overcoming the inherent limitations. To this extent, in this study, we propose a novel limited-resource deep learning architecture, namely DhakaNet, for real-time vehicle detection in on-road (street-view) traffic images. Our proposed architecture leverages enhancing Cross-Stage Partial Network and Path Aggregation Network to build the backbone and head networks, respectively. Besides, we develop a novel multi-scale attention module to extract multi-scale meaningful features from the images, where the developed multi-scale attention module boosts the detection accuracy at the cost of small overhead. Rigorous experimental evaluation of our proposed DhakaNet over three benchmark street-view traffic datasets such as DhakaAI, IITM-HeTra-A, and IITM-HeTra-B shows up to 51% faster inference speed at a similar accuracy, or up to 13% higher accuracy at a similar inference speed compared to other state-of-the-art limited-resource deep learning architectural alternatives.

Increased processing power of MapReduce clusters generally enhances performance and availability at the cost of substantial energy consumption that often incurs higher operational costs (e.g., electricity bills) and negative environmental impacts (e.g., carbon dioxide emissions). There exist a few greening methods for computing clusters in the literature that focus mainly on computational energy consumption leaving cooling energy, which occupies a significant portion of the total energy consumed by the clusters. To this extent, in this article, we propose a machine learning-based approach that reduces the total energy consumption of a MapReduce cluster considering both computational energy and cooling energy. Our approach predicts the number of machines that results in minimum total energy consumption. We perform the prediction through applying different machine learning techniques over year-long data collected from a real setup. We evaluate performance of our approach through both real test-bed experimentation and simulation. Our evaluation reveals that our approach achieves substantial reduction in total energy consumption compared to other state-of-the-art alternatives while experiencing marginal performance degradation in a few cases.

Increased processing power of MapReduce clusters generally enhances performance and availability at the cost of substantial energy consumption that often incurs higher operational costs (e.g., electricity bills) and negative environmental impacts (e.g., carbon dioxide emissions). There exist a few greening methods for computing clusters in the literature that focus mainly on computational energy consumption leaving cooling energy, which occupies a significant portion of the total energy consumed by the clusters. To this extent, in this paper, we propose a machine learning based approach named as Green MapReduce Cluster (GMC) that reduces the total energy consumption of a MapReduce cluster considering both computational energy and cooling energy. GMC predicts the number of machines that results in minimum total energy consumption. We perform the prediction through applying different machine learning techniques over year-long data collected from a real setup. We evaluate performance of GMC over a real testbed. Our evaluation reveals that GMC reduces total energy consumption by up to 47% compared to other alternatives while experiencing marginal throughput degradation in a few cases.

Detecting count of human beings accurately in a closed indoor environment is crucial in diverse application areas including search and rescue, surveillance, customer analytics, abnormal event detection, human gait characterization, congestion analysis and many more. Moreover, it has significant importance in preventing any intrusion in a secured indoor space such as a bank vault. Sensors-based technologies (for example camera, PR, etc.) are becoming more popular day by day as the regular methodologies are not good enough to ensure enhanced security in a closed indoor environment. As sensors used in these technologies have to be deployed in visible places, there exist possibilities of damaging the sensors by the intruder. Therefore, this paper proposes a novel methodology to detect human count in such closed indoor setting, which can be deployed in any hidden place. Here, human count is done based on four environmental gaseous parameters (Carbon Dioxide, Liquefied Petroleum Gas or LPG, Nitrogen Dioxide, and Sulfur Dioxide) and two weather parameters (temperature and humidity). Real experiments are done under closed controlled settings and counting is done using machine learning algorithms such as Bagging, Random-Forest, IBK, and J48. We achieve more than 99% accuracy for some of the classifiers in detecting the number of humans present.

In a heterogeneous computing cluster, cluster objectives are conflicting to each other. Selecting a right combination of machines is necessary to enhance cluster performance, and to optimize all the cluster objectives. In this paper, we perform empirical performance analyses of a real cluster with our year-long collected data, formulate a new many-objective optimization problem for clusters, and integrate a greedy approach with the existing NSGA-III algorithm to solve this problem. From our experimental results, we find our approach performs better than existing optimization approaches.